TTreeFormula Parser

This module provides the parser for ROOT’s TTreeFormula expressions.

class formulate.ttreeformula_parser.Action(name): Bases: object

class formulate.ttreeformula_parser.AmbiguousExpander(to_expand, tree_class, node_builder): Bases: object

class formulate.ttreeformula_parser.AmbiguousIntermediateExpander(tree_class, node_builder): Bases: object

class formulate.ttreeformula_parser.BasicLexer(conf: LexerConf, comparator=None)

Bases: Lexer

callback: dict[str, Callable[[Token], Token]]

ignore_types: frozenset[str]

lex(state: LexerState, parser_state: Any) → Iterator[Token]

match(text, pos)

newline_types: frozenset[str]

next_token(lex_state: LexerState, parser_state: Any = None) → Token

re: ModuleType

property scanner

terminals: Collection[TerminalDef]

user_callbacks: dict[str, Callable[[Token], Token]]

class formulate.ttreeformula_parser.CallChain(callback1, callback2, cond): Bases: object

class formulate.ttreeformula_parser.ChildFilter(to_include, append_none, node_builder): Bases: object

class formulate.ttreeformula_parser.ChildFilterLALR(to_include, append_none, node_builder): Bases: ChildFilter

class formulate.ttreeformula_parser.ChildFilterLALR_NoPlaceholders(to_include, node_builder): Bases: ChildFilter

exception formulate.ttreeformula_parser.ConfigurationError: Bases: LarkError, ValueError

class formulate.ttreeformula_parser.ContextualLexer(conf: LexerConf, states: dict[str, Collection[str]], always_accept: Collection[str] = ())

Bases: Lexer

lex(lexer_state: LexerState, parser_state: Any) → Iterator[Token]

lexers: dict[str, BasicLexer]

root_lexer: BasicLexer

exception formulate.ttreeformula_parser.DedentError: Bases: LarkError

class formulate.ttreeformula_parser.ExpandSingleChild(node_builder): Bases: object

exception formulate.ttreeformula_parser.GrammarError: Bases: LarkError

class formulate.ttreeformula_parser.Indenter

Bases: PostLex, ABC

abstract property CLOSE_PAREN_types: list[str]

abstract property DEDENT_type: str

abstract property INDENT_type: str

abstract property NL_type: str

abstract property OPEN_PAREN_types: list[str]

property always_accept

Built-in immutable sequence.

If no argument is given, the constructor returns an empty tuple. If iterable is specified the tuple is initialized from iterable’s items.

If the argument is a tuple, the return value is the same object.

handle_NL(token: Token) → Iterator[Token]

indent_level: list[int]

paren_level: int

process(stream)

abstract property tab_len: int

class formulate.ttreeformula_parser.InlineTransformer(visit_tokens: bool = True): Bases: Transformer

class formulate.ttreeformula_parser.IntParseTable(states, start_states, end_states)

Bases: ParseTable

classmethod from_ParseTable(parse_table)

class formulate.ttreeformula_parser.Interpreter

Bases: _Decoratable, ABC, Generic[_Leaf_T, _Return_T]

visit(tree: Tree[_Leaf_T]) → _Return_T

visit_children(tree: Tree[_Leaf_T]) → list

class formulate.ttreeformula_parser.LALR_Parser(parser_conf, debug=False, strict=False)

Bases: Serialize

classmethod deserialize(data, memo, callbacks, debug=False)

parse(lexer, start, on_error=None)

parse_interactive(lexer, start)

serialize(memo: Any = None) → dict[str, Any]

class formulate.ttreeformula_parser.Lark(grammar: Grammar | str | IO[str], **options)

Bases: Serialize

get_terminal(name: str) → TerminalDef

grammar: Grammar

lex(text: str, dont_ignore: bool = False) → Iterator[Token]

lexer: Lexer

classmethod load(f) → _T

classmethod open(grammar_filename: str, rel_to: str | None = None, **options) → _T

classmethod open_from_package(package: str, grammar_path: str, search_paths: Sequence[str] = [''], **options) → _T

options: LarkOptions

parse(text: str, start: str | None = None, on_error: Callable[[UnexpectedInput], bool] | None = None) → ParseTree

parse_interactive(text: str | None = None, start: str | None = None) → InteractiveParser

parser: ParsingFrontend

save(f, exclude_options: Collection[str] = ()) → None

source_grammar: str

source_path: str

terminals: Collection[TerminalDef]

class formulate.ttreeformula_parser.LarkOptions(options_dict: dict[str, Any])

Bases: Serialize

OPTIONS_DOC = '\n **=== General Options ===**\n\n start\n The start symbol. Either a string, or a list of strings for multiple possible starts (Default: "start")\n debug\n Display debug information and extra warnings. Use only when debugging (Default: ``False``)\n When used with Earley, it generates a forest graph as "sppf.png", if \'dot\' is installed.\n strict\n Throw an exception on any potential ambiguity, including shift/reduce conflicts, and regex collisions.\n transformer\n Applies the transformer to every parse tree (equivalent to applying it after the parse, but faster)\n propagate_positions\n Propagates positional attributes into the \'meta\' attribute of all tree branches.\n Sets attributes: (line, column, end_line, end_column, start_pos, end_pos,\n container_line, container_column, container_end_line, container_end_column)\n Accepts ``False``, ``True``, or a callable, which will filter which nodes to ignore when propagating.\n maybe_placeholders\n When ``True``, the ``[]`` operator returns ``None`` when not matched.\n When ``False``, ``[]`` behaves like the ``?`` operator, and returns no value at all.\n (default= ``True``)\n cache\n Cache the results of the Lark grammar analysis, for x2 to x3 faster loading. LALR only for now.\n\n - When ``False``, does nothing (default)\n - When ``True``, caches to a temporary file in the local directory\n - When given a string, caches to the path pointed by the string\n regex\n When True, uses the ``regex`` module instead of the stdlib ``re``.\n g_regex_flags\n Flags that are applied to all terminals (both regex and strings)\n keep_all_tokens\n Prevent the tree builder from automagically removing "punctuation" tokens (Default: ``False``)\n tree_class\n Lark will produce trees comprised of instances of this class instead of the default ``lark.Tree``.\n\n **=== Algorithm Options ===**\n\n parser\n Decides which parser engine to use. Accepts "earley" or "lalr". (Default: "earley").\n (there is also a "cyk" option for legacy)\n lexer\n Decides whether or not to use a lexer stage\n\n - "auto" (default): Choose for me based on the parser\n - "basic": Use a basic lexer\n - "contextual": Stronger lexer (only works with parser="lalr")\n - "dynamic": Flexible and powerful (only with parser="earley")\n - "dynamic_complete": Same as dynamic, but tries *every* variation of tokenizing possible.\n ambiguity\n Decides how to handle ambiguity in the parse. Only relevant if parser="earley"\n\n - "resolve": The parser will automatically choose the simplest derivation\n (it chooses consistently: greedy for tokens, non-greedy for rules)\n - "explicit": The parser will return all derivations wrapped in "_ambig" tree nodes (i.e. a forest).\n - "forest": The parser will return the root of the shared packed parse forest.\n\n **=== Misc. / Domain Specific Options ===**\n\n postlex\n Lexer post-processing (Default: ``None``) Only works with the basic and contextual lexers.\n priority\n How priorities should be evaluated - "auto", ``None``, "normal", "invert" (Default: "auto")\n lexer_callbacks\n Dictionary of callbacks for the lexer. May alter tokens during lexing. Use with caution.\n use_bytes\n Accept an input of type ``bytes`` instead of ``str``.\n edit_terminals\n A callback for editing the terminals before parse.\n import_paths\n A List of either paths or loader functions to specify from where grammars are imported\n source_path\n Override the source of from where the grammar was loaded. Useful for relative imports and unconventional grammar loading\n **=== End of Options ===**\n '

ambiguity: Literal[auto, resolve, explicit, forest]

cache: bool | str

debug: bool

classmethod deserialize(data: dict[str, Any], memo: dict[int, TerminalDef | Rule]) → LarkOptions

edit_terminals: Callable[[TerminalDef], TerminalDef] | None

g_regex_flags: int

import_paths: list[str | Callable[[None | str | PackageResource, str], tuple[str, str]]]

keep_all_tokens: bool

lexer: _LexerArgType

lexer_callbacks: dict[str, Callable[[Token], Token]]

maybe_placeholders: bool

parser: _ParserArgType

postlex: PostLex | None

priority: Literal[auto, normal, invert] | None

propagate_positions: bool | str

regex: bool

serialize(memo=None) → dict[str, Any]

source_path: str | None

start: list[str]

strict: bool

transformer: Transformer | None

tree_class: Any

use_bytes: bool

formulate.ttreeformula_parser.Lark_StandAlone(**kwargs)

exception formulate.ttreeformula_parser.LexError: Bases: LarkError

class formulate.ttreeformula_parser.Lexer

Bases: ABC

abstractmethod lex(lexer_state: LexerState, parser_state: Any) → Iterator[Token]

make_lexer_state(text)

class formulate.ttreeformula_parser.LexerConf(terminals: Collection[TerminalDef], re_module: ModuleType, ignore: Collection[str] = (), postlex: PostLex | None = None, callbacks: dict[str, Callable[[Token], Token]] | None = None, g_regex_flags: int = 0, skip_validation: bool = False, use_bytes: bool = False, strict: bool = False)

Bases: Serialize

callbacks: dict[str, _Callback]

g_regex_flags: int

ignore: Collection[str]

lexer_type: _LexerArgType | None

postlex: PostLex | None

re_module: ModuleType

skip_validation: bool

strict: bool

terminals: Collection[TerminalDef]

use_bytes: bool

class formulate.ttreeformula_parser.LexerState(text: str, line_ctr: LineCounter | None = None, last_token: Token | None = None)

Bases: object

last_token: Token | None

line_ctr: LineCounter

text: str

class formulate.ttreeformula_parser.LexerThread(lexer: Lexer, lexer_state: LexerState)

Bases: object

classmethod from_text(lexer: Lexer, text: str)

lex(parser_state)

class formulate.ttreeformula_parser.LineCounter(newline_char)

Bases: object

char_pos

column

feed(token: Token, test_newline=True)

line

line_start_pos

newline_char

class formulate.ttreeformula_parser.Meta

Bases: object

column: int

empty: bool

end_column: int

end_line: int

end_pos: int

line: int

match_tree: bool

orig_expansion: list[TerminalDef]

start_pos: int

exception formulate.ttreeformula_parser.MissingVariableError: Bases: LarkError

class formulate.ttreeformula_parser.NonTerminal(name: str)

Bases: Symbol

is_term: ClassVar[bool] = False

name: str

class formulate.ttreeformula_parser.ParseConf(parse_table, callbacks, start)

Bases: object

callbacks

end_state

parse_table

start

start_state

states

class formulate.ttreeformula_parser.ParseTable(states, start_states, end_states)

Bases: object

classmethod deserialize(data, memo)

serialize(memo)

class formulate.ttreeformula_parser.ParseTreeBuilder(rules, tree_class, propagate_positions=False, ambiguous=False, maybe_placeholders=False)

Bases: object

create_callback(transformer=None)

class formulate.ttreeformula_parser.ParserConf(rules, callbacks, start): Bases: Serialize

class formulate.ttreeformula_parser.ParserState(parse_conf, lexer, state_stack=None, value_stack=None)

Bases: object

copy()

feed_token(token, is_end=False)

lexer

parse_conf

property position

state_stack

value_stack

class formulate.ttreeformula_parser.ParsingFrontend(lexer_conf: LexerConf, parser_conf: ParserConf, options, parser=None)

Bases: Serialize

lexer_conf: LexerConf

options: Any

parse(text: str, start=None, on_error=None)

parse_interactive(text: str | None = None, start=None)

parser_conf: ParserConf

class formulate.ttreeformula_parser.Pattern(value: str, flags: Collection[str] = (), raw: str | None = None)

Bases: Serialize, ABC

flags: Collection[str]

abstract property max_width: int

abstract property min_width: int

raw: str | None

abstractmethod to_regexp() → str

type: ClassVar[str]

value: str

class formulate.ttreeformula_parser.PatternRE(value: str, flags: Collection[str] = (), raw: str | None = None)

Bases: Pattern

property max_width: int

property min_width: int

to_regexp() → str

type: ClassVar[str] = 're'

class formulate.ttreeformula_parser.PatternStr(value: str, flags: Collection[str] = (), raw: str | None = None)

Bases: Pattern

property max_width: int

property min_width: int

to_regexp() → str

type: ClassVar[str] = 'str'

class formulate.ttreeformula_parser.PostLex

Bases: ABC

always_accept: Iterable[str] = ()

abstractmethod process(stream: Iterator[Token]) → Iterator[Token]

class formulate.ttreeformula_parser.PostLexConnector(lexer, postlexer)

Bases: object

lex(lexer_state, parser_state)

class formulate.ttreeformula_parser.PropagatePositions(node_builder, node_filter=None): Bases: object

class formulate.ttreeformula_parser.PythonIndenter

Bases: Indenter

CLOSE_PAREN_types = ['RPAR', 'RSQB', 'RBRACE']

DEDENT_type = '_DEDENT'

INDENT_type = '_INDENT'

NL_type = '_NEWLINE'

OPEN_PAREN_types = ['LPAR', 'LSQB', 'LBRACE']

tab_len = 8

class formulate.ttreeformula_parser.Rule(origin, expansion, order=0, alias=None, options=None)

Bases: Serialize

alias

expansion

options

order

origin

class formulate.ttreeformula_parser.RuleOptions(keep_all_tokens: bool = False, expand1: bool = False, priority: int | None = None, template_source: str | None = None, empty_indices: tuple[bool, ...] = ())

Bases: Serialize

empty_indices: tuple[bool, ...]

expand1: bool

keep_all_tokens: bool

priority: int | None

template_source: str | None

class formulate.ttreeformula_parser.Scanner(terminals, g_regex_flags, re_, use_bytes, match_whole=False)

Bases: object

match(text, pos)

class formulate.ttreeformula_parser.Serialize

Bases: object

classmethod deserialize(data: dict[str, Any], memo: dict[int, Any]) → _T

memo_serialize(types_to_memoize: list) → Any

serialize(memo=None) → dict[str, Any]

class formulate.ttreeformula_parser.SerializeMemoizer(types_to_memoize: list)

Bases: Serialize

classmethod deserialize(data: dict[int, Any], namespace: dict[str, Any], memo: dict[Any, Any]) → dict[int, Any]

in_types(value: Serialize) → bool

serialize() → dict[int, Any]

class formulate.ttreeformula_parser.Symbol(name: str)

Bases: Serialize

property fullrepr

is_term: ClassVar[bool] = NotImplemented

name: str

renamed(f)

class formulate.ttreeformula_parser.Terminal(name, filter_out=False)

Bases: Symbol

property fullrepr

is_term: ClassVar[bool] = True

name: str

renamed(f)

class formulate.ttreeformula_parser.TerminalDef(name: str, pattern: Pattern, priority: int = 0)

Bases: Serialize

name: str

pattern: Pattern

priority: int

user_repr() → str

Bases: str

column: int | None

end_column: int | None

end_line: int | None

end_pos: int | None

line: int | None

classmethod new_borrow_pos(type_: str, value: Any, borrow_t: Token) → _T

start_pos: int | None

type: str

update(type: str | None = None, value: Any | None = None) → Token
update(type_: str | None = None, value: Any | None = None) → Token

value: Any

class formulate.ttreeformula_parser.Transformer(visit_tokens: bool = True)

Bases: _Decoratable, ABC, Generic[_Leaf_T, _Return_T]

transform(tree: Tree[_Leaf_T]) → _Return_T

class formulate.ttreeformula_parser.TransformerChain(*transformers: Transformer | TransformerChain)

Bases: Generic[_Leaf_T, _Return_T]

transform(tree: Tree[_Leaf_T]) → _Return_T

transformers: tuple[Transformer | TransformerChain, ...]

class formulate.ttreeformula_parser.Transformer_InPlace(visit_tokens: bool = True)

Bases: Transformer

transform(tree: Tree[_Leaf_T]) → _Return_T

class formulate.ttreeformula_parser.Transformer_InPlaceRecursive(visit_tokens: bool = True): Bases: Transformer

class formulate.ttreeformula_parser.Transformer_NonRecursive(visit_tokens: bool = True)

Bases: Transformer

transform(tree: Tree[_Leaf_T]) → _Return_T

class formulate.ttreeformula_parser.Tree(data: str, children: list[_Leaf_T | Tree[_Leaf_T]], meta: Meta | None = None)

Bases: Generic[_Leaf_T]

children: list[_Leaf_T | Tree[_Leaf_T]]

data: str

find_data(data: str) → Iterator[Tree[_Leaf_T]]

find_pred(pred: Callable[[Tree[_Leaf_T]], bool]) → Iterator[Tree[_Leaf_T]]

iter_subtrees() → Iterator[Tree[_Leaf_T]]

iter_subtrees_topdown()

property meta: Meta

pretty(indent_str: str = ' ') → str

exception formulate.ttreeformula_parser.UnexpectedCharacters(seq, lex_pos, line, column, allowed=None, considered_tokens=None, state=None, token_history=None, terminals_by_name=None, considered_rules=None)

Bases: LexError, UnexpectedInput

allowed: set[str]

considered_tokens: set[Any]

exception formulate.ttreeformula_parser.UnexpectedEOF(expected, state=None, terminals_by_name=None)

Bases: ParseError, UnexpectedInput

expected: list[Token]

exception formulate.ttreeformula_parser.UnexpectedInput

Bases: LarkError

column: int

get_context(text: str, span: int = 40) → str

line: int

match_examples(parse_fn: Callable[[str], Tree], examples: Mapping[T, Iterable[str]] | Iterable[tuple[T, Iterable[str]]], token_type_match_fallback: bool = False, use_accepts: bool = True) → T | None

pos_in_stream = None

state: Any

exception formulate.ttreeformula_parser.UnexpectedToken(token, expected, considered_rules=None, state=None, interactive_parser=None, terminals_by_name=None, token_history=None)

Bases: ParseError, UnexpectedInput

property accepts: set[str]

considered_rules: set[str]

expected: set[str]

interactive_parser: InteractiveParser

class formulate.ttreeformula_parser.UnlessCallback(scanner): Bases: object

exception formulate.ttreeformula_parser.VisitError(rule, obj, orig_exc)

Bases: LarkError

obj: Tree | Token

orig_exc: Exception

class formulate.ttreeformula_parser.Visitor

Bases: VisitorBase, ABC, Generic[_Leaf_T]

visit(tree: Tree[_Leaf_T]) → Tree[_Leaf_T]

visit_topdown(tree: Tree[_Leaf_T]) → Tree[_Leaf_T]

class formulate.ttreeformula_parser.VisitorBase: Bases: object

class formulate.ttreeformula_parser.Visitor_Recursive

Bases: VisitorBase, Generic[_Leaf_T]

visit(tree: Tree[_Leaf_T]) → Tree[_Leaf_T]

visit_topdown(tree: Tree[_Leaf_T]) → Tree[_Leaf_T]

formulate.ttreeformula_parser.apply_visit_wrapper(func, name, wrapper)

formulate.ttreeformula_parser.assert_config(value, options: Collection, msg='Got %r, expected one of %s')

formulate.ttreeformula_parser.classify(seq: Iterable, key: Callable | None = None, value: Callable | None = None) → dict

formulate.ttreeformula_parser.create_basic_lexer(lexer_conf, parser, postlex, options) → BasicLexer

formulate.ttreeformula_parser.create_contextual_lexer(lexer_conf: LexerConf, parser, postlex, options) → ContextualLexer

formulate.ttreeformula_parser.create_lalr_parser(lexer_conf: LexerConf, parser_conf: ParserConf, options=None) → LALR_Parser

formulate.ttreeformula_parser.get_regexp_width(expr: str) → tuple[int, int] | list[int]

formulate.ttreeformula_parser.inplace_transformer(func)

formulate.ttreeformula_parser.make_propagate_positions(option)

formulate.ttreeformula_parser.maybe_create_ambiguous_expander(tree_class, expansion, keep_all_tokens)

formulate.ttreeformula_parser.maybe_create_child_filter(expansion, keep_all_tokens, ambiguous, _empty_indices: list[bool])

formulate.ttreeformula_parser.merge_transformers(base_transformer=None, **transformers_to_merge)

formulate.ttreeformula_parser.v_args(inline: bool = False, meta: bool = False, tree: bool = False, wrapper: Callable | None = None) → Callable[[Callable[[...], _Return_T] | type], Callable[[...], _Return_T] | type]

formulate.ttreeformula_parser.visit_children_decor(func: Callable[[type[Interpreter], _Return_T], _R]) → Callable[[type[Interpreter], _Return_T], _R]