ox-tender-abstract 0.9.1 → 0.9.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 2dfb0556afbbe98cebec1fbb413fbe4408d5258e6fbd79d090c99df94dc718d6
-  data.tar.gz: 7d3308d579e05d7c651848f2cd2d1459562ab85d9f3991c2ef4784637803df99
+  metadata.gz: c1e519805302809f117b67e75099300485fc5910038e6ab6012eb9a4343f8e0b
+  data.tar.gz: ffccc77f4305ca644cbe5128a2f1178e8ff30170b25180686fc3db12d5a19761
 SHA512:
-  metadata.gz: aa20e0eeebbdebebc3cba7c36112db12a8bbc63bffffe9d6ce79f762520a9f28be0afc587fb47f22e9358facf118e6e80093fbe1b9a9387c356fecc43efcaacf
-  data.tar.gz: 3437061cb5eaa5c84de842c4d57056ef3fa5d080a0f972708db210c48081a807faa866aeb4b9296d759c4855b4c95c4b541f22ba4be924def0ce64a8afea1348
+  metadata.gz: d062a1e8139143c3c86490c54b9e367f9e6053d27e2a981f8202b2496d187d56f11e2b1b2f101c1c3b9ae69045e5388f34365f9d88e77f480177603c8fd7a1f8
+  data.tar.gz: 57710ad7e471c7165d2878b7ffcbac5a2fbd6ffba10bc9c6c2a47af4015ca639df1d53f1cf89956858838dce7d18efdfca811a4d5f5bef2d53fb46c6a4fa14b7

data/.rspec_status

@@ -49,26 +49,26 @@ example_id                                                 | status | run_time
 ./spec/oxtenderabstract/result_spec.rb[1:3:2]              | passed | 0.00002 seconds |
 ./spec/oxtenderabstract/result_spec.rb[1:4:1]              | passed | 0.00002 seconds |
 ./spec/oxtenderabstract/result_spec.rb[1:4:2]              | passed | 0.00002 seconds |
-./spec/oxtenderabstract/xml_parser_spec.rb[1:1:1:1]        | passed | 0.00012 seconds |
-./spec/oxtenderabstract/xml_parser_spec.rb[1:1:2:1]        | passed | 0.00004 seconds |
-./spec/oxtenderabstract/xml_parser_spec.rb[1:1:3:1]        | failed | 0.00122 seconds |
-./spec/oxtenderabstract/xml_parser_spec.rb[1:1:3:2]        | passed | 0.00162 seconds |
-./spec/oxtenderabstract/xml_parser_spec.rb[1:1:3:3]        | failed | 0.00097 seconds |
-./spec/oxtenderabstract/xml_parser_spec.rb[1:1:4:1]        | passed | 0.00336 seconds |
-./spec/oxtenderabstract/xml_parser_spec.rb[1:1:4:2]        | passed | 0.00176 seconds |
-./spec/oxtenderabstract/xml_parser_spec.rb[1:1:4:3]        | passed | 0.0009 seconds  |
-./spec/oxtenderabstract/xml_parser_spec.rb[1:1:5:1]        | passed | 0.00012 seconds |
-./spec/oxtenderabstract/xml_parser_spec.rb[1:1:6:1]        | passed | 0.00008 seconds |
-./spec/oxtenderabstract/xml_parser_spec.rb[1:1:7:1]        | passed | 0.00008 seconds |
-./spec/oxtenderabstract/xml_parser_spec.rb[1:2:1:1]        | failed | 0.0001 seconds  |
-./spec/oxtenderabstract/xml_parser_spec.rb[1:2:2:1]        | failed | 0.00007 seconds |
-./spec/oxtenderabstract/xml_parser_spec.rb[1:2:3:1]        | failed | 0.00012 seconds |
+./spec/oxtenderabstract/xml_parser_spec.rb[1:1:1:1]        | passed | 0.00192 seconds |
+./spec/oxtenderabstract/xml_parser_spec.rb[1:1:2:1]        | passed | 0.00007 seconds |
+./spec/oxtenderabstract/xml_parser_spec.rb[1:1:3:1]        | failed | 0.00615 seconds |
+./spec/oxtenderabstract/xml_parser_spec.rb[1:1:3:2]        | passed | 0.00098 seconds |
+./spec/oxtenderabstract/xml_parser_spec.rb[1:1:3:3]        | failed | 0.00089 seconds |
+./spec/oxtenderabstract/xml_parser_spec.rb[1:1:4:1]        | passed | 0.00194 seconds |
+./spec/oxtenderabstract/xml_parser_spec.rb[1:1:4:2]        | passed | 0.00168 seconds |
+./spec/oxtenderabstract/xml_parser_spec.rb[1:1:4:3]        | passed | 0.00086 seconds |
+./spec/oxtenderabstract/xml_parser_spec.rb[1:1:5:1]        | passed | 0.00008 seconds |
+./spec/oxtenderabstract/xml_parser_spec.rb[1:1:6:1]        | passed | 0.00007 seconds |
+./spec/oxtenderabstract/xml_parser_spec.rb[1:1:7:1]        | passed | 0.00007 seconds |
+./spec/oxtenderabstract/xml_parser_spec.rb[1:2:1:1]        | failed | 0.00016 seconds |
+./spec/oxtenderabstract/xml_parser_spec.rb[1:2:2:1]        | failed | 0.00011 seconds |
+./spec/oxtenderabstract/xml_parser_spec.rb[1:2:3:1]        | failed | 0.00015 seconds |
 ./spec/oxtenderabstract/xml_parser_spec.rb[1:3:1]          | passed | 0.00005 seconds |
-./spec/oxtenderabstract/xml_parser_spec.rb[1:3:2]          | passed | 0.00005 seconds |
+./spec/oxtenderabstract/xml_parser_spec.rb[1:3:2]          | passed | 0.00004 seconds |
 ./spec/oxtenderabstract/xml_parser_spec.rb[1:3:3]          | passed | 0.00004 seconds |
-./spec/oxtenderabstract/xml_parser_spec.rb[1:3:4]          | passed | 0.00005 seconds |
-./spec/oxtenderabstract/xml_parser_spec.rb[1:4:1:1]        | failed | 0.00045 seconds |
-./spec/oxtenderabstract/xml_parser_spec.rb[1:4:2:1]        | failed | 0.00007 seconds |
+./spec/oxtenderabstract/xml_parser_spec.rb[1:3:4]          | passed | 0.00006 seconds |
+./spec/oxtenderabstract/xml_parser_spec.rb[1:4:1:1]        | failed | 0.00131 seconds |
+./spec/oxtenderabstract/xml_parser_spec.rb[1:4:2:1]        | passed | 0.00015 seconds |
 ./spec/oxtenderabstract_spec.rb[1:1:1]                     | passed | 0.00053 seconds |
 ./spec/oxtenderabstract_spec.rb[1:2:1]                     | passed | 0.00003 seconds |
 ./spec/oxtenderabstract_spec.rb[1:3:1]                     | passed | 0.00003 seconds |

data/lib/oxtenderabstract/archive_processor.rb

@@ -1,26 +1,26 @@
 # frozen_string_literal: true
 
-require "net/http"
-require "uri"
-require "openssl"
-require "zlib"
-require "stringio"
-require "zip"
+require 'net/http'
+require 'uri'
+require 'openssl'
+require 'zlib'
+require 'stringio'
+require 'zip'
 
 module OxTenderAbstract
   # Archive processor for downloading and extracting archive files
   class ArchiveProcessor
     include ContextualLogger
 
-    MAX_FILE_SIZE_BYTES = 100 * 1024 * 1024  # 100 MB in bytes
-    
+    MAX_FILE_SIZE_BYTES = 100 * 1024 * 1024 # 100 MB in bytes
+
     def initialize
       # Archive processor initialization
     end
 
     # Download and extract archive data
     def download_and_extract(archive_url)
-      return Result.failure("Empty archive URL") if archive_url.nil? || archive_url.empty?
+      return Result.failure('Empty archive URL') if archive_url.nil? || archive_url.empty?
 
       begin
         # Download archive to memory
@@ -30,9 +30,9 @@ module OxTenderAbstract
         content = download_result.data[:content]
 
         # Determine archive format by first bytes
-        first_bytes = content[0..1].unpack("H*").first
+        first_bytes = content[0..1].unpack1('H*')
 
-        if first_bytes == "1f8b"
+        if first_bytes == '1f8b'
           # This is GZIP archive - decompress GZIP, then ZIP
           gunzip_result = decompress_gzip(content)
           return gunzip_result if gunzip_result.failure?
@@ -40,25 +40,25 @@ module OxTenderAbstract
           zip_result = extract_zip_from_memory(gunzip_result.data[:content])
 
           Result.success({
-            files: zip_result,
-            total_size: download_result.data[:size],
-            compressed_size: gunzip_result.data[:compressed_size],
-            file_count: zip_result.size
-          })
-        elsif content[0..1] == "PK"
+                           files: zip_result,
+                           total_size: download_result.data[:size],
+                           compressed_size: gunzip_result.data[:compressed_size],
+                           file_count: zip_result.size
+                         })
+        elsif content[0..1] == 'PK'
           # This is already ZIP archive - parse directly
           zip_result = extract_zip_from_memory(content)
 
           Result.success({
-            files: zip_result,
-            total_size: download_result.data[:size],
-            compressed_size: nil,
-            file_count: zip_result.size
-          })
+                           files: zip_result,
+                           total_size: download_result.data[:size],
+                           compressed_size: nil,
+                           file_count: zip_result.size
+                         })
         else
-          Result.failure("Unknown archive format (not GZIP and not ZIP)")
+          Result.failure('Unknown archive format (not GZIP and not ZIP)')
         end
-      rescue => e
+      rescue StandardError => e
         Result.failure("Archive processing error: #{e.message}")
       end
     end
@@ -69,9 +69,7 @@ module OxTenderAbstract
       begin
         uri = URI.parse(url)
         # Check if URI is valid HTTP/HTTPS
-        unless uri.is_a?(URI::HTTP) || uri.is_a?(URI::HTTPS)
-          return Result.failure("Invalid URL: not HTTP/HTTPS")
-        end
+        return Result.failure('Invalid URL: not HTTP/HTTPS') unless uri.is_a?(URI::HTTP) || uri.is_a?(URI::HTTPS)
       rescue URI::InvalidURIError => e
         return Result.failure("Invalid URL: #{e.message}")
       end
@@ -80,8 +78,8 @@ module OxTenderAbstract
         http = create_http_client(uri)
 
         request = Net::HTTP::Get.new(uri.request_uri)
-        request["User-Agent"] = "OxTenderAbstract/#{OxTenderAbstract::VERSION}"
-        request["individualPerson_token"] = OxTenderAbstract.configuration.token
+        request['User-Agent'] = "OxTenderAbstract/#{OxTenderAbstract::VERSION}"
+        request['individualPerson_token'] = OxTenderAbstract.configuration.token
 
         log_debug "Downloading archive from: #{url}"
 
@@ -101,20 +99,20 @@ module OxTenderAbstract
         log_debug "Downloaded archive: #{size} bytes"
 
         Result.success({
-          content: content,
-          size: size,
-          content_type: response["content-type"]
-        })
+                         content: content,
+                         size: size,
+                         content_type: response['content-type']
+                       })
       rescue SocketError, Timeout::Error => e
         Result.failure("Network error: #{e.message}")
-      rescue => e
+      rescue StandardError => e
         Result.failure("Download error: #{e.message}")
       end
     end
 
     def create_http_client(uri)
       http = Net::HTTP.new(uri.host, uri.port)
-      http.use_ssl = uri.scheme == "https"
+      http.use_ssl = uri.scheme == 'https'
       http.verify_mode = OxTenderAbstract.configuration.ssl_verify ? OpenSSL::SSL::VERIFY_PEER : OpenSSL::SSL::VERIFY_NONE
       http.open_timeout = OxTenderAbstract.configuration.timeout_open
       http.read_timeout = OxTenderAbstract.configuration.timeout_read
@@ -122,54 +120,52 @@ module OxTenderAbstract
     end
 
     def decompress_gzip(gzip_content)
-      begin
-        log_debug "Decompressing GZIP archive"
-        
-        gz = Zlib::GzipReader.new(StringIO.new(gzip_content))
-        decompressed_content = gz.read
-        gz.close
-
-        Result.success({
-          content: decompressed_content,
-          compressed_size: gzip_content.bytesize,
-          decompressed_size: decompressed_content.bytesize
-        })
-      rescue Zlib::GzipFile::Error => e
-        Result.failure("GZIP decompression error: #{e.message}")
-      rescue => e
-        Result.failure("Decompression error: #{e.message}")
-      end
+      log_debug 'Decompressing GZIP archive'
+
+      gz = Zlib::GzipReader.new(StringIO.new(gzip_content))
+      decompressed_content = gz.read
+      gz.close
+
+      Result.success({
+                       content: decompressed_content,
+                       compressed_size: gzip_content.bytesize,
+                       decompressed_size: decompressed_content.bytesize
+                     })
+    rescue Zlib::GzipFile::Error => e
+      Result.failure("GZIP decompression error: #{e.message}")
+    rescue StandardError => e
+      Result.failure("Decompression error: #{e.message}")
     end
 
     def extract_zip_from_memory(zip_content)
-      begin
-        log_debug "Extracting ZIP archive from memory"
-        
-        files = {}
-        zip_io = StringIO.new(zip_content)
-
-        Zip::File.open_buffer(zip_io) do |zip_file|
-          zip_file.each do |entry|
-            next if entry.directory?
-            
-            log_debug "Extracting file: #{entry.name} (#{entry.size} bytes)"
-            
-            files[entry.name] = {
-              content: entry.get_input_stream.read,
-              size: entry.size,
-              compressed_size: entry.compressed_size,
-              crc: entry.crc
-            }
-          end
-        end
+      log_debug 'Extracting ZIP archive from memory'
+
+      files = {}
+      zip_io = StringIO.new(zip_content)
+
+      Zip::File.open_buffer(zip_io) do |zip_file|
+        zip_file.each do |entry|
+          next if entry.directory?
+
+          log_debug "Extracting file: #{entry.name} (#{entry.size} bytes)"
 
-        log_debug "Extracted #{files.size} files from ZIP archive"
-        files
-      rescue Zip::Error => e
-        raise ArchiveError, "ZIP extraction error: #{e.message}"
-      rescue => e
-        raise ArchiveError, "Archive extraction error: #{e.message}"
+          content = entry.get_input_stream.read
+
+          files[entry.name] = {
+            content: content,
+            size: entry.size,
+            compressed_size: entry.compressed_size,
+            crc: entry.crc
+          }
+        end
       end
+
+      log_debug "Extracted #{files.size} files from ZIP archive"
+      files
+    rescue Zip::Error => e
+      raise ArchiveError, "ZIP extraction error: #{e.message}"
+    rescue StandardError => e
+      raise ArchiveError, "Archive extraction error: #{e.message}"
     end
   end
-end 
+end

data/lib/oxtenderabstract/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module OxTenderAbstract
-  VERSION = '0.9.1'
+  VERSION = '0.9.2'
 end

data/lib/oxtenderabstract/xml_parser.rb

@@ -408,8 +408,11 @@ module OxTenderAbstract
     def extract_price_from_text(text)
       return nil if text.nil? || text.empty?
 
+      # Remove currency symbols and text like 'руб.', 'рублей' etc.
+      cleaned = text.gsub(/[а-яё]+\.?/i, '').strip
+
       # Remove any non-digit characters except decimal separator and spaces
-      cleaned = text.gsub(/[^\d\s.,]/, '').strip
+      cleaned = cleaned.gsub(/[^\d\s.,]/, '').strip
       return nil if cleaned.empty?
 
       # Remove spaces (used as thousand separators in Russian format)
@@ -522,10 +525,13 @@ module OxTenderAbstract
 
     def extract_purchase_object_data(object_node, namespaces)
       # Basic object information
+      # CRITICAL FIX: Extract name that's direct child of purchaseObject, not from characteristics
+      direct_name = object_node.xpath('./ns4:name | ./name', namespaces).first&.text&.strip
+
       object_data = {
         sid: extract_text_from_node(object_node, './/ns4:sid | .//sid'),
         external_sid: extract_text_from_node(object_node, './/ns4:externalSid | .//externalSid'),
-        name: extract_text_from_node(object_node, './/ns4:name | .//name'),
+        name: direct_name,
         price: extract_price_from_text(extract_text_from_node(object_node, './/ns4:price | .//price')),
         quantity: extract_text_from_node(object_node, './/ns4:quantity/ns4:value | .//quantity/value')&.to_i,
         sum: extract_price_from_text(extract_text_from_node(object_node, './/ns4:sum | .//sum')),
@@ -573,7 +579,7 @@ module OxTenderAbstract
         }
       end
 
-      # Extract characteristics (simplified - just count and basic info)
+      # Extract characteristics (detailed extraction)
       characteristics_nodes = object_node.xpath(
         './/ns4:characteristics//ns4:characteristicsUsingReferenceInfo | .//characteristics//characteristicsUsingReferenceInfo', namespaces
       )
@@ -582,32 +588,46 @@ module OxTenderAbstract
       )
 
       if characteristics_nodes.any?
+        characteristics_details = characteristics_nodes.map do |char_node|
+          char_data = {
+            name: extract_text_from_node(char_node, './/ns4:name | .//name'),
+            type: extract_text_from_node(char_node, './/ns4:type | .//type')
+          }
+
+          # Extract values from text form characteristics
+          values_nodes = char_node.xpath('.//ns4:values/ns4:value | .//values/value', namespaces)
+          if values_nodes.any?
+            char_data[:values] = values_nodes.map do |value_node|
+              extract_text_from_node(value_node, './/ns4:qualityDescription | .//qualityDescription') ||
+                extract_text_from_node(value_node, './/ns4:textValue | .//textValue')
+            end.compact
+          end
+
+          char_data
+        end
+
         object_data[:characteristics] = {
           count: characteristics_nodes.size,
-          details: characteristics_nodes.first(5).map do |char_node|
-            {
-              name: extract_text_from_node(char_node, './/ns4:name | .//name'),
-              type: extract_text_from_node(char_node, './/ns4:type | .//type')
-            }
-          end
+          details: characteristics_details
         }
       end
 
       # Determine the actual product name from available sources
-      # Priority: KTRU name > OKPD2 name > name field
-      product_name = nil
-      product_name = if object_data[:ktru] && object_data[:ktru][:name] && !object_data[:ktru][:name].empty?
+      # Priority: Direct name field (now fixed) > KTRU name > OKPD2 name
+      product_name = if object_data[:name] && !object_data[:name].empty?
+                       object_data[:name]
+                     elsif object_data[:ktru] && object_data[:ktru][:name] && !object_data[:ktru][:name].empty?
                        object_data[:ktru][:name]
                      elsif object_data[:okpd2] && object_data[:okpd2][:name] && !object_data[:okpd2][:name].empty?
                        object_data[:okpd2][:name]
                      else
-                       object_data[:name]
+                       'Unknown product'
                      end
 
       object_data[:product_name] = product_name
 
-      # Add field description indicating what the 'name' field actually contains
-      object_data[:name_type] = determine_name_type(object_data[:name])
+      # Now the name field should contain actual product names, not characteristics
+      object_data[:name_type] = 'product_name'
 
       object_data.compact
     end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: ox-tender-abstract
 version: !ruby/object:Gem::Version
-  version: 0.9.1
+  version: 0.9.2
 platform: ruby
 authors:
 - smolev