oddb2xml 3.0.0 → 3.0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ab4100aa6c522cd66ca2a69af3959c576e82cfdaeb41cffd399cb6d451ba7ff2
-  data.tar.gz: 495bcb8a97881ba89f5a1bb9fd8acb264a56cdd8f262e1b7669579bffc9c77be
+  metadata.gz: c0521593bc12b423a74628f04973dcaf43241ce674c415c4e3a82da3ad34a134
+  data.tar.gz: a7b8fe9076dd737105696b525e3c4c0e17e3174ea4d86d0bab9f948324229c05
 SHA512:
-  metadata.gz: f9b839faf528860fdf2ab6e319b1db88812d1aa2c7e628df45ea6de1a932c78b51b93e84b6a30355ed8a40ca4f9782d73edce2ef3742934d8b1cff99c6d19ad8
-  data.tar.gz: a2878be3ff52ef0ee26d366f56bed4d1e443083730aa2253cbba6a1fecfcb40e01140910108649d7065dcbec3a2326208e2a8aca1918b60151df7aaea2983767
+  metadata.gz: 1f0c6275adc2b60930eb961b1745013f81c167a49c035347c49b40af8f59ead028f884981aeb9aa0ce809b7007a1b4c78993d2adfa5c3e31e3ed56e8866ac035
+  data.tar.gz: c02f68d34884adbabe1465cf7180e6ef51cbb84049a71a931880bcb383abb4c3dc8196f92e21932b3529a68e5211f546fb053112f27037434313517de4d22961

data/CLAUDE.md

@@ -0,0 +1,69 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+## Project Overview
+
+oddb2xml is a Ruby gem that downloads Swiss pharmaceutical data from 10+ sources (Swissmedic, BAG, Refdata, ZurRose, EPha, etc.), parses multiple formats (XML, XLSX, CSV, SOAP, fixed-width DAT), merges/deduplicates them, and generates standardized XML/DAT output files for healthcare systems. It also supports the Elexis EHR Artikelstamm format.
+
+## Common Commands
+
+```bash
+# Install dependencies
+bundle install
+
+# Run full test suite
+bundle exec rake spec
+
+# Run a single test file
+bundle exec rspec spec/builder_spec.rb
+
+# Run a single test by line number
+bundle exec rspec spec/builder_spec.rb:42
+
+# Lint with StandardRB
+bundle exec standardrb
+
+# Auto-fix lint issues
+bundle exec standardrb --fix
+
+# Build the gem
+bundle exec rake build
+```
+
+## Architecture
+
+The system follows a **download → extract → build → compress** pipeline:
+
+1. **CLI** (`lib/oddb2xml/cli.rb`) — Entry point. Parses options via Optimist (`options.rb`), orchestrates the pipeline, manages multi-threaded downloads.
+
+2. **Downloaders** (`lib/oddb2xml/downloader.rb`) — 11 subclasses of `Downloader`, each fetching from a specific Swiss data source. Files cached in `./downloads/`.
+
+3. **Extractors** (`lib/oddb2xml/extractor.rb`) — Matching extractor classes that parse downloaded files into Ruby hashes. Formats include XML (nokogiri/sax-machine), XLSX (rubyXL), SOAP (savon), CSV, and fixed-width text.
+
+4. **Builder** (`lib/oddb2xml/builder.rb`) — The largest file (~1900 lines). Merges extracted data and generates output XML/DAT files. Methods follow `prepare_*` (data assembly) and `build_*` (output generation) naming.
+
+5. **Calc** (`lib/oddb2xml/calc.rb`) — Composition calculation logic, works with `parslet_compositions.rb` and `compositions_syntax.rb` (Parslet-based PEG parser for drug composition strings).
+
+6. **Compressor** (`lib/oddb2xml/compressor.rb`) — Optional ZIP/TAR.GZ output compression.
+
+### Key data identifiers
+- **GTIN/EAN13**: Primary article identifier (13-digit barcode)
+- **Pharmacode**: Swiss pharmacy code
+- **IKSNR**: Swissmedic registration number (5-digit)
+- **Swissmedic sequence/pack numbers**: Combined with IKSNR to form full identifiers
+
+### Static data overrides
+YAML files in `data/` provide manual overrides and mappings: `article_overrides.yaml`, `product_overrides.yaml`, `gtin2ignore.yaml`, `gal_forms.yaml`, `gal_groups.yaml`.
+
+## Testing
+
+- Framework: RSpec with flexmock (mocking), webmock + VCR (HTTP recording/playback)
+- Test fixtures: `spec/data/` (sample files), `spec/fixtures/vcr_cassettes/` (recorded HTTP responses)
+- `spec/spec_helper.rb` defines test constants (GTINs) and configures VCR to avoid real HTTP calls during tests
+- CI runs on Ruby 3.0, 3.1, 3.2
+
+## Ruby Version
+
+- Minimum: Ruby >= 2.5.0 (gemspec)
+- Current development: Ruby 3.2.0 (`.ruby-version`)

data/Gemfile

@@ -7,5 +7,6 @@ group :debugger do
   gem "pry-doc"
 end
 
-gem "nokogiri", "1.13.9"
-gem "rack", "3.0.11"
+gem "nokogiri", ">= 1.19.1"
+gem "rack", ">= 3.1.20"
+gem "mutex_m"

data/Gemfile.lock

@@ -4,50 +4,50 @@ PATH
     oddb2xml (3.0.0)
       htmlentities
       httpi
-      mechanize
+      mechanize (>= 2.8.5)
       minitar
       multi_json
-      nokogiri (>= 1.8.2)
+      nokogiri (>= 1.19.1)
       optimist
       ox
       parslet
-      rack (= 3.0.11)
-      rexml
+      rack (>= 3.1.20)
+      rexml (>= 3.3.9)
       rubyXL (~> 3.4.0)
-      rubyntlm (= 0.5.1)
+      rubyntlm (>= 0.6.3)
       rubyzip (~> 3.0.1)
       savon (~> 2.12.0)
       sax-machine
       spreadsheet
       standardrb
-      webrick
+      webrick (>= 1.8.2)
       xml-simple
 
 GEM
   remote: https://rubygems.org/
   specs:
-    addressable (2.8.5)
-      public_suffix (>= 2.0.2, < 6.0)
+    addressable (2.8.8)
+      public_suffix (>= 2.0.2, < 8.0)
     akami (1.3.1)
       gyoku (>= 0.4.0)
       nokogiri
     ast (2.4.2)
+    base64 (0.3.0)
     builder (3.2.4)
     byebug (11.1.3)
     coderay (1.1.3)
-    connection_pool (2.4.1)
+    connection_pool (3.0.2)
     crack (0.4.5)
       rexml
     diff-lcs (1.5.0)
-    domain_name (0.5.20190701)
-      unf (>= 0.0.5, < 1.0.0)
+    domain_name (0.6.20240107)
     flexmock (2.3.8)
     gyoku (1.4.0)
       builder (>= 2.1.2)
       rexml (~> 3.0)
     hashdiff (1.0.1)
     htmlentities (4.3.4)
-    http-cookie (1.0.5)
+    http-cookie (1.1.0)
       domain_name (~> 0.5)
     httpi (2.5.0)
       rack
@@ -55,31 +55,37 @@ GEM
     json (2.6.3)
     language_server-protocol (3.17.0.3)
     lint_roller (1.1.0)
-    mechanize (2.7.7)
-      domain_name (~> 0.5, >= 0.5.1)
-      http-cookie (~> 1.0)
-      mime-types (>= 1.17.2)
-      net-http-digest_auth (~> 1.1, >= 1.1.1)
-      net-http-persistent (>= 2.5.2)
-      nokogiri (~> 1.6)
-      ntlm-http (~> 0.1, >= 0.1.1)
+    logger (1.7.0)
+    mechanize (2.14.0)
+      addressable (~> 2.8)
+      base64
+      domain_name (~> 0.5, >= 0.5.20190701)
+      http-cookie (~> 1.0, >= 1.0.3)
+      mime-types (~> 3.3)
+      net-http-digest_auth (~> 1.4, >= 1.4.1)
+      net-http-persistent (>= 2.5.2, < 5.0.dev)
+      nkf
+      nokogiri (~> 1.11, >= 1.11.2)
+      rubyntlm (~> 0.6, >= 0.6.3)
       webrick (~> 1.7)
-      webrobots (>= 0.0.9, < 0.2)
+      webrobots (~> 0.1.2)
     method_source (1.0.0)
-    mime-types (3.5.1)
-      mime-types-data (~> 3.2015)
-    mime-types-data (3.2023.0808)
-    mini_portile2 (2.8.4)
+    mime-types (3.7.0)
+      logger
+      mime-types-data (~> 3.2025, >= 3.2025.0507)
+    mime-types-data (3.2026.0203)
+    mini_portile2 (2.8.9)
     minitar (0.9)
     multi_json (1.15.0)
+    mutex_m (0.3.0)
     net-http-digest_auth (1.4.1)
-    net-http-persistent (4.0.2)
-      connection_pool (~> 2.2)
-    nokogiri (1.13.9)
-      mini_portile2 (~> 2.8.0)
+    net-http-persistent (4.0.8)
+      connection_pool (>= 2.2.4, < 4)
+    nkf (0.2.0)
+    nokogiri (1.19.1)
+      mini_portile2 (~> 2.8.2)
       racc (~> 1.4)
     nori (2.6.0)
-    ntlm-http (0.1.1)
     optimist (3.1.0)
     ox (2.14.14)
     parallel (1.23.0)
@@ -97,14 +103,14 @@ GEM
       pry (~> 0.11)
       yard (~> 0.9.11)
     psych (3.3.4)
-    public_suffix (5.0.3)
-    racc (1.7.1)
-    rack (3.0.11)
+    public_suffix (7.0.2)
+    racc (1.8.1)
+    rack (3.2.5)
     rainbow (3.1.1)
     rake (13.0.6)
-    rdoc (6.3.3)
+    rdoc (6.3.4.1)
     regexp_parser (2.8.1)
-    rexml (3.2.6)
+    rexml (3.4.4)
     rspec (3.12.0)
       rspec-core (~> 3.12.0)
       rspec-expectations (~> 3.12.0)
@@ -138,7 +144,8 @@ GEM
     rubyXL (3.4.25)
       nokogiri (>= 1.10.8)
       rubyzip (>= 1.3.0)
-    rubyntlm (0.5.1)
+    rubyntlm (0.6.5)
+      base64
     rubyzip (3.0.1)
     savon (2.12.1)
       akami (~> 1.2)
@@ -167,9 +174,6 @@ GEM
     standardrb (1.0.1)
       standard
     timecop (0.9.8)
-    unf (0.1.4)
-      unf_ext
-    unf_ext (0.0.8.2)
     unicode-display_width (2.5.0)
     vcr (6.1.0)
     wasabi (3.7.0)
@@ -180,7 +184,7 @@ GEM
       addressable (>= 2.8.0)
       crack (>= 0.3.2)
       hashdiff (>= 0.4.0, < 2.0.0)
-    webrick (1.8.1)
+    webrick (1.9.2)
     webrobots (0.1.2)
     xml-simple (1.1.9)
       rexml
@@ -192,14 +196,15 @@ PLATFORMS
 DEPENDENCIES
   bundler
   flexmock
-  nokogiri (= 1.13.9)
+  mutex_m
+  nokogiri (>= 1.19.1)
   oddb2xml!
   pry-byebug
   pry-doc
   psych (< 4.0.0)
-  rack (= 3.0.11)
+  rack (>= 3.1.20)
   rake
-  rdoc (~> 6.3.3)
+  rdoc (>= 6.3.4.1)
   rspec
   timecop
   vcr

data/lib/oddb2xml/cli.rb

@@ -60,14 +60,21 @@ module Oddb2xml
         threads << download(:zurrose)
         threads << download(:package) # swissmedic
         threads << download(:lppv) # oddb2xml_files
-        threads << download(:bag) # bag.e-mediat
+        
+        # Use FHIR or XML for BAG data
+        if @options[:fhir]
+          threads << download(:fhir) # FHIR from FOPH/BAG
+        else
+          threads << download(:bag) # XML from bag.e-mediat
+        end
+        
         if @options[:firstbase]
           threads << download(:firstbase) # https://github.com/zdavatz/oddb2xml/issues/63
         end
         types.each do |type|
           begin
             threads << download(:refdata, type) # refdata
-          rescue error
+          rescue => error
             # Should continue even when error #102
             Oddb2xml.log("Error in downloading refdata #{error}")
           end
@@ -274,6 +281,19 @@ module Oddb2xml
           @lppvs
         end
 
+      when :fhir
+        # instead of Thread.new do
+
+        downloader = FhirDownloader.new(@options)
+        fhir_file = downloader.download
+        Oddb2xml.log("FhirDownloader downloaded #{File.size(fhir_file)} bytes")
+        @mutex.synchronize do
+          hsh = FhirExtractor.new(fhir_file).to_hash
+          @items = hsh
+          Oddb2xml.log("FhirExtractor added #{@items.size} items from FHIR")
+          @items
+        end
+
       when :bag
         # instead of Thread.new do
 
@@ -321,7 +341,7 @@ module Oddb2xml
             @refdata_types[type] = hsh
             Oddb2xml.log("RefdataExtractor #{type} added #{hsh.size} keys now #{@refdata_types.keys} items from xml with #{xml.size} bytes")
             @refdata_types[type]
-          rescue error
+          rescue => error
             # Should continue even when error https://github.com/zdavatz/oddb2xml/issues/102
             Oddb2xml.log("Error in RefdataExtractor #{error}")
           end

data/lib/oddb2xml/compressor.rb

@@ -1,10 +1,8 @@
 require "zlib"
 require "minitar"
 require "zip"
-
 module Oddb2xml
   class Compressor
-    include Archive::Tar
     attr_accessor :contents
     def initialize(prefix = "oddb", options = {})
       @options = options

data/lib/oddb2xml/fhir_support.rb

@@ -0,0 +1,752 @@
+# frozen_string_literal: true
+
+# fhir_support.rb
+# Complete FHIR support module for oddb2xml
+# This file provides all FHIR functionality in one place
+
+require "json"
+require "date"
+require "ostruct"
+
+module Oddb2xml
+  # FHIR Downloader - Downloads NDJSON from FOPH/BAG
+  class FhirDownloader < Downloader
+    include DownloadMethod
+
+    BASE_URL = "https://epl.bag.admin.ch"
+    STATIC_FHIR_PATH = "/static/fhir"
+
+    def initialize(options = {})
+      @options = options
+      @url = find_latest_fhir_url
+      super(options, @url)
+    end
+
+    def download
+      filename = File.basename(@url)
+      file = File.join(WORK_DIR, filename)
+      @file2save = File.join(DOWNLOADS, filename)
+
+      report_download(@url, @file2save)
+
+      # Check if we should skip download (file exists and is recent)
+      if skip_download?
+        Oddb2xml.log "FhirDownloader: Skip downloading #{@file2save} (#{format_size(File.size(@file2save))}, less than 24h old)"
+        return File.expand_path(@file2save)
+      end
+
+      begin
+        # Download the file
+        download_as(file, "w+")
+
+        # Validate NDJSON format
+        if validate_ndjson(@file2save)
+          line_count = count_ndjson_lines(@file2save)
+          Oddb2xml.log "FhirDownloader: NDJSON validation successful (#{line_count} bundles, #{format_size(File.size(@file2save))})"
+        else
+          Oddb2xml.log "FhirDownloader: WARNING - NDJSON validation failed!"
+        end
+
+        File.expand_path(@file2save)
+      rescue Timeout::Error, Errno::ETIMEDOUT
+        retrievable? ? retry : raise
+      rescue => error
+        Oddb2xml.log "FhirDownloader: Error downloading FHIR file: #{error.message}"
+        raise
+      ensure
+        Oddb2xml.download_finished(@file2save, false)
+        FileUtils.rm_f(file, verbose: true) if File.exist?(file) && file != @file2save
+      end
+    end
+
+    private
+
+    def find_latest_fhir_url
+      agent = Mechanize.new
+      response = agent.get "https://epl.bag.admin.ch/api/sl/public/resources/current"
+      resources = JSON.parse(response.body)
+      "https://epl.bag.admin.ch/static/" + resources["fhir"]["fileUrl"]
+    rescue => e
+      Oddb2xml.log "FhirDownloader: Error finding latest URL: #{e.message}"
+      nil
+    end
+
+    def skip_download?
+        @options[:skip_download] || (File.exist?(@file2save) && file_age_hours(@file2save) < 24)
+    end
+
+    def file_age_hours(file)
+      ((Time.now - File.ctime(file)).to_i / 3600.0).round(1)
+    end
+
+    def format_size(bytes)
+      if bytes < 1024
+        "#{bytes} bytes"
+      elsif bytes < 1024 * 1024
+        "#{(bytes / 1024.0).round(1)} KB"
+      else
+        "#{(bytes / (1024.0 * 1024)).round(1)} MB"
+      end
+    end
+
+    def validate_ndjson(file)
+      # Validate NDJSON format by checking first few lines
+      return false unless File.exist?(file)
+
+      begin
+        line_count = 0
+        valid_count = 0
+        error_lines = []
+
+        File.open(file, "r:utf-8") do |f|
+          # Check first 10 lines
+          10.times do
+            line = f.gets
+            break if line.nil?
+
+            line_count += 1
+            next if line.strip.empty?
+
+            begin
+              data = JSON.parse(line)
+              # Check if it's a FHIR Bundle
+              if data["resourceType"] == "Bundle"
+                valid_count += 1
+              else
+                error_lines << "Line #{line_count}: Not a Bundle (resourceType: #{data["resourceType"]})"
+              end
+            rescue JSON::ParserError => e
+              error_lines << "Line #{line_count}: Invalid JSON - #{e.message}"
+            end
+          end
+        end
+
+        if error_lines.any?
+          error_lines.each { |err| Oddb2xml.log "FhirDownloader: #{err}" }
+        end
+
+        # Valid if we found at least some valid bundles
+        valid_count > 0
+      rescue => e
+        Oddb2xml.log "FhirDownloader: Validation error: #{e.message}"
+        false
+      end
+    end
+
+    def count_ndjson_lines(file)
+      # Count non-empty lines in the NDJSON file
+      count = 0
+      File.open(file, "r") do |f|
+        f.each_line do |line|
+          count += 1 unless line.strip.empty?
+        end
+      end
+      count
+    rescue => e
+      Oddb2xml.log "FhirDownloader: Error counting lines: #{e.message}"
+      0
+    end
+  end
+
+  # FHIR Parser - Parses NDJSON and creates compatible structure
+  module FHIR
+    # Bundle represents one line in the NDJSON file
+    class Bundle
+      attr_reader :medicinal_product, :packages, :authorizations, :ingredients
+
+      def initialize(json_line)
+        data = JSON.parse(json_line)
+        @entries = data["entry"] || []
+        parse_entries
+      end
+
+      private
+
+      def parse_entries
+        @medicinal_product = nil
+        @packages = []
+        @authorizations = []
+        @ingredients = []
+
+        @entries.each do |entry|
+          resource = entry["resource"]
+          case resource["resourceType"]
+          when "MedicinalProductDefinition"
+            @medicinal_product = MedicinalProduct.new(resource)
+          when "PackagedProductDefinition"
+            @packages << Package.new(resource)
+          when "RegulatedAuthorization"
+            @authorizations << Authorization.new(resource)
+          when "Ingredient"
+            @ingredients << Ingredient.new(resource)
+          end
+        end
+      end
+    end
+
+    class MedicinalProduct
+      attr_reader :names, :atc_code, :classification, :it_codes
+
+      def initialize(resource)
+        @names = {}
+        resource["name"]&.each do |name|
+          lang = name.dig("usage", 0, "language", "coding", 0, "code")
+          @names[lang] = name["productName"]
+        end
+
+        # Get ATC code (classification[0])
+        @atc_code = resource.dig("classification", 0, "coding", 0, "code")
+
+        # Get product classification (generic/reference) (classification[1])
+        @classification = resource.dig("classification", 1, "coding", 0, "code")
+        
+        # Get IT codes (Index Therapeuticus) from classification with correct system
+        @it_codes = []
+        resource["classification"]&.each do |cls|
+          cls["coding"]&.each do |coding|
+            if coding["system"]&.include?("index-therapeuticus")
+              # Format IT code from "080300" to "08.03.00" or "08.03."
+              it_code = format_it_code(coding["code"])
+              @it_codes << it_code if it_code
+            end
+          end
+        end
+      end
+
+      def name_de
+        @names["de-CH"] || @names["de"]
+      end
+
+      def name_fr
+        @names["fr-CH"] || @names["fr"]
+      end
+
+      def name_it
+        @names["it-CH"] || @names["it"]
+      end
+      
+      def it_code
+        # Return first IT code (primary), formatted like "08.03.00"
+        @it_codes.first
+      end
+      
+      private
+      
+      def format_it_code(code)
+        return nil unless code && code.match?(/^\d{6}$/)
+        
+        # Convert "080300" to "08.03.00"
+        "#{code[0..1]}.#{code[2..3]}.#{code[4..5]}"
+      end
+    end
+
+    class Package
+      attr_reader :gtin, :description, :swissmedic_no8, :legal_status, :resource_id
+
+      def initialize(resource)
+        @resource_id = resource["id"]
+        @gtin = resource.dig("packaging", "identifier", 0, "value")
+        @description = resource["description"]
+
+        # Extract SwissmedicNo8 from GTIN (last 8 digits)
+        if @gtin && @gtin.length >= 8
+          @swissmedic_no8 = @gtin[-8..-1]
+        end
+
+        @legal_status = resource.dig("legalStatusOfSupply", 0, "code", "coding", 0, "code")
+      end
+    end
+
+    class Authorization
+      attr_reader :identifier, :auth_type, :holder_name, :prices, :foph_dossier_no,
+        :status, :listing_status, :subject_reference, :cost_share, :limitations
+
+      def initialize(resource)
+        @identifier = resource.dig("identifier", 0, "value")
+        @auth_type = resource.dig("type", "coding", 0, "display")
+        @holder_name = resource.dig("contained", 0, "name")
+        @subject_reference = resource.dig("subject", 0, "reference")
+        @prices = []
+        @foph_dossier_no = nil
+        @status = nil
+        @listing_status = nil
+        @cost_share = nil
+        @limitations = []
+
+        # Parse extensions for reimbursement info and prices
+        resource["extension"]&.each do |ext|
+          if ext["url"]&.include?("reimbursementSL")
+            parse_reimbursement_extension(ext)
+          end
+        end
+        
+        # Parse indications for limitations
+        parse_indications(resource["indication"])
+      end
+
+      def marketing_authorization?
+        @auth_type == "Marketing Authorisation"
+      end
+
+      def reimbursement_sl?
+        @auth_type == "Reimbursement SL"
+      end
+
+      private
+
+      def parse_reimbursement_extension(ext)
+        ext["extension"]&.each do |sub_ext|
+          case sub_ext["url"]
+          when "FOPHDossierNumber"
+            @foph_dossier_no = sub_ext.dig("valueIdentifier", "value")
+          when "status"
+            @status = sub_ext.dig("valueCodeableConcept", "coding", 0, "display")
+          when "listingStatus"
+            @listing_status = sub_ext.dig("valueCodeableConcept", "coding", 0, "display")
+          when "costShare"
+            @cost_share = sub_ext["valueInteger"]
+          else
+            # Check if this is a productPrice extension (has nested extensions)
+            if sub_ext["url"]&.include?("productPrice")
+              @prices << parse_price_extension(sub_ext)
+            end
+          end
+        end
+      end
+
+      def parse_price_extension(ext)
+        price = {}
+        ext["extension"]&.each do |sub_ext|
+          case sub_ext["url"]
+          when "type"
+            price[:type] = sub_ext.dig("valueCodeableConcept", "coding", 0, "code")
+          when "value"
+            price[:value] = sub_ext.dig("valueMoney", "value")
+            price[:currency] = sub_ext.dig("valueMoney", "currency")
+          when "changeDate"
+            price[:change_date] = sub_ext["valueDate"]
+          when "changeType"
+            price[:change_type] = sub_ext.dig("valueCodeableConcept", "coding", 0, "display")
+          end
+        end
+        price
+      end
+      
+      def parse_indications(indications)
+        return unless indications
+        
+        indications.each do |indication|
+          indication["extension"]&.each do |ext|
+            if ext["url"]&.include?("regulatedAuthorization-limitation")
+              @limitations << parse_limitation_extension(ext)
+            end
+          end
+        end
+      end
+      
+      def parse_limitation_extension(ext)
+        limitation = {}
+        ext["extension"]&.each do |sub_ext|
+          case sub_ext["url"]
+          when "status"
+            limitation[:status] = sub_ext.dig("valueCodeableConcept", "coding", 0, "display")
+            limitation[:status_code] = sub_ext.dig("valueCodeableConcept", "coding", 0, "code")
+          when "statusDate"
+            limitation[:status_date] = sub_ext["valueDate"]
+          when "limitationText"
+            limitation[:text] = sub_ext["valueString"]
+          when "period"
+            limitation[:start_date] = sub_ext.dig("valuePeriod", "start")
+            limitation[:end_date] = sub_ext.dig("valuePeriod", "end")
+          when "firstLimitationDate"
+            limitation[:first_date] = sub_ext["valueDate"]
+          end
+        end
+        limitation
+      end
+    end
+
+    class Ingredient
+      attr_reader :substance_name, :quantity, :unit
+
+      def initialize(resource)
+        @substance_name = resource.dig("substance", "code", "concept", "text")
+        strength = resource.dig("substance", "strength", 0)
+        @quantity = strength&.dig("presentationQuantity", "value")
+        @unit = strength&.dig("presentationQuantity", "unit")
+
+        # Handle textPresentation for ranges like "340-660"
+        @text_presentation = strength&.dig("textPresentation")
+      end
+
+      def quantity_text
+        @text_presentation || (@quantity ? "#{@quantity}" : "")
+      end
+    end
+
+    # Main parser class that provides compatibility with XML parser
+    class PreparationsParser
+      attr_reader :preparations
+
+      def initialize(ndjson_file)
+        @preparations = []
+        parse_file(ndjson_file)
+      end
+
+      def parse_file(ndjson_file)
+        File.foreach(ndjson_file, encoding: 'UTF-8') do |line|
+          next if line.strip.empty?
+
+          bundle = Bundle.new(line)
+          next unless bundle.medicinal_product
+
+          # Create a preparation structure compatible with XML parser output
+          prep = create_preparation(bundle)
+          @preparations << prep if prep
+        end
+      end
+
+      private
+
+      def create_preparation(bundle)
+        mp = bundle.medicinal_product
+
+        # Create preparation hash structure
+        prep = OpenStruct.new
+        prep.NameDe = mp.name_de
+        prep.NameFr = mp.name_fr
+        prep.NameIt = mp.name_it
+        prep.AtcCode = mp.atc_code
+        prep.OrgGenCode = map_org_gen_code(mp.classification)
+        prep.ItCode = mp.it_code  # Add IT code
+
+        # Map packages
+        prep.Packs = OpenStruct.new
+        prep.Packs.Pack = bundle.packages.map do |pkg|
+          pack = OpenStruct.new
+          pack.GTIN = pkg.gtin
+          pack.SwissmedicNo8 = pkg.swissmedic_no8
+          pack.DescriptionDe = pkg.description
+          pack.DescriptionFr = pkg.description
+          pack.DescriptionIt = pkg.description
+          pack.SwissmedicCategory = map_legal_status(pkg.legal_status)
+
+          # Find prices and additional data for this package
+          pack.Prices = create_prices_for_package(bundle, pkg)
+          
+          # Add limitations and cost share
+          pack.Limitations = create_limitations_for_package(bundle, pkg)
+          pack.CostShare = get_cost_share_for_package(bundle, pkg)
+
+          pack
+        end
+
+        # Map ingredients
+        prep.Substances = OpenStruct.new
+        prep.Substances.Substance = bundle.ingredients.map do |ing|
+          substance = OpenStruct.new
+          substance.DescriptionLa = ing.substance_name
+          substance.Quantity = ing.quantity_text
+          substance.QuantityUnit = ing.unit
+          substance
+        end
+
+        # Extract SwissmedicNo5 from the first authorization
+        marketing_auth = bundle.authorizations.find(&:marketing_authorization?)
+        if marketing_auth
+          # SwissmedicNo5 is typically the first 5 digits of the identifier
+          prep.SwissmedicNo5 = marketing_auth.identifier&.to_s&.[](0, 5)
+        end
+
+        prep
+      end
+
+      def create_prices_for_package(bundle, package)
+        prices = OpenStruct.new
+
+        # Find reimbursement authorization for this package by resource ID
+        # Match by ending with ID to handle both PackagedProductDefinition and CHIDMPPackagedProductDefinition
+        reimbursement = bundle.authorizations.find do |auth|
+          auth.reimbursement_sl? && auth.subject_reference&.end_with?(package.resource_id)
+        end
+
+        return prices unless reimbursement
+
+        reimbursement.prices.each do |price|
+          if price[:type] == "756002005002"
+            exf = OpenStruct.new
+            exf.Price = price[:value]
+            exf.ValidFromDate = price[:change_date]
+            exf.PriceTypeCode = price[:type]
+            prices.ExFactoryPrice = exf
+          elsif price[:type] == "756002005001"
+            pub = OpenStruct.new
+            pub.Price = price[:value]
+            pub.ValidFromDate = price[:change_date]
+            pub.PriceTypeCode = price[:type]
+            prices.PublicPrice = pub
+          end
+        end
+
+        prices
+      end
+      
+      def create_limitations_for_package(bundle, package)
+        # Find reimbursement authorization for this package
+        reimbursement = bundle.authorizations.find do |auth|
+          auth.reimbursement_sl? && auth.subject_reference&.end_with?(package.resource_id)
+        end
+
+        return nil unless reimbursement
+        return nil if reimbursement.limitations.empty?
+        
+        # Convert FHIR limitations to OpenStruct format
+        limitations = OpenStruct.new
+        limitations.Limitation = reimbursement.limitations.map do |lim|
+          limitation = OpenStruct.new
+          limitation.LimitationCode = ""  # Not in FHIR
+          limitation.LimitationType = ""  # Could derive from status
+          limitation.LimitationNiveau = ""  # Not in FHIR
+          limitation.LimitationValue = ""  # Not in FHIR
+          limitation.DescriptionDe = lim[:text] || ""
+          limitation.DescriptionFr = ""  # May need separate language version
+          limitation.DescriptionIt = ""  # May need separate language version
+          limitation.ValidFromDate = lim[:status_date] || lim[:start_date] || ""
+          limitation.ValidThruDate = lim[:end_date] || ""
+          limitation
+        end
+        
+        limitations
+      end
+      
+      def get_cost_share_for_package(bundle, package)
+        # Find reimbursement authorization for this package
+        reimbursement = bundle.authorizations.find do |auth|
+          auth.reimbursement_sl? && auth.subject_reference&.end_with?(package.resource_id)
+        end
+
+        reimbursement&.cost_share
+      end
+
+      def map_org_gen_code(classification)
+        return nil unless classification
+
+        case classification
+        when "756001003001"
+          "G"
+        when "756001003002"
+          "O"
+        else
+          nil
+        end
+      end
+
+      def map_legal_status(status_code)
+        return nil unless status_code
+
+        # Map FHIR codes to Swissmedic categories
+        case status_code
+        when "756005022001"
+          "A"
+        when "756005022003"
+          "B"
+        when "756005022005"
+          "C"
+        when "756005022007"
+          "D"
+        when "756005022009"
+          "E"
+        else
+          nil
+        end
+      end
+    end
+  end
+
+  # FHIR Extractor - Compatible with existing BagXmlExtractor
+  class FhirExtractor < Extractor
+    def initialize(fhir_file)
+      @fhir_file = fhir_file
+    end
+
+    def to_hash
+      data = {}
+      Oddb2xml.log "FhirExtractor: Parsing FHIR file #{@fhir_file}"
+
+      # Parse FHIR NDJSON
+      result = FhirPreparationsEntry.parse(@fhir_file)
+
+      result.Preparations.Preparation.each do |seq|
+        next unless seq
+        next if seq.SwissmedicNo5 && seq.SwissmedicNo5.eql?("0")
+
+        # Build item structure matching BagXmlExtractor
+        item = {}
+        item[:data_origin] = "fhir"
+        item[:refdata] = true
+        item[:product_key] = nil  # Not available in FHIR
+        item[:desc_de] = ""  # Not in FHIR at product level
+        item[:desc_fr] = ""
+        item[:desc_it] = ""
+        item[:name_de] = (name = seq.NameDe) ? name : ""
+        item[:name_fr] = (name = seq.NameFr) ? name : ""
+        item[:name_it] = (name = seq.NameIt) ? name : ""
+        item[:swissmedic_number5] = (num5 = seq.SwissmedicNo5) ? num5.to_s.rjust(5, "0") : ""
+        item[:org_gen_code] = (orgc = seq.OrgGenCode) ? orgc : ""
+        item[:deductible] = ""  # Will be set per package based on cost_share
+        item[:deductible20] = ""  # Will be set per package based on cost_share  
+        item[:atc_code] = (atcc = seq.AtcCode) ? atcc : ""
+        item[:comment_de] = ""  # Not available in FHIR
+        item[:comment_fr] = ""
+        item[:comment_it] = ""
+        item[:it_code] = (itc = seq.ItCode) ? itc : ""  # NOW available in FHIR!
+
+        # Build substances array
+        item[:substances] = []
+        if seq.Substances && seq.Substances.Substance
+          seq.Substances.Substance.each_with_index do |sub, i|
+            item[:substances] << {
+              index: i.to_s,
+              name: (name = sub.DescriptionLa) ? name : "",
+              quantity: (qtty = sub.Quantity) ? qtty : "",
+              unit: (unit = sub.QuantityUnit) ? unit : ""
+            }
+          end
+        end
+
+        item[:pharmacodes] = []
+        item[:packages] = {}
+
+        # Process packages
+        if seq.Packs && seq.Packs.Pack
+          seq.Packs.Pack.each do |pac|
+            next unless pac.GTIN
+
+            ean13 = pac.GTIN.to_s
+
+            # Ensure SwissmedicNo8 has leading zeros
+            if pac.SwissmedicNo8 && pac.SwissmedicNo8.length < 8
+              pac.SwissmedicNo8 = pac.SwissmedicNo8.rjust(8, "0")
+            end
+
+            Oddb2xml.setEan13forNo8(pac.SwissmedicNo8, ean13) if pac.SwissmedicNo8
+
+            # Build price structures
+            exf = {price: "", valid_date: "", price_code: ""}
+            if pac.Prices && pac.Prices.ExFactoryPrice
+              exf[:price] = pac.Prices.ExFactoryPrice.Price.to_s if pac.Prices.ExFactoryPrice.Price
+              exf[:valid_date] = pac.Prices.ExFactoryPrice.ValidFromDate if pac.Prices.ExFactoryPrice.ValidFromDate
+              exf[:price_code] = "PEXF"
+            end
+
+            pub = {price: "", valid_date: "", price_code: ""}
+            if pac.Prices && pac.Prices.PublicPrice
+              pub[:price] = pac.Prices.PublicPrice.Price.to_s if pac.Prices.PublicPrice.Price
+              pub[:valid_date] = pac.Prices.PublicPrice.ValidFromDate if pac.Prices.PublicPrice.ValidFromDate
+              pub[:price_code] = "PPUB"
+            end
+
+            # Build package entry matching BagXmlExtractor structure
+            item[:packages][ean13] = {
+              ean13: ean13,
+              name_de: (name = seq.NameDe) ? name : "",
+              name_fr: (name = seq.NameFr) ? name : "",
+              name_it: (name = seq.NameIt) ? name : "",
+              desc_de: (desc = pac.DescriptionDe) ? desc : "",
+              desc_fr: (desc = pac.DescriptionFr) ? desc : "",
+              desc_it: (desc = pac.DescriptionIt) ? desc : "",
+              sl_entry: true,
+              swissmedic_category: (cat = pac.SwissmedicCategory) ? cat : "",
+              swissmedic_number8: (num = pac.SwissmedicNo8) ? num : "",
+              prices: {exf_price: exf, pub_price: pub}
+            }
+
+            # Map limitations from FHIR
+            item[:packages][ean13][:limitations] = []
+            if pac.Limitations && pac.Limitations.Limitation
+              pac.Limitations.Limitation.each do |lim|
+                # Calculate is_deleted safely
+                is_deleted = false
+                if lim.ValidThruDate
+                  begin
+                    is_deleted = Date.parse(lim.ValidThruDate) < Date.today
+                  rescue
+                    is_deleted = false
+                  end
+                end
+                
+                item[:packages][ean13][:limitations] << {
+                  it: item[:it_code],
+                  key: :swissmedic_number8,
+                  id: pac.SwissmedicNo8 || "",
+                  code: lim.LimitationCode || "",
+                  type: lim.LimitationType || "",
+                  value: lim.LimitationValue || "",
+                  niv: lim.LimitationNiveau || "",
+                  desc_de: lim.DescriptionDe || "",
+                  desc_fr: lim.DescriptionFr || "",
+                  desc_it: lim.DescriptionIt || "",
+                  vdate: lim.ValidFromDate || "",
+                  del: is_deleted
+                }
+              end
+            end
+            item[:packages][ean13][:limitation_points] = ""
+            
+            # Map cost_share to deductible flags
+            if pac.CostShare
+              case pac.CostShare
+              when 10
+                item[:deductible] = "Y"
+              when 20
+                item[:deductible20] = "Y"
+              when 40
+                # New value - might need new field or special handling
+                item[:deductible] = "Y"  # Fallback to standard deductible
+              end
+            end
+
+            # Store in data hash with ean13 as key
+            data[ean13] = item
+          end
+        end
+      end
+
+      Oddb2xml.log "FhirExtractor: Extracted #{data.size} packages"
+      data
+    end
+  end
+end
+
+# Compatibility layer - makes FHIR parser compatible with existing XML parser usage
+class FhirPreparationsEntry
+  attr_reader :Preparations
+
+  def self.parse(ndjson_file)
+    parser = Oddb2xml::FHIR::PreparationsParser.new(ndjson_file)
+    entry = new
+    entry.Preparations = OpenStruct.new
+    entry.Preparations.Preparation = parser.preparations
+    entry
+  end
+
+  attr_writer :Preparations
+end
+
+# Extend PreparationsEntry to handle both XML and FHIR
+class PreparationsEntry
+  class << self
+    alias_method :original_parse, :parse
+
+    def parse(input, **kwargs)
+      # Check if input is a file path ending in .ndjson
+      if input.is_a?(String) && File.exist?(input) && input.end_with?(".ndjson")
+        # Parse as FHIR
+        FhirPreparationsEntry.parse(input)
+      else
+        # Parse as XML (original behavior)
+        original_parse(input, **kwargs)
+      end
+    end
+  end
+end

data/lib/oddb2xml/options.rb

@@ -22,6 +22,8 @@ module Oddb2xml
         opt :extended, "pharma, non-pharma plus prices and non-pharma from zurrose.
                             Products without EAN-Code will also be listed.
                             File oddb_calc.xml will also be generated"
+        opt :fhir, "Use FHIR NDJSON format from FOPH/BAG instead of XML from Spezialitätenliste", default: false
+        opt :fhir_url, "Specific FHIR NDJSON URL to download (implies --fhir)", type: :string, default: nil
         opt :format, "File format F, default is xml. {xml|dat}
                             If F is given, -o option is ignored.", type: :string, default: "xml"
         opt :include, "Include target option for ean14  for 'dat' format.
@@ -69,6 +71,10 @@ module Oddb2xml
         @opts[:extended] = true
         @opts[:price] = :zurrose
       end
+      # FHIR URL implies FHIR mode
+      if @opts[:fhir_url]
+        @opts[:fhir] = true
+      end
       @opts[:price] = :zurrose if @opts[:price].is_a?(TrueClass)
       @opts[:price] = @opts[:price].to_sym if @opts[:price]
       @opts[:ean14] = @opts[:include]

data/lib/oddb2xml/version.rb

@@ -1,3 +1,3 @@
 module Oddb2xml
-  VERSION = "3.0.0"
+  VERSION = "3.0.1"
 end

data/lib/oddb2xml.rb

@@ -1,5 +1,15 @@
+# frozen_string_literal: true
+
 require "oddb2xml/version"
+require "oddb2xml/util"
+require "oddb2xml/options"
+require "oddb2xml/downloader"
+require "oddb2xml/xml_definitions"
+require "oddb2xml/extractor"
+require "oddb2xml/builder"
+require "oddb2xml/fhir_support"
 require "oddb2xml/cli"
 
 module Oddb2xml
+  class Error < StandardError; end
 end

data/oddb2xml.gemspec

@@ -22,30 +22,30 @@ Gem::Specification.new do |spec|
   # Consulted the Gemfile.lock to get
   spec.add_dependency "rubyzip", '~> 3.0.1'
   spec.add_dependency "minitar" # , '~> 0.5.2'
-  spec.add_dependency "mechanize" # , '~> 2.5.1'
-  spec.add_dependency "nokogiri", ">= 1.8.2"
+  spec.add_dependency "mechanize", ">= 2.8.5"
+  spec.add_dependency "nokogiri", ">= 1.19.1"
   spec.add_dependency "savon" , '~> 2.12.0'
   spec.add_dependency "spreadsheet" # , '~> 1.0.0'
   spec.add_dependency "rubyXL", "~> 3.4.0"
   spec.add_dependency "sax-machine" # ,  '~> 0.1.0'
   spec.add_dependency "parslet" # , '~> 1.7.0'
-  spec.add_dependency "rubyntlm", "0.5.1"
+  spec.add_dependency "rubyntlm", ">= 0.6.3"
   spec.add_dependency "multi_json" # , '>= 0.3.2'
   spec.add_dependency "httpi" # , '>= 2.4.1'
   spec.add_dependency "optimist"
   spec.add_dependency "xml-simple"
   spec.add_dependency "ox"
   spec.add_dependency "htmlentities"
-  spec.add_dependency "webrick"
-  spec.add_dependency "rexml"
+  spec.add_dependency "webrick", ">= 1.8.2"
+  spec.add_dependency "rexml", ">= 3.3.9"
   spec.add_dependency "standardrb"
-  spec.add_dependency "rack", "3.0.11"
+  spec.add_dependency "rack", ">= 3.1.20"
 
   spec.add_development_dependency "bundler"
   spec.add_development_dependency "rake"
   spec.add_development_dependency "rspec"
   spec.add_development_dependency "webmock"
-  spec.add_development_dependency "rdoc", "~> 6.3.3" # rdoc 6.4 depends on psych 4.0 which breaks savon!
+  spec.add_development_dependency "rdoc", ">= 6.3.4.1"
   spec.add_development_dependency "vcr"
   spec.add_development_dependency "timecop"
   spec.add_development_dependency "flexmock"

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: oddb2xml
 version: !ruby/object:Gem::Version
-  version: 3.0.0
+  version: 3.0.1
 platform: ruby
 authors:
 - Yasuhiro Asaka, Zeno R.R. Davatz, Niklaus Giger
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2025-08-21 00:00:00.000000000 Z
+date: 2026-02-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rubyzip
@@ -44,28 +44,28 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 2.8.5
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 2.8.5
 - !ruby/object:Gem::Dependency
   name: nokogiri
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 1.8.2
+        version: 1.19.1
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 1.8.2
+        version: 1.19.1
 - !ruby/object:Gem::Dependency
   name: savon
   requirement: !ruby/object:Gem::Requirement
@@ -140,16 +140,16 @@ dependencies:
   name: rubyntlm
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '='
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 0.5.1
+        version: 0.6.3
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '='
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 0.5.1
+        version: 0.6.3
 - !ruby/object:Gem::Dependency
   name: multi_json
   requirement: !ruby/object:Gem::Requirement
@@ -240,28 +240,28 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 1.8.2
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 1.8.2
 - !ruby/object:Gem::Dependency
   name: rexml
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 3.3.9
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 3.3.9
 - !ruby/object:Gem::Dependency
   name: standardrb
   requirement: !ruby/object:Gem::Requirement
@@ -280,16 +280,16 @@ dependencies:
   name: rack
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '='
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 3.0.11
+        version: 3.1.20
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '='
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 3.0.11
+        version: 3.1.20
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
@@ -350,16 +350,16 @@ dependencies:
   name: rdoc
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 6.3.3
+        version: 6.3.4.1
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 6.3.3
+        version: 6.3.4.1
 - !ruby/object:Gem::Dependency
   name: vcr
   requirement: !ruby/object:Gem::Requirement
@@ -433,6 +433,7 @@ files:
 - ".rspec"
 - ".ruby-version"
 - ".standard.yml"
+- CLAUDE.md
 - Elexis_Artikelstamm_v003.xsd
 - Elexis_Artikelstamm_v5.xsd
 - Gemfile
@@ -466,6 +467,7 @@ files:
 - lib/oddb2xml/compressor.rb
 - lib/oddb2xml/downloader.rb
 - lib/oddb2xml/extractor.rb
+- lib/oddb2xml/fhir_support.rb
 - lib/oddb2xml/options.rb
 - lib/oddb2xml/parslet_compositions.rb
 - lib/oddb2xml/semantic_check.rb