From 4f9e993c8b6e5e57e2df31bfa9bedf67d64bfa69 Mon Sep 17 00:00:00 2001 From: Jim Pivarski Date: Fri, 12 Jan 2024 10:47:34 -0600 Subject: [PATCH] chore: restore files that generated the type-parser (#2926) * chore: restore files that generated the type-parser * style: pre-commit fixes * Revert "style: pre-commit fixes" pre-commit should not be allowed to modify auto-generated code. Or any of these files; they're for historical reference. This reverts commit fd96676f0089be718379a3c3286259d418a6051d. * Prevent linters from touching these files. * style: pre-commit fixes * Including this diff is useless if pre-commit is going to keep changing it. * Move to studies/type-parser-1.5. --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> --- studies/type-parser-1.5/generated_parser.py | 2571 +++++++++++++++++++ studies/type-parser-1.5/parser.py | 322 +++ studies/type-parser-1.5/type-grammar.lark | 82 + 3 files changed, 2975 insertions(+) create mode 100644 studies/type-parser-1.5/generated_parser.py create mode 100644 studies/type-parser-1.5/parser.py create mode 100644 studies/type-parser-1.5/type-grammar.lark diff --git a/studies/type-parser-1.5/generated_parser.py b/studies/type-parser-1.5/generated_parser.py new file mode 100644 index 0000000000..5aa0f8c820 --- /dev/null +++ b/studies/type-parser-1.5/generated_parser.py @@ -0,0 +1,2571 @@ +# flake8: noqa +# fmt: off +# pylint: skip-file + +# The file was automatically generated by Lark v0.11.1 +__version__ = "0.11.1" + +# +# +# Lark Stand-alone Generator Tool +# ---------------------------------- +# Generates a stand-alone LALR(1) parser with a standard lexer +# +# Git: https://github.com/erezsh/lark +# Author: Erez Shinan (erezshin@gmail.com) +# +# +# >>> LICENSE +# +# This tool and its generated code use a separate license from Lark, +# and are subject to the terms of the Mozilla Public License, v. 2.0. +# If a copy of the MPL was not distributed with this +# file, You can obtain one at https://mozilla.org/MPL/2.0/. +# +# If you wish to purchase a commercial license for this tool and its +# generated code, you may contact me via email or otherwise. +# +# If MPL2 is incompatible with your free or open-source project, +# contact me and we'll work it out. +# +# + +from io import open + + + +class LarkError(Exception): + pass + + +class GrammarError(LarkError): + pass + + +class ParseError(LarkError): + pass + + +class LexError(LarkError): + pass + + +class UnexpectedEOF(ParseError): + def __init__(self, expected): + self.expected = expected + + message = ("Unexpected end-of-input. Expected one of: \n\t* %s\n" % '\n\t* '.join(x.name for x in self.expected)) + super(UnexpectedEOF, self).__init__(message) + + +class UnexpectedInput(LarkError): + #-- + pos_in_stream = None + + def get_context(self, text, span=40): + #-- + pos = self.pos_in_stream + start = max(pos - span, 0) + end = pos + span + if not isinstance(text, bytes): + before = text[start:pos].rsplit('\n', 1)[-1] + after = text[pos:end].split('\n', 1)[0] + return before + after + '\n' + ' ' * len(before.expandtabs()) + '^\n' + else: + before = text[start:pos].rsplit(b'\n', 1)[-1] + after = text[pos:end].split(b'\n', 1)[0] + return (before + after + b'\n' + b' ' * len(before.expandtabs()) + b'^\n').decode("ascii", "backslashreplace") + + def match_examples(self, parse_fn, examples, token_type_match_fallback=False, use_accepts=False): + #-- + assert self.state is not None, "Not supported for this exception" + + if isinstance(examples, dict): + examples = examples.items() + + candidate = (None, False) + for i, (label, example) in enumerate(examples): + assert not isinstance(example, STRING_TYPE) + + for j, malformed in enumerate(example): + try: + parse_fn(malformed) + except UnexpectedInput as ut: + if ut.state == self.state: + if use_accepts and ut.accepts != self.accepts: + logger.debug("Different accepts with same state[%d]: %s != %s at example [%s][%s]" % + (self.state, self.accepts, ut.accepts, i, j)) + continue + try: + if ut.token == self.token: ## + + logger.debug("Exact Match at example [%s][%s]" % (i, j)) + return label + + if token_type_match_fallback: + ## + + if (ut.token.type == self.token.type) and not candidate[-1]: + logger.debug("Token Type Fallback at example [%s][%s]" % (i, j)) + candidate = label, True + + except AttributeError: + pass + if not candidate[0]: + logger.debug("Same State match at example [%s][%s]" % (i, j)) + candidate = label, False + + return candidate[0] + + +class UnexpectedCharacters(LexError, UnexpectedInput): + def __init__(self, seq, lex_pos, line, column, allowed=None, considered_tokens=None, state=None, token_history=None): + self.line = line + self.column = column + self.pos_in_stream = lex_pos + self.state = state + + self.allowed = allowed + self.considered_tokens = considered_tokens + + if isinstance(seq, bytes): + _s = seq[lex_pos:lex_pos+1].decode("ascii", "backslashreplace") + else: + _s = seq[lex_pos] + + message = "No terminal defined for %r at line %d col %d" % (_s, line, column) + message += '\n\n' + self.get_context(seq) + if allowed: + message += '\nExpecting: %s\n' % allowed + if token_history: + message += '\nPrevious tokens: %s\n' % ', '.join(repr(t) for t in token_history) + + super(UnexpectedCharacters, self).__init__(message) + + +class UnexpectedToken(ParseError, UnexpectedInput): + #-- + def __init__(self, token, expected, considered_rules=None, state=None, puppet=None): + self.line = getattr(token, 'line', '?') + self.column = getattr(token, 'column', '?') + self.pos_in_stream = getattr(token, 'pos_in_stream', None) + self.state = state + + self.token = token + self.expected = expected ## + + self.considered_rules = considered_rules + self.puppet = puppet + + ## + + ## + + self.accepts = puppet and puppet.accepts() + + message = ("Unexpected token %r at line %s, column %s.\n" + "Expected one of: \n\t* %s\n" + % (token, self.line, self.column, '\n\t* '.join(self.accepts or self.expected))) + + super(UnexpectedToken, self).__init__(message) + + +class VisitError(LarkError): + #-- + def __init__(self, rule, obj, orig_exc): + self.obj = obj + self.orig_exc = orig_exc + + message = 'Error trying to process rule "%s":\n\n%s' % (rule, orig_exc) + super(VisitError, self).__init__(message) + +import sys, re +import logging +logger = logging.getLogger("lark") +logger.addHandler(logging.StreamHandler()) +## + +logger.setLevel(logging.CRITICAL) + + +def classify(seq, key=None, value=None): + d = {} + for item in seq: + k = key(item) if (key is not None) else item + v = value(item) if (value is not None) else item + if k in d: + d[k].append(v) + else: + d[k] = [v] + return d + + +def _deserialize(data, namespace, memo): + if isinstance(data, dict): + if '__type__' in data: ## + + class_ = namespace[data['__type__']] + return class_.deserialize(data, memo) + elif '@' in data: + return memo[data['@']] + return {key:_deserialize(value, namespace, memo) for key, value in data.items()} + elif isinstance(data, list): + return [_deserialize(value, namespace, memo) for value in data] + return data + + +class Serialize(object): + #-- + + def memo_serialize(self, types_to_memoize): + memo = SerializeMemoizer(types_to_memoize) + return self.serialize(memo), memo.serialize() + + def serialize(self, memo=None): + if memo and memo.in_types(self): + return {'@': memo.memoized.get(self)} + + fields = getattr(self, '__serialize_fields__') + res = {f: _serialize(getattr(self, f), memo) for f in fields} + res['__type__'] = type(self).__name__ + postprocess = getattr(self, '_serialize', None) + if postprocess: + postprocess(res, memo) + return res + + @classmethod + def deserialize(cls, data, memo): + namespace = getattr(cls, '__serialize_namespace__', {}) + namespace = {c.__name__:c for c in namespace} + + fields = getattr(cls, '__serialize_fields__') + + if '@' in data: + return memo[data['@']] + + inst = cls.__new__(cls) + for f in fields: + try: + setattr(inst, f, _deserialize(data[f], namespace, memo)) + except KeyError as e: + raise KeyError("Cannot find key for class", cls, e) + postprocess = getattr(inst, '_deserialize', None) + if postprocess: + postprocess() + return inst + + +class SerializeMemoizer(Serialize): + #-- + + __serialize_fields__ = 'memoized', + + def __init__(self, types_to_memoize): + self.types_to_memoize = tuple(types_to_memoize) + self.memoized = Enumerator() + + def in_types(self, value): + return isinstance(value, self.types_to_memoize) + + def serialize(self): + return _serialize(self.memoized.reversed(), None) + + @classmethod + def deserialize(cls, data, namespace, memo): + return _deserialize(data, namespace, memo) + + +try: + STRING_TYPE = basestring +except NameError: ## + + STRING_TYPE = str + + +import types +from functools import wraps, partial +from contextlib import contextmanager + +Str = type(u'') +try: + classtype = types.ClassType ## + +except AttributeError: + classtype = type ## + + + +def smart_decorator(f, create_decorator): + if isinstance(f, types.FunctionType): + return wraps(f)(create_decorator(f, True)) + + elif isinstance(f, (classtype, type, types.BuiltinFunctionType)): + return wraps(f)(create_decorator(f, False)) + + elif isinstance(f, types.MethodType): + return wraps(f)(create_decorator(f.__func__, True)) + + elif isinstance(f, partial): + ## + + return wraps(f.func)(create_decorator(lambda *args, **kw: f(*args[1:], **kw), True)) + + else: + return create_decorator(f.__func__.__call__, True) + + +try: + import regex +except ModuleNotFoundError: + regex = None + +import sre_parse +import sre_constants +categ_pattern = re.compile(r'\\p{[A-Za-z_]+}') + +def get_regexp_width(expr): + if regex: + ## + + ## + + ## + + regexp_final = re.sub(categ_pattern, 'A', expr) + else: + if re.search(categ_pattern, expr): + raise ImportError('`regex` module must be installed in order to use Unicode categories.', expr) + regexp_final = expr + try: + return [int(x) for x in sre_parse.parse(regexp_final).getwidth()] + except sre_constants.error: + raise ValueError(expr) + + +from collections import OrderedDict + + +class Meta: + def __init__(self): + self.empty = True + + +class Tree(object): + #-- + def __init__(self, data, children, meta=None): + self.data = data + self.children = children + self._meta = meta + + @property + def meta(self): + if self._meta is None: + self._meta = Meta() + return self._meta + + def __repr__(self): + return 'Tree(%r, %r)' % (self.data, self.children) + + def _pretty_label(self): + return self.data + + def _pretty(self, level, indent_str): + if len(self.children) == 1 and not isinstance(self.children[0], Tree): + return [indent_str*level, self._pretty_label(), '\t', '%s' % (self.children[0],), '\n'] + + l = [indent_str*level, self._pretty_label(), '\n'] + for n in self.children: + if isinstance(n, Tree): + l += n._pretty(level+1, indent_str) + else: + l += [indent_str*(level+1), '%s' % (n,), '\n'] + + return l + + def pretty(self, indent_str=' '): + #-- + return ''.join(self._pretty(0, indent_str)) + + def __eq__(self, other): + try: + return self.data == other.data and self.children == other.children + except AttributeError: + return False + + def __ne__(self, other): + return not (self == other) + + def __hash__(self): + return hash((self.data, tuple(self.children))) + + def iter_subtrees(self): + #-- + queue = [self] + subtrees = OrderedDict() + for subtree in queue: + subtrees[id(subtree)] = subtree + queue += [c for c in reversed(subtree.children) + if isinstance(c, Tree) and id(c) not in subtrees] + + del queue + return reversed(list(subtrees.values())) + + def find_pred(self, pred): + #-- + return filter(pred, self.iter_subtrees()) + + def find_data(self, data): + #-- + return self.find_pred(lambda t: t.data == data) + + +from inspect import getmembers, getmro + + +class Discard(Exception): + #-- + pass + +## + + + +class _Decoratable: + #-- + + @classmethod + def _apply_decorator(cls, decorator, **kwargs): + mro = getmro(cls) + assert mro[0] is cls + libmembers = {name for _cls in mro[1:] for name, _ in getmembers(_cls)} + for name, value in getmembers(cls): + + ## + + if name.startswith('_') or (name in libmembers and name not in cls.__dict__): + continue + if not callable(value): + continue + + ## + + if hasattr(cls.__dict__[name], 'vargs_applied') or hasattr(value, 'vargs_applied'): + continue + + static = isinstance(cls.__dict__[name], (staticmethod, classmethod)) + setattr(cls, name, decorator(value, static=static, **kwargs)) + return cls + + def __class_getitem__(cls, _): + return cls + + +class Transformer(_Decoratable): + #-- + __visit_tokens__ = True ## + + + def __init__(self, visit_tokens=True): + self.__visit_tokens__ = visit_tokens + + def _call_userfunc(self, tree, new_children=None): + ## + + children = new_children if new_children is not None else tree.children + try: + f = getattr(self, tree.data) + except AttributeError: + return self.__default__(tree.data, children, tree.meta) + else: + try: + wrapper = getattr(f, 'visit_wrapper', None) + if wrapper is not None: + return f.visit_wrapper(f, tree.data, children, tree.meta) + else: + return f(children) + except (GrammarError, Discard): + raise + except Exception as e: + raise VisitError(tree.data, tree, e) + + def _call_userfunc_token(self, token): + try: + f = getattr(self, token.type) + except AttributeError: + return self.__default_token__(token) + else: + try: + return f(token) + except (GrammarError, Discard): + raise + except Exception as e: + raise VisitError(token.type, token, e) + + def _transform_children(self, children): + for c in children: + try: + if isinstance(c, Tree): + yield self._transform_tree(c) + elif self.__visit_tokens__ and isinstance(c, Token): + yield self._call_userfunc_token(c) + else: + yield c + except Discard: + pass + + def _transform_tree(self, tree): + children = list(self._transform_children(tree.children)) + return self._call_userfunc(tree, children) + + def transform(self, tree): + #-- + return self._transform_tree(tree) + + def __mul__(self, other): + #-- + return TransformerChain(self, other) + + def __default__(self, data, children, meta): + #-- + return Tree(data, children, meta) + + def __default_token__(self, token): + #-- + return token + + +class InlineTransformer(Transformer): ## + + def _call_userfunc(self, tree, new_children=None): + ## + + children = new_children if new_children is not None else tree.children + try: + f = getattr(self, tree.data) + except AttributeError: + return self.__default__(tree.data, children, tree.meta) + else: + return f(*children) + + +class TransformerChain(object): + def __init__(self, *transformers): + self.transformers = transformers + + def transform(self, tree): + for t in self.transformers: + tree = t.transform(tree) + return tree + + def __mul__(self, other): + return TransformerChain(*self.transformers + (other,)) + + +class Transformer_InPlace(Transformer): + #-- + def _transform_tree(self, tree): ## + + return self._call_userfunc(tree) + + def transform(self, tree): + for subtree in tree.iter_subtrees(): + subtree.children = list(self._transform_children(subtree.children)) + + return self._transform_tree(tree) + + +class Transformer_NonRecursive(Transformer): + #-- + + def transform(self, tree): + ## + + rev_postfix = [] + q = [tree] + while q: + t = q.pop() + rev_postfix.append(t) + if isinstance(t, Tree): + q += t.children + + ## + + stack = [] + for x in reversed(rev_postfix): + if isinstance(x, Tree): + size = len(x.children) + if size: + args = stack[-size:] + del stack[-size:] + else: + args = [] + stack.append(self._call_userfunc(x, args)) + else: + stack.append(x) + + t ,= stack ## + + return t + + +class Transformer_InPlaceRecursive(Transformer): + #-- + def _transform_tree(self, tree): + tree.children = list(self._transform_children(tree.children)) + return self._call_userfunc(tree) + + +## + + +class VisitorBase: + def _call_userfunc(self, tree): + return getattr(self, tree.data, self.__default__)(tree) + + def __default__(self, tree): + #-- + return tree + + def __class_getitem__(cls, _): + return cls + + +class Visitor(VisitorBase): + #-- + + def visit(self, tree): + #-- + for subtree in tree.iter_subtrees(): + self._call_userfunc(subtree) + return tree + + def visit_topdown(self,tree): + #-- + for subtree in tree.iter_subtrees_topdown(): + self._call_userfunc(subtree) + return tree + + +class Visitor_Recursive(VisitorBase): + #-- + + def visit(self, tree): + #-- + for child in tree.children: + if isinstance(child, Tree): + self.visit(child) + + self._call_userfunc(tree) + return tree + + def visit_topdown(self,tree): + #-- + self._call_userfunc(tree) + + for child in tree.children: + if isinstance(child, Tree): + self.visit_topdown(child) + + return tree + + +def visit_children_decor(func): + #-- + @wraps(func) + def inner(cls, tree): + values = cls.visit_children(tree) + return func(cls, values) + return inner + + +class Interpreter(_Decoratable): + #-- + + def visit(self, tree): + f = getattr(self, tree.data) + wrapper = getattr(f, 'visit_wrapper', None) + if wrapper is not None: + return f.visit_wrapper(f, tree.data, tree.children, tree.meta) + else: + return f(tree) + + def visit_children(self, tree): + return [self.visit(child) if isinstance(child, Tree) else child + for child in tree.children] + + def __getattr__(self, name): + return self.__default__ + + def __default__(self, tree): + return self.visit_children(tree) + + +## + + +def _apply_decorator(obj, decorator, **kwargs): + try: + _apply = obj._apply_decorator + except AttributeError: + return decorator(obj, **kwargs) + else: + return _apply(decorator, **kwargs) + + +def _inline_args__func(func): + @wraps(func) + def create_decorator(_f, with_self): + if with_self: + def f(self, children): + return _f(self, *children) + else: + def f(self, children): + return _f(*children) + return f + + return smart_decorator(func, create_decorator) + + +def inline_args(obj): ## + + return _apply_decorator(obj, _inline_args__func) + + +def _visitor_args_func_dec(func, visit_wrapper=None, static=False): + def create_decorator(_f, with_self): + if with_self: + def f(self, *args, **kwargs): + return _f(self, *args, **kwargs) + else: + def f(self, *args, **kwargs): + return _f(*args, **kwargs) + return f + + if static: + f = wraps(func)(create_decorator(func, False)) + else: + f = smart_decorator(func, create_decorator) + f.vargs_applied = True + f.visit_wrapper = visit_wrapper + return f + + +def _vargs_inline(f, _data, children, _meta): + return f(*children) +def _vargs_meta_inline(f, _data, children, meta): + return f(meta, *children) +def _vargs_meta(f, _data, children, meta): + return f(children, meta) ## + +def _vargs_tree(f, data, children, meta): + return f(Tree(data, children, meta)) + + +def v_args(inline=False, meta=False, tree=False, wrapper=None): + #-- + if tree and (meta or inline): + raise ValueError("Visitor functions cannot combine 'tree' with 'meta' or 'inline'.") + + func = None + if meta: + if inline: + func = _vargs_meta_inline + else: + func = _vargs_meta + elif inline: + func = _vargs_inline + elif tree: + func = _vargs_tree + + if wrapper is not None: + if func is not None: + raise ValueError("Cannot use 'wrapper' along with 'tree', 'meta' or 'inline'.") + func = wrapper + + def _visitor_args_dec(obj): + return _apply_decorator(obj, _visitor_args_func_dec, visit_wrapper=func) + return _visitor_args_dec + + + +class Indenter: + def __init__(self): + self.paren_level = None + self.indent_level = None + assert self.tab_len > 0 + + def handle_NL(self, token): + if self.paren_level > 0: + return + + yield token + + indent_str = token.rsplit('\n', 1)[1] ## + + indent = indent_str.count(' ') + indent_str.count('\t') * self.tab_len + + if indent > self.indent_level[-1]: + self.indent_level.append(indent) + yield Token.new_borrow_pos(self.INDENT_type, indent_str, token) + else: + while indent < self.indent_level[-1]: + self.indent_level.pop() + yield Token.new_borrow_pos(self.DEDENT_type, indent_str, token) + + assert indent == self.indent_level[-1], '%s != %s' % (indent, self.indent_level[-1]) + + def _process(self, stream): + for token in stream: + if token.type == self.NL_type: + for t in self.handle_NL(token): + yield t + else: + yield token + + if token.type in self.OPEN_PAREN_types: + self.paren_level += 1 + elif token.type in self.CLOSE_PAREN_types: + self.paren_level -= 1 + assert self.paren_level >= 0 + + while len(self.indent_level) > 1: + self.indent_level.pop() + yield Token(self.DEDENT_type, '') + + assert self.indent_level == [0], self.indent_level + + def process(self, stream): + self.paren_level = 0 + self.indent_level = [0] + return self._process(stream) + + ## + + @property + def always_accept(self): + return (self.NL_type,) + + + +class Symbol(Serialize): + __slots__ = ('name',) + + is_term = NotImplemented + + def __init__(self, name): + self.name = name + + def __eq__(self, other): + assert isinstance(other, Symbol), other + return self.is_term == other.is_term and self.name == other.name + + def __ne__(self, other): + return not (self == other) + + def __hash__(self): + return hash(self.name) + + def __repr__(self): + return '%s(%r)' % (type(self).__name__, self.name) + + fullrepr = property(__repr__) + + +class Terminal(Symbol): + __serialize_fields__ = 'name', 'filter_out' + + is_term = True + + def __init__(self, name, filter_out=False): + self.name = name + self.filter_out = filter_out + + @property + def fullrepr(self): + return '%s(%r, %r)' % (type(self).__name__, self.name, self.filter_out) + + +class NonTerminal(Symbol): + __serialize_fields__ = 'name', + + is_term = False + + +class RuleOptions(Serialize): + __serialize_fields__ = 'keep_all_tokens', 'expand1', 'priority', 'template_source', 'empty_indices' + + def __init__(self, keep_all_tokens=False, expand1=False, priority=None, template_source=None, empty_indices=()): + self.keep_all_tokens = keep_all_tokens + self.expand1 = expand1 + self.priority = priority + self.template_source = template_source + self.empty_indices = empty_indices + + def __repr__(self): + return 'RuleOptions(%r, %r, %r, %r)' % ( + self.keep_all_tokens, + self.expand1, + self.priority, + self.template_source + ) + + +class Rule(Serialize): + #-- + __slots__ = ('origin', 'expansion', 'alias', 'options', 'order', '_hash') + + __serialize_fields__ = 'origin', 'expansion', 'order', 'alias', 'options' + __serialize_namespace__ = Terminal, NonTerminal, RuleOptions + + def __init__(self, origin, expansion, order=0, alias=None, options=None): + self.origin = origin + self.expansion = expansion + self.alias = alias + self.order = order + self.options = options or RuleOptions() + self._hash = hash((self.origin, tuple(self.expansion))) + + def _deserialize(self): + self._hash = hash((self.origin, tuple(self.expansion))) + + def __str__(self): + return '<%s : %s>' % (self.origin.name, ' '.join(x.name for x in self.expansion)) + + def __repr__(self): + return 'Rule(%r, %r, %r, %r)' % (self.origin, self.expansion, self.alias, self.options) + + def __hash__(self): + return self._hash + + def __eq__(self, other): + if not isinstance(other, Rule): + return False + return self.origin == other.origin and self.expansion == other.expansion + + + +from copy import copy + + +class Pattern(Serialize): + + def __init__(self, value, flags=()): + self.value = value + self.flags = frozenset(flags) + + def __repr__(self): + return repr(self.to_regexp()) + + ## + + def __hash__(self): + return hash((type(self), self.value, self.flags)) + + def __eq__(self, other): + return type(self) == type(other) and self.value == other.value and self.flags == other.flags + + def to_regexp(self): + raise NotImplementedError() + + def _get_flags(self, value): + for f in self.flags: + value = f'(?{f}:{value})' + return value + + +class PatternStr(Pattern): + __serialize_fields__ = 'value', 'flags' + + type = "str" + + def to_regexp(self): + return self._get_flags(re.escape(self.value)) + + @property + def min_width(self): + return len(self.value) + max_width = min_width + + +class PatternRE(Pattern): + __serialize_fields__ = 'value', 'flags', '_width' + + type = "re" + + def to_regexp(self): + return self._get_flags(self.value) + + _width = None + def _get_width(self): + if self._width is None: + self._width = get_regexp_width(self.to_regexp()) + return self._width + + @property + def min_width(self): + return self._get_width()[0] + + @property + def max_width(self): + return self._get_width()[1] + + +class TerminalDef(Serialize): + __serialize_fields__ = 'name', 'pattern', 'priority' + __serialize_namespace__ = PatternStr, PatternRE + + def __init__(self, name, pattern, priority=1): + assert isinstance(pattern, Pattern), pattern + self.name = name + self.pattern = pattern + self.priority = priority + + def __repr__(self): + return '%s(%r, %r)' % (type(self).__name__, self.name, self.pattern) + + +class Token(Str): + #-- + __slots__ = ('type', 'pos_in_stream', 'value', 'line', 'column', 'end_line', 'end_column', 'end_pos') + + def __new__(cls, type_, value, pos_in_stream=None, line=None, column=None, end_line=None, end_column=None, end_pos=None): + try: + self = super(Token, cls).__new__(cls, value) + except UnicodeDecodeError: + value = value.decode('latin1') + self = super(Token, cls).__new__(cls, value) + + self.type = type_ + self.pos_in_stream = pos_in_stream + self.value = value + self.line = line + self.column = column + self.end_line = end_line + self.end_column = end_column + self.end_pos = end_pos + return self + + def update(self, type_=None, value=None): + return Token.new_borrow_pos( + type_ if type_ is not None else self.type, + value if value is not None else self.value, + self + ) + + @classmethod + def new_borrow_pos(cls, type_, value, borrow_t): + return cls(type_, value, borrow_t.pos_in_stream, borrow_t.line, borrow_t.column, borrow_t.end_line, borrow_t.end_column, borrow_t.end_pos) + + def __reduce__(self): + return (self.__class__, (self.type, self.value, self.pos_in_stream, self.line, self.column)) + + def __repr__(self): + return 'Token(%r, %r)' % (self.type, self.value) + + def __deepcopy__(self, memo): + return Token(self.type, self.value, self.pos_in_stream, self.line, self.column) + + def __eq__(self, other): + if isinstance(other, Token) and self.type != other.type: + return False + + return Str.__eq__(self, other) + + __hash__ = Str.__hash__ + + +class LineCounter: + __slots__ = 'char_pos', 'line', 'column', 'line_start_pos', 'newline_char' + + def __init__(self, newline_char): + self.newline_char = newline_char + self.char_pos = 0 + self.line = 1 + self.column = 1 + self.line_start_pos = 0 + + def feed(self, token, test_newline=True): + #-- + if test_newline: + newlines = token.count(self.newline_char) + if newlines: + self.line += newlines + self.line_start_pos = self.char_pos + token.rindex(self.newline_char) + 1 + + self.char_pos += len(token) + self.column = self.char_pos - self.line_start_pos + 1 + + +class UnlessCallback: + def __init__(self, mres): + self.mres = mres + + def __call__(self, t): + for mre, type_from_index in self.mres: + m = mre.match(t.value) + if m: + t.type = type_from_index[m.lastindex] + break + return t + + +class CallChain: + def __init__(self, callback1, callback2, cond): + self.callback1 = callback1 + self.callback2 = callback2 + self.cond = cond + + def __call__(self, t): + t2 = self.callback1(t) + return self.callback2(t) if self.cond(t2) else t2 + + +def _create_unless(terminals, g_regex_flags, re_, use_bytes): + tokens_by_type = classify(terminals, lambda t: type(t.pattern)) + assert len(tokens_by_type) <= 2, tokens_by_type.keys() + embedded_strs = set() + callback = {} + for retok in tokens_by_type.get(PatternRE, []): + unless = [] + for strtok in tokens_by_type.get(PatternStr, []): + if strtok.priority > retok.priority: + continue + s = strtok.pattern.value + m = re_.match(retok.pattern.to_regexp(), s, g_regex_flags) + if m and m.group(0) == s: + unless.append(strtok) + if strtok.pattern.flags <= retok.pattern.flags: + embedded_strs.add(strtok) + if unless: + callback[retok.name] = UnlessCallback(build_mres(unless, g_regex_flags, re_, match_whole=True, use_bytes=use_bytes)) + + terminals = [t for t in terminals if t not in embedded_strs] + return terminals, callback + + +def _build_mres(terminals, max_size, g_regex_flags, match_whole, re_, use_bytes): + ## + + ## + + ## + + postfix = '$' if match_whole else '' + mres = [] + while terminals: + pattern = u'|'.join(u'(?P<%s>%s)' % (t.name, t.pattern.to_regexp() + postfix) for t in terminals[:max_size]) + if use_bytes: + pattern = pattern.encode('latin-1') + try: + mre = re_.compile(pattern, g_regex_flags) + except AssertionError: ## + + return _build_mres(terminals, max_size//2, g_regex_flags, match_whole, re_, use_bytes) + + mres.append((mre, {i: n for n, i in mre.groupindex.items()})) + terminals = terminals[max_size:] + return mres + + +def build_mres(terminals, g_regex_flags, re_, use_bytes, match_whole=False): + return _build_mres(terminals, len(terminals), g_regex_flags, match_whole, re_, use_bytes) + + +def _regexp_has_newline(r): + #-- + return '\n' in r or '\\n' in r or '\\s' in r or '[^' in r or ('(?s' in r and '.' in r) + + +class Lexer(object): + #-- + lex = NotImplemented + + def make_lexer_state(self, text): + line_ctr = LineCounter(b'\n' if isinstance(text, bytes) else '\n') + return LexerState(text, line_ctr) + + +class TraditionalLexer(Lexer): + + def __init__(self, conf): + terminals = list(conf.tokens) + assert all(isinstance(t, TerminalDef) for t in terminals), terminals + + self.re = conf.re_module + + if not conf.skip_validation: + ## + + for t in terminals: + try: + self.re.compile(t.pattern.to_regexp(), conf.g_regex_flags) + except self.re.error: + raise LexError("Cannot compile token %s: %s" % (t.name, t.pattern)) + + if t.pattern.min_width == 0: + raise LexError("Lexer does not allow zero-width terminals. (%s: %s)" % (t.name, t.pattern)) + + assert set(conf.ignore) <= {t.name for t in terminals} + + ## + + self.newline_types = frozenset(t.name for t in terminals if _regexp_has_newline(t.pattern.to_regexp())) + self.ignore_types = frozenset(conf.ignore) + + terminals.sort(key=lambda x: (-x.priority, -x.pattern.max_width, -len(x.pattern.value), x.name)) + self.terminals = terminals + self.user_callbacks = conf.callbacks + self.g_regex_flags = conf.g_regex_flags + self.use_bytes = conf.use_bytes + + self._mres = None + + def _build(self): + terminals, self.callback = _create_unless(self.terminals, self.g_regex_flags, self.re, self.use_bytes) + assert all(self.callback.values()) + + for type_, f in self.user_callbacks.items(): + if type_ in self.callback: + ## + + self.callback[type_] = CallChain(self.callback[type_], f, lambda t: t.type == type_) + else: + self.callback[type_] = f + + self._mres = build_mres(terminals, self.g_regex_flags, self.re, self.use_bytes) + + @property + def mres(self): + if self._mres is None: + self._build() + return self._mres + + def match(self, text, pos): + for mre, type_from_index in self.mres: + m = mre.match(text, pos) + if m: + return m.group(0), type_from_index[m.lastindex] + + def lex(self, state, _parser_state): + with suppress(EOFError): + while True: + yield self.next_token(state) + + def next_token(self, lex_state): + line_ctr = lex_state.line_ctr + while line_ctr.char_pos < len(lex_state.text): + res = self.match(lex_state.text, line_ctr.char_pos) + if not res: + allowed = {v for m, tfi in self.mres for v in tfi.values()} - self.ignore_types + if not allowed: + allowed = {""} + raise UnexpectedCharacters(lex_state.text, line_ctr.char_pos, line_ctr.line, line_ctr.column, + allowed=allowed, token_history=lex_state.last_token and [lex_state.last_token]) + + value, type_ = res + + if type_ not in self.ignore_types: + t = Token(type_, value, line_ctr.char_pos, line_ctr.line, line_ctr.column) + line_ctr.feed(value, type_ in self.newline_types) + t.end_line = line_ctr.line + t.end_column = line_ctr.column + t.end_pos = line_ctr.char_pos + if t.type in self.callback: + t = self.callback[t.type](t) + if not isinstance(t, Token): + raise ValueError("Callbacks must return a token (returned %r)" % t) + lex_state.last_token = t + return t + else: + if type_ in self.callback: + t2 = Token(type_, value, line_ctr.char_pos, line_ctr.line, line_ctr.column) + self.callback[type_](t2) + line_ctr.feed(value, type_ in self.newline_types) + + ## + + raise EOFError(self) + + +class LexerState: + __slots__ = 'text', 'line_ctr', 'last_token' + + def __init__(self, text, line_ctr, last_token=None): + self.text = text + self.line_ctr = line_ctr + self.last_token = last_token + + def __copy__(self): + return type(self)(self.text, copy(self.line_ctr), self.last_token) + + +class ContextualLexer(Lexer): + + def __init__(self, conf, states, always_accept=()): + terminals = list(conf.tokens) + tokens_by_name = {} + for t in terminals: + assert t.name not in tokens_by_name, t + tokens_by_name[t.name] = t + + trad_conf = copy(conf) + trad_conf.tokens = terminals + + lexer_by_tokens = {} + self.lexers = {} + for state, accepts in states.items(): + key = frozenset(accepts) + try: + lexer = lexer_by_tokens[key] + except KeyError: + accepts = set(accepts) | set(conf.ignore) | set(always_accept) + state_tokens = [tokens_by_name[n] for n in accepts if n and n in tokens_by_name] + lexer_conf = copy(trad_conf) + lexer_conf.tokens = state_tokens + lexer = TraditionalLexer(lexer_conf) + lexer_by_tokens[key] = lexer + + self.lexers[state] = lexer + + assert trad_conf.tokens is terminals + self.root_lexer = TraditionalLexer(trad_conf) + + def make_lexer_state(self, text): + return self.root_lexer.make_lexer_state(text) + + def lex(self, lexer_state, parser_state): + try: + while True: + lexer = self.lexers[parser_state.position] + yield lexer.next_token(lexer_state) + except EOFError: + pass + except UnexpectedCharacters as e: + ## + + ## + + token = self.root_lexer.next_token(lexer_state) + raise UnexpectedToken(token, e.allowed, state=parser_state.position) + + +class LexerThread: + #-- + + def __init__(self, lexer, text): + self.lexer = lexer + self.state = lexer.make_lexer_state(text) + + def lex(self, parser_state): + return self.lexer.lex(self.state, parser_state) + + + +class LexerConf(Serialize): + __serialize_fields__ = 'tokens', 'ignore', 'g_regex_flags', 'use_bytes' + __serialize_namespace__ = TerminalDef, + + def __init__(self, tokens, re_module, ignore=(), postlex=None, callbacks=None, g_regex_flags=0, skip_validation=False, use_bytes=False): + self.tokens = tokens ## + + self.ignore = ignore + self.postlex = postlex + self.callbacks = callbacks or {} + self.g_regex_flags = g_regex_flags + self.re_module = re_module + self.skip_validation = skip_validation + self.use_bytes = use_bytes + + +from functools import partial, wraps +from itertools import repeat, product + + +class ExpandSingleChild: + def __init__(self, node_builder): + self.node_builder = node_builder + + def __call__(self, children): + if len(children) == 1: + return children[0] + else: + return self.node_builder(children) + + +class PropagatePositions: + def __init__(self, node_builder): + self.node_builder = node_builder + + def __call__(self, children): + res = self.node_builder(children) + + ## + + if isinstance(res, Tree): + res_meta = res.meta + for c in children: + if isinstance(c, Tree): + child_meta = c.meta + if not child_meta.empty: + res_meta.line = child_meta.line + res_meta.column = child_meta.column + res_meta.start_pos = child_meta.start_pos + res_meta.empty = False + break + elif isinstance(c, Token): + res_meta.line = c.line + res_meta.column = c.column + res_meta.start_pos = c.pos_in_stream + res_meta.empty = False + break + + for c in reversed(children): + if isinstance(c, Tree): + child_meta = c.meta + if not child_meta.empty: + res_meta.end_line = child_meta.end_line + res_meta.end_column = child_meta.end_column + res_meta.end_pos = child_meta.end_pos + res_meta.empty = False + break + elif isinstance(c, Token): + res_meta.end_line = c.end_line + res_meta.end_column = c.end_column + res_meta.end_pos = c.end_pos + res_meta.empty = False + break + + return res + + +class ChildFilter: + def __init__(self, to_include, append_none, node_builder): + self.node_builder = node_builder + self.to_include = to_include + self.append_none = append_none + + def __call__(self, children): + filtered = [] + + for i, to_expand, add_none in self.to_include: + if add_none: + filtered += [None] * add_none + if to_expand: + filtered += children[i].children + else: + filtered.append(children[i]) + + if self.append_none: + filtered += [None] * self.append_none + + return self.node_builder(filtered) + + +class ChildFilterLALR(ChildFilter): + #-- + + def __call__(self, children): + filtered = [] + for i, to_expand, add_none in self.to_include: + if add_none: + filtered += [None] * add_none + if to_expand: + if filtered: + filtered += children[i].children + else: ## + + filtered = children[i].children + else: + filtered.append(children[i]) + + if self.append_none: + filtered += [None] * self.append_none + + return self.node_builder(filtered) + + +class ChildFilterLALR_NoPlaceholders(ChildFilter): + #-- + def __init__(self, to_include, node_builder): + self.node_builder = node_builder + self.to_include = to_include + + def __call__(self, children): + filtered = [] + for i, to_expand in self.to_include: + if to_expand: + if filtered: + filtered += children[i].children + else: ## + + filtered = children[i].children + else: + filtered.append(children[i]) + return self.node_builder(filtered) + + +def _should_expand(sym): + return not sym.is_term and sym.name.startswith('_') + + +def maybe_create_child_filter(expansion, keep_all_tokens, ambiguous, _empty_indices): + ## + + if _empty_indices: + assert _empty_indices.count(False) == len(expansion) + s = ''.join(str(int(b)) for b in _empty_indices) + empty_indices = [len(ones) for ones in s.split('0')] + assert len(empty_indices) == len(expansion)+1, (empty_indices, len(expansion)) + else: + empty_indices = [0] * (len(expansion)+1) + + to_include = [] + nones_to_add = 0 + for i, sym in enumerate(expansion): + nones_to_add += empty_indices[i] + if keep_all_tokens or not (sym.is_term and sym.filter_out): + to_include.append((i, _should_expand(sym), nones_to_add)) + nones_to_add = 0 + + nones_to_add += empty_indices[len(expansion)] + + if _empty_indices or len(to_include) < len(expansion) or any(to_expand for i, to_expand,_ in to_include): + if _empty_indices or ambiguous: + return partial(ChildFilter if ambiguous else ChildFilterLALR, to_include, nones_to_add) + else: + ## + + return partial(ChildFilterLALR_NoPlaceholders, [(i, x) for i,x,_ in to_include]) + + +class AmbiguousExpander: + #-- + def __init__(self, to_expand, tree_class, node_builder): + self.node_builder = node_builder + self.tree_class = tree_class + self.to_expand = to_expand + + def __call__(self, children): + def _is_ambig_tree(t): + return hasattr(t, 'data') and t.data == '_ambig' + + ## + + ## + + ## + + ## + + ambiguous = [] + for i, child in enumerate(children): + if _is_ambig_tree(child): + if i in self.to_expand: + ambiguous.append(i) + + to_expand = [j for j, grandchild in enumerate(child.children) if _is_ambig_tree(grandchild)] + child.expand_kids_by_index(*to_expand) + + if not ambiguous: + return self.node_builder(children) + + expand = [iter(child.children) if i in ambiguous else repeat(child) for i, child in enumerate(children)] + return self.tree_class('_ambig', [self.node_builder(list(f[0])) for f in product(zip(*expand))]) + + +def maybe_create_ambiguous_expander(tree_class, expansion, keep_all_tokens): + to_expand = [i for i, sym in enumerate(expansion) + if keep_all_tokens or ((not (sym.is_term and sym.filter_out)) and _should_expand(sym))] + if to_expand: + return partial(AmbiguousExpander, to_expand, tree_class) + + +class AmbiguousIntermediateExpander: + #-- + + def __init__(self, tree_class, node_builder): + self.node_builder = node_builder + self.tree_class = tree_class + + def __call__(self, children): + def _is_iambig_tree(child): + return hasattr(child, 'data') and child.data == '_iambig' + + def _collapse_iambig(children): + #-- + + ## + + ## + + if children and _is_iambig_tree(children[0]): + iambig_node = children[0] + result = [] + for grandchild in iambig_node.children: + collapsed = _collapse_iambig(grandchild.children) + if collapsed: + for child in collapsed: + child.children += children[1:] + result += collapsed + else: + new_tree = self.tree_class('_inter', grandchild.children + children[1:]) + result.append(new_tree) + return result + + collapsed = _collapse_iambig(children) + if collapsed: + processed_nodes = [self.node_builder(c.children) for c in collapsed] + return self.tree_class('_ambig', processed_nodes) + + return self.node_builder(children) + + +def ptb_inline_args(func): + @wraps(func) + def f(children): + return func(*children) + return f + + +def inplace_transformer(func): + @wraps(func) + def f(children): + ## + + tree = Tree(func.__name__, children) + return func(tree) + return f + + +def apply_visit_wrapper(func, name, wrapper): + if wrapper is _vargs_meta or wrapper is _vargs_meta_inline: + raise NotImplementedError("Meta args not supported for internal transformer") + + @wraps(func) + def f(children): + return wrapper(func, name, children, None) + return f + + +class ParseTreeBuilder: + def __init__(self, rules, tree_class, propagate_positions=False, ambiguous=False, maybe_placeholders=False): + self.tree_class = tree_class + self.propagate_positions = propagate_positions + self.ambiguous = ambiguous + self.maybe_placeholders = maybe_placeholders + + self.rule_builders = list(self._init_builders(rules)) + + def _init_builders(self, rules): + for rule in rules: + options = rule.options + keep_all_tokens = options.keep_all_tokens + expand_single_child = options.expand1 + + wrapper_chain = list(filter(None, [ + (expand_single_child and not rule.alias) and ExpandSingleChild, + maybe_create_child_filter(rule.expansion, keep_all_tokens, self.ambiguous, options.empty_indices if self.maybe_placeholders else None), + self.propagate_positions and PropagatePositions, + self.ambiguous and maybe_create_ambiguous_expander(self.tree_class, rule.expansion, keep_all_tokens), + self.ambiguous and partial(AmbiguousIntermediateExpander, self.tree_class) + ])) + + yield rule, wrapper_chain + + def create_callback(self, transformer=None): + callbacks = {} + + for rule, wrapper_chain in self.rule_builders: + + user_callback_name = rule.alias or rule.options.template_source or rule.origin.name + try: + f = getattr(transformer, user_callback_name) + ## + + wrapper = getattr(f, 'visit_wrapper', None) + if wrapper is not None: + f = apply_visit_wrapper(f, user_callback_name, wrapper) + else: + if isinstance(transformer, InlineTransformer): + f = ptb_inline_args(f) + elif isinstance(transformer, Transformer_InPlace): + f = inplace_transformer(f) + except AttributeError: + f = partial(self.tree_class, user_callback_name) + + for w in wrapper_chain: + f = w(f) + + if rule in callbacks: + raise GrammarError("Rule '%s' already exists" % (rule,)) + + callbacks[rule] = f + + return callbacks + + + +class LALR_Parser(object): + def __init__(self, parser_conf, debug=False): + analysis = LALR_Analyzer(parser_conf, debug=debug) + analysis.compute_lalr() + callbacks = parser_conf.callbacks + + self._parse_table = analysis.parse_table + self.parser_conf = parser_conf + self.parser = _Parser(analysis.parse_table, callbacks, debug) + + @classmethod + def deserialize(cls, data, memo, callbacks, debug=False): + inst = cls.__new__(cls) + inst._parse_table = IntParseTable.deserialize(data, memo) + inst.parser = _Parser(inst._parse_table, callbacks, debug) + return inst + + def serialize(self, memo): + return self._parse_table.serialize(memo) + + def parse(self, *args): + return self.parser.parse(*args) + + +class ParseConf: + __slots__ = 'parse_table', 'callbacks', 'start', 'start_state', 'end_state', 'states' + + def __init__(self, parse_table, callbacks, start): + self.parse_table = parse_table + + self.start_state = self.parse_table.start_states[start] + self.end_state = self.parse_table.end_states[start] + self.states = self.parse_table.states + + self.callbacks = callbacks + self.start = start + + +class ParserState: + __slots__ = 'parse_conf', 'lexer', 'state_stack', 'value_stack' + + def __init__(self, parse_conf, lexer, state_stack=None, value_stack=None): + self.parse_conf = parse_conf + self.lexer = lexer + self.state_stack = state_stack or [self.parse_conf.start_state] + self.value_stack = value_stack or [] + + @property + def position(self): + return self.state_stack[-1] + + def __copy__(self): + return type(self)( + self.parse_conf, + self.lexer, ## + + copy(self.state_stack), + deepcopy(self.value_stack), + ) + + def copy(self): + return copy(self) + + def feed_token(self, token, is_end=False): + state_stack = self.state_stack + value_stack = self.value_stack + states = self.parse_conf.states + end_state = self.parse_conf.end_state + callbacks = self.parse_conf.callbacks + + while True: + state = state_stack[-1] + try: + action, arg = states[state][token.type] + except KeyError: + expected = {s for s in states[state].keys() if s.isupper()} + raise UnexpectedToken(token, expected, state=state, puppet=None) + + assert arg != end_state + + if action is Shift: + ## + + assert not is_end + state_stack.append(arg) + value_stack.append(token) + return + else: + ## + + rule = arg + size = len(rule.expansion) + if size: + s = value_stack[-size:] + del state_stack[-size:] + del value_stack[-size:] + else: + s = [] + + value = callbacks[rule](s) + + _action, new_state = states[state_stack[-1]][rule.origin.name] + assert _action is Shift + state_stack.append(new_state) + value_stack.append(value) + + if is_end and state_stack[-1] == end_state: + return value_stack[-1] + +class _Parser: + def __init__(self, parse_table, callbacks, debug=False): + self.parse_table = parse_table + self.callbacks = callbacks + self.debug = debug + + def parse(self, lexer, start, value_stack=None, state_stack=None): + parse_conf = ParseConf(self.parse_table, self.callbacks, start) + parser_state = ParserState(parse_conf, lexer, state_stack, value_stack) + return self.parse_from_state(parser_state) + + def parse_from_state(self, state): + ## + + try: + token = None + for token in state.lexer.lex(state): + state.feed_token(token) + + token = Token.new_borrow_pos('$END', '', token) if token else Token('$END', '', 0, 1, 1) + return state.feed_token(token, True) + except UnexpectedInput as e: + try: + e.puppet = ParserPuppet(self, state, state.lexer) + except NameError: + pass + raise e + except Exception as e: + if self.debug: + print("") + print("STATE STACK DUMP") + print("----------------") + for i, s in enumerate(state.state_stack): + print('%d)' % i , s) + print("") + + raise + + +class Action: + def __init__(self, name): + self.name = name + def __str__(self): + return self.name + def __repr__(self): + return str(self) + +Shift = Action('Shift') +Reduce = Action('Reduce') + + +class ParseTable: + def __init__(self, states, start_states, end_states): + self.states = states + self.start_states = start_states + self.end_states = end_states + + def serialize(self, memo): + tokens = Enumerator() + rules = Enumerator() + + states = { + state: {tokens.get(token): ((1, arg.serialize(memo)) if action is Reduce else (0, arg)) + for token, (action, arg) in actions.items()} + for state, actions in self.states.items() + } + + return { + 'tokens': tokens.reversed(), + 'states': states, + 'start_states': self.start_states, + 'end_states': self.end_states, + } + + @classmethod + def deserialize(cls, data, memo): + tokens = data['tokens'] + states = { + state: {tokens[token]: ((Reduce, Rule.deserialize(arg, memo)) if action==1 else (Shift, arg)) + for token, (action, arg) in actions.items()} + for state, actions in data['states'].items() + } + return cls(states, data['start_states'], data['end_states']) + + +class IntParseTable(ParseTable): + + @classmethod + def from_ParseTable(cls, parse_table): + enum = list(parse_table.states) + state_to_idx = {s:i for i,s in enumerate(enum)} + int_states = {} + + for s, la in parse_table.states.items(): + la = {k:(v[0], state_to_idx[v[1]]) if v[0] is Shift else v + for k,v in la.items()} + int_states[ state_to_idx[s] ] = la + + + start_states = {start:state_to_idx[s] for start, s in parse_table.start_states.items()} + end_states = {start:state_to_idx[s] for start, s in parse_table.end_states.items()} + return cls(int_states, start_states, end_states) + + + +def get_frontend(parser, lexer): + if parser=='lalr': + if lexer is None: + raise ValueError('The LALR parser requires use of a lexer') + elif lexer == 'standard': + return LALR_TraditionalLexer + elif lexer == 'contextual': + return LALR_ContextualLexer + elif issubclass(lexer, Lexer): + class CustomLexerWrapper(Lexer): + def __init__(self, lexer_conf): + self.lexer = lexer(lexer_conf) + def lex(self, lexer_state, parser_state): + return self.lexer.lex(lexer_state.text) + + class LALR_CustomLexerWrapper(LALR_WithLexer): + def __init__(self, lexer_conf, parser_conf, options=None): + super(LALR_CustomLexerWrapper, self).__init__(lexer_conf, parser_conf, options=options) + def init_lexer(self): + future_interface = getattr(lexer, '__future_interface__', False) + if future_interface: + self.lexer = lexer(self.lexer_conf) + else: + self.lexer = CustomLexerWrapper(self.lexer_conf) + + return LALR_CustomLexerWrapper + else: + raise ValueError('Unknown lexer: %s' % lexer) + elif parser=='earley': + if lexer=='standard': + return Earley + elif lexer=='dynamic': + return XEarley + elif lexer=='dynamic_complete': + return XEarley_CompleteLex + elif lexer=='contextual': + raise ValueError('The Earley parser does not support the contextual parser') + else: + raise ValueError('Unknown lexer: %s' % lexer) + elif parser == 'cyk': + if lexer == 'standard': + return CYK + else: + raise ValueError('CYK parser requires using standard parser.') + else: + raise ValueError('Unknown parser: %s' % parser) + + +class _ParserFrontend(Serialize): + def _parse(self, start, input, *args): + if start is None: + start = self.start + if len(start) > 1: + raise ValueError("Lark initialized with more than 1 possible start rule. Must specify which start rule to parse", start) + start ,= start + return self.parser.parse(input, start, *args) + + +def _get_lexer_callbacks(transformer, terminals): + result = {} + for terminal in terminals: + callback = getattr(transformer, terminal.name, None) + if callback is not None: + result[terminal.name] = callback + return result + +class PostLexConnector: + def __init__(self, lexer, postlexer): + self.lexer = lexer + self.postlexer = postlexer + + def make_lexer_state(self, text): + return self.lexer.make_lexer_state(text) + + def lex(self, lexer_state, parser_state): + i = self.lexer.lex(lexer_state, parser_state) + return self.postlexer.process(i) + + +class WithLexer(_ParserFrontend): + lexer = None + parser = None + lexer_conf = None + start = None + + __serialize_fields__ = 'parser', 'lexer_conf', 'start' + __serialize_namespace__ = LexerConf, + + def __init__(self, lexer_conf, parser_conf, options=None): + self.lexer_conf = lexer_conf + self.start = parser_conf.start + self.postlex = lexer_conf.postlex + + @classmethod + def deserialize(cls, data, memo, callbacks, options): + inst = super(WithLexer, cls).deserialize(data, memo) + + inst.postlex = options.postlex + inst.parser = LALR_Parser.deserialize(inst.parser, memo, callbacks, options.debug) + + terminals = [item for item in memo.values() if isinstance(item, TerminalDef)] + inst.lexer_conf.callbacks = _get_lexer_callbacks(options.transformer, terminals) + inst.lexer_conf.re_module = regex if options.regex else re + inst.lexer_conf.use_bytes = options.use_bytes + inst.lexer_conf.g_regex_flags = options.g_regex_flags + inst.lexer_conf.skip_validation = True + inst.init_lexer() + + return inst + + def _serialize(self, data, memo): + data['parser'] = data['parser'].serialize(memo) + + def make_lexer(self, text): + lexer = self.lexer + if self.postlex: + lexer = PostLexConnector(self.lexer, self.postlex) + return LexerThread(lexer, text) + + def parse(self, text, start=None): + return self._parse(start, self.make_lexer(text)) + + def init_traditional_lexer(self): + self.lexer = TraditionalLexer(self.lexer_conf) + +class LALR_WithLexer(WithLexer): + def __init__(self, lexer_conf, parser_conf, options=None): + debug = options.debug if options else False + self.parser = LALR_Parser(parser_conf, debug=debug) + WithLexer.__init__(self, lexer_conf, parser_conf, options) + + self.init_lexer() + + def init_lexer(self, **kw): + raise NotImplementedError() + +class LALR_TraditionalLexer(LALR_WithLexer): + def init_lexer(self): + self.init_traditional_lexer() + +class LALR_ContextualLexer(LALR_WithLexer): + def init_lexer(self): + states = {idx:list(t.keys()) for idx, t in self.parser._parse_table.states.items()} + always_accept = self.postlex.always_accept if self.postlex else () + self.lexer = ContextualLexer(self.lexer_conf, states, always_accept=always_accept) + + + + +class LarkOptions(Serialize): + #-- + OPTIONS_DOC = """ + **=== General Options ===** + + start + The start symbol. Either a string, or a list of strings for multiple possible starts (Default: "start") + debug + Display debug information and extra warnings. Use only when debugging (default: False) + When used with Earley, it generates a forest graph as "sppf.png", if 'dot' is installed. + transformer + Applies the transformer to every parse tree (equivalent to applying it after the parse, but faster) + propagate_positions + Propagates (line, column, end_line, end_column) attributes into all tree branches. + maybe_placeholders + When True, the ``[]`` operator returns ``None`` when not matched. + + When ``False``, ``[]`` behaves like the ``?`` operator, and returns no value at all. + (default= ``False``. Recommended to set to ``True``) + cache + Cache the results of the Lark grammar analysis, for x2 to x3 faster loading. LALR only for now. + + - When ``False``, does nothing (default) + - When ``True``, caches to a temporary file in the local directory + - When given a string, caches to the path pointed by the string + regex + When True, uses the ``regex`` module instead of the stdlib ``re``. + g_regex_flags + Flags that are applied to all terminals (both regex and strings) + keep_all_tokens + Prevent the tree builder from automagically removing "punctuation" tokens (default: False) + tree_class + Lark will produce trees comprised of instances of this class instead of the default ``lark.Tree``. + + **=== Algorithm Options ===** + + parser + Decides which parser engine to use. Accepts "earley" or "lalr". (Default: "earley"). + (there is also a "cyk" option for legacy) + lexer + Decides whether or not to use a lexer stage + + - "auto" (default): Choose for me based on the parser + - "standard": Use a standard lexer + - "contextual": Stronger lexer (only works with parser="lalr") + - "dynamic": Flexible and powerful (only with parser="earley") + - "dynamic_complete": Same as dynamic, but tries *every* variation of tokenizing possible. + ambiguity + Decides how to handle ambiguity in the parse. Only relevant if parser="earley" + + - "resolve": The parser will automatically choose the simplest derivation + (it chooses consistently: greedy for tokens, non-greedy for rules) + - "explicit": The parser will return all derivations wrapped in "_ambig" tree nodes (i.e. a forest). + - "forest": The parser will return the root of the shared packed parse forest. + + **=== Misc. / Domain Specific Options ===** + + postlex + Lexer post-processing (Default: None) Only works with the standard and contextual lexers. + priority + How priorities should be evaluated - auto, none, normal, invert (Default: auto) + lexer_callbacks + Dictionary of callbacks for the lexer. May alter tokens during lexing. Use with caution. + use_bytes + Accept an input of type ``bytes`` instead of ``str`` (Python 3 only). + edit_terminals + A callback for editing the terminals before parse. + import_paths + A List of either paths or loader functions to specify from where grammars are imported + source_path + Override the source of from where the grammar was loaded. Useful for relative imports and unconventional grammar loading + + **=== End Options ===** + """ + if __doc__: + __doc__ += OPTIONS_DOC + + + ## + + ## + + ## + + ## + + ## + + ## + + ## + + ## + + _defaults = { + 'debug': False, + 'keep_all_tokens': False, + 'tree_class': None, + 'cache': False, + 'postlex': None, + 'parser': 'earley', + 'lexer': 'auto', + 'transformer': None, + 'start': 'start', + 'priority': 'auto', + 'ambiguity': 'auto', + 'regex': False, + 'propagate_positions': False, + 'lexer_callbacks': {}, + 'maybe_placeholders': False, + 'edit_terminals': None, + 'g_regex_flags': 0, + 'use_bytes': False, + 'import_paths': [], + 'source_path': None, + } + + def __init__(self, options_dict): + o = dict(options_dict) + + options = {} + for name, default in self._defaults.items(): + if name in o: + value = o.pop(name) + if isinstance(default, bool) and name not in ('cache', 'use_bytes'): + value = bool(value) + else: + value = default + + options[name] = value + + if isinstance(options['start'], STRING_TYPE): + options['start'] = [options['start']] + + self.__dict__['options'] = options + + assert self.parser in ('earley', 'lalr', 'cyk', None) + + if self.parser == 'earley' and self.transformer: + raise ValueError('Cannot specify an embedded transformer when using the Earley algorithm.' + 'Please use your transformer on the resulting parse tree, or use a different algorithm (i.e. LALR)') + + if o: + raise ValueError("Unknown options: %s" % o.keys()) + + def __getattr__(self, name): + try: + return self.options[name] + except KeyError as e: + raise AttributeError(e) + + def __setattr__(self, name, value): + assert name in self.options + self.options[name] = value + + def serialize(self, memo): + return self.options + + @classmethod + def deserialize(cls, data, memo): + return cls(data) + + +## + +## + +_LOAD_ALLOWED_OPTIONS = {'postlex', 'transformer', 'use_bytes', 'debug', 'g_regex_flags', 'regex', 'propagate_positions', 'tree_class'} + +_VALID_PRIORITY_OPTIONS = ('auto', 'normal', 'invert', None) +_VALID_AMBIGUITY_OPTIONS = ('auto', 'resolve', 'explicit', 'forest') + + +class Lark(Serialize): + #-- + def __init__(self, grammar, **options): + self.options = LarkOptions(options) + + ## + + use_regex = self.options.regex + if use_regex: + if regex: + re_module = regex + else: + raise ImportError('`regex` module must be installed if calling `Lark(regex=True)`.') + else: + re_module = re + + ## + + if self.options.source_path is None: + try: + self.source_path = grammar.name + except AttributeError: + self.source_path = '' + else: + self.source_path = self.options.source_path + + ## + + try: + read = grammar.read + except AttributeError: + pass + else: + grammar = read() + + assert isinstance(grammar, STRING_TYPE) + self.source_grammar = grammar + if self.options.use_bytes: + if not isascii(grammar): + raise ValueError("Grammar must be ascii only, when use_bytes=True") + + cache_fn = None + if self.options.cache: + if self.options.parser != 'lalr': + raise NotImplementedError("cache only works with parser='lalr' for now") + if isinstance(self.options.cache, STRING_TYPE): + cache_fn = self.options.cache + else: + if self.options.cache is not True: + raise ValueError("cache argument must be bool or str") + unhashable = ('transformer', 'postlex', 'lexer_callbacks', 'edit_terminals') + from . import __version__ + options_str = ''.join(k+str(v) for k, v in options.items() if k not in unhashable) + s = grammar + options_str + __version__ + md5 = hashlib.md5(s.encode()).hexdigest() + cache_fn = tempfile.gettempdir() + '/.lark_cache_%s.tmp' % md5 + + if FS.exists(cache_fn): + logger.debug('Loading grammar from cache: %s', cache_fn) + ## + + for name in (set(options) - _LOAD_ALLOWED_OPTIONS): + del options[name] + with FS.open(cache_fn, 'rb') as f: + self._load(f, **options) + return + + if self.options.lexer == 'auto': + if self.options.parser == 'lalr': + self.options.lexer = 'contextual' + elif self.options.parser == 'earley': + self.options.lexer = 'dynamic' + elif self.options.parser == 'cyk': + self.options.lexer = 'standard' + else: + assert False, self.options.parser + lexer = self.options.lexer + assert lexer in ('standard', 'contextual', 'dynamic', 'dynamic_complete') or issubclass(lexer, Lexer) + + if self.options.ambiguity == 'auto': + if self.options.parser == 'earley': + self.options.ambiguity = 'resolve' + else: + disambig_parsers = ['earley', 'cyk'] + assert self.options.parser in disambig_parsers, ( + 'Only %s supports disambiguation right now') % ', '.join(disambig_parsers) + + if self.options.priority == 'auto': + self.options.priority = 'normal' + + if self.options.priority not in _VALID_PRIORITY_OPTIONS: + raise ValueError("invalid priority option: %r. Must be one of %r" % (self.options.priority, _VALID_PRIORITY_OPTIONS)) + assert self.options.ambiguity not in ('resolve__antiscore_sum', ), 'resolve__antiscore_sum has been replaced with the option priority="invert"' + if self.options.ambiguity not in _VALID_AMBIGUITY_OPTIONS: + raise ValueError("invalid ambiguity option: %r. Must be one of %r" % (self.options.ambiguity, _VALID_AMBIGUITY_OPTIONS)) + + ## + + self.grammar = load_grammar(grammar, self.source_path, self.options.import_paths, self.options.keep_all_tokens) + + if self.options.postlex is not None: + terminals_to_keep = set(self.options.postlex.always_accept) + else: + terminals_to_keep = set() + + ## + + self.terminals, self.rules, self.ignore_tokens = self.grammar.compile(self.options.start, terminals_to_keep) + + if self.options.edit_terminals: + for t in self.terminals: + self.options.edit_terminals(t) + + self._terminals_dict = {t.name: t for t in self.terminals} + + ## + + ## + + if self.options.priority == 'invert': + for rule in self.rules: + if rule.options.priority is not None: + rule.options.priority = -rule.options.priority + ## + + ## + + ## + + elif self.options.priority is None: + for rule in self.rules: + if rule.options.priority is not None: + rule.options.priority = None + + ## + + lexer_callbacks = (_get_lexer_callbacks(self.options.transformer, self.terminals) + if self.options.transformer + else {}) + lexer_callbacks.update(self.options.lexer_callbacks) + + self.lexer_conf = LexerConf(self.terminals, re_module, self.ignore_tokens, self.options.postlex, lexer_callbacks, self.options.g_regex_flags, use_bytes=self.options.use_bytes) + + if self.options.parser: + self.parser = self._build_parser() + elif lexer: + self.lexer = self._build_lexer() + + if cache_fn: + logger.debug('Saving grammar to cache: %s', cache_fn) + with FS.open(cache_fn, 'wb') as f: + self.save(f) + + if __doc__: + __doc__ += "\n\n" + LarkOptions.OPTIONS_DOC + + __serialize_fields__ = 'parser', 'rules', 'options' + + def _build_lexer(self): + return TraditionalLexer(self.lexer_conf) + + def _prepare_callbacks(self): + self.parser_class = get_frontend(self.options.parser, self.options.lexer) + self._callbacks = None + ## + + if self.options.ambiguity != 'forest': + self._parse_tree_builder = ParseTreeBuilder( + self.rules, + self.options.tree_class or Tree, + self.options.propagate_positions, + self.options.parser != 'lalr' and self.options.ambiguity == 'explicit', + self.options.maybe_placeholders + ) + self._callbacks = self._parse_tree_builder.create_callback(self.options.transformer) + + def _build_parser(self): + self._prepare_callbacks() + parser_conf = ParserConf(self.rules, self._callbacks, self.options.start) + return self.parser_class(self.lexer_conf, parser_conf, options=self.options) + + def save(self, f): + #-- + data, m = self.memo_serialize([TerminalDef, Rule]) + pickle.dump({'data': data, 'memo': m}, f, protocol=pickle.HIGHEST_PROTOCOL) + + @classmethod + def load(cls, f): + #-- + inst = cls.__new__(cls) + return inst._load(f) + + def _load(self, f, **kwargs): + if isinstance(f, dict): + d = f + else: + d = pickle.load(f) + memo = d['memo'] + data = d['data'] + + assert memo + memo = SerializeMemoizer.deserialize(memo, {'Rule': Rule, 'TerminalDef': TerminalDef}, {}) + options = dict(data['options']) + if (set(kwargs) - _LOAD_ALLOWED_OPTIONS) & set(LarkOptions._defaults): + raise ValueError("Some options are not allowed when loading a Parser: {}" + .format(set(kwargs) - _LOAD_ALLOWED_OPTIONS)) + options.update(kwargs) + self.options = LarkOptions.deserialize(options, memo) + self.rules = [Rule.deserialize(r, memo) for r in data['rules']] + self.source_path = '' + self._prepare_callbacks() + self.parser = self.parser_class.deserialize( + data['parser'], + memo, + self._callbacks, + self.options, ## + + ) + self.terminals = self.parser.lexer_conf.tokens + self._terminals_dict = {t.name: t for t in self.terminals} + return self + + @classmethod + def _load_from_dict(cls, data, memo, **kwargs): + inst = cls.__new__(cls) + return inst._load({'data': data, 'memo': memo}, **kwargs) + + @classmethod + def open(cls, grammar_filename, rel_to=None, **options): + #-- + if rel_to: + basepath = os.path.dirname(rel_to) + grammar_filename = os.path.join(basepath, grammar_filename) + with open(grammar_filename, encoding='utf8') as f: + return cls(f, **options) + + @classmethod + def open_from_package(cls, package, grammar_path, search_paths=("",), **options): + #-- + package = FromPackageLoader(package, search_paths) + full_path, text = package(None, grammar_path) + options.setdefault('source_path', full_path) + options.setdefault('import_paths', []) + options['import_paths'].append(package) + return cls(text, **options) + + def __repr__(self): + return 'Lark(open(%r), parser=%r, lexer=%r, ...)' % (self.source_path, self.options.parser, self.options.lexer) + + + def lex(self, text): + #-- + if not hasattr(self, 'lexer'): + self.lexer = self._build_lexer() + stream = self.lexer.lex(text) + if self.options.postlex: + return self.options.postlex.process(stream) + return stream + + def get_terminal(self, name): + #-- + return self._terminals_dict[name] + + def parse(self, text, start=None, on_error=None): + #-- + + try: + return self.parser.parse(text, start=start) + except UnexpectedInput as e: + if on_error is None: + raise + + while True: + if isinstance(e, UnexpectedCharacters): + s = e.puppet.lexer_state.state + p = s.line_ctr.char_pos + + if not on_error(e): + raise e + + if isinstance(e, UnexpectedCharacters): + ## + + if p == s.line_ctr.char_pos: + s.line_ctr.feed(s.text[p:p+1]) + + try: + return e.puppet.resume_parse() + except UnexpectedToken as e2: + if isinstance(e, UnexpectedToken) and e.token.type == e2.token.type == '$END' and e.puppet == e2.puppet: + ## + + raise e2 + e = e2 + except UnexpectedCharacters as e2: + e = e2 + + @property + def source(self): + warn("Lark.source attribute has been renamed to Lark.source_path", DeprecationWarning) + return self.source_path + + @source.setter + def source(self, value): + self.source_path = value + + @property + def grammar_source(self): + warn("Lark.grammar_source attribute has been renamed to Lark.source_grammar", DeprecationWarning) + return self.source_grammar + + @grammar_source.setter + def grammar_source(self, value): + self.source_grammar = value + + + +import pickle, zlib, base64 +DATA = ( +{'parser': {'parser': {'tokens': {0: 'RSQB', 1: 'COMMA', 2: 'option_parm', 3: 'option_highlevel', 4: 'VAR', 5: 'record_highlevel', 6: 'predefined_typestr', 7: 'LPAR', 8: 'LSQB', 9: 'record_tuple', 10: 'UNKNOWN', 11: 'HARDCODED', 12: 'UNQUOTED_STRING', 13: 'listtype', 14: 'input', 15: 'list_single', 16: 'UNION', 17: 'STRUCT', 18: 'option_single', 19: 'QMARK', 20: 'regular_outparm', 21: 'union_parm', 22: 'regular_inparm', 23: 'LBRACE', 24: 'uniontype', 25: 'TUPLE', 26: 'TYPE', 27: 'record', 28: 'unknown', 29: 'list_parm', 30: 'optiontype', 31: 'union_single', 32: 'CATEGORICAL', 33: 'record_dict', 34: 'categories', 35: 'regular', 36: 'number', 37: 'OPTION', 38: 'record_tuple_param', 39: 'record_struct', 40: 'SIGNED_NUMBER', 41: 'primitive', 42: 'PARAMETERS', 43: 'def_option', 44: '$END', 45: 'RBRACE', 46: 'RPAR', 47: 'STAR', 48: '__union_single_star_0', 49: 'start', 50: '__record_struct_star_2', 51: 'COLON', 52: '__ANON_1', 53: 'string', 54: 'options', 55: '__record_dict_star_1', 56: 'TRUE', 57: 'NULL', 58: 'list_obj', 59: 'FALSE', 60: 'dict_obj', 61: 'json', 62: '__list_obj_star_3', 63: 'pair', 64: '__ANON_0', 65: '__dict_obj_star_4', 66: 'EQUAL'}, 'states': {0: {0: (1, {'@': 29}), 1: (1, {'@': 29})}, 1: {2: (0, 22), 3: (0, 47), 4: (0, 55), 5: (0, 29), 6: (0, 114), 7: (0, 90), 8: (0, 85), 9: (0, 38), 10: (0, 35), 11: (0, 151), 12: (0, 136), 13: (0, 158), 14: (0, 163), 15: (0, 162), 16: (0, 146), 17: (0, 192), 18: (0, 143), 19: (0, 142), 20: (0, 147), 21: (0, 132), 22: (0, 141), 23: (0, 195), 24: (0, 172), 25: (0, 175), 26: (0, 129), 27: (0, 135), 28: (0, 86), 29: (0, 25), 30: (0, 19), 31: (0, 80), 32: (0, 7), 33: (0, 53), 34: (0, 17), 35: (0, 16), 36: (0, 51), 37: (0, 23), 38: (0, 74), 39: (0, 8), 40: (0, 30), 41: (0, 48)}, 2: {1: (0, 3)}, 3: {42: (0, 193), 43: (0, 113)}, 4: {0: (1, {'@': 30}), 1: (1, {'@': 30}), 44: (1, {'@': 30}), 45: (1, {'@': 30}), 8: (1, {'@': 30}), 46: (1, {'@': 30})}, 5: {47: (0, 182)}, 6: {2: (0, 22), 3: (0, 47), 4: (0, 55), 5: (0, 29), 6: (0, 114), 7: (0, 90), 8: (0, 85), 9: (0, 38), 10: (0, 35), 11: (0, 151), 12: (0, 136), 13: (0, 158), 15: (0, 162), 16: (0, 146), 17: (0, 192), 14: (0, 13), 19: (0, 142), 18: (0, 143), 20: (0, 147), 21: (0, 132), 22: (0, 141), 23: (0, 195), 24: (0, 172), 25: (0, 175), 26: (0, 129), 27: (0, 135), 28: (0, 86), 29: (0, 25), 30: (0, 19), 31: (0, 80), 32: (0, 7), 33: (0, 53), 34: (0, 17), 35: (0, 16), 36: (0, 51), 37: (0, 23), 38: (0, 74), 39: (0, 8), 40: (0, 30), 41: (0, 48)}, 7: {8: (0, 101)}, 8: {0: (1, {'@': 31}), 1: (1, {'@': 31}), 44: (1, {'@': 31}), 45: (1, {'@': 31}), 8: (1, {'@': 31}), 46: (1, {'@': 31})}, 9: {0: (1, {'@': 32}), 1: (1, {'@': 32}), 44: (1, {'@': 32}), 45: (1, {'@': 32}), 8: (1, {'@': 32}), 46: (1, {'@': 32})}, 10: {0: (0, 77), 1: (0, 179)}, 11: {42: (0, 193), 43: (0, 93)}, 12: {45: (1, {'@': 33}), 1: (1, {'@': 33})}, 13: {48: (0, 10), 1: (0, 164), 0: (0, 83)}, 14: {45: (1, {'@': 34}), 1: (1, {'@': 34})}, 15: {2: (0, 22), 3: (0, 47), 4: (0, 55), 5: (0, 29), 6: (0, 114), 7: (0, 90), 8: (0, 85), 9: (0, 38), 10: (0, 35), 11: (0, 151), 12: (0, 136), 13: (0, 158), 15: (0, 162), 16: (0, 146), 17: (0, 192), 18: (0, 143), 19: (0, 142), 20: (0, 147), 21: (0, 132), 22: (0, 141), 14: (0, 153), 23: (0, 195), 24: (0, 172), 25: (0, 175), 26: (0, 129), 27: (0, 135), 28: (0, 86), 29: (0, 25), 30: (0, 19), 31: (0, 80), 32: (0, 7), 33: (0, 53), 34: (0, 17), 35: (0, 16), 36: (0, 51), 37: (0, 23), 49: (0, 65), 38: (0, 74), 39: (0, 8), 40: (0, 30), 41: (0, 48)}, 16: {0: (1, {'@': 35}), 1: (1, {'@': 35}), 44: (1, {'@': 35}), 45: (1, {'@': 35}), 8: (1, {'@': 35}), 46: (1, {'@': 35})}, 17: {0: (1, {'@': 36}), 1: (1, {'@': 36}), 44: (1, {'@': 36}), 45: (1, {'@': 36}), 8: (1, {'@': 36}), 46: (1, {'@': 36})}, 18: {2: (0, 22), 3: (0, 47), 4: (0, 55), 5: (0, 29), 6: (0, 114), 7: (0, 90), 8: (0, 85), 9: (0, 38), 10: (0, 35), 11: (0, 151), 12: (0, 136), 13: (0, 158), 15: (0, 162), 16: (0, 146), 17: (0, 192), 18: (0, 143), 19: (0, 142), 20: (0, 147), 21: (0, 132), 22: (0, 141), 23: (0, 195), 24: (0, 172), 25: (0, 175), 14: (0, 72), 26: (0, 129), 27: (0, 135), 28: (0, 86), 29: (0, 25), 30: (0, 19), 31: (0, 80), 32: (0, 7), 33: (0, 53), 34: (0, 17), 35: (0, 16), 36: (0, 51), 37: (0, 23), 38: (0, 74), 39: (0, 8), 40: (0, 30), 41: (0, 48)}, 19: {0: (1, {'@': 37}), 1: (1, {'@': 37}), 44: (1, {'@': 37}), 45: (1, {'@': 37}), 8: (1, {'@': 37}), 46: (1, {'@': 37})}, 20: {45: (1, {'@': 38}), 1: (1, {'@': 38}), 0: (1, {'@': 38})}, 21: {0: (0, 75), 1: (0, 33), 50: (0, 104)}, 22: {0: (1, {'@': 39}), 1: (1, {'@': 39}), 44: (1, {'@': 39}), 45: (1, {'@': 39}), 8: (1, {'@': 39}), 46: (1, {'@': 39})}, 23: {8: (0, 1)}, 24: {2: (0, 22), 3: (0, 47), 4: (0, 55), 5: (0, 29), 6: (0, 114), 7: (0, 90), 8: (0, 85), 9: (0, 38), 10: (0, 35), 11: (0, 151), 12: (0, 136), 13: (0, 158), 15: (0, 162), 16: (0, 146), 17: (0, 192), 18: (0, 143), 19: (0, 142), 20: (0, 147), 21: (0, 132), 14: (0, 145), 22: (0, 141), 23: (0, 195), 24: (0, 172), 25: (0, 175), 26: (0, 129), 27: (0, 135), 28: (0, 86), 29: (0, 25), 30: (0, 19), 31: (0, 80), 32: (0, 7), 33: (0, 53), 34: (0, 17), 35: (0, 16), 36: (0, 51), 37: (0, 23), 38: (0, 74), 39: (0, 8), 40: (0, 30), 41: (0, 48)}, 25: {0: (1, {'@': 40}), 1: (1, {'@': 40}), 44: (1, {'@': 40}), 45: (1, {'@': 40}), 8: (1, {'@': 40}), 46: (1, {'@': 40})}, 26: {0: (1, {'@': 41}), 1: (1, {'@': 41}), 44: (1, {'@': 41}), 45: (1, {'@': 41}), 8: (1, {'@': 41}), 46: (1, {'@': 41})}, 27: {51: (0, 140)}, 28: {0: (1, {'@': 42}), 1: (1, {'@': 42}), 45: (1, {'@': 42})}, 29: {0: (1, {'@': 43}), 1: (1, {'@': 43}), 44: (1, {'@': 43}), 45: (1, {'@': 43}), 8: (1, {'@': 43}), 46: (1, {'@': 43})}, 30: {47: (1, {'@': 44}), 0: (1, {'@': 44}), 1: (1, {'@': 44}), 45: (1, {'@': 44})}, 31: {0: (0, 107)}, 32: {0: (1, {'@': 45}), 1: (1, {'@': 45}), 45: (1, {'@': 45})}, 33: {52: (0, 61), 53: (0, 67)}, 34: {0: (1, {'@': 46}), 1: (1, {'@': 46}), 45: (1, {'@': 46})}, 35: {54: (0, 118), 8: (0, 183), 0: (1, {'@': 47}), 1: (1, {'@': 47}), 44: (1, {'@': 47}), 45: (1, {'@': 47}), 46: (1, {'@': 47})}, 36: {8: (0, 18)}, 37: {55: (0, 81), 45: (0, 45), 1: (0, 115)}, 38: {0: (1, {'@': 48}), 1: (1, {'@': 48}), 44: (1, {'@': 48}), 45: (1, {'@': 48}), 8: (1, {'@': 48}), 46: (1, {'@': 48})}, 39: {0: (1, {'@': 49}), 1: (1, {'@': 49}), 45: (1, {'@': 49})}, 40: {51: (0, 68)}, 41: {0: (0, 43)}, 42: {0: (1, {'@': 50}), 1: (1, {'@': 50}), 45: (1, {'@': 50})}, 43: {0: (1, {'@': 51}), 1: (1, {'@': 51}), 44: (1, {'@': 51}), 45: (1, {'@': 51}), 8: (1, {'@': 51}), 46: (1, {'@': 51})}, 44: {0: (1, {'@': 52}), 1: (1, {'@': 52}), 45: (1, {'@': 52})}, 45: {0: (1, {'@': 53}), 1: (1, {'@': 53}), 44: (1, {'@': 53}), 45: (1, {'@': 53}), 8: (1, {'@': 53}), 46: (1, {'@': 53})}, 46: {0: (1, {'@': 54}), 1: (1, {'@': 54})}, 47: {0: (1, {'@': 55}), 1: (1, {'@': 55}), 44: (1, {'@': 55}), 45: (1, {'@': 55}), 8: (1, {'@': 55}), 46: (1, {'@': 55})}, 48: {0: (1, {'@': 56}), 1: (1, {'@': 56}), 44: (1, {'@': 56}), 45: (1, {'@': 56}), 8: (1, {'@': 56}), 46: (1, {'@': 56})}, 49: {1: (0, 98)}, 50: {23: (0, 173), 56: (0, 66), 57: (0, 34), 58: (0, 42), 59: (0, 121), 60: (0, 39), 8: (0, 125), 61: (0, 46), 52: (0, 61), 53: (0, 100), 36: (0, 28), 40: (0, 30)}, 51: {47: (0, 122)}, 52: {8: (0, 6)}, 53: {0: (1, {'@': 57}), 1: (1, {'@': 57}), 44: (1, {'@': 57}), 45: (1, {'@': 57}), 8: (1, {'@': 57}), 46: (1, {'@': 57})}, 54: {23: (0, 173), 56: (0, 66), 61: (0, 12), 57: (0, 34), 58: (0, 42), 59: (0, 121), 60: (0, 39), 8: (0, 125), 52: (0, 61), 53: (0, 100), 36: (0, 28), 40: (0, 30)}, 55: {47: (0, 24)}, 56: {2: (0, 22), 3: (0, 47), 4: (0, 55), 5: (0, 29), 6: (0, 114), 7: (0, 90), 8: (0, 85), 9: (0, 38), 10: (0, 35), 11: (0, 151), 12: (0, 136), 13: (0, 158), 15: (0, 162), 16: (0, 146), 17: (0, 192), 18: (0, 143), 19: (0, 142), 20: (0, 147), 21: (0, 132), 22: (0, 141), 23: (0, 195), 24: (0, 172), 14: (0, 37), 25: (0, 175), 26: (0, 129), 27: (0, 135), 28: (0, 86), 29: (0, 25), 30: (0, 19), 31: (0, 80), 32: (0, 7), 33: (0, 53), 34: (0, 17), 35: (0, 16), 36: (0, 51), 37: (0, 23), 38: (0, 74), 39: (0, 8), 40: (0, 30), 41: (0, 48)}, 57: {53: (0, 27), 52: (0, 61)}, 58: {0: (1, {'@': 58}), 1: (1, {'@': 58}), 45: (1, {'@': 58})}, 59: {0: (1, {'@': 59}), 1: (1, {'@': 59}), 44: (1, {'@': 59}), 45: (1, {'@': 59}), 8: (1, {'@': 59}), 46: (1, {'@': 59})}, 60: {53: (0, 88), 52: (0, 61)}, 61: {0: (1, {'@': 60}), 1: (1, {'@': 60}), 45: (1, {'@': 60}), 51: (1, {'@': 60})}, 62: {0: (1, {'@': 61}), 1: (1, {'@': 61}), 44: (1, {'@': 61}), 45: (1, {'@': 61}), 8: (1, {'@': 61}), 46: (1, {'@': 61})}, 63: {62: (0, 117), 1: (0, 50), 0: (0, 44)}, 64: {48: (0, 160), 1: (0, 164), 46: (0, 167)}, 65: {}, 66: {0: (1, {'@': 62}), 1: (1, {'@': 62}), 45: (1, {'@': 62})}, 67: {0: (1, {'@': 63}), 1: (1, {'@': 63})}, 68: {2: (0, 22), 3: (0, 47), 4: (0, 55), 5: (0, 29), 6: (0, 114), 7: (0, 90), 8: (0, 85), 9: (0, 38), 10: (0, 35), 11: (0, 151), 12: (0, 136), 13: (0, 158), 15: (0, 162), 16: (0, 146), 17: (0, 192), 18: (0, 143), 19: (0, 142), 20: (0, 147), 21: (0, 132), 22: (0, 141), 23: (0, 195), 24: (0, 172), 25: (0, 175), 26: (0, 129), 27: (0, 135), 28: (0, 86), 29: (0, 25), 30: (0, 19), 31: (0, 80), 32: (0, 7), 33: (0, 53), 34: (0, 17), 35: (0, 16), 36: (0, 51), 37: (0, 23), 38: (0, 74), 39: (0, 8), 40: (0, 30), 14: (0, 20), 41: (0, 48)}, 69: {0: (0, 59)}, 70: {45: (1, {'@': 64}), 1: (1, {'@': 64})}, 71: {0: (1, {'@': 65}), 1: (1, {'@': 65}), 44: (1, {'@': 65}), 45: (1, {'@': 65}), 8: (1, {'@': 65}), 46: (1, {'@': 65})}, 72: {48: (0, 186), 1: (0, 164), 0: (0, 82)}, 73: {0: (1, {'@': 66}), 1: (1, {'@': 66}), 45: (1, {'@': 66})}, 74: {0: (1, {'@': 67}), 1: (1, {'@': 67}), 44: (1, {'@': 67}), 45: (1, {'@': 67}), 8: (1, {'@': 67}), 46: (1, {'@': 67})}, 75: {1: (0, 52)}, 76: {0: (1, {'@': 68}), 1: (1, {'@': 68}), 44: (1, {'@': 68}), 45: (1, {'@': 68}), 8: (1, {'@': 68}), 46: (1, {'@': 68})}, 77: {1: (0, 169)}, 78: {51: (0, 56)}, 79: {42: (0, 193), 43: (0, 41)}, 80: {0: (1, {'@': 69}), 1: (1, {'@': 69}), 44: (1, {'@': 69}), 45: (1, {'@': 69}), 8: (1, {'@': 69}), 46: (1, {'@': 69})}, 81: {45: (0, 99), 1: (0, 57)}, 82: {1: (0, 79)}, 83: {1: (0, 94)}, 84: {0: (0, 138), 1: (0, 179)}, 85: {36: (0, 110), 40: (0, 30), 4: (0, 5)}, 86: {0: (1, {'@': 70}), 1: (1, {'@': 70}), 44: (1, {'@': 70}), 45: (1, {'@': 70}), 8: (1, {'@': 70}), 46: (1, {'@': 70})}, 87: {0: (0, 123), 55: (0, 106), 1: (0, 115)}, 88: {0: (1, {'@': 71}), 1: (1, {'@': 71})}, 89: {0: (1, {'@': 72}), 1: (1, {'@': 72}), 44: (1, {'@': 72}), 45: (1, {'@': 72}), 8: (1, {'@': 72}), 46: (1, {'@': 72})}, 90: {2: (0, 22), 3: (0, 47), 4: (0, 55), 5: (0, 29), 6: (0, 114), 14: (0, 64), 7: (0, 90), 8: (0, 85), 9: (0, 38), 10: (0, 35), 11: (0, 151), 12: (0, 136), 13: (0, 158), 15: (0, 162), 16: (0, 146), 17: (0, 192), 18: (0, 143), 19: (0, 142), 20: (0, 147), 21: (0, 132), 22: (0, 141), 23: (0, 195), 24: (0, 172), 25: (0, 175), 26: (0, 129), 27: (0, 135), 28: (0, 86), 29: (0, 25), 30: (0, 19), 31: (0, 80), 32: (0, 7), 33: (0, 53), 34: (0, 17), 35: (0, 16), 36: (0, 51), 37: (0, 23), 38: (0, 74), 39: (0, 8), 40: (0, 30), 41: (0, 48)}, 91: {8: (0, 170)}, 92: {48: (0, 84), 1: (0, 164), 0: (0, 156)}, 93: {0: (0, 62)}, 94: {42: (0, 193), 43: (0, 189)}, 95: {54: (0, 26), 8: (0, 183), 0: (1, {'@': 73}), 1: (1, {'@': 73}), 44: (1, {'@': 73}), 45: (1, {'@': 73}), 46: (1, {'@': 73})}, 96: {0: (0, 71)}, 97: {63: (0, 14), 53: (0, 102), 52: (0, 61)}, 98: {8: (0, 181)}, 99: {0: (1, {'@': 74}), 1: (1, {'@': 74}), 44: (1, {'@': 74}), 45: (1, {'@': 74}), 8: (1, {'@': 74}), 46: (1, {'@': 74})}, 100: {0: (1, {'@': 75}), 1: (1, {'@': 75}), 45: (1, {'@': 75})}, 101: {64: (0, 126)}, 102: {51: (0, 54)}, 103: {0: (0, 89)}, 104: {0: (0, 49), 1: (0, 60)}, 105: {0: (1, {'@': 76})}, 106: {0: (0, 168), 1: (0, 57)}, 107: {0: (1, {'@': 77}), 1: (1, {'@': 77}), 44: (1, {'@': 77}), 45: (1, {'@': 77}), 8: (1, {'@': 77}), 46: (1, {'@': 77})}, 108: {0: (1, {'@': 78}), 1: (1, {'@': 78}), 44: (1, {'@': 78}), 45: (1, {'@': 78}), 8: (1, {'@': 78}), 46: (1, {'@': 78})}, 109: {0: (0, 9)}, 110: {47: (0, 161)}, 111: {42: (0, 193), 43: (0, 109)}, 112: {52: (0, 61), 63: (0, 70), 53: (0, 102)}, 113: {0: (0, 185)}, 114: {0: (1, {'@': 79}), 1: (1, {'@': 79}), 44: (1, {'@': 79}), 45: (1, {'@': 79}), 8: (1, {'@': 79}), 46: (1, {'@': 79})}, 115: {53: (0, 40), 52: (0, 61)}, 116: {1: (0, 112), 65: (0, 120), 45: (0, 73)}, 117: {0: (0, 137), 1: (0, 174)}, 118: {0: (1, {'@': 80}), 1: (1, {'@': 80}), 44: (1, {'@': 80}), 45: (1, {'@': 80}), 8: (1, {'@': 80}), 46: (1, {'@': 80})}, 119: {2: (0, 22), 3: (0, 47), 4: (0, 55), 5: (0, 29), 6: (0, 114), 7: (0, 90), 8: (0, 85), 9: (0, 38), 10: (0, 35), 11: (0, 151), 12: (0, 136), 13: (0, 158), 15: (0, 162), 14: (0, 159), 16: (0, 146), 17: (0, 192), 18: (0, 143), 19: (0, 142), 20: (0, 147), 21: (0, 132), 22: (0, 141), 23: (0, 195), 24: (0, 172), 25: (0, 175), 26: (0, 129), 27: (0, 135), 28: (0, 86), 43: (0, 31), 29: (0, 25), 30: (0, 19), 31: (0, 80), 32: (0, 7), 33: (0, 53), 34: (0, 17), 35: (0, 16), 36: (0, 51), 37: (0, 23), 38: (0, 74), 39: (0, 8), 40: (0, 30), 42: (0, 193), 41: (0, 48)}, 120: {45: (0, 58), 1: (0, 97)}, 121: {0: (1, {'@': 81}), 1: (1, {'@': 81}), 45: (1, {'@': 81})}, 122: {2: (0, 22), 3: (0, 47), 4: (0, 55), 5: (0, 29), 6: (0, 114), 14: (0, 154), 7: (0, 90), 8: (0, 85), 9: (0, 38), 10: (0, 35), 11: (0, 151), 12: (0, 136), 13: (0, 158), 15: (0, 162), 16: (0, 146), 17: (0, 192), 18: (0, 143), 19: (0, 142), 20: (0, 147), 21: (0, 132), 22: (0, 141), 23: (0, 195), 24: (0, 172), 25: (0, 175), 26: (0, 129), 27: (0, 135), 28: (0, 86), 29: (0, 25), 30: (0, 19), 31: (0, 80), 32: (0, 7), 33: (0, 53), 34: (0, 17), 35: (0, 16), 36: (0, 51), 37: (0, 23), 38: (0, 74), 39: (0, 8), 40: (0, 30), 41: (0, 48)}, 123: {0: (1, {'@': 82}), 1: (1, {'@': 82}), 44: (1, {'@': 82}), 45: (1, {'@': 82}), 8: (1, {'@': 82}), 46: (1, {'@': 82})}, 124: {0: (1, {'@': 83}), 1: (1, {'@': 83}), 45: (1, {'@': 83})}, 125: {23: (0, 173), 61: (0, 63), 56: (0, 66), 57: (0, 34), 58: (0, 42), 59: (0, 121), 0: (0, 32), 60: (0, 39), 8: (0, 125), 52: (0, 61), 53: (0, 100), 36: (0, 28), 40: (0, 30)}, 126: {66: (0, 166)}, 127: {42: (0, 193), 43: (0, 96)}, 128: {0: (0, 150)}, 129: {54: (0, 108), 8: (0, 183), 0: (1, {'@': 84}), 1: (1, {'@': 84}), 44: (1, {'@': 84}), 45: (1, {'@': 84}), 46: (1, {'@': 84})}, 130: {42: (0, 193), 43: (0, 69)}, 131: {42: (0, 193), 43: (0, 103)}, 132: {0: (1, {'@': 85}), 1: (1, {'@': 85}), 44: (1, {'@': 85}), 45: (1, {'@': 85}), 8: (1, {'@': 85}), 46: (1, {'@': 85})}, 133: {23: (0, 173), 60: (0, 105)}, 134: {0: (0, 76)}, 135: {0: (1, {'@': 86}), 1: (1, {'@': 86}), 44: (1, {'@': 86}), 45: (1, {'@': 86}), 8: (1, {'@': 86}), 46: (1, {'@': 86})}, 136: {8: (0, 155)}, 137: {0: (1, {'@': 87}), 1: (1, {'@': 87}), 45: (1, {'@': 87})}, 138: {1: (0, 131)}, 139: {2: (0, 22), 3: (0, 47), 4: (0, 55), 5: (0, 29), 6: (0, 114), 7: (0, 90), 8: (0, 85), 14: (0, 87), 9: (0, 38), 10: (0, 35), 11: (0, 151), 12: (0, 136), 13: (0, 158), 15: (0, 162), 16: (0, 146), 17: (0, 192), 18: (0, 143), 19: (0, 142), 20: (0, 147), 21: (0, 132), 22: (0, 141), 23: (0, 195), 24: (0, 172), 25: (0, 175), 26: (0, 129), 27: (0, 135), 28: (0, 86), 29: (0, 25), 30: (0, 19), 31: (0, 80), 32: (0, 7), 33: (0, 53), 34: (0, 17), 35: (0, 16), 36: (0, 51), 37: (0, 23), 38: (0, 74), 39: (0, 8), 40: (0, 30), 41: (0, 48)}, 140: {2: (0, 22), 3: (0, 47), 4: (0, 55), 5: (0, 29), 6: (0, 114), 7: (0, 90), 8: (0, 85), 9: (0, 38), 10: (0, 35), 11: (0, 151), 12: (0, 136), 13: (0, 158), 15: (0, 162), 16: (0, 146), 14: (0, 157), 17: (0, 192), 18: (0, 143), 19: (0, 142), 20: (0, 147), 21: (0, 132), 22: (0, 141), 23: (0, 195), 24: (0, 172), 25: (0, 175), 26: (0, 129), 27: (0, 135), 28: (0, 86), 29: (0, 25), 30: (0, 19), 31: (0, 80), 32: (0, 7), 33: (0, 53), 34: (0, 17), 35: (0, 16), 36: (0, 51), 37: (0, 23), 38: (0, 74), 39: (0, 8), 40: (0, 30), 41: (0, 48)}, 141: {0: (1, {'@': 88}), 1: (1, {'@': 88}), 44: (1, {'@': 88}), 45: (1, {'@': 88}), 8: (1, {'@': 88}), 46: (1, {'@': 88})}, 142: {2: (0, 22), 3: (0, 47), 4: (0, 55), 5: (0, 29), 6: (0, 114), 14: (0, 95), 7: (0, 90), 8: (0, 85), 9: (0, 38), 10: (0, 35), 11: (0, 151), 12: (0, 136), 13: (0, 158), 15: (0, 162), 16: (0, 146), 17: (0, 192), 18: (0, 143), 19: (0, 142), 20: (0, 147), 21: (0, 132), 22: (0, 141), 23: (0, 195), 24: (0, 172), 25: (0, 175), 26: (0, 129), 27: (0, 135), 28: (0, 86), 29: (0, 25), 30: (0, 19), 31: (0, 80), 32: (0, 7), 33: (0, 53), 34: (0, 17), 35: (0, 16), 36: (0, 51), 37: (0, 23), 38: (0, 74), 39: (0, 8), 40: (0, 30), 41: (0, 48)}, 143: {0: (1, {'@': 89}), 1: (1, {'@': 89}), 44: (1, {'@': 89}), 45: (1, {'@': 89}), 8: (1, {'@': 89}), 46: (1, {'@': 89})}, 144: {1: (0, 11)}, 145: {0: (1, {'@': 90}), 1: (1, {'@': 90}), 44: (1, {'@': 90}), 45: (1, {'@': 90}), 8: (1, {'@': 90}), 46: (1, {'@': 90})}, 146: {8: (0, 191)}, 147: {0: (1, {'@': 91}), 1: (1, {'@': 91}), 44: (1, {'@': 91}), 45: (1, {'@': 91}), 8: (1, {'@': 91}), 46: (1, {'@': 91})}, 148: {1: (0, 111)}, 149: {0: (1, {'@': 92}), 1: (1, {'@': 92}), 44: (1, {'@': 92}), 45: (1, {'@': 92}), 8: (1, {'@': 92}), 46: (1, {'@': 92})}, 150: {0: (1, {'@': 93}), 1: (1, {'@': 93}), 44: (1, {'@': 93}), 45: (1, {'@': 93}), 8: (1, {'@': 93}), 46: (1, {'@': 93})}, 151: {0: (1, {'@': 94}), 1: (1, {'@': 94}), 44: (1, {'@': 94}), 45: (1, {'@': 94}), 8: (1, {'@': 94}), 46: (1, {'@': 94})}, 152: {1: (0, 171), 48: (0, 180), 0: (0, 184)}, 153: {44: (1, {'@': 95})}, 154: {0: (1, {'@': 96}), 1: (1, {'@': 96}), 44: (1, {'@': 96}), 45: (1, {'@': 96}), 8: (1, {'@': 96}), 46: (1, {'@': 96})}, 155: {52: (0, 61), 53: (0, 190)}, 156: {1: (0, 130)}, 157: {45: (1, {'@': 97}), 1: (1, {'@': 97}), 0: (1, {'@': 97})}, 158: {0: (1, {'@': 98}), 1: (1, {'@': 98}), 44: (1, {'@': 98}), 45: (1, {'@': 98}), 8: (1, {'@': 98}), 46: (1, {'@': 98})}, 159: {0: (1, {'@': 99}), 1: (1, {'@': 99}), 46: (1, {'@': 99})}, 160: {46: (0, 177), 1: (0, 179)}, 161: {2: (0, 22), 3: (0, 47), 4: (0, 55), 5: (0, 29), 6: (0, 114), 7: (0, 90), 8: (0, 85), 14: (0, 148), 9: (0, 38), 10: (0, 35), 11: (0, 151), 12: (0, 136), 13: (0, 158), 15: (0, 162), 16: (0, 146), 17: (0, 192), 18: (0, 143), 19: (0, 142), 20: (0, 147), 21: (0, 132), 22: (0, 141), 23: (0, 195), 24: (0, 172), 25: (0, 175), 26: (0, 129), 27: (0, 135), 28: (0, 86), 29: (0, 25), 30: (0, 19), 31: (0, 80), 32: (0, 7), 33: (0, 53), 34: (0, 17), 35: (0, 16), 36: (0, 51), 37: (0, 23), 38: (0, 74), 39: (0, 8), 40: (0, 30), 41: (0, 48)}, 162: {0: (1, {'@': 100}), 1: (1, {'@': 100}), 44: (1, {'@': 100}), 45: (1, {'@': 100}), 8: (1, {'@': 100}), 46: (1, {'@': 100})}, 163: {0: (0, 178), 1: (0, 127)}, 164: {2: (0, 22), 3: (0, 47), 4: (0, 55), 5: (0, 29), 6: (0, 114), 7: (0, 90), 8: (0, 85), 37: (0, 23), 9: (0, 38), 10: (0, 35), 11: (0, 151), 12: (0, 136), 13: (0, 158), 15: (0, 162), 16: (0, 146), 17: (0, 192), 18: (0, 143), 19: (0, 142), 20: (0, 147), 21: (0, 132), 22: (0, 141), 23: (0, 195), 24: (0, 172), 25: (0, 175), 26: (0, 129), 27: (0, 135), 28: (0, 86), 29: (0, 25), 30: (0, 19), 31: (0, 80), 32: (0, 7), 33: (0, 53), 34: (0, 17), 35: (0, 16), 36: (0, 51), 38: (0, 74), 39: (0, 8), 40: (0, 30), 14: (0, 187), 41: (0, 48)}, 165: {44: (1, {'@': 101}), 8: (1, {'@': 101}), 46: (1, {'@': 101}), 1: (1, {'@': 101}), 45: (1, {'@': 101}), 0: (1, {'@': 101})}, 166: {2: (0, 22), 3: (0, 47), 4: (0, 55), 5: (0, 29), 6: (0, 114), 7: (0, 90), 8: (0, 85), 9: (0, 38), 10: (0, 35), 11: (0, 151), 12: (0, 136), 13: (0, 158), 15: (0, 162), 16: (0, 146), 17: (0, 192), 14: (0, 176), 18: (0, 143), 19: (0, 142), 20: (0, 147), 21: (0, 132), 22: (0, 141), 23: (0, 195), 24: (0, 172), 25: (0, 175), 26: (0, 129), 27: (0, 135), 28: (0, 86), 29: (0, 25), 30: (0, 19), 31: (0, 80), 32: (0, 7), 33: (0, 53), 34: (0, 17), 35: (0, 16), 36: (0, 51), 37: (0, 23), 38: (0, 74), 39: (0, 8), 40: (0, 30), 41: (0, 48)}, 167: {0: (1, {'@': 102}), 1: (1, {'@': 102}), 44: (1, {'@': 102}), 45: (1, {'@': 102}), 8: (1, {'@': 102}), 46: (1, {'@': 102})}, 168: {0: (1, {'@': 103}), 1: (1, {'@': 103}), 44: (1, {'@': 103}), 45: (1, {'@': 103}), 8: (1, {'@': 103}), 46: (1, {'@': 103})}, 169: {42: (0, 193), 43: (0, 128)}, 170: {53: (0, 21), 52: (0, 61)}, 171: {2: (0, 22), 3: (0, 47), 4: (0, 55), 5: (0, 29), 6: (0, 114), 7: (0, 90), 8: (0, 85), 37: (0, 23), 9: (0, 38), 10: (0, 35), 11: (0, 151), 12: (0, 136), 13: (0, 158), 15: (0, 162), 16: (0, 146), 17: (0, 192), 43: (0, 134), 18: (0, 143), 19: (0, 142), 20: (0, 147), 21: (0, 132), 22: (0, 141), 23: (0, 195), 24: (0, 172), 25: (0, 175), 26: (0, 129), 27: (0, 135), 28: (0, 86), 29: (0, 25), 30: (0, 19), 31: (0, 80), 32: (0, 7), 33: (0, 53), 34: (0, 17), 35: (0, 16), 36: (0, 51), 38: (0, 74), 39: (0, 8), 40: (0, 30), 42: (0, 193), 14: (0, 187), 41: (0, 48)}, 172: {0: (1, {'@': 104}), 1: (1, {'@': 104}), 44: (1, {'@': 104}), 45: (1, {'@': 104}), 8: (1, {'@': 104}), 46: (1, {'@': 104})}, 173: {63: (0, 116), 52: (0, 61), 53: (0, 102), 45: (0, 124)}, 174: {23: (0, 173), 56: (0, 66), 61: (0, 0), 57: (0, 34), 58: (0, 42), 59: (0, 121), 60: (0, 39), 8: (0, 125), 52: (0, 61), 53: (0, 100), 36: (0, 28), 40: (0, 30)}, 175: {8: (0, 36)}, 176: {0: (0, 188)}, 177: {0: (1, {'@': 105}), 1: (1, {'@': 105}), 44: (1, {'@': 105}), 45: (1, {'@': 105}), 8: (1, {'@': 105}), 46: (1, {'@': 105})}, 178: {0: (1, {'@': 106}), 1: (1, {'@': 106}), 44: (1, {'@': 106}), 45: (1, {'@': 106}), 8: (1, {'@': 106}), 46: (1, {'@': 106})}, 179: {2: (0, 22), 3: (0, 47), 4: (0, 55), 5: (0, 29), 6: (0, 114), 7: (0, 90), 8: (0, 85), 9: (0, 38), 10: (0, 35), 11: (0, 151), 12: (0, 136), 13: (0, 158), 15: (0, 162), 14: (0, 159), 16: (0, 146), 17: (0, 192), 18: (0, 143), 19: (0, 142), 20: (0, 147), 21: (0, 132), 22: (0, 141), 23: (0, 195), 24: (0, 172), 25: (0, 175), 26: (0, 129), 27: (0, 135), 28: (0, 86), 29: (0, 25), 30: (0, 19), 31: (0, 80), 32: (0, 7), 33: (0, 53), 34: (0, 17), 35: (0, 16), 36: (0, 51), 37: (0, 23), 38: (0, 74), 39: (0, 8), 40: (0, 30), 41: (0, 48)}, 180: {1: (0, 119), 0: (0, 4)}, 181: {2: (0, 22), 3: (0, 47), 4: (0, 55), 5: (0, 29), 6: (0, 114), 7: (0, 90), 8: (0, 85), 9: (0, 38), 10: (0, 35), 11: (0, 151), 12: (0, 136), 13: (0, 158), 15: (0, 162), 16: (0, 146), 17: (0, 192), 18: (0, 143), 19: (0, 142), 20: (0, 147), 21: (0, 132), 22: (0, 141), 23: (0, 195), 24: (0, 172), 25: (0, 175), 26: (0, 129), 27: (0, 135), 28: (0, 86), 29: (0, 25), 30: (0, 19), 31: (0, 80), 32: (0, 7), 33: (0, 53), 14: (0, 92), 34: (0, 17), 35: (0, 16), 36: (0, 51), 37: (0, 23), 38: (0, 74), 39: (0, 8), 40: (0, 30), 41: (0, 48)}, 182: {2: (0, 22), 3: (0, 47), 4: (0, 55), 5: (0, 29), 6: (0, 114), 7: (0, 90), 8: (0, 85), 9: (0, 38), 10: (0, 35), 11: (0, 151), 12: (0, 136), 13: (0, 158), 15: (0, 162), 16: (0, 146), 17: (0, 192), 18: (0, 143), 19: (0, 142), 20: (0, 147), 21: (0, 132), 22: (0, 141), 23: (0, 195), 24: (0, 172), 25: (0, 175), 26: (0, 129), 27: (0, 135), 28: (0, 86), 29: (0, 25), 30: (0, 19), 31: (0, 80), 32: (0, 7), 33: (0, 53), 34: (0, 17), 35: (0, 16), 36: (0, 51), 14: (0, 144), 37: (0, 23), 38: (0, 74), 39: (0, 8), 40: (0, 30), 41: (0, 48)}, 183: {42: (0, 193), 43: (0, 194)}, 184: {0: (1, {'@': 107}), 1: (1, {'@': 107}), 44: (1, {'@': 107}), 45: (1, {'@': 107}), 8: (1, {'@': 107}), 46: (1, {'@': 107})}, 185: {0: (1, {'@': 108}), 1: (1, {'@': 108}), 44: (1, {'@': 108}), 45: (1, {'@': 108}), 8: (1, {'@': 108}), 46: (1, {'@': 108})}, 186: {0: (0, 2), 1: (0, 179)}, 187: {0: (1, {'@': 109}), 1: (1, {'@': 109}), 46: (1, {'@': 109})}, 188: {0: (1, {'@': 110}), 1: (1, {'@': 110}), 44: (1, {'@': 110}), 45: (1, {'@': 110}), 8: (1, {'@': 110}), 46: (1, {'@': 110})}, 189: {0: (0, 149)}, 190: {51: (0, 139)}, 191: {2: (0, 22), 3: (0, 47), 4: (0, 55), 5: (0, 29), 6: (0, 114), 7: (0, 90), 8: (0, 85), 9: (0, 38), 10: (0, 35), 11: (0, 151), 12: (0, 136), 13: (0, 158), 15: (0, 162), 16: (0, 146), 17: (0, 192), 18: (0, 143), 19: (0, 142), 20: (0, 147), 21: (0, 132), 22: (0, 141), 23: (0, 195), 24: (0, 172), 25: (0, 175), 26: (0, 129), 14: (0, 152), 27: (0, 135), 28: (0, 86), 29: (0, 25), 30: (0, 19), 31: (0, 80), 32: (0, 7), 33: (0, 53), 34: (0, 17), 35: (0, 16), 36: (0, 51), 37: (0, 23), 38: (0, 74), 39: (0, 8), 40: (0, 30), 41: (0, 48)}, 192: {8: (0, 91)}, 193: {66: (0, 133)}, 194: {0: (0, 165)}, 195: {52: (0, 61), 53: (0, 78)}}, 'start_states': {'start': 15}, 'end_states': {'start': 65}}, 'lexer_conf': {'tokens': [{'@': 0}, {'@': 1}, {'@': 2}, {'@': 3}, {'@': 4}, {'@': 5}, {'@': 6}, {'@': 7}, {'@': 8}, {'@': 9}, {'@': 10}, {'@': 11}, {'@': 12}, {'@': 13}, {'@': 14}, {'@': 15}, {'@': 16}, {'@': 17}, {'@': 18}, {'@': 19}, {'@': 20}, {'@': 21}, {'@': 22}, {'@': 23}, {'@': 24}, {'@': 25}, {'@': 26}, {'@': 27}, {'@': 28}], 'ignore': ['WS'], 'g_regex_flags': 0, 'use_bytes': False, '__type__': 'LexerConf'}, 'start': ['start'], '__type__': 'LALR_ContextualLexer'}, 'rules': [{'@': 95}, {'@': 86}, {'@': 70}, {'@': 56}, {'@': 37}, {'@': 35}, {'@': 98}, {'@': 104}, {'@': 79}, {'@': 36}, {'@': 48}, {'@': 67}, {'@': 57}, {'@': 31}, {'@': 43}, {'@': 78}, {'@': 84}, {'@': 80}, {'@': 47}, {'@': 89}, {'@': 39}, {'@': 55}, {'@': 88}, {'@': 91}, {'@': 100}, {'@': 40}, {'@': 69}, {'@': 85}, {'@': 110}, {'@': 94}, {'@': 41}, {'@': 73}, {'@': 65}, {'@': 106}, {'@': 30}, {'@': 107}, {'@': 77}, {'@': 68}, {'@': 61}, {'@': 90}, {'@': 105}, {'@': 102}, {'@': 108}, {'@': 51}, {'@': 74}, {'@': 53}, {'@': 72}, {'@': 59}, {'@': 93}, {'@': 92}, {'@': 103}, {'@': 82}, {'@': 96}, {'@': 32}, {'@': 101}, {'@': 76}, {'@': 49}, {'@': 50}, {'@': 75}, {'@': 42}, {'@': 62}, {'@': 81}, {'@': 46}, {'@': 87}, {'@': 52}, {'@': 45}, {'@': 58}, {'@': 66}, {'@': 83}, {'@': 33}, {'@': 60}, {'@': 44}, {'@': 109}, {'@': 111}, {'@': 99}, {'@': 112}, {'@': 38}, {'@': 113}, {'@': 97}, {'@': 114}, {'@': 63}, {'@': 115}, {'@': 71}, {'@': 116}, {'@': 54}, {'@': 29}, {'@': 64}, {'@': 34}], 'options': {'debug': False, 'keep_all_tokens': False, 'tree_class': None, 'cache': False, 'postlex': None, 'parser': 'lalr', 'lexer': 'contextual', 'transformer': None, 'start': ['start'], 'priority': 'normal', 'ambiguity': 'auto', 'regex': False, 'propagate_positions': False, 'lexer_callbacks': {}, 'maybe_placeholders': False, 'edit_terminals': None, 'g_regex_flags': 0, 'use_bytes': False, 'import_paths': [], 'source_path': None}, '__type__': 'Lark'} +) +MEMO = ( +{0: {'name': 'HARDCODED', 'pattern': {'value': '(?:(?:(?:string|char)|bytes)|byte)', 'flags': [], '_width': [4, 6], '__type__': 'PatternRE'}, 'priority': 1, '__type__': 'TerminalDef'}, 1: {'name': 'TYPE', 'pattern': {'value': '(?:(?:(?:(?:(?:(?:(?:(?:(?:(?:(?:(?:int8|int16)|int32)|int64)|int128)|uint8)|uint16)|uint32)|uint64)|uint128)|float32)|float64)|bool)', 'flags': [], '_width': [4, 7], '__type__': 'PatternRE'}, 'priority': 1, '__type__': 'TerminalDef'}, 2: {'name': 'UNQUOTED_STRING', 'pattern': {'value': '[a-zA-Z]+', 'flags': [], '_width': [1, 4294967295], '__type__': 'PatternRE'}, 'priority': -1, '__type__': 'TerminalDef'}, 3: {'name': 'SIGNED_NUMBER', 'pattern': {'value': '(?:(?:\\+|\\-))?(?:(?:(?:[0-9])+(?:e|E)(?:(?:\\+|\\-))?(?:[0-9])+|(?:(?:[0-9])+\\.(?:(?:[0-9])+)?|\\.(?:[0-9])+)(?:(?:e|E)(?:(?:\\+|\\-))?(?:[0-9])+)?)|(?:[0-9])+)', 'flags': [], '_width': [1, 4294967295], '__type__': 'PatternRE'}, 'priority': 1, '__type__': 'TerminalDef'}, 4: {'name': 'WS', 'pattern': {'value': '(?:[ \t\x0c\r\n])+', 'flags': [], '_width': [1, 4294967295], '__type__': 'PatternRE'}, 'priority': 1, '__type__': 'TerminalDef'}, 5: {'name': 'UNKNOWN', 'pattern': {'value': 'unknown', 'flags': [], '__type__': 'PatternStr'}, 'priority': 1, '__type__': 'TerminalDef'}, 6: {'name': 'CATEGORICAL', 'pattern': {'value': 'categorical', 'flags': [], '__type__': 'PatternStr'}, 'priority': 1, '__type__': 'TerminalDef'}, 7: {'name': 'LSQB', 'pattern': {'value': '[', 'flags': [], '__type__': 'PatternStr'}, 'priority': 1, '__type__': 'TerminalDef'}, 8: {'name': '__ANON_0', 'pattern': {'value': 'type', 'flags': [], '__type__': 'PatternStr'}, 'priority': 1, '__type__': 'TerminalDef'}, 9: {'name': 'EQUAL', 'pattern': {'value': '=', 'flags': [], '__type__': 'PatternStr'}, 'priority': 1, '__type__': 'TerminalDef'}, 10: {'name': 'RSQB', 'pattern': {'value': ']', 'flags': [], '__type__': 'PatternStr'}, 'priority': 1, '__type__': 'TerminalDef'}, 11: {'name': 'QMARK', 'pattern': {'value': '?', 'flags': [], '__type__': 'PatternStr'}, 'priority': 1, '__type__': 'TerminalDef'}, 12: {'name': 'OPTION', 'pattern': {'value': 'option', 'flags': [], '__type__': 'PatternStr'}, 'priority': 1, '__type__': 'TerminalDef'}, 13: {'name': 'COMMA', 'pattern': {'value': ',', 'flags': [], '__type__': 'PatternStr'}, 'priority': 1, '__type__': 'TerminalDef'}, 14: {'name': 'UNION', 'pattern': {'value': 'union', 'flags': [], '__type__': 'PatternStr'}, 'priority': 1, '__type__': 'TerminalDef'}, 15: {'name': 'VAR', 'pattern': {'value': 'var', 'flags': [], '__type__': 'PatternStr'}, 'priority': 1, '__type__': 'TerminalDef'}, 16: {'name': 'STAR', 'pattern': {'value': '*', 'flags': [], '__type__': 'PatternStr'}, 'priority': 1, '__type__': 'TerminalDef'}, 17: {'name': 'LPAR', 'pattern': {'value': '(', 'flags': [], '__type__': 'PatternStr'}, 'priority': 1, '__type__': 'TerminalDef'}, 18: {'name': 'RPAR', 'pattern': {'value': ')', 'flags': [], '__type__': 'PatternStr'}, 'priority': 1, '__type__': 'TerminalDef'}, 19: {'name': 'TUPLE', 'pattern': {'value': 'tuple', 'flags': [], '__type__': 'PatternStr'}, 'priority': 1, '__type__': 'TerminalDef'}, 20: {'name': 'COLON', 'pattern': {'value': ':', 'flags': [], '__type__': 'PatternStr'}, 'priority': 1, '__type__': 'TerminalDef'}, 21: {'name': 'LBRACE', 'pattern': {'value': '{', 'flags': [], '__type__': 'PatternStr'}, 'priority': 1, '__type__': 'TerminalDef'}, 22: {'name': 'RBRACE', 'pattern': {'value': '}', 'flags': [], '__type__': 'PatternStr'}, 'priority': 1, '__type__': 'TerminalDef'}, 23: {'name': 'STRUCT', 'pattern': {'value': 'struct', 'flags': [], '__type__': 'PatternStr'}, 'priority': 1, '__type__': 'TerminalDef'}, 24: {'name': 'PARAMETERS', 'pattern': {'value': 'parameters', 'flags': [], '__type__': 'PatternStr'}, 'priority': 1, '__type__': 'TerminalDef'}, 25: {'name': 'TRUE', 'pattern': {'value': 'true', 'flags': [], '__type__': 'PatternStr'}, 'priority': 1, '__type__': 'TerminalDef'}, 26: {'name': 'FALSE', 'pattern': {'value': 'false', 'flags': [], '__type__': 'PatternStr'}, 'priority': 1, '__type__': 'TerminalDef'}, 27: {'name': 'NULL', 'pattern': {'value': 'null', 'flags': [], '__type__': 'PatternStr'}, 'priority': 1, '__type__': 'TerminalDef'}, 28: {'name': '__ANON_1', 'pattern': {'value': '((?:"(?:[^"\n\r\\\\]|(?:\\\\u[0-9a-fA-F]{4})|(?:\\\\["bfnrt]))*")|(?:\\\\\\\'(?:[^\\\\\\\'\n\r\\\\]|(?:\\\\u[0-9a-fA-F]{4})|(?:\\\\[\\\'bfnrt]))*")*\\\\\\\')', 'flags': [], '_width': [2, 4294967295], '__type__': 'PatternRE'}, 'priority': 1, '__type__': 'TerminalDef'}, 29: {'origin': {'name': '__list_obj_star_3', '__type__': 'NonTerminal'}, 'expansion': [{'name': '__list_obj_star_3', '__type__': 'NonTerminal'}, {'name': 'COMMA', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'json', '__type__': 'NonTerminal'}], 'order': 1, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 30: {'origin': {'name': 'union_single', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'UNION', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'input', '__type__': 'NonTerminal'}, {'name': '__union_single_star_0', '__type__': 'NonTerminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 31: {'origin': {'name': 'record', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'record_struct', '__type__': 'NonTerminal'}], 'order': 3, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 32: {'origin': {'name': 'regular_outparm', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'number', '__type__': 'NonTerminal'}, {'name': 'STAR', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'input', '__type__': 'NonTerminal'}, {'name': 'COMMA', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'def_option', '__type__': 'NonTerminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 33: {'origin': {'name': 'pair', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'string', '__type__': 'NonTerminal'}, {'name': 'COLON', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'json', '__type__': 'NonTerminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 34: {'origin': {'name': '__dict_obj_star_4', '__type__': 'NonTerminal'}, 'expansion': [{'name': '__dict_obj_star_4', '__type__': 'NonTerminal'}, {'name': 'COMMA', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'pair', '__type__': 'NonTerminal'}], 'order': 1, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 35: {'origin': {'name': 'input', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'regular', '__type__': 'NonTerminal'}], 'order': 4, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 36: {'origin': {'name': 'input', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'categories', '__type__': 'NonTerminal'}], 'order': 8, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 37: {'origin': {'name': 'input', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'optiontype', '__type__': 'NonTerminal'}], 'order': 3, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 38: {'origin': {'name': '__record_dict_star_1', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'COMMA', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'string', '__type__': 'NonTerminal'}, {'name': 'COLON', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'input', '__type__': 'NonTerminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 39: {'origin': {'name': 'optiontype', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'option_parm', '__type__': 'NonTerminal'}], 'order': 1, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 40: {'origin': {'name': 'listtype', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'list_parm', '__type__': 'NonTerminal'}], 'order': 1, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 41: {'origin': {'name': 'option_single', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'QMARK', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'input', '__type__': 'NonTerminal'}, {'name': 'options', '__type__': 'NonTerminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 42: {'origin': {'name': 'json', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'number', '__type__': 'NonTerminal'}], 'order': 3, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': True, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 43: {'origin': {'name': 'record', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'record_highlevel', '__type__': 'NonTerminal'}], 'order': 4, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 44: {'origin': {'name': 'number', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'SIGNED_NUMBER', 'filter_out': False, '__type__': 'Terminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 45: {'origin': {'name': 'list_obj', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}], 'order': 2, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': [False, True, False], '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 46: {'origin': {'name': 'json', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'NULL', 'filter_out': True, '__type__': 'Terminal'}], 'order': 6, 'alias': 'null', 'options': {'keep_all_tokens': False, 'expand1': True, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 47: {'origin': {'name': 'unknown', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'UNKNOWN', 'filter_out': True, '__type__': 'Terminal'}], 'order': 1, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': [False, True], '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 48: {'origin': {'name': 'record', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'record_tuple', '__type__': 'NonTerminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 49: {'origin': {'name': 'json', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'dict_obj', '__type__': 'NonTerminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': True, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 50: {'origin': {'name': 'json', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'list_obj', '__type__': 'NonTerminal'}], 'order': 1, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': True, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 51: {'origin': {'name': 'record_tuple_param', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'TUPLE', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'input', '__type__': 'NonTerminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'COMMA', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'def_option', '__type__': 'NonTerminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}], 'order': 1, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 52: {'origin': {'name': 'list_obj', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'json', '__type__': 'NonTerminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}], 'order': 1, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 53: {'origin': {'name': 'record_dict', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'LBRACE', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'string', '__type__': 'NonTerminal'}, {'name': 'COLON', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'input', '__type__': 'NonTerminal'}, {'name': 'RBRACE', 'filter_out': True, '__type__': 'Terminal'}], 'order': 1, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 54: {'origin': {'name': '__list_obj_star_3', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'COMMA', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'json', '__type__': 'NonTerminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 55: {'origin': {'name': 'optiontype', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'option_highlevel', '__type__': 'NonTerminal'}], 'order': 2, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 56: {'origin': {'name': 'input', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'primitive', '__type__': 'NonTerminal'}], 'order': 2, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 57: {'origin': {'name': 'record', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'record_dict', '__type__': 'NonTerminal'}], 'order': 2, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 58: {'origin': {'name': 'dict_obj', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'LBRACE', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'pair', '__type__': 'NonTerminal'}, {'name': '__dict_obj_star_4', '__type__': 'NonTerminal'}, {'name': 'RBRACE', 'filter_out': True, '__type__': 'Terminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 59: {'origin': {'name': 'record_struct', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'STRUCT', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'string', '__type__': 'NonTerminal'}, {'name': '__record_struct_star_2', '__type__': 'NonTerminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'COMMA', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'input', '__type__': 'NonTerminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'COMMA', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'def_option', '__type__': 'NonTerminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}], 'order': 1, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 60: {'origin': {'name': 'string', '__type__': 'NonTerminal'}, 'expansion': [{'name': '__ANON_1', 'filter_out': False, '__type__': 'Terminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 61: {'origin': {'name': 'list_parm', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'VAR', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'STAR', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'input', '__type__': 'NonTerminal'}, {'name': 'COMMA', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'def_option', '__type__': 'NonTerminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 62: {'origin': {'name': 'json', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'TRUE', 'filter_out': True, '__type__': 'Terminal'}], 'order': 4, 'alias': 'true', 'options': {'keep_all_tokens': False, 'expand1': True, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 63: {'origin': {'name': '__record_struct_star_2', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'COMMA', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'string', '__type__': 'NonTerminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 64: {'origin': {'name': '__dict_obj_star_4', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'COMMA', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'pair', '__type__': 'NonTerminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 65: {'origin': {'name': 'option_parm', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'OPTION', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'input', '__type__': 'NonTerminal'}, {'name': 'COMMA', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'def_option', '__type__': 'NonTerminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 66: {'origin': {'name': 'dict_obj', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'LBRACE', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'pair', '__type__': 'NonTerminal'}, {'name': 'RBRACE', 'filter_out': True, '__type__': 'Terminal'}], 'order': 1, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 67: {'origin': {'name': 'record', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'record_tuple_param', '__type__': 'NonTerminal'}], 'order': 1, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 68: {'origin': {'name': 'union_parm', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'UNION', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'input', '__type__': 'NonTerminal'}, {'name': 'COMMA', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'def_option', '__type__': 'NonTerminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}], 'order': 1, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 69: {'origin': {'name': 'uniontype', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'union_single', '__type__': 'NonTerminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 70: {'origin': {'name': 'input', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'unknown', '__type__': 'NonTerminal'}], 'order': 1, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 71: {'origin': {'name': '__record_struct_star_2', '__type__': 'NonTerminal'}, 'expansion': [{'name': '__record_struct_star_2', '__type__': 'NonTerminal'}, {'name': 'COMMA', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'string', '__type__': 'NonTerminal'}], 'order': 2, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 72: {'origin': {'name': 'record_struct', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'STRUCT', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'string', '__type__': 'NonTerminal'}, {'name': '__record_struct_star_2', '__type__': 'NonTerminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'COMMA', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'input', '__type__': 'NonTerminal'}, {'name': '__union_single_star_0', '__type__': 'NonTerminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'COMMA', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'def_option', '__type__': 'NonTerminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 73: {'origin': {'name': 'option_single', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'QMARK', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'input', '__type__': 'NonTerminal'}], 'order': 1, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': [False, False, True], '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 74: {'origin': {'name': 'record_dict', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'LBRACE', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'string', '__type__': 'NonTerminal'}, {'name': 'COLON', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'input', '__type__': 'NonTerminal'}, {'name': '__record_dict_star_1', '__type__': 'NonTerminal'}, {'name': 'RBRACE', 'filter_out': True, '__type__': 'Terminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 75: {'origin': {'name': 'json', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'string', '__type__': 'NonTerminal'}], 'order': 2, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': True, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 76: {'origin': {'name': 'def_option', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'PARAMETERS', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'EQUAL', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'dict_obj', '__type__': 'NonTerminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 77: {'origin': {'name': 'union_parm', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'UNION', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'input', '__type__': 'NonTerminal'}, {'name': '__union_single_star_0', '__type__': 'NonTerminal'}, {'name': 'COMMA', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'def_option', '__type__': 'NonTerminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 78: {'origin': {'name': 'primitive', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'TYPE', 'filter_out': False, '__type__': 'Terminal'}, {'name': 'options', '__type__': 'NonTerminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 79: {'origin': {'name': 'input', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'predefined_typestr', '__type__': 'NonTerminal'}], 'order': 7, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 80: {'origin': {'name': 'unknown', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'UNKNOWN', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'options', '__type__': 'NonTerminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 81: {'origin': {'name': 'json', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'FALSE', 'filter_out': True, '__type__': 'Terminal'}], 'order': 5, 'alias': 'false', 'options': {'keep_all_tokens': False, 'expand1': True, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 82: {'origin': {'name': 'record_highlevel', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'UNQUOTED_STRING', 'filter_out': False, '__type__': 'Terminal'}, {'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'string', '__type__': 'NonTerminal'}, {'name': 'COLON', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'input', '__type__': 'NonTerminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}], 'order': 1, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 83: {'origin': {'name': 'dict_obj', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'LBRACE', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'RBRACE', 'filter_out': True, '__type__': 'Terminal'}], 'order': 2, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': [False, True, False], '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 84: {'origin': {'name': 'primitive', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'TYPE', 'filter_out': False, '__type__': 'Terminal'}], 'order': 1, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': [False, True], '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 85: {'origin': {'name': 'uniontype', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'union_parm', '__type__': 'NonTerminal'}], 'order': 1, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 86: {'origin': {'name': 'input', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'record', '__type__': 'NonTerminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 87: {'origin': {'name': 'list_obj', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'json', '__type__': 'NonTerminal'}, {'name': '__list_obj_star_3', '__type__': 'NonTerminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 88: {'origin': {'name': 'regular', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'regular_inparm', '__type__': 'NonTerminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 89: {'origin': {'name': 'optiontype', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'option_single', '__type__': 'NonTerminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 90: {'origin': {'name': 'list_single', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'VAR', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'STAR', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'input', '__type__': 'NonTerminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 91: {'origin': {'name': 'regular', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'regular_outparm', '__type__': 'NonTerminal'}], 'order': 1, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 92: {'origin': {'name': 'record_struct', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'STRUCT', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'string', '__type__': 'NonTerminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'COMMA', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'input', '__type__': 'NonTerminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'COMMA', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'def_option', '__type__': 'NonTerminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}], 'order': 3, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 93: {'origin': {'name': 'record_struct', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'STRUCT', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'string', '__type__': 'NonTerminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'COMMA', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'input', '__type__': 'NonTerminal'}, {'name': '__union_single_star_0', '__type__': 'NonTerminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'COMMA', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'def_option', '__type__': 'NonTerminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}], 'order': 2, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 94: {'origin': {'name': 'predefined_typestr', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'HARDCODED', 'filter_out': False, '__type__': 'Terminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 95: {'origin': {'name': 'start', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'input', '__type__': 'NonTerminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 96: {'origin': {'name': 'regular_inparm', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'number', '__type__': 'NonTerminal'}, {'name': 'STAR', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'input', '__type__': 'NonTerminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 97: {'origin': {'name': '__record_dict_star_1', '__type__': 'NonTerminal'}, 'expansion': [{'name': '__record_dict_star_1', '__type__': 'NonTerminal'}, {'name': 'COMMA', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'string', '__type__': 'NonTerminal'}, {'name': 'COLON', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'input', '__type__': 'NonTerminal'}], 'order': 2, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 98: {'origin': {'name': 'input', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'listtype', '__type__': 'NonTerminal'}], 'order': 5, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 99: {'origin': {'name': '__union_single_star_0', '__type__': 'NonTerminal'}, 'expansion': [{'name': '__union_single_star_0', '__type__': 'NonTerminal'}, {'name': 'COMMA', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'input', '__type__': 'NonTerminal'}], 'order': 2, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 100: {'origin': {'name': 'listtype', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'list_single', '__type__': 'NonTerminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 101: {'origin': {'name': 'options', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'def_option', '__type__': 'NonTerminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 102: {'origin': {'name': 'record_tuple', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'LPAR', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'input', '__type__': 'NonTerminal'}, {'name': 'RPAR', 'filter_out': True, '__type__': 'Terminal'}], 'order': 1, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 103: {'origin': {'name': 'record_highlevel', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'UNQUOTED_STRING', 'filter_out': False, '__type__': 'Terminal'}, {'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'string', '__type__': 'NonTerminal'}, {'name': 'COLON', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'input', '__type__': 'NonTerminal'}, {'name': '__record_dict_star_1', '__type__': 'NonTerminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 104: {'origin': {'name': 'input', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'uniontype', '__type__': 'NonTerminal'}], 'order': 6, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 105: {'origin': {'name': 'record_tuple', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'LPAR', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'input', '__type__': 'NonTerminal'}, {'name': '__union_single_star_0', '__type__': 'NonTerminal'}, {'name': 'RPAR', 'filter_out': True, '__type__': 'Terminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 106: {'origin': {'name': 'option_highlevel', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'OPTION', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'input', '__type__': 'NonTerminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 107: {'origin': {'name': 'union_single', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'UNION', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'input', '__type__': 'NonTerminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}], 'order': 1, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 108: {'origin': {'name': 'record_tuple_param', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'TUPLE', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'input', '__type__': 'NonTerminal'}, {'name': '__union_single_star_0', '__type__': 'NonTerminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'COMMA', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'def_option', '__type__': 'NonTerminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 109: {'origin': {'name': '__union_single_star_0', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'COMMA', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'input', '__type__': 'NonTerminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 110: {'origin': {'name': 'categories', '__type__': 'NonTerminal'}, 'expansion': [{'name': 'CATEGORICAL', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'LSQB', 'filter_out': True, '__type__': 'Terminal'}, {'name': '__ANON_0', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'EQUAL', 'filter_out': True, '__type__': 'Terminal'}, {'name': 'input', '__type__': 'NonTerminal'}, {'name': 'RSQB', 'filter_out': True, '__type__': 'Terminal'}], 'order': 0, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': (), '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 111: {'origin': {'name': '__union_single_star_0', '__type__': 'NonTerminal'}, 'expansion': [], 'order': 1, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': [True], '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 112: {'origin': {'name': '__union_single_star_0', '__type__': 'NonTerminal'}, 'expansion': [{'name': '__union_single_star_0', '__type__': 'NonTerminal'}], 'order': 3, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': [False, True], '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 113: {'origin': {'name': '__record_dict_star_1', '__type__': 'NonTerminal'}, 'expansion': [], 'order': 1, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': [True], '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 114: {'origin': {'name': '__record_dict_star_1', '__type__': 'NonTerminal'}, 'expansion': [{'name': '__record_dict_star_1', '__type__': 'NonTerminal'}], 'order': 3, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': [False, True], '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 115: {'origin': {'name': '__record_struct_star_2', '__type__': 'NonTerminal'}, 'expansion': [], 'order': 1, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': [True], '__type__': 'RuleOptions'}, '__type__': 'Rule'}, 116: {'origin': {'name': '__record_struct_star_2', '__type__': 'NonTerminal'}, 'expansion': [{'name': '__record_struct_star_2', '__type__': 'NonTerminal'}], 'order': 3, 'alias': None, 'options': {'keep_all_tokens': False, 'expand1': False, 'priority': None, 'template_source': None, 'empty_indices': [False, True], '__type__': 'RuleOptions'}, '__type__': 'Rule'}} +) +Shift = 0 +Reduce = 1 +def Lark_StandAlone(**kwargs): + return Lark._load_from_dict(DATA, MEMO, **kwargs) diff --git a/studies/type-parser-1.5/parser.py b/studies/type-parser-1.5/parser.py new file mode 100644 index 0000000000..dec387e86a --- /dev/null +++ b/studies/type-parser-1.5/parser.py @@ -0,0 +1,322 @@ +# flake8: noqa +# fmt: off +# pylint: skip-file + +# BSD 3-Clause License; see https://github.com/scikit-hep/awkward-1.0/blob/main/LICENSE + +# v2: keep this file, but drop the two *_v1 functions + +import awkward as ak + +from awkward._typeparser.generated_parser import Lark_StandAlone, Transformer + + +class TreeToJson(Transformer): + def string(self, s): + (s,) = s + return s[1:-1] + + def number(self, n): + (n,) = n + if "." in n: + return float(n) + else: + return int(n) + + list_obj = list + pair = tuple + dict_obj = dict + + def null(self, s): + return None + + def true(self, s): + return True + + def false(self, s): + return False + + +def toast_v1(ptnode, highlevel, categorical): + if ptnode.__class__.__name__ == "Token": + return ptnode.value + + elif ptnode.data == "start": + return toast_v1(ptnode.children[0], highlevel, categorical) + + elif ptnode.data == "input": + assert len(ptnode.children) == 1 + return toast_v1(ptnode.children[0], highlevel, categorical) + + elif ptnode.data == "predefined_typestr": + if ptnode.children[0] == "string": + parms = {"__array__": "string"} + if categorical: + parms.update({"__categorical__": True}) + categorical = False + return ak.types.ListType( + ak.types.PrimitiveType( + "uint8", parameters={"__array__": "char"}, typestr="char" + ), + parameters=parms, + typestr="string", + ) + elif ptnode.children[0] == "char": + parms = {"__array__": "char"} + if categorical: + parms.update({"__categorical__": True}) + categorical = False + return ak.types.PrimitiveType("uint8", parameters=parms, typestr="char") + elif ptnode.children[0] == "byte": + parms = {"__array__": "byte"} + if categorical: + parms.update({"__categorical__": True}) + categorical = False + return ak.types.PrimitiveType("uint8", parameters=parms, typestr="byte") + elif ptnode.children[0] == "bytes": + parms = {"__array__": "bytestring"} + if categorical: + parms.update({"__categorical__": True}) + categorical = False + return ak.types.ListType( + ak.types.PrimitiveType( + "uint8", parameters={"__array__": "byte"}, typestr="byte" + ), + parameters=parms, + typestr="bytes", + ) + else: + raise AssertionError(f"unhandled typestring {ptnode.children[0]}") + + elif ptnode.data == "primitive": + if len(ptnode.children) == 1: + parms = {} + if categorical: + parms.update({"__categorical__": True}) + categorical = False + return ak.types.PrimitiveType( + toast_v1(ptnode.children[0], highlevel, False), parameters=parms + ) + elif len(ptnode.children) == 2: + parms = toast_v1(ptnode.children[1], highlevel, False) + if categorical: + parms.update({"__categorical__": True}) + categorical = False + return ak.types.PrimitiveType( + toast_v1(ptnode.children[0], highlevel, categorical), + parms, + ) + else: + raise AssertionError("unhandled PrimitiveType node") + + elif ptnode.data == "categories": + assert highlevel is True + return toast_v1(ptnode.children[0], highlevel, True) + + elif ptnode.data == "unknown": + if len(ptnode.children) == 0: + parms = {} + if categorical: + parms.update({"__categorical__": True}) + categorical = False + return ak.types.UnknownType(parameters=parms) + elif len(ptnode.children) == 1: + parms = toast_v1(ptnode.children[0], highlevel, False) + if categorical: + parms.update({"__categorical__": True}) + categorical = False + return ak.types.UnknownType(parameters=parms) + else: + raise AssertionError("unhandled UnknownType node") + + elif ptnode.data == "listtype": + return toast_v1(ptnode.children[0], highlevel, categorical) + + elif ptnode.data == "list_single": + parms = {} + if categorical: + parms.update({"__categorical__": True}) + categorical = False + return ak.types.ListType( + toast_v1(ptnode.children[0], highlevel, False), parameters=parms + ) + + elif ptnode.data == "list_parm": + parms = toast_v1(ptnode.children[1], highlevel, False) + if categorical: + parms.update({"__categorical__": True}) + categorical = False + return ak.types.ListType( + toast_v1(ptnode.children[0], highlevel, categorical), parms + ) + + elif ptnode.data == "uniontype": + return toast_v1(ptnode.children[0], highlevel, categorical) + + elif ptnode.data == "union_single": + parms = {} + if categorical: + parms.update({"__categorical__": True}) + categorical = False + content_list = [] + for node in ptnode.children: + content_list.append(toast_v1(node, highlevel, False)) + return ak.types.UnionType(content_list, parameters=parms) + + elif ptnode.data == "union_parm": + parms = toast_v1(ptnode.children[-1], highlevel, False) + if categorical: + parms.update({"__categorical__": True}) + categorical = False + content_list = [] + for node in ptnode.children[:-1]: + content_list.append(toast_v1(node, highlevel, False)) + return ak.types.UnionType(content_list, parms) + + elif ptnode.data == "optiontype": + return toast_v1(ptnode.children[0], highlevel, categorical) + + elif ptnode.data == "option_single": + parms = {} + if categorical: + parms.update({"__categorical__": True}) + categorical = False + return ak.types.OptionType( + toast_v1(ptnode.children[0], highlevel, False), parameters=parms + ) + + elif ptnode.data == "option_parm": + parms = toast_v1(ptnode.children[1], highlevel, False) + if categorical: + parms.update({"__categorical__": True}) + categorical = False + return ak.types.OptionType( + toast_v1(ptnode.children[0], highlevel, False), + parameters=parms, + ) + + elif ptnode.data == "option_highlevel": + assert highlevel + parms = {} + if categorical: + parms.update({"__categorical__": True}) + categorical = False + return ak.types.OptionType( + toast_v1(ptnode.children[0], highlevel, False), parameters=parms + ) + + elif ptnode.data == "record": + return toast_v1(ptnode.children[0], highlevel, categorical) + + elif ptnode.data == "record_tuple": + parms = {} + if categorical: + parms.update({"__categorical__": True}) + categorical = False + content_list = [] + for node in ptnode.children: + content_list.append(toast_v1(node, highlevel, categorical)) + return ak.types.RecordType(tuple(content_list), parameters=parms) + + elif ptnode.data == "record_dict": + parms = {} + if categorical: + parms.update({"__categorical__": True}) + categorical = False + content_types = [] + content_keys = [] + for i in range(0, len(ptnode.children), 2): + content_keys.append(ptnode.children[i]) + content_types.append( + toast_v1(ptnode.children[i + 1], highlevel, categorical) + ) + return ak.types.RecordType(content_types, content_keys, parameters=parms) + + elif ptnode.data == "record_tuple_param": + parms = toast_v1(ptnode.children[-1], highlevel, False) + if categorical: + parms.update({"__categorical__": True}) + categorical = False + content_list = [] + for node in ptnode.children[:-1]: + content_list.append(toast_v1(node, highlevel, False)) + return ak.types.RecordType(tuple(content_list), parameters=parms) + + elif ptnode.data == "record_struct": + parms = toast_v1(ptnode.children[-1], highlevel, False) + if categorical: + parms.update({"__categorical__": True}) + categorical = False + content_list = [] + content_keys = [] + for node in ptnode.children[:-1]: + if isinstance(node, str): + content_keys.append(node) + else: + content_list.append(toast_v1(node, highlevel, False)) + return ak.types.RecordType( + tuple(content_list), + keys=content_keys, + parameters=parms, + ) + + elif ptnode.data == "record_highlevel": + assert highlevel + parms = {"__record__": ptnode.children[0]} + if categorical: + parms.update({"__categorical__": True}) + categorical = False + content_list = [] + content_keys = [] + for node in ptnode.children[1:]: + if isinstance(node, str): + content_keys.append(node) + else: + content_list.append(toast_v1(node, highlevel, False)) + return ak.types.RecordType( + tuple(content_list), + keys=content_keys, + parameters=parms, + ) + + elif ptnode.data == "regular": + assert (len(ptnode.children)) == 1 + return toast_v1(ptnode.children[0], highlevel, categorical) + + elif ptnode.data == "regular_inparm": + assert len(ptnode.children) == 2 + if highlevel: + return ak.types.ArrayType( + toast_v1(ptnode.children[1], highlevel, categorical), ptnode.children[0] + ) + return ak.types.RegularType( + toast_v1(ptnode.children[1], highlevel, categorical), ptnode.children[0] + ) + + elif ptnode.data == "regular_outparm": + assert len(ptnode.children) == 3 + parms = toast_v1(ptnode.children[2], highlevel, False) + if categorical: + parms.update({"__categorical__": True}) + categorical = False + return ak.types.RegularType( + toast_v1(ptnode.children[1], highlevel, False), + ptnode.children[0], + parms, + ) + + elif ptnode.data == "def_option": + assert len(ptnode.children) == 1 + return ptnode.children[0] + + elif ptnode.data == "options": + assert len(ptnode.children) == 1 + return toast_v1(ptnode.children[0], highlevel, categorical) + + else: + raise AssertionError("unhandled node") + + +def from_datashape_v1(typestr, highlevel=False): + parseobj = Lark_StandAlone(transformer=TreeToJson()) + return toast_v1(parseobj.parse(typestr), highlevel, False) diff --git a/studies/type-parser-1.5/type-grammar.lark b/studies/type-parser-1.5/type-grammar.lark new file mode 100644 index 0000000000..436ca681b8 --- /dev/null +++ b/studies/type-parser-1.5/type-grammar.lark @@ -0,0 +1,82 @@ +start: input + +input: record + | unknown + | primitive + | optiontype + | regular + | listtype + | uniontype + | predefined_typestr + | categories + +record: record_tuple + | record_tuple_param + | record_dict + | record_struct + | record_highlevel +primitive: TYPE [options] +unknown: "unknown" [options] +optiontype: option_single + | option_parm + | option_highlevel +regular: regular_inparm + | regular_outparm +listtype: list_single + | list_parm +uniontype: union_single + | union_parm +categories: "categorical" "[" "type" "=" input "]" +predefined_typestr: HARDCODED + +HARDCODED: "string" + | "char" + | "bytes" + | "byte" +option_single: "?" input [options] +option_parm: "option" "[" input "," def_option "]" +option_highlevel: "option" "[" input "]" +union_single: "union" "[" input [ "," input]* "]" +union_parm: "union" "[" input [ "," input]* "," def_option "]" +list_parm: "[" "var" "*" input "," def_option "]" +list_single: "var" "*" input +record_tuple: "(" input ["," input]* ")" +record_tuple_param: "tuple" "[" "[" input ["," input]* "]" "," def_option "]" +record_dict: "{" string ":" input ["," string ":" input]* "}" +record_struct: "struct" "[" "[" string ["," string]* "]" "," "[" input ["," input]* "]" "," def_option "]" +record_highlevel: UNQUOTED_STRING "[" string ":" input ["," string ":" input]* "]" +regular_inparm: number "*" input +regular_outparm: "[" number "*" input "," def_option "]" +options: "[" def_option "]" +def_option: "parameters" "=" dict_obj +TYPE: "int8" + | "int16" + | "int32" + | "int64" + | "int128" + | "uint8" + | "uint16" + | "uint32" + | "uint64" + | "uint128" + | "float32" + | "float64" + | "bool" +?json: dict_obj + | list_obj + | string + | number + | "true" -> true + | "false" -> false + | "null" -> null +list_obj: "[" [json ("," json)*] "]" +dict_obj: "{" [pair ("," pair)*] "}" +pair: string ":" json +string: /((?:"(?:[^"\n\r\\]|(?:\\u[0-9a-fA-F]{4})|(?:\\["bfnrt]))*")|(?:\\\'(?:[^\\\'\n\r\\]|(?:\\u[0-9a-fA-F]{4})|(?:\\[\'bfnrt]))*")*\\\')/ +UNQUOTED_STRING.-1: /[a-zA-Z]+/ +number: SIGNED_NUMBER + +%import common.SIGNED_NUMBER +%import common.WS + +%ignore WS