oddb2xml 3.0.0 → 3.0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ab4100aa6c522cd66ca2a69af3959c576e82cfdaeb41cffd399cb6d451ba7ff2
-  data.tar.gz: 495bcb8a97881ba89f5a1bb9fd8acb264a56cdd8f262e1b7669579bffc9c77be
+  metadata.gz: 55725f8e11fa91216b5f7189f9339a6bacf6fd69af78c633421abc8c573a2326
+  data.tar.gz: acd34c442ef756f43aeac9e2551df614fff4bad81894a87add521e4c7efab8cd
 SHA512:
-  metadata.gz: f9b839faf528860fdf2ab6e319b1db88812d1aa2c7e628df45ea6de1a932c78b51b93e84b6a30355ed8a40ca4f9782d73edce2ef3742934d8b1cff99c6d19ad8
-  data.tar.gz: a2878be3ff52ef0ee26d366f56bed4d1e443083730aa2253cbba6a1fecfcb40e01140910108649d7065dcbec3a2326208e2a8aca1918b60151df7aaea2983767
+  metadata.gz: 273f80bb691ae1d0e86db41d9215456c48822f4a764163c3675d87ca6f975f11cd8d2dce89f4bf71abd9b8e320b61babd45c73d0683faafbeb25adf56f2d12b6
+  data.tar.gz: c0014b66c15ebddcff17cf1435d24faab68ab856faa5d198208f94d9d6925540d4939ce4ff82f4f4d38c1fc319156dbaecf49415f56e8fce1d676d3e06b179fc

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

@@ -1,53 +1,53 @@
 PATH
   remote: .
   specs:
-    oddb2xml (3.0.0)
+    oddb2xml (3.0.2)
       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/History.txt

@@ -1,3 +1,8 @@
+=== 3.0.2 / 09.03.2026
+* Use raw.githubusercontent.com URL for ATC CSV to avoid 429 Too Many Requests errors
+* Add retry logic with exponential backoff for HTTP 429 errors in uri_open
+* Remove obsolete Ruby version check in uri_open (Ruby >= 2.5 already required)
+
 === 2.7.9 / 19.09.22
 * Remove newly generated DSCRI when not running --artikelstamm and 
   generate always (as before 2.7.8) a DSCRF fiele

data/README.md

@@ -284,6 +284,7 @@ We use the following files:
 * http://download.swissmedicinfo.ch/ (AipsDownload)
 * https://raw.githubusercontent.com/zdavatz/oddb2xml_files/master/LPPV.txt
 * https://raw.githubusercontent.com/epha/robot/master/data/manual/swissmedic/atc.csv
+* https://raw.githubusercontent.com/zdavatz/cpp2sqlite/master/input/atc_codes_multi_lingual.txt
 
 ## Rules for matching GTIN (aka EAN13), product number and IKSNR
 

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