Class: Psych::Parser

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



43
44
45
# File 'lib/psych/parser.rb', line 43

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

Instance Attribute Details

#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

#external_encoding=(encoding) ⇒ Object

Set the encoding for this parser to encoding



319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
# File 'ext/psych/parser.c', line 319

static VALUE set_external_encoding(VALUE self, VALUE encoding)
{
    yaml_parser_t * parser;
    VALUE exception;

    Data_Get_Struct(self, yaml_parser_t, parser);

    if(parser->encoding) {
	exception = rb_const_get_at(mPsych, rb_intern("Exception"));
	rb_raise(exception, "don't set the encoding twice!");
    }

    yaml_parser_set_encoding(parser, NUM2INT(encoding));

    return encoding;
}

#markObject

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



343
344
345
346
347
348
349
350
351
352
353
354
355
356
# File 'ext/psych/parser.c', line 343

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



71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
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
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
# File 'ext/psych/parser.c', line 71

static VALUE parse(VALUE self, VALUE yaml)
{
    yaml_parser_t * parser;
    yaml_event_t event;
    int done = 0;
    int tainted = 0;
#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");

    Data_Get_Struct(self, yaml_parser_t, parser);

    if (OBJ_TAINTED(yaml)) tainted = 1;

    if(rb_respond_to(yaml, id_read)) {
	yaml_parser_set_input(parser, io_reader, (void *)yaml);
	if (RTEST(rb_obj_is_kind_of(yaml, rb_cIO))) tainted = 1;
    } else {
	StringValue(yaml);
	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 path;
	    size_t line   = parser->mark.line;
	    size_t column = parser->mark.column;

	    if(rb_respond_to(yaml, id_path))
		path = rb_funcall(yaml, id_path, 0);
	    else
		path = rb_str_new2("<unknown>");

	    yaml_parser_delete(parser);
	    yaml_parser_initialize(parser);

	    rb_raise(ePsychSyntaxError, "(%s): couldn't parse YAML at line %d column %d",
		    StringValuePtr(path),
		    (int)line, (int)column);
	}

	switch(event.type) {
	  case YAML_STREAM_START_EVENT:

	    rb_funcall(handler, id_start_stream, 1,
		       INT2NUM((long)event.data.stream_start.encoding)
		);
	    break;
	  case YAML_DOCUMENT_START_EVENT:
	    {
		/* 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));
		    }
		}
		rb_funcall(handler, id_start_document, 3,
			   version, tag_directives,
			   event.data.document_start.implicit == 1 ? Qtrue : Qfalse
		    );
	    }
	    break;
	  case YAML_DOCUMENT_END_EVENT:
	    rb_funcall(handler, id_end_document, 1,
		       event.data.document_end.implicit == 1 ? Qtrue : Qfalse
		);
	    break;
	  case YAML_ALIAS_EVENT:
	    {
		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
		}

		rb_funcall(handler, id_alias, 1, alias);
	    }
	    break;
	  case YAML_SCALAR_EVENT:
	    {
		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);

		rb_funcall(handler, id_scalar, 6,
			   val, anchor, tag, plain_implicit, quoted_implicit, style);
	    }
	    break;
	  case YAML_SEQUENCE_START_EVENT:
	    {
		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);

		rb_funcall(handler, id_start_sequence, 4,
			   anchor, tag, implicit, style);
	    }
	    break;
	  case YAML_SEQUENCE_END_EVENT:
	    rb_funcall(handler, id_end_sequence, 0);
	    break;
	  case YAML_MAPPING_START_EVENT:
	    {
		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);

		rb_funcall(handler, id_start_mapping, 4,
			   anchor, tag, implicit, style);
	    }
	    break;
	  case YAML_MAPPING_END_EVENT:
	    rb_funcall(handler, id_end_mapping, 0);
	    break;
	  case YAML_NO_EVENT:
	    rb_funcall(handler, id_empty, 0);
	    break;
	  case YAML_STREAM_END_EVENT:
	    rb_funcall(handler, id_end_stream, 0);
	    done = 1;
	    break;
	}
	yaml_event_delete(&event);
    }

    return self;
}