Class: HQ::Engine::Transformer

Inherits:
Object
  • Object
show all
Includes:
LibXmlRubyMixin
Defined in:
lib/hq/transform/transformer.rb

Instance Attribute Summary collapse

Instance Method Summary collapse

Methods included from LibXmlRubyMixin

#field_to_json, #field_to_xml, #get_record_id_long, #get_record_id_short, #js_to_xml, #load_data_file, #load_data_string, #load_schema_file, #to_xml_string, #write_data_file, #xml_to_json

Instance Attribute Details

#dataObject (readonly)

Returns the value of attribute data.



21
22
23
# File 'lib/hq/transform/transformer.rb', line 21

def data
  @data
end

#include_dirObject

Returns the value of attribute include_dir.



17
18
19
# File 'lib/hq/transform/transformer.rb', line 17

def include_dir
  @include_dir
end

#input_dirObject

Returns the value of attribute input_dir.



18
19
20
# File 'lib/hq/transform/transformer.rb', line 18

def input_dir
  @input_dir
end

#output_dirObject

Returns the value of attribute output_dir.



19
20
21
# File 'lib/hq/transform/transformer.rb', line 19

def output_dir
  @output_dir
end

#parentObject

Returns the value of attribute parent.



10
11
12
# File 'lib/hq/transform/transformer.rb', line 10

def parent
  @parent
end

#rules_dirObject

Returns the value of attribute rules_dir.



16
17
18
# File 'lib/hq/transform/transformer.rb', line 16

def rules_dir
  @rules_dir
end

#schema_fileObject

Returns the value of attribute schema_file.



15
16
17
# File 'lib/hq/transform/transformer.rb', line 15

def schema_file
  @schema_file
end

Instance Method Details

#init_backend_sessionObject



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
# File 'lib/hq/transform/transformer.rb', line 76

def init_backend_session

	@backend_session =
		transform_backend.session

	# add hq module
	# TODO move this somewhere

	@backend_session.set_library_module \
		"hq",
		"
			module namespace hq = \"hq\";

			declare function hq:get (
				$id as xs:string
			) as element () ?
			external;

			declare function hq:get (
				$type as xs:string,
				$id-parts as xs:string *
			) as element () ?
			external;

			declare function hq:find (
				$type as xs:string
			) as element () *
			external;
		"

end

#load_includesObject



189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
# File 'lib/hq/transform/transformer.rb', line 189

def load_includes

	Dir["#{include_dir}/*.xquery"].each do
		|path|

		path =~ /^ #{Regexp.quote include_dir} \/ (.+) $/x
		name = $1

		@backend_session.set_library_module \
			name,
			File.read(path)

	end

end

#load_inputObject



164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
# File 'lib/hq/transform/transformer.rb', line 164

def load_input

	logger.debug "reading input from disk"

	logger.time "reading input from disk" do

		Dir["#{input_dir}/*.xml"].each do
			|filename|

			input_data =
				load_data_file filename

			input_data.each do
				|item_dom|

				store_data item_dom

			end

		end

	end

end

#load_rulesObject



30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
# File 'lib/hq/transform/transformer.rb', line 30

def load_rules

	logger.debug "loading transformation rules"

	@rules = {}

	Dir.glob("#{rules_dir}/**/*").each do
		|filename|

		extensions_re =
			"(?:%s)" % [
				transform_backend.extensions
					.map { |ext| Regexp.quote ext }
					.join("|")
			]

		next unless filename =~ /^
			#{Regexp.quote "#{rules_dir}/"}
			(
				(.+)
				\. (#{extensions_re})
			)
		$/x

		rule = {}
		rule[:name] = $2
		rule[:type] = $3
		rule[:filename] = "#{$2}.#{$3}"
		rule[:path] = filename
		rule[:source] = File.read rule[:path]
		rule[:in] = []
		rule[:out] = []
		rule[:source].scan(
			/\(: (in|out) ([a-z0-9]+(?:-[a-z0-9]+)*) :\)$/
		).each do |type, name|
			rule[type.to_sym] << name
		end

		@rules[rule[:name]] = rule

	end

	@rules = Hash[@rules.sort]

end

#load_schemaObject



23
24
25
26
27
28
# File 'lib/hq/transform/transformer.rb', line 23

def load_schema

	@schemas =
		load_schema_file schema_file

end

#loggerObject



12
# File 'lib/hq/transform/transformer.rb', line 12

def logger() parent.logger end

#rebuildObject



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
# File 'lib/hq/transform/transformer.rb', line 108

def rebuild

	logger.notice "performing transformation"

	logger.time "performing transformation" do

		remove_output

		init_backend_session

		@data = {}

		load_schema
		load_rules
		load_input
		load_includes

		@remaining_rules =
			@rules.clone

		pass_number = 0

		loop do

			num_processed =
				rebuild_pass pass_number

			break if num_processed == 0

			pass_number += 1

		end

	end

	return {
		:success => @remaining_rules.empty?,
		:remaining_rules => @remaining_rules.keys,
		:missing_types =>
			(
				@remaining_rules
					.values
					.map { |rule| rule[:in] }
					.flatten
					.uniq
					.sort
			) - (
				@schema_types
					.to_a
					.select { |type| type =~ /^schema\// }
					.map { |type| type.gsub /^schema\//, "" }
			)
	}

end

#rebuild_one(rule) ⇒ Object



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
# File 'lib/hq/transform/transformer.rb', line 314

def rebuild_one rule

	rule_name = rule[:name]
	rule_type = rule[:type]

	logger.debug "rebuilding rule #{rule_name}"
	logger.time "rebuilding rule #{rule_name}" do

		# perform query

		used_types = Set.new
		result_str = nil

		begin

			@backend_session.compile_xquery \
				rule[:source],
				rule[:filename]

			result_str =
				@backend_session.run_xquery \
					"<xml/>" \
			do
				|name, args|

				case name

				when "get record by id"
					args["id"] =~ /^([^\/]+)\//
					used_types << $1
					record = @data[args["id"]]
					record ? [ record ] : []

				when "get record by id parts"
					used_types << args["type"]
					id = [ args["type"], *args["id parts"] ].join "/"
					record = @data[id]
					record ? [ record ] : []

				when "search records"
					used_types << args["type"]
					regex = /^#{Regexp.escape args["type"]}\//
					@data \
						.select { |id, record| id =~ regex }
						.sort
						.map { |id, record| record }

				else
					raise "No such function #{name}"

				end

			end

#puts "USED: #{used_types.to_a.join " "}"
#puts "INCOMPLETE: #{@incomplete_types.to_a.join " "}"
			missing_types = used_types & @incomplete_types
puts "MISSING: #{missing_types.to_a.join " "}" unless missing_types.empty?
			return missing_types unless missing_types.empty?

		rescue RuleError => exception

			logger.die "%s:%s:%s %s" % [
				exception.file,
				exception.line,
				exception.column,
				exception.message
			]

		rescue => exception
			logger.error "%s: %s" % [
				exception.class,
				exception.to_s,
			]
			logger.detail exception.backtrace.join("\n")
			FileUtils.touch "#{work_dir}/error-flag"
			raise "error compiling #{rule[:path]}"
		end

		# process output

		result_doms =
			load_data_string result_str

		result_doms.each do
			|item_dom|

			begin

				item_id =
					get_record_id_long \
						@schemas,
						item_dom

			rescue => e

				logger.die "record id error for %s created by %s" % [
					item_dom.name,
					rule_name,
				]

			end

			store_data item_dom

		end

		return []

	end

end

#rebuild_pass(pass_number) ⇒ Object



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
312
# File 'lib/hq/transform/transformer.rb', line 215

def rebuild_pass pass_number

	logger.debug "beginning pass #{pass_number}"

	@incomplete_types =
		Set.new(
			@remaining_rules.map {
				|rule_name, rule|
				rule[:out]
			}.flatten.uniq.sort
		)

	@schema_types =
		Set.new(
			@schemas.keys
		)

	rules_for_pass =
		Hash[
			@remaining_rules.select do
				|rule_name, rule|

				missing_input_types =
					rule[:in].select {
						|in_type|
						@incomplete_types.include? in_type
					}

				missing_input_schemas =
					rule[:in].select {
						|in_type|
						! @schema_types.include? "schema/#{in_type}"
					}

				missing_output_schemas =
					rule[:out].select {
						|out_type|
						! @schema_types.include? "schema/#{out_type}"
					}

				result = [
					missing_input_types,
					missing_input_schemas,
					missing_output_schemas,
				].flatten.empty?

				messages = []

				messages << "incomplete inputs: %s" % [
					missing_input_types.join(", "),
				] unless missing_input_types.empty?

				messages << "missing input schemas: %s" % [
					missing_input_schemas.join(", "),
				] unless missing_input_schemas.empty?

				messages << "missing output schemas: %s" % [
					missing_output_schemas.join(", "),
				] unless missing_output_schemas.empty?

				unless messages.empty?
					logger.debug "rule %s: %s" % [
						rule_name,
						messages.join("; "),
					]
				end

				result

			end
		]

	num_processed = 0

	rules_for_pass.each do
		|rule_name, rule|

		used_types =
			rebuild_one rule

		missing_types =
			used_types.select {
				|type|
				@incomplete_types.include? type
			}

		raise "Error" unless missing_types.empty?

		if missing_types.empty?
			@remaining_rules.delete rule_name
			num_processed += 1
		end

	end

	return num_processed

end

#remove_outputObject



205
206
207
208
209
210
211
212
213
# File 'lib/hq/transform/transformer.rb', line 205

def remove_output

	if File.directory? output_dir
		FileUtils.remove_entry_secure output_dir
	end

	FileUtils.mkdir output_dir

end

#store_data(item_dom) ⇒ Object



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
# File 'lib/hq/transform/transformer.rb', line 427

def store_data item_dom

	# determine id

	item_id =
		get_record_id_long \
			@schemas,
			item_dom

	if @data[item_id]
		raise "duplicate record id #{item_id}"
	end

	# store in memory

	item_xml =
		to_xml_string item_dom

	@data[item_id] =
		item_xml

	# store in filesystem

	item_path =
		"#{output_dir}/data/#{item_id}.xml"

	item_dir =
		File.dirname item_path

	FileUtils.mkdir_p \
		item_dir

	File.open item_path, "w" do
		|file_io|
		file_io.puts item_xml
	end

end

#transform_backendObject



13
# File 'lib/hq/transform/transformer.rb', line 13

def transform_backend() parent.transform_backend end