Module: EBNF::PEG::Parser
- Included in:
- ABNF, ISOEBNF, EBNF::Parser
- Defined in:
- lib/ebnf/peg/parser.rb
Overview
A Generic PEG parser using the parsed rules modified for PEG parseing.
Defined Under Namespace
Modules: ClassMethods Classes: Error, Unmatched
Instance Attribute Summary collapse
-
#packrat ⇒ Hash{Integer => Hash{Symbol => Object}}
readonly
A Hash structure used for memoizing rule results for a given input location.
-
#scanner ⇒ Scanner
readonly
Used for scanning input.
-
#whitespace ⇒ Regexp, Rule
readonly
How to remove inter-rule whitespace.
Class Method Summary collapse
Instance Method Summary collapse
-
#clear_packrat ⇒ Object
Clear out packrat memoizer.
-
#debug(node, message, **options) ⇒ Object
Debug logging.
-
#depth ⇒ Object
Depth of parsing, for log output.
-
#error(node, message, **options) ⇒ Object
Error information, used as level ‘3` logger messages.
-
#find_rule(sym) ⇒ Rule
Find a rule for a symbol.
-
#find_terminal_regexp(sym) ⇒ Regexp
Find a regular expression defined for a terminal.
-
#onFinish(result) ⇒ Object
Finish of production.
-
#onStart(prod) ⇒ Hash
Start for production Adds data avoiable during the processing of the production.
-
#onTerminal(prod, value) ⇒ String, Object
A terminal with a defined handler.
-
#parse(input = nil, start = nil, rules = nil, **options) {|context, *data| ... } ⇒ Object
Initializes a new parser instance.
-
#prod_data ⇒ Object
Current ProdData element.
-
#progress(node, message, **options, &block) ⇒ Object
Progress logged when parsing.
-
#update_furthest_failure(pos, lineno, token) ⇒ Object
Record furthest failure.
-
#warn(node, message, **options) ⇒ Object
Warning information, used as level ‘2` logger messages.
Instance Attribute Details
#packrat ⇒ Hash{Integer => Hash{Symbol => Object}} (readonly)
A Hash structure used for memoizing rule results for a given input location.
@example Partial structure for memoizing results for a particular rule
{
rule: {
86: {
pos:
result: [<EBNF::Rule:80 {
sym: :ebnf,
id: "1",
kind: :rule,
expr: [:star, [:alt, :declaration, :rule]]}>],
}
131: [<EBNF::Rule:80 {sym: :ebnf,
id: "1",
kind: :rule,
expr: [:star, [:alt, :declaration, :rule]]}>,
<EBNF::Rule:100 {
sym: :declaration,
id: "2",
kind: :rule,
expr: [:alt, "@terminals", :pass]}>]
},
POSTFIX: {
80: "*",
368: "*",
399: "+"
}
}
45 46 47 |
# File 'lib/ebnf/peg/parser.rb', line 45 def packrat @packrat end |
#scanner ⇒ Scanner (readonly)
Returns used for scanning input.
11 12 13 |
# File 'lib/ebnf/peg/parser.rb', line 11 def scanner @scanner end |
#whitespace ⇒ Regexp, Rule (readonly)
Returns how to remove inter-rule whitespace.
7 8 9 |
# File 'lib/ebnf/peg/parser.rb', line 7 def whitespace @whitespace end |
Class Method Details
.included(base) ⇒ Object
47 48 49 |
# File 'lib/ebnf/peg/parser.rb', line 47 def self.included(base) base.extend(ClassMethods) end |
Instance Method Details
#clear_packrat ⇒ Object
Clear out packrat memoizer. This is appropriate when completing a top-level rule when there is no possibility of backtracking.
260 |
# File 'lib/ebnf/peg/parser.rb', line 260 def clear_packrat; @packrat.clear; end |
#debug(node, message, **options) ⇒ Object
Debug logging.
The call is ignored, unless ‘@options` is set.
342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 |
# File 'lib/ebnf/peg/parser.rb', line 342 def debug(*args, &block) return unless @options[:logger] = args.last.is_a?(Hash) ? args.pop : {} lineno = [:lineno] || (scanner.lineno if scanner) level = .fetch(:level, 0) depth = [:depth] || self.depth if self.respond_to?(:log_debug) level = [:debug, :info, :warn, :error, :fatal][level] log_debug(*args, **.merge(level: level, lineno: lineno, depth: depth), &block) elsif @options[:logger].respond_to?(:add) args << yield if block_given? @options[:logger].add(level, "[#{lineno}]" + (" " * depth) + args.join(" ")) elsif @options[:logger].respond_to?(:<<) args << yield if block_given? @options[:logger] << "[#{lineno}]" + (" " * depth) + args.join(" ") end end |
#depth ⇒ Object
Depth of parsing, for log output.
254 |
# File 'lib/ebnf/peg/parser.rb', line 254 def depth; (@productions || []).length; end |
#error(node, message, **options) ⇒ Object
Error information, used as level ‘3` logger messages. Messages may be logged and are saved for reporting at end of parsing.
273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 |
# File 'lib/ebnf/peg/parser.rb', line 273 def error(node, , **) lineno = [:lineno] || (scanner.lineno if scanner) m = "ERROR " m += "[line: #{lineno}] " if lineno m += m += " (found #{[:rest].inspect})" if [:rest] m += ", production = #{[:production].inspect}" if [:production] @error_log << m unless @recovering @recovering = true debug(node, m, level: 3, **) if [:raise] || @options[:validate] raise Error.new(m, lineno: lineno, rest: [:rest], production: [:production], backtrace: [:backtrace]) end end |
#find_rule(sym) ⇒ Rule
Find a rule for a symbol
461 462 463 |
# File 'lib/ebnf/peg/parser.rb', line 461 def find_rule(sym) @rules[sym] end |
#find_terminal_regexp(sym) ⇒ Regexp
Find a regular expression defined for a terminal
470 471 472 |
# File 'lib/ebnf/peg/parser.rb', line 470 def find_terminal_regexp(sym) self.class.terminal_regexps[sym] end |
#onFinish(result) ⇒ Object
Finish of production
400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 |
# File 'lib/ebnf/peg/parser.rb', line 400 def onFinish(result) #puts "prod_data(f): " + @prod_data.inspect prod = @productions.last handler, clear_packrat = self.class.production_handlers[prod] data = @prod_data.pop if handler || self.class.start_handlers[prod] error("finish", "prod_data production mismatch: expected #{prod.inspect}, got #{data[:_production].inspect}", production: prod, prod_data: @prod_data) if data && prod != data[:_production] if handler && !@recovering && result != :unmatched # Pop production data element from stack, potentially allowing handler to use it result = begin self.class.eval_with_binding(self) { handler.call(result, data, @parse_callback) } rescue ArgumentError, Error => e error("finish", "#{e.class}: #{e.}", production: prod, backtrace: e.backtrace) @recovering = false end end debug("#{prod}(:finish)", "", lineno: (scanner.lineno if scanner), level: result == :unmatched ? 0 : 1) do "#{result.inspect}@(#{scanner ? scanner.pos : '?'}), rest: #{scanner ? scanner.rest[0..20].inspect : '?'}" end self.clear_packrat if clear_packrat @productions.pop result end |
#onStart(prod) ⇒ Hash
Start for production Adds data avoiable during the processing of the production
366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 |
# File 'lib/ebnf/peg/parser.rb', line 366 def onStart(prod) handler = self.class.start_handlers[prod] @productions << prod debug("#{prod}(:start)", "", lineno: (scanner.lineno if scanner), pos: (scanner.pos if scanner) ) do "#{prod}, pos: #{scanner ? scanner.pos : '?'}, rest: #{scanner ? scanner.rest[0..20].inspect : '?'}" end if handler # Create a new production data element, potentially allowing handler # to customize before pushing on the @prod_data stack data = {_production: prod} begin self.class.eval_with_binding(self) { handler.call(data, @parse_callback) } rescue ArgumentError, Error => e error("start", "#{e.class}: #{e.}", production: prod, backtrace: e.backtrace) @recovering = false end @prod_data << data elsif self.class.production_handlers[prod] # Make sure we push as many was we pop, even if there is no # explicit start handler @prod_data << {_production: prod} end return self.class..fetch(prod, {}) # any options on this production end |
#onTerminal(prod, value) ⇒ String, Object
A terminal with a defined handler
434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 |
# File 'lib/ebnf/peg/parser.rb', line 434 def onTerminal(prod, value) parentProd = @productions.last handler = self.class.terminal_handlers[prod] if handler && value != :unmatched value = begin self.class.eval_with_binding(self) { handler.call(value, parentProd, @parse_callback) } rescue ArgumentError, Error => e error("terminal", "#{e.class}: #{e.}", value: value, production: prod, backtrace: e.backtrace) @recovering = false end end progress("#{prod}(:terminal)", "", depth: (depth + 1), lineno: (scanner.lineno if scanner), level: value == :unmatched ? 0 : 1) do "#{value.inspect}@(#{scanner ? scanner.pos : '?'})" end value end |
#parse(input = nil, start = nil, rules = nil, **options) {|context, *data| ... } ⇒ Object
Initializes a new parser instance.
198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 |
# File 'lib/ebnf/peg/parser.rb', line 198 def parse(input = nil, start = nil, rules = nil, **, &block) start ||= [:start] rules ||= [:rules] || [] @rules = rules.inject({}) {|memo, rule| memo.merge(rule.sym => rule)} @packrat = {} # Add parser reference to each rule @rules.each_value {|rule| rule.parser = self} # Take whitespace from options, a named rule, a `pass` rule, a rule named :WS, or a default @whitespace = case [:whitespace] when Regexp then [:whitespace] when Symbol then @rules[[:whitespace]] else [:whitespace] end || @rules.values.detect(&:pass?) || /(?:\s|(?:#[^x][^\n\r]*))+/m.freeze @options = .dup @productions = [] @parse_callback = block @error_log = [] @prod_data = [] @scanner = EBNF::LL1::Scanner.new(input) start = start.split('#').last.to_sym unless start.is_a?(Symbol) start_rule = @rules[start] raise Error, "Starting production #{start.inspect} not defined" unless start_rule result = start_rule.parse(scanner) if result == :unmatched # Start rule wasn't matched, which is about the only error condition error("--top--", @furthest_failure.to_s, pos: @furthest_failure.pos, lineno: @furthest_failure.lineno, rest: scanner.string[@furthest_failure.pos, 20]) end # Eat any remaining whitespace start_rule.eat_whitespace(scanner) if !scanner.eos? error("--top--", @furthest_failure.to_s, pos: @furthest_failure.pos, lineno: @furthest_failure.lineno, rest: scanner.string[@furthest_failure.pos, 20]) end # When all is said and done, raise the error log unless @error_log.empty? raise Error, @error_log.join("\n") end result end |
#prod_data ⇒ Object
Current ProdData element
257 |
# File 'lib/ebnf/peg/parser.rb', line 257 def prod_data; @prod_data.last || {}; end |
#progress(node, message, **options, &block) ⇒ Object
Progress logged when parsing. Passed as level ‘1` logger messages.
The call is ignored, unless ‘@options` is set.
324 325 326 327 328 329 |
# File 'lib/ebnf/peg/parser.rb', line 324 def progress(node, *args, &block) return unless @options[:logger] args << {} unless args.last.is_a?(Hash) args.last[:level] ||= 1 debug(node, *args, &block) end |
#update_furthest_failure(pos, lineno, token) ⇒ Object
Record furthest failure.
484 485 486 487 488 489 490 491 492 |
# File 'lib/ebnf/peg/parser.rb', line 484 def update_furthest_failure(pos, lineno, token) # Skip generated productions return if token.is_a?(Symbol) && token.to_s.start_with?('_') if @furthest_failure.nil? || pos > @furthest_failure.pos @furthest_failure = Unmatched.new(pos, lineno, [token]) elsif pos == @furthest_failure.pos && !@furthest_failure[:expecting].include?(token) @furthest_failure[:expecting] << token end end |
#warn(node, message, **options) ⇒ Object
Warning information, used as level ‘2` logger messages. Messages may be logged and are saved for reporting at end of parsing.
302 303 304 305 306 307 308 309 310 |
# File 'lib/ebnf/peg/parser.rb', line 302 def warn(node, , **) lineno = [:lineno] || (scanner.lineno if scanner) m = "WARNING " m += "[line: #{lineno}] " if lineno m += m += " (found #{[:rest].inspect})" if [:rest] m += ", production = #{[:production].inspect}" if [:production] debug(node, m, level: 2, **) end |