swissmedic-diff 0.1.9 → 0.2.0

data/.gitignore

@@ -1,2 +1,9 @@
 tags
 *.swp
+pkg
+.*#
+.bundle
+.ruby-version
+*.patch
+InstalledFiles
+SetupConfig

data/.travis.yml

@@ -11,7 +11,6 @@ rvm:
   - 2.1.2
   - 2.0.0
   - 1.9.3
-  - 1.8.7
 matrix:
   allow_failures:
     - rvm: ruby-head

data/Gemfile

@@ -11,6 +11,6 @@ group :debugger do
     gem 'pry-debugger'
   else
     gem 'pry-byebug'
+    gem 'pry-doc'
   end
 end unless RUBY_VERSION =~ /^1\.8/
-

data/Gemfile.lock

@@ -1,9 +1,9 @@
 PATH
   remote: .
   specs:
-    swissmedic-diff (0.1.9)
+    swissmedic-diff (0.2.0)
       nokogiri
-      rubyXL
+      rubyXL (= 3.3.1)
       rubyzip
       spreadsheet
 
@@ -25,7 +25,7 @@ GEM
     method_source (0.8.2)
     mini_portile (0.6.2)
     minitest (5.7.0)
-    minitest-reporters (1.0.16)
+    minitest-reporters (1.0.17)
       ansi
       builder
       minitest (>= 5.0)
@@ -42,7 +42,7 @@ GEM
     rake (10.4.2)
     ruby-ole (1.2.11.8)
     ruby-progressbar (1.7.5)
-    rubyXL (3.3.8)
+    rubyXL (3.3.1)
       nokogiri (>= 1.4.4)
       rubyzip (>= 1.1.6)
     rubyzip (1.1.7)
@@ -60,3 +60,6 @@ DEPENDENCIES
   pry-debugger
   rake
   swissmedic-diff!
+
+BUNDLED WITH
+   1.10.5

data/History.txt

@@ -1,3 +1,10 @@
+=== 0.2.0 / 03.07.2015
+
+* Abort if Swissmedic introduces incompatible header lines
+* Support new format of SwissMedic July 2015
+* Reworked compating xlsx-files
+* Remove support for old .xls-format (used before 2013)
+
 === 0.1.9 / 08.06.2015
 
 * Swissmedic has different header lines

data/Manifest.txt

@@ -13,12 +13,8 @@ lib/swissmedic-diff.rb
 lib/version.rb
 setup.rb
 swissmedic-diff.gemspec
-test/data/Packungen-2013.10.14.xls
-test/data/Packungen.older.xls
-test/data/Packungen.xls
-test/data/Packungen_2013_small.xls
-test/data/Packungen_2014_small.xlsx
-test/data/Packungen_error_column.xls
-test/data/Packungen_error_missing1.xls
-test/data/Packungen_error_missing2.xls
+test/data/Packungen-2014.01.01.xlsx
+test/data/Packungen-2014.02.01.xlsx
+test/data/Packungen-2015.06.04.xlsx
+test/data/Packungen-2015.07.02.xlsx
 test/test_swissmedic-diff.rb

data/README.txt

@@ -29,7 +29,7 @@ Then you can get the version 0.1.2.
 
 == REQUIREMENTS:
 
-* ruby 1.8 (with oniguruma patch) or ruby 1.9
+* ruby 1.9, ruby 2.x
 * spreadsheet
 
 == INSTALL:
@@ -62,6 +62,7 @@ Usage: /usr/bin/swissmedic-diff [-gnr] <file1> <file2> [<output>]
   * Hannes Wyss <hwyss@ywesee.com>
   * Masaomi Hatakeyama <mhatakeyama@ywesee.com>
   * Zeno R.R. Davatz <zdavatz@ywesee.com>
+  * Niklaus Giger <ngiger@ywesee.com>
 
 == LICENSE:
 

data/lib/swissmedic-diff.rb

@@ -23,11 +23,59 @@ require File.join(File.dirname(__FILE__), 'compatibility.rb')
 #Source::    http://scm.ywesee.com/?p=swissmedic-diff/.git;a=summary
 class SwissmedicDiff
   module Diff
-    COLUMNS = [ :iksnr, :seqnr, :name_base, :company,
+    COLUMNS_2014 = {
+        :iksnr => /Zulassungs-Nummer/i,                # column-nr: 0
+        :seqnr => /Dosistärke-nummer|^Sequenz$/i,
+        :name_base => /Präparatebezeichnung|^Sequenzname$/i,
+        :company => /Zulassungsinhaberin/i,
+        :index_therapeuticus => /IT-Nummer/i,
+        :atc_class => /ATC-Code/i,                     # column-nr: 5
+        :production_science => /Heilmittelcode/i,
+        :registration_date => /Erstzul.datum Präp./i,
+        :sequence_date => /Zul.datum Dosisstärke *|Zul.datum Sequenz/i,
+        :expiry_date => /Gültigkeits-datum */i,
+        :ikscd => /Verpackungs ID/i,                   # column-nr: 10
+        :size => /Packungsgrösse/i,
+        :unit => /Einheit/i,
+        :ikscat => /Abgabekategorie/i,
+        :substances => /Wirkstoff/i,
+        :composition => /Zusammensetzung/i,             # column-nr: 15
+        :indication_registration => /Anwendungsgebiet Präparate/i,
+        :indication_sequence => /Anwendungsgebiet Dosisstärke|Anwendungsgebiet Sequenz/i,
+    }
+
+    COLUMNS_OLD = [ :iksnr, :seqnr, :name_base, :company,
                 :index_therapeuticus, :atc_class, :production_science,
                 :registration_date, :sequence_date, :expiry_date, :ikscd,
                 :size, :unit, :ikscat, :substances, :composition,
                 :indication_registration, :indication_sequence ]
+
+    COLUMNS_JULY_2015 = {
+        :iksnr => /Zulassungs-Nummer/i,                  # column-nr: 0
+        :seqnr => /Dosisstärke-nummer/i,
+        :name_base => /Präparatebezeichnung/i,
+        :company => /Zulassungsinhaberin/i,
+        :production_science => /Heilmittelcode/i,
+        :index_therapeuticus => /IT-Nummer/i,            # column-nr: 5
+        :atc_class => /ATC-Code/i,
+        :registration_date => /Erstzulassungs-datum./i,
+        :sequence_date => /Zul.datum Dosisstärke/i,
+        :expiry_date => /Gültigkeitsdauer der Zulassung/i,
+        :ikscd => /Packungscode/i,                 # column-nr: 10
+        :size => /Packungsgrösse/i,
+        :unit => /Einheit/i,
+        :ikscat => /Abgabekategorie Packung/i,
+        :ikscat_seq => /Abgabekategorie Dosisstärke/i,
+        :ikscat_preparation => /Abgabekategorie Präparat/i, # column-nr: 15
+        :substances => /Wirkstoff/i,
+        :composition => /Zusammensetzung/i,
+        :indication_registration => /Anwendungsgebiet Präparat/i,
+        :indication_sequence => /Anwendungsgebiet Dosisstärke/i,
+        :gen_production => /Gentechnisch hergestellte Wirkstoffe/i, # column-nr 20
+        :insulin_category => /Kategorie bei Insulinen/i,
+        :drug_index       => /Verz. bei betäubunsmittel-haltigen Präparaten/i,
+    }
+
     FLAGS = {
       :new                      =>  'Neues Produkt',
       :name_base                =>  'Namensänderung',
@@ -58,9 +106,6 @@ class SwissmedicDiff
         cell.to_s
       end
     end
-    def column(key)
-      COLUMNS.index(key)
-    end
     def describe(diff, iksnr)
       sprintf("%s: %s", iksnr, name(diff, iksnr))
     end
@@ -77,10 +122,10 @@ class SwissmedicDiff
         sprintf "%s (%s)", txt, pairs.join(',')
       when :registration_date, :expiry_date
         row = diff.newest_rows[iksnr].sort.first.last
-        sprintf "%s (%s)", txt, row[column(flag)].strftime('%d.%m.%Y')
+        sprintf "%s (%s)", txt, row[COLUMNS_2014.keys.index(flag)].value.strftime('%d.%m.%Y')
       else
         row = diff.newest_rows[iksnr].sort.first.last
-        sprintf "%s (%s)", txt, cell(row, column(flag))
+        sprintf "%s (%s)", txt, cell(row, COLUMNS_2014.keys.index(flag))
       end
     end
 
@@ -101,26 +146,27 @@ class SwissmedicDiff
       @diff.newest_rows = newest_rows
       Spreadsheet.client_encoding = 'UTF-8'
       tbook = Spreadsheet.open(target)
-      sheet = tbook.worksheet(0)
       idx, prr, prp = nil
       multiples = {}
+      latest_keys = get_column_indices(Spreadsheet.open(latest)).keys
+      target_keys = get_column_indices(tbook).keys
       each_valid_row(tbook) { |row|
-        iksnr = cell(row, column(:iksnr))
-        seqnr = cell(row, column(:seqnr))
-        pacnr = cell(row, column(:ikscd))
+        iksnr = cell(row, target_keys.index(:iksnr))
+        seqnr = cell(row, target_keys.index(:seqnr))
+        pacnr = cell(row, target_keys.index(:ikscd))
         (multiples[iksnr] ||= {})
         if prr == iksnr && prp == pacnr
           idx += 1
         elsif previous = multiples[iksnr][pacnr]
           prr = iksnr
           prp = pacnr
-          idx = previous[COLUMNS.size].to_i + 1
+          idx = previous[target_keys.size].to_i + 1
         else
           prr = iksnr
           prp = pacnr
           idx = 0
         end
-        row[COLUMNS.size] = idx
+        row[target_keys.size] = idx
         (newest_rows[iksnr] ||= {})[pacnr] = row
         multiples[iksnr][pacnr] = row
         if(other = known_regs.delete([iksnr]))
@@ -130,12 +176,12 @@ class SwissmedicDiff
         end
         known_seqs.delete([iksnr, seqnr])
         if(other = known_pacs.delete([iksnr, pacnr, idx]))
-          flags = rows_diff(row, other, ignore)
+          flags = rows_diff(row, target_keys, other, latest_keys, ignore)
           (changes[iksnr].concat flags).uniq!
           updates.push row unless flags.empty?
         else
-          replacements.store [ iksnr, seqnr, cell(row, column(:size)),
-                                cell(row, column(:unit)) ], row
+          replacements.store [ iksnr, seqnr, cell(row, target_keys.index(:size)),
+                                cell(row, target_keys.index(:unit)) ], row
           flags = changes[iksnr]
           flags.push(:sequence).uniq! unless(flags.include? :new)
           news.push row
@@ -143,8 +189,8 @@ class SwissmedicDiff
       }
       @diff.replacements = reps = {}
       known_pacs.each { |(iksnr, pacnr), row|
-        key = [iksnr, '%02i' % cell(row, column(:seqnr)).to_i,
-                      cell(row, column(:size)), cell(row, column(:unit))]
+        key = [iksnr, '%02i' % cell(row, target_keys.index(:seqnr)).to_i,
+                      cell(row, target_keys.index(:size)), cell(row, target_keys.index(:unit))]
         if(rep = replacements[key])
           changes[iksnr].push :replaced_package
           reps.store rep, pacnr
@@ -156,7 +202,7 @@ class SwissmedicDiff
         ## the keys in known_pacs don't include the sequence number (which
         #  would prevent us from properly recognizing multi-sequence-Packages),
         #  so we need complete the path to the package now
-        key[1,0] = '%02i' % cell(row, column(:seqnr)).to_i
+        key[1,0] = '%02i' % cell(row, target_keys.index(:seqnr)).to_i
         key
       }
       @diff.sequence_deletions = known_seqs.keys
@@ -181,24 +227,25 @@ class SwissmedicDiff
       lbook = Spreadsheet.open(latest)
       idx, prr, prp = nil
       multiples = {}
+      latest_keys = get_column_indices(lbook).keys
       each_valid_row(lbook) { |row|
-        iksnr = cell(row, column(:iksnr))
-        seqnr = cell(row, column(:seqnr))
-        pacnr = cell(row, column(:ikscd))
+        iksnr = cell(row, latest_keys.index(:iksnr))
+        seqnr = cell(row, latest_keys.index(:seqnr))
+        pacnr = cell(row, latest_keys.index(:ikscd))
         multiples[iksnr] ||= {}
         if prr == iksnr && prp == pacnr
           idx += 1
         elsif previous = multiples[iksnr][pacnr]
           prr = iksnr
           prp = pacnr
-          idx = previous[COLUMNS.size].to_i + 1
+          idx = previous[latest_keys.size].to_i + 1
         else
           prr = iksnr
           prp = pacnr
           idx = 0
         end
         multiples[iksnr][pacnr] = row
-        row[COLUMNS.size] = idx
+        row[latest_keys.size] = idx
         known_regs.store [iksnr], row
         known_seqs.store [iksnr, seqnr], row
         known_pacs.store [iksnr, pacnr, idx], row
@@ -208,16 +255,19 @@ class SwissmedicDiff
     def name(diff, iksnr)
       rows = diff.newest_rows[iksnr]
       row = rows.sort.first.last
-      cell(row, column(:name_base))
+      cell(row, COLUMNS_2014.keys.index(:name_base))
     end
-    def rows_diff(row, other, ignore = [])
+    def rows_diff(row, row_keys, other, other_keys, ignore = [])
       flags = []
-      COLUMNS.each_with_index { |key, idx|
-        if(!ignore.include?(key) \
-           && _comparable(key, row, idx) != _comparable(key, other, idx))
-          # binding.pry if key == :expiry_date
-
-          flags.push key
+      COLUMNS_OLD.each_with_index {
+        |key, idx|
+        if !ignore.include?(key)
+          left  = _comparable(key, row,   row_keys.index(key))
+          right = _comparable(key, other, other_keys.index(key))
+          if left != right
+            puts "Pushing key #{key}: '#{left.inspect}' != '#{right.inspect}'" if $VERBOSE
+            flags.push key
+          end
         end
       }
       flags
@@ -277,6 +327,42 @@ class SwissmedicDiff
       end
     end
 
+    def get_column_indices(spreadsheet)
+      error_2014 = nil
+      filename = spreadsheet.root.filepath
+      headerRowId = rows_to_skip(spreadsheet)-1
+      row = spreadsheet.worksheet(0)[headerRowId]
+
+      COLUMNS_2014.each{
+        |key, value|
+        header_name = row[COLUMNS_2014.keys.index(key)].value
+        unless value.match(header_name)
+          puts "#{__LINE__}: #{key} ->  #{COLUMNS_2014.keys.index(key)} #{value}\nbut was  #{header_name}" if $VERBOSE
+          error_2014 = "#{filename}_has_unexpected_column_#{COLUMNS_2014.keys.index(key)}_#{key}_#{value.to_s}_but_was_#{header_name}"
+          break
+        end
+      }
+      return COLUMNS_2014 unless error_2014
+      error_2015 = nil
+      COLUMNS_JULY_2015.each{
+        |key, value|
+        header_name = row[COLUMNS_JULY_2015.keys.index(key)].value
+        unless value.match(header_name)
+          puts "#{__LINE__}: #{key} ->  #{COLUMNS_JULY_2015.keys.index(key)} #{value}\nbut was  #{header_name}" if $VERBOSE
+          error_2015 = "#{filename}_has_unexpected_column_#{COLUMNS_JULY_2015.keys.index(key)}_#{key}_#{value.to_s}_but_was_#{header_name}"
+          break
+        end
+      }
+      unless error_2015
+        idx14 = COLUMNS_2014.keys.index(:name_base)
+        idx15 = COLUMNS_2014.keys.index(:name_base)
+        if (idx14 != idx15)
+          raise ":name_base must be same index in COLUMNS_JULY_2015 and COLUMNS_2014. Is #{idx14} and #{idx15}"
+        end
+        return COLUMNS_JULY_2015
+      end
+      raise "#{error_2015}\n#{error_2014}"
+    end
     #=== iterate over all valid rows of a swissmedic Packungen.xls
     #
     # Iterates over all rows, ignoring Tierarzneimittel and
@@ -292,20 +378,22 @@ class SwissmedicDiff
     #return  ::
     def each_valid_row(spreadsheet)
       skipRows = rows_to_skip(spreadsheet)
+      column_keys = get_column_indices(spreadsheet).keys
       worksheet = spreadsheet.worksheet(0)
       row_nr = 0
       worksheet.each() {
         |row|
         row_nr += 1
         next if row_nr <= skipRows
-        if row.size < COLUMNS.size/2
+        break unless row
+        if row.size < column_keys.size/2
           $stdout.puts "Data missing in \n(line " + (row_nr).to_s + "): " + row.join(", ").to_s + "\n"
           next
         end
-        next if (cell(row, column(:production_science)) == 'Tierarzneimittel')
-        row[column(:iksnr)] = "%05i" % cell(row, column(:iksnr)).to_i
-        row[column(:seqnr)] = "%02i" % cell(row, column(:seqnr)).to_i
-        row[column(:ikscd)] = "%03i" % cell(row, column(:ikscd)).to_i
+        next if (cell(row, column_keys.index(:production_science)) == 'Tierarzneimittel')
+        row[column_keys.index(:iksnr)] = "%05i" % cell(row, column_keys.index(:iksnr)).to_i
+        row[column_keys.index(:seqnr)] = "%02i" % cell(row, column_keys.index(:seqnr)).to_i
+        row[column_keys.index(:ikscd)] = "%03i" % cell(row, column_keys.index(:ikscd)).to_i
         yield row
       }
     end

data/lib/version.rb

@@ -1,3 +1,3 @@
 class SwissmedicDiff
-  VERSION = '0.1.9'
+  VERSION = '0.2.0'
 end

data/swissmedic-diff.gemspec

@@ -15,7 +15,7 @@ spec = Gem::Specification.new do |s|
                    Dir.glob('test/data/*.xls')
    s.test_file   = "test/test_swissmedic-diff.rb"
    s.executables << 'swissmedic-diff'
-   s.add_dependency('rubyXL')
+   s.add_dependency('rubyXL', '3.3.1')
    s.add_dependency('nokogiri')
    s.add_dependency('rubyzip')
    s.add_dependency('spreadsheet')

data/test/test_swissmedic-diff.rb

@@ -6,58 +6,40 @@ $: << File.expand_path("../lib", File.dirname(__FILE__))
 
 require 'minitest/autorun'
 require 'swissmedic-diff'
-require 'pp'  
+require 'pp'
 
 module ODDB
   class SwissmedicPluginTest < Minitest::Test
     def setup
       @diff = SwissmedicDiff.new
-      @data = File.expand_path 'data/Packungen.xls',
-                                File.dirname(__FILE__)
-      @older = File.expand_path 'data/Packungen.older.xls',
-                                File.dirname(__FILE__)
-      @data_error_column = File.expand_path 'data/Packungen_error_column.xls',
-                                File.dirname(__FILE__)
-      @data_error_missing_case1 = File.expand_path 'data/Packungen_error_missing1.xls',
-                                File.dirname(__FILE__)
-      @data_error_missing_case2 = File.expand_path 'data/Packungen_error_missing2.xls',
-                                File.dirname(__FILE__)
-      @data_2013 = File.expand_path 'data/Packungen-2013.10.14.xls',
-                                File.dirname(__FILE__)
-      @workbook = Spreadsheet.open(@data)
+      @january_2014 = File.expand_path 'data/Packungen-2014.01.01.xlsx',  File.dirname(__FILE__)
+      @february_2014 = File.expand_path 'data/Packungen-2014.02.01.xlsx',  File.dirname(__FILE__)
     end
-    
-    def test_diff_xls_and_xlsx
+
+    def test_diff_new_format_july_2015
       @diff = SwissmedicDiff.new
-      last_month = File.expand_path 'data/Packungen_2013_small.xls',  File.dirname(__FILE__)
-      this_month = File.expand_path 'data/Packungen_2014_small.xlsx',  File.dirname(__FILE__)
-      result = @diff.diff last_month, this_month, [:atc_class, :sequence_date]
+      last_month = File.expand_path 'data/Packungen-2015.06.04.xlsx',  File.dirname(__FILE__)
+      this_month = File.expand_path 'data/Packungen-2015.07.02.xlsx',  File.dirname(__FILE__)
+      result = @diff.diff this_month, last_month, [:atc_class, :sequence_date]
       assert(result.changes.flatten.index('Zulassungs-Nummer') == nil, "Should not find Zulassungs-Nummer in changes")
-      # puts "Got #{result.news.size} news, #{result.changes.size} changes, #{result.updates.size} updates."
-      assert_equal(8, result.news.size)
-      assert_equal(4, result.changes.size)
-      assert_equal(2, result.updates.size)
-      assert(result.news.first.index('00280'), "Should find 00280 in news")
-      assert(result.news.flatten.index('65034'), "Should find 65034 in news")
-      assert(result.news.flatten.index('00277') == nil, "Should not find 00277 in news")
-      assert(result.news.flatten.index('Zulassungs-Nummer') == nil, "Should not find Zulassungs-Nummer in changes")
+      assert_equal(1, result.news.size)
+      assert_equal(2, result.changes.size)
+      assert_equal(1, result.updates.size)
+      assert_equal(['65838'], result.news.collect{|x| x[0] if x[0] == '65838'})
+      assert_equal({"65837"=>[:indication_sequence], "65838"=>[:new]}, result.changes)
     end
 
-    def test_date_xls
-      tbook = Spreadsheet.open(File.expand_path('data/Packungen.xls',  File.dirname(__FILE__)))
-      sheet = tbook.worksheet(0)
-      assert_equal(nil, sheet.row(0)[8]) # sequence_date
-      assert_equal(2010, sheet.row(4).date(8).year)
-      assert_equal(26, sheet.row(4).date(8).day)
-      # assert_equal(26, Spreadsheet.date_cell(sheet.row(4), 8))
-      assert_equal(26, Spreadsheet.date_cell(sheet.row(4), 8).day)
-      assert_equal(2010, Spreadsheet.date_cell(sheet.row(4), 8).year)
+    def test_diff_wrong_header
+      @diff = SwissmedicDiff.new
+      last_month = File.expand_path 'data/Packungen-2015.06.04.xlsx',  File.dirname(__FILE__)
+      this_month = File.expand_path 'data/Packungen-wrong-header.xlsx',  File.dirname(__FILE__)
+      assert_raises(RuntimeError) { @diff.diff this_month, last_month, [:atc_class, :sequence_date]}
     end
-    
+
+
     def test_date_xlsx
-      tbook = Spreadsheet.open(File.expand_path('data/Packungen_2014_small.xlsx',  File.dirname(__FILE__)))
+      tbook = Spreadsheet.open(@january_2014)
       sheet = tbook.worksheet(0)
-      # sheet = RubyXL::Parser.parse(File.expand_path(File.expand_path 'data/Packungen_2014_small.xlsx',  File.dirname(__FILE__)))[0]
       assert_equal(nil, sheet.row(0)[8]) # sequence_date
       assert_equal(2010, sheet.row(4).date(8).year)
       assert_equal(26, sheet.row(4).date(8).day)
@@ -65,188 +47,87 @@ module ODDB
       assert_equal(2010, Spreadsheet.date_cell(sheet.row(4), 8).year)
     end
 
-    def test_diff_xlsx_and_xls
-      @diff = SwissmedicDiff.new
-      last_month = File.expand_path 'data/Packungen_2014_01.xlsx',  File.dirname(__FILE__)
-      this_month = File.expand_path 'data/Packungen.xls',  File.dirname(__FILE__)
-      result = @diff.diff last_month, this_month, [:atc_class, :sequence_date]
-      assert_equal(7, result.news.size)
-      assert_equal(2, result.updates.size)
-      assert_equal(10, result.changes.size)
-      assert(result.changes.flatten.index('00275'), "Should find 00275 in changes")
-      assert(result.changes.flatten.index('00277'), "Should find 00277 in changes")
-      assert(result.news.flatten.index('Zulassungs-Nummer') == nil, "Should not find Zulassungs-Nummer in changes")
-    end
     def test_diff_xlsx_and_xlsx
-      @diff = SwissmedicDiff.new
-      last_month = File.expand_path 'data/Packungen_2014_01.xlsx',  File.dirname(__FILE__)
-      this_month = File.expand_path 'data/Packungen_2014_small.xlsx',  File.dirname(__FILE__)
-      result = @diff.diff last_month, this_month, [:atc_class, :sequence_date]
-      assert_equal({"00277"=>[:expiry_date, :indication_sequence]}, result.changes)
-      assert_equal(1, result.updates.size)
-      assert_equal([], result.news)
-    end
-
-    def test_iterate
-      diff = SwissmedicDiff.new
-      strings = []
-      diff.each_valid_row(Spreadsheet.open(@data_2013)) { |x| strings << "iksnr #{x[0]} packungs id #{x[diff.column(:ikscd)]}" }
-      expected = [
-        "iksnr 00277 packungs id 001",
-        "iksnr 00277 packungs id 002",
-        "iksnr 61338 packungs id 001",
-        "iksnr 61338 packungs id 002",
-        "iksnr 61367 packungs id 001",
-        "iksnr 61367 packungs id 002",
-        "iksnr 61367 packungs id 003",
-        "iksnr 61367 packungs id 004",
-        "iksnr 61367 packungs id 005",
-        "iksnr 61416 packungs id 001",
-        "iksnr 63164 packungs id 001",
-        "iksnr 63164 packungs id 002",
-        "iksnr 63164 packungs id 003",
-        "iksnr 65040 packungs id 001"
-      ]
-      assert_equal(expected, strings)
-    end
-
-    def test_diff_pre_2013_to_2013
-      result = @diff.diff(@data_2013, @data)
-      assert(result.changes.flatten.index('Zulassungs-Nummer') == nil, "Should not find Zulassungs-Nummer in changes")
-      assert(result.news.flatten.index('Zulassungs-Nummer') == nil, "Should not find Zulassungs-Nummer in changes")
-      assert(result.news.flatten.index('00277') == nil, "Should not find 00277 in news")
-      assert_equal 6, result.news.size
+      result = @diff.diff @february_2014, @january_2014, [:atc_class, :sequence_date]
+      assert_equal 4, result.news.size
       expected = {
-"00277"=>[:company, :sequence_date, :substances, :composition, :name_base],
- "61338"=>[:sequence_date, :company, :atc_class],
- "61367"=>
-  [:sequence_date,
-   :ikscat,
-   :substances,
-   :composition,
-   :sequence,
-   :replaced_package],
- "61416"=>[:sequence_date],
- "63164"=>[:new],
- "65040"=>[:new],
- "00275"=>[:delete],
- "61345"=>[:delete]
-      }
-      assert_equal(expected, result.changes)
-      diff_string =%(+ 63164: Rivastigmin Patch Sandoz 5, Transdermales Pflaster
-+ 65040: Panthoben, Salbe
-- 00275: Cardio-Pulmo-Rénal Sérocytol, suppositoire
-- 61345: Terbinafin-Teva 125 mg, Tabletten
-> 00277: Coeur-Vaisseaux Sérocytol, suppositoire; Zulassungsinhaber (Sérolab, société anonyme), Zulassungsdatum Sequenz (2010-04-26), Wirkstoffe (globulina equina (immunisé avec coeur, endothélium vasculaire porcins)), Zusammensetzung (globulina equina (immunisé avec coeur, endothélium vasculaire porcins) 8 mg, propylenglycolum, conserv.: E 216, E 218, excipiens pro suppositorio.), Namensänderung (Coeur-Vaisseaux Sérocytol, suppositoire)
-> 61338: Cefuroxim Fresenius i.v. 750 mg, Pulver zur Herstellung einer i.v. Lösung; Zulassungsdatum Sequenz (2010-03-16), Zulassungsinhaber (Fresenius Kabi (Schweiz) AG), ATC-Code (J01DC02)
-> 61367: Hypericum-Mepha 250, Lactab; Zulassungsdatum Sequenz (2010-04-23), Abgabekategorie (D), Wirkstoffe (hyperici herbae extractum ethanolicum siccum quantificatum), Zusammensetzung (hyperici herbae extractum ethanolicum siccum quantificatum 250 mg corresp. hypericinum 0.25-0.75 mg, DER: 4-7:1, excipiens pro compresso obducto.), Packungs-Nummer (006 -> 005)
-> 61416: Otriduo Schnupfen, Nasentropfen; Zulassungsdatum Sequenz (2010-05-12))
-      assert_equal(diff_string, @diff.to_s)      
-    end
-    def test_diff
-      result = @diff.diff(@data, @older)
-      assert_equal 3, result.news.size
-      assert_equal 'Cardio-Pulmo-Rénal Sérocytol, suppositoire',
-                   result.news.first.at(2)
-      assert_equal 2, result.updates.size
-      assert_equal 'Coeur-Vaisseaux Sérocytol, suppositoire(update)',
-                   result.updates.first.at(2)
-      assert_equal 6, result.changes.size
-      expected = {
-        "00275"=>[:new],
-        "00277"=>[:name_base],
-        "61338"=>[:company, :atc_class],
-        "61367"=>[:sequence, :replaced_package],
-        "61416"=>[:new],
-        "00274"=>[:delete]
+          "00277"=>[:name_base, :expiry_date, :indication_sequence],
+          "65040"=>[:sequence, :replaced_package],
+          "60125"=>[:new],
+          "61367"=>[:new],
+          "00274"=>[:delete]
       }
       assert_equal(expected, result.changes)
+      assert_equal 1, result.updates.size
+      assert_equal 5, result.changes.size
       assert_equal 3, result.package_deletions.size
       assert_equal 4, result.package_deletions.first.size
       iksnrs = result.package_deletions.collect { |row| row.at(0) }.sort
       ikscds = result.package_deletions.collect { |row| row.at(2) }.sort
-      assert_equal ["00274", "61367", "61367"], iksnrs
-      assert_equal ["001", "002", "005"], ikscds
+      assert_equal ["00274", "00274", "65040"], iksnrs
+      assert_equal ["001", "001", "002"], ikscds
       assert_equal 1, result.sequence_deletions.size
       assert_equal ["00274", "01"], result.sequence_deletions.at(0)
       assert_equal 1, result.registration_deletions.size
       assert_equal ["00274"], result.registration_deletions.at(0)
       assert_equal 1, result.replacements.size
-      assert_equal '005', result.replacements.values.first
+      assert_equal '001', result.replacements.values.first
+
+      assert_equal 'Panthoben, Salbe', result.news.first[2].value
+      assert_equal 'Coeur-Vaisseaux Sérocytol, Namensänderung', result.updates.first[2].value
     end
+
     def test_diff_error_column
-      res = @diff.diff(@data_error_column, @older)
+      res = @diff.diff(@february_2014, @january_2014)
       assert_equal(OpenStruct, res.class)
     end
 
-    # if row.size < COLUMNS.size/2
-    # as per december 2013 does no longer raise an error, but outputs the problematic line
-    def test_diff_error_missing_case1
-      @diff.diff(@data_error_missing_case1, @older)
-    end
-
-    # if row.select{|val| val==nil}.size > COLUMNS.size/2
-    # as per december 2013 does no longer raise an error, but outputs the problematic line
-    def test_diff_error_missing_case2
-      @diff.diff(@data_error_missing_case2, @older)
-    end
     def test_diff__ignore
-      ignore = [:company, :atc_class]
-      result = @diff.diff(@data, @older, ignore)
-      assert_equal 3, result.news.size
-      assert_equal 'Cardio-Pulmo-Rénal Sérocytol, suppositoire',
-                   result.news.first.at(2)
-      assert_equal 1, result.updates.size
-      assert_equal 'Coeur-Vaisseaux Sérocytol, suppositoire(update)',
-                   result.updates.first.at(2)
-      assert_equal 5, result.changes.size
+      ignore = [:company, :name_base, :expiry_date, :indication_sequence]
+      result = @diff.diff(@february_2014, @january_2014, ignore)
       expected = {
-        "00275"=>[:new],
-        "00277"=>[:name_base],
-        "61367"=>[:sequence, :replaced_package],
-        "61416"=>[:new],
+        "00278"=>[:atc_class],
+        "00279"=>[:atc_class],
+        "65040"=>[:sequence, :replaced_package],
+        "60125"=>[:new],
+        "61367"=>[:new],
         "00274"=>[:delete]
       }
       assert_equal(expected, result.changes)
+      assert_equal 4, result.news.size
+      assert_equal 3, result.updates.size
+      assert_equal 6, result.changes.size
       assert_equal 3, result.package_deletions.size
-      assert_equal 4, result.package_deletions.first.size
-      iksnrs = result.package_deletions.collect { |row| row.at(0) }.sort
-      ikscds = result.package_deletions.collect { |row| row.at(2) }.sort
-      assert_equal ["00274", "61367", "61367"], iksnrs
-      assert_equal ["001", "002", "005"], ikscds
-      assert_equal 1, result.sequence_deletions.size
-      assert_equal ["00274", "01"], result.sequence_deletions.at(0)
-      assert_equal 1, result.registration_deletions.size
-      assert_equal ["00274"], result.registration_deletions.at(0)
-      assert_equal 1, result.replacements.size
-      assert_equal '005', result.replacements.values.first
     end
     def test_to_s
       @diff.to_s
-      @diff.diff(@data, @older)
+      @diff.diff(@february_2014, @january_2014)
       assert_equal <<-EOS.strip, @diff.to_s
-+ 00275: Cardio-Pulmo-Rénal Sérocytol, suppositoire
-+ 61416: Otriduo Schnupfen, Nasentropfen
++ 60125: Otriduo Schnupfen, Dosierspray
++ 61367: Hypericum-Mepha 250, Lactab
 - 00274: Cardio-Pulmo-Rénal Sérocytol, suppositoire
-> 00277: Coeur-Vaisseaux Sérocytol, suppositoire; Namensänderung (Coeur-Vaisseaux Sérocytol, suppositoire)
-> 61338: Cefuroxim Fresenius i.v. 750 mg, Pulver zur Herstellung einer i.v. Lösung; Zulassungsinhaber (Fresenius Kabi (Schweiz) AG), ATC-Code (J01DC02)
-> 61367: Hypericum-Mepha 250, Lactab; Packungs-Nummer (005 -> 006)
+> 00277: Coeur-Vaisseaux Sérocytol, Namensänderung; Namensänderung (Coeur-Vaisseaux Sérocytol, Namensänderung), Ablaufdatum der Zulassung (25.04.2020), Anwendungsgebiet Sequenz ()
+> 00278: Colon Sérocytol, suppositoire; ATC-Code (J06AA)
+> 00279: Conjonctif Sérocytol, suppositoire; ATC-Code (D03AX04)
+> 65040: Panthoben, Salbe; Packungs-Nummer (001 -> 003)
       EOS
       assert_equal <<-EOS.strip, @diff.to_s(:name)
 - 00274: Cardio-Pulmo-Rénal Sérocytol, suppositoire
-+ 00275: Cardio-Pulmo-Rénal Sérocytol, suppositoire
-> 61338: Cefuroxim Fresenius i.v. 750 mg, Pulver zur Herstellung einer i.v. Lösung; Zulassungsinhaber (Fresenius Kabi (Schweiz) AG), ATC-Code (J01DC02)
-> 00277: Coeur-Vaisseaux Sérocytol, suppositoire; Namensänderung (Coeur-Vaisseaux Sérocytol, suppositoire)
-> 61367: Hypericum-Mepha 250, Lactab; Packungs-Nummer (005 -> 006)
-+ 61416: Otriduo Schnupfen, Nasentropfen
-      EOS
+> 00277: Coeur-Vaisseaux Sérocytol, Namensänderung; Namensänderung (Coeur-Vaisseaux Sérocytol, Namensänderung), Ablaufdatum der Zulassung (25.04.2020), Anwendungsgebiet Sequenz ()
+> 00278: Colon Sérocytol, suppositoire; ATC-Code (J06AA)
+> 00279: Conjonctif Sérocytol, suppositoire; ATC-Code (D03AX04)
++ 61367: Hypericum-Mepha 250, Lactab
++ 60125: Otriduo Schnupfen, Dosierspray
+> 65040: Panthoben, Salbe; Packungs-Nummer (001 -> 003)
+    EOS
       assert_equal <<-EOS.strip, @diff.to_s(:registration)
 - 00274: Cardio-Pulmo-Rénal Sérocytol, suppositoire
-+ 00275: Cardio-Pulmo-Rénal Sérocytol, suppositoire
-> 00277: Coeur-Vaisseaux Sérocytol, suppositoire; Namensänderung (Coeur-Vaisseaux Sérocytol, suppositoire)
-> 61338: Cefuroxim Fresenius i.v. 750 mg, Pulver zur Herstellung einer i.v. Lösung; Zulassungsinhaber (Fresenius Kabi (Schweiz) AG), ATC-Code (J01DC02)
-> 61367: Hypericum-Mepha 250, Lactab; Packungs-Nummer (005 -> 006)
-+ 61416: Otriduo Schnupfen, Nasentropfen
+> 00277: Coeur-Vaisseaux Sérocytol, Namensänderung; Namensänderung (Coeur-Vaisseaux Sérocytol, Namensänderung), Ablaufdatum der Zulassung (25.04.2020), Anwendungsgebiet Sequenz ()
+> 00278: Colon Sérocytol, suppositoire; ATC-Code (J06AA)
+> 00279: Conjonctif Sérocytol, suppositoire; ATC-Code (D03AX04)
++ 60125: Otriduo Schnupfen, Dosierspray
++ 61367: Hypericum-Mepha 250, Lactab
+> 65040: Panthoben, Salbe; Packungs-Nummer (001 -> 003)
       EOS
     end
   end

metadata

@@ -1,18 +1,20 @@
 --- !ruby/object:Gem::Specification
 name: swissmedic-diff
 version: !ruby/object:Gem::Version
-  version: 0.1.9
+  version: 0.2.0
+  prerelease: 
 platform: ruby
 authors:
 - Masaomi Hatakeyama, Zeno R.R. Davatz
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-06-08 00:00:00.000000000 Z
+date: 2015-07-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rdoc
   requirement: !ruby/object:Gem::Requirement
+    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
@@ -20,6 +22,7 @@ dependencies:
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
+    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
@@ -27,17 +30,19 @@ dependencies:
 - !ruby/object:Gem::Dependency
   name: hoe
   requirement: !ruby/object:Gem::Requirement
+    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: '3.7'
+        version: '3.13'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
+    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
-        version: '3.7'
+        version: '3.13'
 description: ! '* Compares two Excel Documents provided by Swissmedic and displays
   the
 
@@ -60,7 +65,6 @@ extra_rdoc_files:
 - Manifest.txt
 - README.txt
 files:
-- .gemtest
 - .gitignore
 - .travis.yml
 - Gemfile
@@ -76,19 +80,15 @@ files:
 - lib/version.rb
 - setup.rb
 - swissmedic-diff.gemspec
-- test/data/Packungen-2013.10.14.xls
-- test/data/Packungen.older.xls
-- test/data/Packungen.xls
-- test/data/Packungen_2013_small.xls
-- test/data/Packungen_2014_small.xlsx
-- test/data/Packungen_error_column.xls
-- test/data/Packungen_error_missing1.xls
-- test/data/Packungen_error_missing2.xls
+- test/data/Packungen-2014.01.01.xlsx
+- test/data/Packungen-2014.02.01.xlsx
+- test/data/Packungen-2015.06.04.xlsx
+- test/data/Packungen-2015.07.02.xlsx
 - test/test_swissmedic-diff.rb
+- .gemtest
 homepage: https://github.com/zdavatz/swissmedic-diff
 licenses:
 - MIT
-metadata: {}
 post_install_message: 
 rdoc_options:
 - --main
@@ -96,21 +96,28 @@ rdoc_options:
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
   requirements:
   - - ! '>='
     - !ruby/object:Gem::Version
       version: '0'
+      segments:
+      - 0
+      hash: -1183980882964765712
 required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
   requirements:
   - - ! '>='
     - !ruby/object:Gem::Version
       version: '0'
+      segments:
+      - 0
+      hash: -1183980882964765712
 requirements: []
-rubyforge_project: swissmedic-diff
-rubygems_version: 2.3.0
+rubyforge_project: 
+rubygems_version: 1.8.23.2
 signing_key: 
-specification_version: 4
+specification_version: 3
 summary: ! '* Compares two Excel Documents provided by Swissmedic and displays the
   salient differences'
-test_files:
-- test/test_swissmedic-diff.rb
+test_files: []

checksums.yaml

@@ -1,15 +0,0 @@
----
-!binary "U0hBMQ==":
-  metadata.gz: !binary |-
-    NGZmZDYzOTBkNGI4MWQ5OTdlMTU4YmYyNzExNzI0YmU1MmZjOWIyMg==
-  data.tar.gz: !binary |-
-    NTA2M2YwNTU3M2RjNTIxNzJmZTUxZjM5MTg2NWZhZjg1NGM3ZGZlNA==
-SHA512:
-  metadata.gz: !binary |-
-    YzU4YjQ4ODRkMzc4OTZmMWM3MWM2MjUxNTBlNDFmY2Q5ZmM0ZmVhMTJhZDZj
-    MmQ2MTg2NWY2NzY1MzEzZTRkZTBlY2FkMTA3MGY0OGRkOWE4M2YxOTIxM2M2
-    YTZkZWQyODMzZDRjMDE2OGVjNGVhNGM5NTFhNjc2ZjYyYTQ0ZmI=
-  data.tar.gz: !binary |-
-    MjUwYjRmZThhMGUxMTZkMDUxNzdjZTRkNWQyYWFlMzZmMzdmNjI2YmMwZjFk
-    MWFjMmEwOWMwYTNjNTM3YTkyODNjOGE1MGMxNTFhMDIyZjRjOWQ0OWM4M2Qz
-    YTM1ZTgyY2MwZTIwNTM0NzcyNjkwNDFhMjExM2MyZDMzNTgzZjI=