Class: Psych::Parser

Inherits:
Object show all
Defined in:
lib/psych/parser.rb,
parser.c

Overview

YAML event parser class. This class parses a YAML document and calls events on the handler that is passed to the constructor. The events can be used for things such as constructing a YAML AST or deserializing YAML documents. It can even be fed back to Psych::Emitter to emit the same document that was parsed.

See Psych::Handler for documentation on the events that Psych::Parser emits.

Here is an example that prints out ever scalar found in a YAML document:

# Handler for detecting scalar values
class ScalarHandler < Psych::Handler
  def scalar value, anchor, tag, plain, quoted, style
    puts value
  end
end

parser = Psych::Parser.new(ScalarHandler.new)
parser.parse(yaml_document)

Here is an example that feeds the parser back in to Psych::Emitter. The YAML document is read from STDIN and written back out to STDERR:

parser = Psych::Parser.new(Psych::Emitter.new($stderr))
parser.parse($stdin)

Psych uses Psych::Parser in combination with Psych::TreeBuilder to construct an AST of the parsed YAML document.

Defined Under Namespace

Classes: Mark

Constant Summary collapse

ANY =

Let the parser choose the encoding

Any encoding
UTF8 =

UTF-8 Encoding

INT2NUM(YAML_UTF8_ENCODING)
UTF16LE =

UTF-16-LE Encoding with BOM

INT2NUM(YAML_UTF16LE_ENCODING)
UTF16BE =

UTF-16-BE Encoding with BOM

INT2NUM(YAML_UTF16BE_ENCODING)

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(handler = Handler.new) ⇒ Parser

Creates a new Psych::Parser instance with handler. YAML events will be called on handler. See Psych::Parser for more details.



46
47
48
49
# File 'lib/psych/parser.rb', line 46

def initialize handler = Handler.new
  @handler = handler
  @external_encoding = ANY
end

Instance Attribute Details

#external_encoding=(value) ⇒ Object (writeonly)

Set the encoding for this parser to encoding



40
41
42
# File 'lib/psych/parser.rb', line 40

def external_encoding=(value)
  @external_encoding = value
end

#handlerObject

The handler on which events will be called



37
38
39
# File 'lib/psych/parser.rb', line 37

def handler
  @handler
end

Instance Method Details

#markObject

Returns a Psych::Parser::Mark object that contains line, column, and index information.



523
524
525
526
527
528
529
530
531
532
533
534
535
536
# File 'parser.c', line 523

static VALUE mark(VALUE self)
{
    VALUE mark_klass;
    VALUE args[3];
    yaml_parser_t * parser;

    Data_Get_Struct(self, yaml_parser_t, parser);
    mark_klass = rb_const_get_at(cPsychParser, rb_intern("Mark"));
    args[0] = INT2NUM(parser->mark.index);
    args[1] = INT2NUM(parser->mark.line);
    args[2] = INT2NUM(parser->mark.column);

    return rb_class_new_instance(3, args, mark_klass);
}

#parse(yaml) ⇒ Object

Parse the YAML document contained in yaml. Events will be called on the handler set on the parser instance.

See Psych::Parser and Psych::Parser#handler



229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
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
395
396
397
398
399
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
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
# File 'parser.c', line 229

static VALUE parse(int argc, VALUE *argv, VALUE self)
{
    VALUE yaml, path;
    yaml_parser_t * parser;
    yaml_event_t event;
    int done = 0;
    int tainted = 0;
    int state = 0;
    int parser_encoding = YAML_ANY_ENCODING;
#ifdef HAVE_RUBY_ENCODING_H
    int encoding = rb_utf8_encindex();
    rb_encoding * internal_enc = rb_default_internal_encoding();
#endif
    VALUE handler = rb_iv_get(self, "@handler");

    if (rb_scan_args(argc, argv, "11", &yaml, &path) == 1) {
	if(rb_respond_to(yaml, id_path))
	    path = rb_funcall(yaml, id_path, 0);
	else
	    path = rb_str_new2("<unknown>");
    }

    Data_Get_Struct(self, yaml_parser_t, parser);

    yaml_parser_delete(parser);
    yaml_parser_initialize(parser);

    if (OBJ_TAINTED(yaml)) tainted = 1;

    if (rb_respond_to(yaml, id_read)) {
#ifdef HAVE_RUBY_ENCODING_H
	yaml = transcode_io(yaml, &parser_encoding);
	yaml_parser_set_encoding(parser, parser_encoding);
#endif
	yaml_parser_set_input(parser, io_reader, (void *)yaml);
	if (RTEST(rb_obj_is_kind_of(yaml, rb_cIO))) tainted = 1;
    } else {
	StringValue(yaml);
#ifdef HAVE_RUBY_ENCODING_H
	yaml = transcode_string(yaml, &parser_encoding);
	yaml_parser_set_encoding(parser, parser_encoding);
#endif
	yaml_parser_set_input_string(
		parser,
		(const unsigned char *)RSTRING_PTR(yaml),
		(size_t)RSTRING_LEN(yaml)
		);
    }

    while(!done) {
	if(!yaml_parser_parse(parser, &event)) {
	    VALUE exception;

	    exception = make_exception(parser, path);
	    yaml_parser_delete(parser);
	    yaml_parser_initialize(parser);

	    rb_exc_raise(exception);
	}

	switch(event.type) {
	    case YAML_STREAM_START_EVENT:
	      {
		  VALUE args[2];

		  args[0] = handler;
		  args[1] = INT2NUM((long)event.data.stream_start.encoding);
		  rb_protect(protected_start_stream, (VALUE)args, &state);
	      }
	      break;
	  case YAML_DOCUMENT_START_EVENT:
	    {
		VALUE args[4];
		/* Get a list of tag directives (if any) */
		VALUE tag_directives = rb_ary_new();
		/* Grab the document version */
		VALUE version = event.data.document_start.version_directive ?
		    rb_ary_new3(
			(long)2,
			INT2NUM((long)event.data.document_start.version_directive->major),
			INT2NUM((long)event.data.document_start.version_directive->minor)
			) : rb_ary_new();

		if(event.data.document_start.tag_directives.start) {
		    yaml_tag_directive_t *start =
			event.data.document_start.tag_directives.start;
		    yaml_tag_directive_t *end =
			event.data.document_start.tag_directives.end;
		    for(; start != end; start++) {
			VALUE handle = Qnil;
			VALUE prefix = Qnil;
			if(start->handle) {
			    handle = rb_str_new2((const char *)start->handle);
			    if (tainted) OBJ_TAINT(handle);
#ifdef HAVE_RUBY_ENCODING_H
			    PSYCH_TRANSCODE(handle, encoding, internal_enc);
#endif
			}

			if(start->prefix) {
			    prefix = rb_str_new2((const char *)start->prefix);
			    if (tainted) OBJ_TAINT(prefix);
#ifdef HAVE_RUBY_ENCODING_H
			    PSYCH_TRANSCODE(prefix, encoding, internal_enc);
#endif
			}

			rb_ary_push(tag_directives, rb_ary_new3((long)2, handle, prefix));
		    }
		}
		args[0] = handler;
		args[1] = version;
		args[2] = tag_directives;
		args[3] = event.data.document_start.implicit == 1 ? Qtrue : Qfalse;
		rb_protect(protected_start_document, (VALUE)args, &state);
	    }
	    break;
	  case YAML_DOCUMENT_END_EVENT:
	    {
		VALUE args[2];

		args[0] = handler;
		args[1] = event.data.document_end.implicit == 1 ? Qtrue : Qfalse;
		rb_protect(protected_end_document, (VALUE)args, &state);
	    }
	    break;
	  case YAML_ALIAS_EVENT:
	    {
		VALUE args[2];
		VALUE alias = Qnil;
		if(event.data.alias.anchor) {
		    alias = rb_str_new2((const char *)event.data.alias.anchor);
		    if (tainted) OBJ_TAINT(alias);
#ifdef HAVE_RUBY_ENCODING_H
		    PSYCH_TRANSCODE(alias, encoding, internal_enc);
#endif
		}

		args[0] = handler;
		args[1] = alias;
		rb_protect(protected_alias, (VALUE)args, &state);
	    }
	    break;
	  case YAML_SCALAR_EVENT:
	    {
		VALUE args[7];
		VALUE anchor = Qnil;
		VALUE tag = Qnil;
		VALUE plain_implicit, quoted_implicit, style;
		VALUE val = rb_str_new(
		    (const char *)event.data.scalar.value,
		    (long)event.data.scalar.length
		    );
		if (tainted) OBJ_TAINT(val);

#ifdef HAVE_RUBY_ENCODING_H
		PSYCH_TRANSCODE(val, encoding, internal_enc);
#endif

		if(event.data.scalar.anchor) {
		    anchor = rb_str_new2((const char *)event.data.scalar.anchor);
		    if (tainted) OBJ_TAINT(anchor);
#ifdef HAVE_RUBY_ENCODING_H
		    PSYCH_TRANSCODE(anchor, encoding, internal_enc);
#endif
		}

		if(event.data.scalar.tag) {
		    tag = rb_str_new2((const char *)event.data.scalar.tag);
		    if (tainted) OBJ_TAINT(tag);
#ifdef HAVE_RUBY_ENCODING_H
		    PSYCH_TRANSCODE(tag, encoding, internal_enc);
#endif
		}

		plain_implicit =
		    event.data.scalar.plain_implicit == 0 ? Qfalse : Qtrue;

		quoted_implicit =
		    event.data.scalar.quoted_implicit == 0 ? Qfalse : Qtrue;

		style = INT2NUM((long)event.data.scalar.style);

		args[0] = handler;
		args[1] = val;
		args[2] = anchor;
		args[3] = tag;
		args[4] = plain_implicit;
		args[5] = quoted_implicit;
		args[6] = style;
		rb_protect(protected_scalar, (VALUE)args, &state);
	    }
	    break;
	  case YAML_SEQUENCE_START_EVENT:
	    {
		VALUE args[5];
		VALUE anchor = Qnil;
		VALUE tag = Qnil;
		VALUE implicit, style;
		if(event.data.sequence_start.anchor) {
		    anchor = rb_str_new2((const char *)event.data.sequence_start.anchor);
		    if (tainted) OBJ_TAINT(anchor);
#ifdef HAVE_RUBY_ENCODING_H
		    PSYCH_TRANSCODE(anchor, encoding, internal_enc);
#endif
		}

		tag = Qnil;
		if(event.data.sequence_start.tag) {
		    tag = rb_str_new2((const char *)event.data.sequence_start.tag);
		    if (tainted) OBJ_TAINT(tag);
#ifdef HAVE_RUBY_ENCODING_H
		    PSYCH_TRANSCODE(tag, encoding, internal_enc);
#endif
		}

		implicit =
		    event.data.sequence_start.implicit == 0 ? Qfalse : Qtrue;

		style = INT2NUM((long)event.data.sequence_start.style);

		args[0] = handler;
		args[1] = anchor;
		args[2] = tag;
		args[3] = implicit;
		args[4] = style;

		rb_protect(protected_start_sequence, (VALUE)args, &state);
	    }
	    break;
	  case YAML_SEQUENCE_END_EVENT:
	    rb_protect(protected_end_sequence, handler, &state);
	    break;
	  case YAML_MAPPING_START_EVENT:
	    {
		VALUE args[5];
		VALUE anchor = Qnil;
		VALUE tag = Qnil;
		VALUE implicit, style;
		if(event.data.mapping_start.anchor) {
		    anchor = rb_str_new2((const char *)event.data.mapping_start.anchor);
		    if (tainted) OBJ_TAINT(anchor);
#ifdef HAVE_RUBY_ENCODING_H
		    PSYCH_TRANSCODE(anchor, encoding, internal_enc);
#endif
		}

		if(event.data.mapping_start.tag) {
		    tag = rb_str_new2((const char *)event.data.mapping_start.tag);
		    if (tainted) OBJ_TAINT(tag);
#ifdef HAVE_RUBY_ENCODING_H
		    PSYCH_TRANSCODE(tag, encoding, internal_enc);
#endif
		}

		implicit =
		    event.data.mapping_start.implicit == 0 ? Qfalse : Qtrue;

		style = INT2NUM((long)event.data.mapping_start.style);

		args[0] = handler;
		args[1] = anchor;
		args[2] = tag;
		args[3] = implicit;
		args[4] = style;

		rb_protect(protected_start_mapping, (VALUE)args, &state);
	    }
	    break;
	  case YAML_MAPPING_END_EVENT:
	    rb_protect(protected_end_mapping, handler, &state);
	    break;
	  case YAML_NO_EVENT:
	    rb_protect(protected_empty, handler, &state);
	    break;
	  case YAML_STREAM_END_EVENT:
	    rb_protect(protected_end_stream, handler, &state);
	    done = 1;
	    break;
	}
	yaml_event_delete(&event);
	if (state) rb_jump_tag(state);
    }

    return self;
}