oddb2xml 2.0.0 → 2.0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 3a0dff7ea1897c93913176510675ffb84641763c
-  data.tar.gz: ea3b174167d1a38862cf5eba377989c3ed8244f2
+  metadata.gz: 82754e27fde87282a1643f1acb81a8e30f2bee99
+  data.tar.gz: 13ae8919c8572bf3d8bf3261802a096bbab9ead2
 SHA512:
-  metadata.gz: ab2bef6593e7fbd5957d97d0e7fe42808527585ad63af64d689630fb29650ce7d0b4fd2cf208e7e81ff9e2bc66a807f4cb2ed6c05831cd80daff0a71427415a8
-  data.tar.gz: 61757a8be3030715495f361467febf3f991e6669637b5cefe2cb967739d20009f2feca35c0ac12e88a2e9aafda421e4c3c7db654f1f4a085d77f302a8016bc91
+  metadata.gz: 74e386dab573b605b60e3e4fd92740f1ab482b546e41998bd51e60105361bb8c2164723098a24bec2c64e43ff4c338612c6212806c22748c94077788bca59967
+  data.tar.gz: 785ab82c497388b1278c5dba170e9318fdec62fe223fa4fa4a7aa22be3100b3094339d74d29bf7f9bb03f8fa758c8e2d9131d6e2d08ea09d3ae9873ff4a34572

data/History.txt

@@ -1,3 +1,7 @@
+=== 2.0.1 / 17.03.2015
+
+* Readded description for label
+
 === 2.0.0 / 17.03.2015
 
 * Adding CHEMICAL_SUBSTANCE/DOSE for ut|corresponding

data/lib/oddb2xml/builder.rb

@@ -681,6 +681,7 @@ module Oddb2xml
                   xml.COMPOSITION {
                     # xml.SOURCE composition.source # emit this if you want to debug the results
                     xml.LABEL composition.label if composition.label
+                    xml.LABEL_DESCRIPTION composition.label_description if composition.label_description
                     xml.SUBSTANCES {
                       composition.substances.each { |substance|
                         xml.SUBSTANCE {

data/lib/oddb2xml/calc.rb

@@ -1,6 +1,7 @@
 # encoding: utf-8
 
 require 'oddb2xml/util'
+require 'oddb2xml/parse_compositions'
 require 'yaml'
 
 module Oddb2xml
@@ -150,78 +151,11 @@ module Oddb2xml
         "\n\n\nColumn Präparateliste has everywhere a name\n"
       end
     end
-public
-    SCALE_P = %r{pro\s+(?<scale>(?<qty>[\d.,]+)\s*(?<unit>[kcmuµn]?[glh]))}u
 private
     def remove_duplicated_spaces(string)
       string ? string.to_s.gsub(/\s\s+/, ' ') : nil
     end
 public
-    # Update of active substances, etc picked up from oddb.org/src/plugin/swissmedic.rb update_compositions
-    Composition   = Struct.new("Composition",  :source, :label, :substances, :galenic_form, :route_of_administration)
-    Substance     = Struct.new("Substance",  :name, :qty, :unit, :chemical_substance, :chemical_dose)
-    def update_compositions(active_substance)
-      rep_1 = '----';   to_1 = '('
-      rep_2 = '-----';  to_2 = ')'
-      rep_3 = '------'; to_3 = ','
-
-      comps = []
-      label_pattern = /^(?<label>A|I|B|II|C|III|D|IV|E|V|F|VI)[)]\s*(?<designation>[^)]+):/
-      composition_text = composition.gsub(/\r\n?/u, "\n")
-      puts "composition_text for #{name}: #{composition_text}" if composition_text.split(/\n/u).size > 1 and $VERBOSE
-      lines = composition_text.split(/\n/u)
-      idx = 0
-      compositions = lines.select do |line|
-        if match = label_pattern.match(line)
-          label = match[:label]
-        else
-          label = nil
-        end
-        idx += 1
-        next if idx > 1 and not label # avoid lines like 'I) et II)'
-        substances = []
-        filler = line.split(',')[-1].sub(/\.$/, '')
-        filler_match = /^(?<name>[^,\d]+)\s*(?<dose>[\d\-.]+(\s*(?:(Mio\.?\s*)?(U\.\s*Ph\.\s*Eur\.|[^\s,]+))))/.match(filler)
-        components = line.split(/([^\(]+\([^)]+\)[^,]+|),/).each {
-          |component|
-          next unless component.size > 0
-          to_consider = component.strip.split(':')[-1] # remove label
-          # very ugly hack to ignore ,()
-          m = /^(?<name>[^,\d()]+)\s*(?<dose>[\d\-.]+(\s*(?:(Mio\.?\s*)?(U\.\s*Ph\.\s*Eur\.|[^\s,]+))))/.match(to_consider
-                                                            .gsub(to_1, rep_1).gsub(to_2, rep_2).gsub(to_3, rep_3))
-          if m2 = /^(|[^:]+:\s)(E\s+\d+)$/.match(component.strip)
-            to_add = Substance.new(m2[2], '', '')
-            substances << to_add
-          elsif m
-            ptrn = /(\s*(?:ut|corresp\.?)\s+(?<chemical>[^\d,]+)\s*(?<cdose>[\d\-.]+(\s*(?:(Mio\.?\s*)?(U\.\s*Ph\.\s*Eur\.|[^\s,]+))(\s*[mv]\/[mv])?))?)/
-            m3 = ptrn.match(component.strip)
-            dose = nil
-            unit = nil
-            name = m[:name].split(/\s/).collect{ |x| x.capitalize }.join(' ').strip.gsub(rep_3, to_3).gsub(rep_2, to_2).gsub(rep_1, to_1)
-            dose = m[:dose].split(/\b\s*(?![.,\d\-]|Mio\.?)/u, 2) if m[:dose]
-            if dose && (scale = SCALE_P.match(filler)) && dose[1] && !dose[1].include?('/')
-              unit = dose[1] << '/'
-              num = scale[:qty].to_f
-              if num <= 1
-                unit << scale[:unit]
-              else
-                unit << scale[:scale]
-              end
-            elsif dose.size == 2
-              unit = dose[1]
-            end
-            next if /\s+pro($|\s+)|emulsion|solution/i.match(name)
-            chemical = m3 ? capitalize(m3[:chemical]) : nil
-            cdose    = m3 ? m3[:cdose] : nil
-            substances << Substance.new(name, dose ? dose[0].to_f : nil, unit ? unit.gsub(rep_3, to_3).gsub(rep_2, to_2).gsub(rep_1, to_1) : nil,
-                                        chemical, cdose)
-          end
-        }
-        comps << Composition.new(line, label, substances) if substances.size > 0
-      end
-      comps
-    end
-
     def initialize(name = nil, size = nil, unit = nil, active_substance = nil, composition= nil)
       @name = remove_duplicated_spaces(name)
       @pkg_size = remove_duplicated_spaces(size)
@@ -233,10 +167,10 @@ public
       @measure = @galenic_form.description if @galenic_form and not @measure
       @galenic_form  ||= @@galenic_forms[UnknownGalenicForm]
 
-      unless active_substance
+      unless composition
         @compositions = []
       else
-        @compositions = update_compositions(active_substance)
+        @compositions = ParseUtil.parse_compositions(composition)
       end
     end
 
@@ -263,9 +197,6 @@ public
       @galenic_form.description
     end
   private
-    def capitalize(string)
-      string.split(/\s+/u).collect { |word| word.capitalize }.join(' ')
-    end
 
     def update_rule(rulename)
       @@rules_counter[rulename] ||= 0
@@ -362,7 +293,7 @@ public
     end
     def search_galenic_info
       @substances = nil
-      @substances = @composition.split(/\s*,(?!\d|[^(]+\))\s*/u).collect { |name| capitalize(name) }.uniq if @composition
+      @substances = @composition.split(/\s*,(?!\d|[^(]+\))\s*/u).collect { |name| ParseUtil.capitalize(name) }.uniq if @composition
 
       name = @name ? @name.clone : ''
       parts = name.split(',')

data/lib/oddb2xml/parse_compositions.rb

@@ -0,0 +1,80 @@
+# encoding: utf-8
+
+# This file is shared since oddb2xml 2.0.0 (lib/oddb2xml/parse_compositions.rb)
+# with oddb.org src/plugin/parse_compositions.rb
+#
+# It allows an easy parsing of the column P Zusammensetzung of the swissmedic packages.xlsx file
+#
+
+module ParseUtil
+  SCALE_P = %r{pro\s+(?<scale>(?<qty>[\d.,]+)\s*(?<unit>[kcmuµn]?[glh]))}u
+  ParseComposition   = Struct.new("ParseComposition",  :source, :label, :label_description, :substances, :galenic_form, :route_of_administration)
+  ParseSubstance     = Struct.new("ParseSubstance",    :name, :qty, :unit, :chemical_substance, :chemical_dose)
+  def ParseUtil.capitalize(string)
+    string.split(/\s+/u).collect { |word| word.capitalize }.join(' ')
+  end
+
+  def ParseUtil.parse_compositions(composition)
+    rep_1 = '----';   to_1 = '('
+    rep_2 = '-----';  to_2 = ')'
+    rep_3 = '------'; to_3 = ','
+
+    comps = []
+    label_pattern = /^(?<label>A|I|B|II|C|III|D|IV|E|V|F|VI)[)]\s*(?<description>[^)]+):/
+    composition_text = composition.gsub(/\r\n?/u, "\n")
+    puts "composition_text for #{name}: #{composition_text}" if composition_text.split(/\n/u).size > 1 and $VERBOSE
+    lines = composition_text.split(/\n/u)
+    idx = 0
+    compositions = lines.select do |line|
+      if match = label_pattern.match(line)
+        label = match[:label]
+        label_description = match[:description]
+      else
+        label = nil
+        label_description = nil
+      end
+      idx += 1
+      next if idx > 1 and not label # avoid lines like 'I) et II)'
+      substances = []
+      filler = line.split(',')[-1].sub(/\.$/, '')
+      filler_match = /^(?<name>[^,\d]+)\s*(?<dose>[\d\-.]+(\s*(?:(Mio\.?\s*)?(U\.\s*Ph\.\s*Eur\.|[^\s,]+))))/.match(filler)
+      components = line.split(/([^\(]+\([^)]+\)[^,]+|),/).each {
+        |component|
+        next unless component.size > 0
+        to_consider = component.strip.split(':')[-1] # remove label
+        # very ugly hack to ignore ,()
+        m = /^(?<name>[^,\d()]+)\s*(?<dose>[\d\-.]+(\s*(?:(Mio\.?\s*)?(U\.\s*Ph\.\s*Eur\.|[^\s,]+))))/.match(to_consider
+                                                          .gsub(to_1, rep_1).gsub(to_2, rep_2).gsub(to_3, rep_3))
+        if m2 = /^(|[^:]+:\s)(E\s+\d+)$/.match(component.strip)
+          to_add = ParseSubstance.new(m2[2], '', '')
+          substances << to_add
+        elsif m
+          ptrn = /(\s*(?:ut|corresp\.?)\s+(?<chemical>[^\d,]+)\s*(?<cdose>[\d\-.]+(\s*(?:(Mio\.?\s*)?(U\.\s*Ph\.\s*Eur\.|[^\s,]+))(\s*[mv]\/[mv])?))?)/
+          m3 = ptrn.match(component.strip)
+          dose = nil
+          unit = nil
+          name = m[:name].split(/\s/).collect{ |x| x.capitalize }.join(' ').strip.gsub(rep_3, to_3).gsub(rep_2, to_2).gsub(rep_1, to_1)
+          dose = m[:dose].split(/\b\s*(?![.,\d\-]|Mio\.?)/u, 2) if m[:dose]
+          if dose && (scale = SCALE_P.match(filler)) && dose[1] && !dose[1].include?('/')
+            unit = dose[1] << '/'
+            num = scale[:qty].to_f
+            if num <= 1
+              unit << scale[:unit]
+            else
+              unit << scale[:scale]
+            end
+          elsif dose.size == 2
+            unit = dose[1]
+          end
+          next if /\s+pro($|\s+)|emulsion|solution/i.match(name)
+          chemical = m3 ? capitalize(m3[:chemical]) : nil
+          cdose    = m3 ? m3[:cdose] : nil
+          substances << ParseSubstance.new(name, dose ? dose[0].to_f : nil, unit ? unit.gsub(rep_3, to_3).gsub(rep_2, to_2).gsub(rep_1, to_1) : nil,
+                                      chemical, cdose)
+        end
+      }
+      comps << ParseComposition.new(line, label, label_description, substances) if substances.size > 0
+    end
+    comps
+  end
+end

data/lib/oddb2xml/version.rb

@@ -1,3 +1,3 @@
 module Oddb2xml
-  VERSION = "2.0.0"
+  VERSION = "2.0.1"
 end

data/spec/calc_spec.rb

@@ -314,6 +314,7 @@ Corresp. 5300 kJ.",
       XPath.match( doc, "//ARTICLE[GTIN='7680545250363']/COMPOSITIONS/COMPOSITION/SUBSTANCES/SUBSTANCE/SUBSTANCE_NAME").last.text.should eq 'Alprostadilum'
       XPath.match( doc, "//ARTICLE[GTIN='7680458820202']/NAME").last.text.should eq 'Magnesiumchlorid 0,5 molar B. Braun, Zusatzampulle für Infusionslösungen'
       XPath.match( doc, "//ARTICLE[GTIN='7680555940018']/COMPOSITIONS/COMPOSITION/LABEL").first.text.should eq 'I'
+      XPath.match( doc, "//ARTICLE[GTIN='7680555940018']/COMPOSITIONS/COMPOSITION/LABEL_DESCRIPTION").first.text.should eq 'Glucoselösung'
       XPath.match( doc, "//ARTICLE[GTIN='7680555940018']/COMPOSITIONS/COMPOSITION/LABEL").last.text.should eq 'III'
    end
   end
@@ -423,6 +424,7 @@ Corresp. 5300 kJ.",
 
     specify { expect(result.compositions[0].source).to eq Line_1}
     specify { expect(result.compositions[0].label).to eq 'I'}
+    specify { expect(result.compositions[0].label_description).to eq 'Glucoselösung'}
     specify { expect(result.compositions[1].label).to eq 'II' }
     specify { expect(result.compositions[2].label).to eq 'III' }
     glucosum = result.compositions.first.substances.first

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: oddb2xml
 version: !ruby/object:Gem::Version
-  version: 2.0.0
+  version: 2.0.1
 platform: ruby
 authors:
 - Yasuhiro Asaka, Zeno R.R. Davatz
@@ -221,6 +221,7 @@ files:
 - lib/oddb2xml/downloader.rb
 - lib/oddb2xml/extractor.rb
 - lib/oddb2xml/options.rb
+- lib/oddb2xml/parse_compositions.rb
 - lib/oddb2xml/util.rb
 - lib/oddb2xml/version.rb
 - lib/oddb2xml/xml_definitions.rb