Class: OxTenderAbstract::Client

Inherits:
Object
  • Object
show all
Includes:
ContextualLogger
Defined in:
lib/oxtenderabstract/client.rb

Overview

Main client for working with Zakupki SOAP API

Instance Method Summary collapse

Methods included from ContextualLogger

included, #log_debug, #log_error, #log_fatal, #log_info, #log_warn, #logger

Constructor Details

#initialize(token: nil) ⇒ Client

Returns a new instance of Client.



20
21
22
23
24
25
 
# File 'lib/oxtenderabstract/client.rb', line 20

def initialize(token: nil)
  @token = token || OxTenderAbstract.configuration.token
  @xml_parser = XmlParser.new
  @archive_processor = ArchiveProcessor.new
  validate_token!
end

Instance Method Details

#download_archive_data(archive_url) ⇒ Object

Download and parse archive data



63
64
65
 
# File 'lib/oxtenderabstract/client.rb', line 63

def download_archive_data(archive_url)
  @archive_processor.download_and_extract(archive_url)
end

#enhanced_search_tenders(org_region:, exact_date:, subsystem_type: DocumentTypes::DEFAULT_SUBSYSTEM, document_type: DocumentTypes::DEFAULT_DOCUMENT_TYPE, include_attachments: true) ⇒ Object

Enhanced search tenders with detailed information extraction



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
 
# File 'lib/oxtenderabstract/client.rb', line 175

def enhanced_search_tenders(org_region:, exact_date:, subsystem_type: DocumentTypes::DEFAULT_SUBSYSTEM,
                            document_type: DocumentTypes::DEFAULT_DOCUMENT_TYPE,
                            include_attachments: true)
  log_info "Starting enhanced tender search for region #{org_region}, date #{exact_date}"

  # Step 1: Get archive URLs from API
  api_result = get_docs_by_region(
    org_region: org_region,
    subsystem_type: subsystem_type,
    document_type: document_type,
    exact_date: exact_date
  )

  return api_result if api_result.failure?

  archive_urls = api_result.data[:archive_urls]
  return Result.success({ tenders: [], total_archives: 0, total_files: 0 }) if archive_urls.empty?

  log_info "Found #{archive_urls.size} archives to process"

  # Step 2: Process each archive with detailed information extraction
  all_tenders = []
  total_files = 0

  archive_urls.each_with_index do |archive_url, index|
    log_info "Processing archive #{index + 1}/#{archive_urls.size}"

    archive_result = download_archive_data(archive_url)
    next if archive_result.failure?

    files = archive_result.data[:files]
    total_files += files.size

    # Step 3: Parse XML files from archive with enhanced data extraction
    xml_files = files.select { |name, _| name.downcase.end_with?('.xml') }

    xml_files.each do |file_name, file_data|
      parse_result = parse_xml_document(file_data[:content])
      next if parse_result.failure?
      next unless parse_result.data[:document_type] == :tender

      tender_data = parse_result.data[:content]
      next if tender_data[:reestr_number].nil? || tender_data[:reestr_number].empty?

      # Step 4: Extract additional detailed information
      if include_attachments
        attachments_result = extract_attachments_from_xml(file_data[:content])
        if attachments_result.success?
          tender_data[:attachments] = attachments_result.data[:attachments]
          tender_data[:attachments_count] = attachments_result.data[:total_count]
        end
      end

      # Add metadata
      tender_data[:source_file] = file_name
      tender_data[:archive_url] = archive_url
      tender_data[:processed_at] = Time.now

      all_tenders << tender_data
    end
  end

  log_info "Enhanced search completed. Found #{all_tenders.size} tenders in #{total_files} files"

  Result.success({
                   tenders: all_tenders,
                   total_archives: archive_urls.size,
                   total_files: total_files,
                   processed_at: Time.now,
                   enhanced: true
                 })
end

#extract_attachments_from_xml(xml_content) ⇒ Object

Extract attachments info from XML



73
74
75
 
# File 'lib/oxtenderabstract/client.rb', line 73

def extract_attachments_from_xml(xml_content)
  @xml_parser.extract_attachments(xml_content)
end

#get_docs_by_reestr_number(reestr_number:, subsystem_type: DocumentTypes::DEFAULT_SUBSYSTEM) ⇒ Object

Get documents by registry number



42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
 
# File 'lib/oxtenderabstract/client.rb', line 42

def get_docs_by_reestr_number(reestr_number:, subsystem_type: DocumentTypes::DEFAULT_SUBSYSTEM)
  validate_params!({
                     reestr_number: reestr_number,
                     subsystem_type: subsystem_type
                   })

  request_data = build_reestr_request(reestr_number, subsystem_type)
  log_info "Requesting documents for registry number: #{reestr_number}, type: #{subsystem_type}"

  result = execute_soap_request(:get_docs_by_reestr_number, request_data)

  if result.success?
    log_info "Success response for #{reestr_number}. Found archives: #{result.data[:archive_urls]&.size || 0}"
  else
    log_error "Error for #{reestr_number}: #{result.error}"
  end

  result
end

#get_docs_by_region(org_region:, exact_date:, subsystem_type: DocumentTypes::DEFAULT_SUBSYSTEM, document_type: DocumentTypes::DEFAULT_DOCUMENT_TYPE) ⇒ Object

Get documents by region and date



28
29
30
31
32
33
34
35
36
37
38
39
 
# File 'lib/oxtenderabstract/client.rb', line 28

def get_docs_by_region(org_region:, exact_date:, subsystem_type: DocumentTypes::DEFAULT_SUBSYSTEM,
                       document_type: DocumentTypes::DEFAULT_DOCUMENT_TYPE)
  validate_params!({
                     org_region: org_region,
                     subsystem_type: subsystem_type,
                     document_type: document_type,
                     exact_date: exact_date
                   })

  request_data = build_region_request(org_region, subsystem_type, document_type, exact_date)
  execute_soap_request(:get_docs_by_org_region, request_data)
end

#parse_xml_document(xml_content) ⇒ Object

Parse XML document



68
69
70
 
# File 'lib/oxtenderabstract/client.rb', line 68

def parse_xml_document(xml_content)
  @xml_parser.parse(xml_content)
end

#search_tenders(org_region:, exact_date:, subsystem_type: DocumentTypes::DEFAULT_SUBSYSTEM, document_type: DocumentTypes::DEFAULT_DOCUMENT_TYPE, include_attachments: true) ⇒ Object

Search tenders with full workflow: API -> Archive -> Parse



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
 
# File 'lib/oxtenderabstract/client.rb', line 78

def search_tenders(org_region:, exact_date:, subsystem_type: DocumentTypes::DEFAULT_SUBSYSTEM,
                   document_type: DocumentTypes::DEFAULT_DOCUMENT_TYPE, include_attachments: true)
  log_info "Starting tender search for region #{org_region}, date #{exact_date}, subsystem: #{subsystem_type}, type: #{document_type}"

  # Step 1: Get archive URLs from API
  api_result = get_docs_by_region(
    org_region: org_region,
    subsystem_type: subsystem_type,
    document_type: document_type,
    exact_date: exact_date
  )

  return api_result if api_result.failure?

  archive_urls = api_result.data[:archive_urls]
  return Result.success({ tenders: [], total_archives: 0, total_files: 0 }) if archive_urls.empty?

  log_info "Found #{archive_urls.size} archives to process"

  # Step 2: Process each archive with error resilience
  all_tenders = []
  total_files = 0
  processed_archives = 0
  failed_archives = 0

  archive_urls.each_with_index do |archive_url, index|
    log_info "Processing archive #{index + 1}/#{archive_urls.size}"

    begin
      archive_result = download_archive_data(archive_url)

      if archive_result.failure?
        log_error "Failed to download archive #{index + 1}: #{archive_result.error}"
        failed_archives += 1
        next
      end

      processed_archives += 1
      files = archive_result.data[:files]
      total_files += files.size

      # Step 3: Parse XML files from archive
      xml_files = files.select { |name, _| name.downcase.end_with?('.xml') }
      log_debug "Found #{xml_files.size} XML files in archive #{index + 1}"

      xml_files.each do |file_name, file_data|
        parse_result = parse_xml_document(file_data[:content])

        if parse_result.failure?
          log_debug "Failed to parse #{file_name}: #{parse_result.error}"
          next
        end

        next unless parse_result.data[:document_type] == :tender

        tender_data = parse_result.data[:content]
        next if tender_data[:reestr_number].nil? || tender_data[:reestr_number].empty?

        # Extract attachments if requested
        if include_attachments
          attachments_result = extract_attachments_from_xml(file_data[:content])
          if attachments_result.success?
            tender_data[:attachments] = attachments_result.data[:attachments]
            tender_data[:attachments_count] = attachments_result.data[:total_count]
          end
        end

        # Add metadata
        tender_data[:source_file] = file_name
        tender_data[:archive_url] = archive_url
        tender_data[:processed_at] = Time.now

        all_tenders << tender_data
      rescue StandardError => e
        log_error "Error processing file #{file_name}: #{e.message}"
        # Continue with other files
      end
    rescue StandardError => e
      log_error "Critical error processing archive #{index + 1}: #{e.message}"
      failed_archives += 1
      # Continue with other archives
    end
  end

  log_info "Search completed. Processed: #{processed_archives}/#{archive_urls.size} archives, Failed: #{failed_archives}, Found #{all_tenders.size} tenders in #{total_files} files"

  Result.success({
                   tenders: all_tenders,
                   total_archives: archive_urls.size,
                   processed_archives: processed_archives,
                   failed_archives: failed_archives,
                   total_files: total_files,
                   processed_at: Time.now
                 })
end

#search_tenders_with_resume(org_region:, exact_date:, subsystem_type: DocumentTypes::DEFAULT_SUBSYSTEM, document_type: DocumentTypes::DEFAULT_DOCUMENT_TYPE, start_from_archive: 0, resume_state: nil, include_attachments: true) ⇒ Object

Search tenders with automatic resume capability Позволяет продолжить загрузку с места паузы при блокировках API



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
 
# File 'lib/oxtenderabstract/client.rb', line 250

def search_tenders_with_resume(org_region:, exact_date:, subsystem_type: DocumentTypes::DEFAULT_SUBSYSTEM,
                               document_type: DocumentTypes::DEFAULT_DOCUMENT_TYPE,
                               start_from_archive: 0, resume_state: nil, include_attachments: true)
  log_info "Starting tender search with resume capability for region #{org_region}, date #{exact_date}"
  log_info "Starting from archive #{start_from_archive}" if start_from_archive > 0

  # Восстанавливаем состояние если есть
  if resume_state
    log_info "Resuming from previous state: #{resume_state[:processed_archives]} archives processed"
    all_tenders = resume_state[:tenders] || []
    total_files = resume_state[:total_files] || 0
    processed_archives = resume_state[:processed_archives] || 0
    failed_archives = resume_state[:failed_archives] || 0
    archive_urls = resume_state[:archive_urls]
  else
    # Step 1: Get archive URLs from API
    api_result = get_docs_by_region(
      org_region: org_region,
      subsystem_type: subsystem_type,
      document_type: document_type,
      exact_date: exact_date
    )

    return api_result if api_result.failure?

    archive_urls = api_result.data[:archive_urls]
    return Result.success({ tenders: [], total_archives: 0, total_files: 0 }) if archive_urls.empty?

    all_tenders = []
    total_files = 0
    processed_archives = 0
    failed_archives = 0
  end

  log_info "Found #{archive_urls.size} archives to process (starting from #{start_from_archive})"

  # Step 2: Process archives starting from specified position
  (start_from_archive...archive_urls.size).each do |index|
    archive_url = archive_urls[index]
    log_info "Processing archive #{index + 1}/#{archive_urls.size}"

    begin
      archive_result = download_archive_data(archive_url)

      if archive_result.failure?
        # Проверяем, была ли блокировка с автоматическим ожиданием
        if archive_result.metadata[:error_type] == :blocked &&
           !OxTenderAbstract.configuration.auto_wait_on_block
          # Возвращаем состояние для возможности продолжения
          resume_state = {
            tenders: all_tenders,
            total_files: total_files,
            processed_archives: processed_archives,
            failed_archives: failed_archives,
            archive_urls: archive_urls,
            next_archive_index: index
          }

          return Result.failure(
            "Archive download blocked, can resume from archive #{index + 1}",
            error_type: :blocked,
            retry_after: 600,
            resume_state: resume_state
          )
        else
          log_error "Failed to download archive #{index + 1}: #{archive_result.error}"
          failed_archives += 1
          next
        end
      end

      processed_archives += 1
      files = archive_result.data[:files]
      total_files += files.size

      # Step 3: Parse XML files from archive
      xml_files = files.select { |name, _| name.downcase.end_with?('.xml') }
      log_debug "Found #{xml_files.size} XML files in archive #{index + 1}"

      xml_files.each do |file_name, file_data|
        parse_result = parse_xml_document(file_data[:content])

        if parse_result.failure?
          log_debug "Failed to parse #{file_name}: #{parse_result.error}"
          next
        end

        next unless parse_result.data[:document_type] == :tender

        tender_data = parse_result.data[:content]
        next if tender_data[:reestr_number].nil? || tender_data[:reestr_number].empty?

        # Extract attachments if requested
        if include_attachments
          attachments_result = extract_attachments_from_xml(file_data[:content])
          if attachments_result.success?
            tender_data[:attachments] = attachments_result.data[:attachments]
            tender_data[:attachments_count] = attachments_result.data[:total_count]
          end
        end

        # Add metadata
        tender_data[:source_file] = file_name
        tender_data[:archive_url] = archive_url
        tender_data[:processed_at] = Time.now
        tender_data[:archive_index] = index

        all_tenders << tender_data
      rescue StandardError => e
        log_error "Error processing file #{file_name}: #{e.message}"
        # Continue with other files
      end
    rescue StandardError => e
      log_error "Critical error processing archive #{index + 1}: #{e.message}"
      failed_archives += 1
      # Continue with other archives
    end
  end

  log_info "Search completed. Processed: #{processed_archives}/#{archive_urls.size} archives, Failed: #{failed_archives}, Found #{all_tenders.size} tenders in #{total_files} files"

  Result.success({
                   tenders: all_tenders,
                   total_archives: archive_urls.size,
                   processed_archives: processed_archives,
                   failed_archives: failed_archives,
                   total_files: total_files,
                   processed_at: Time.now,
                   completed: true
                 })
end