dcm_dict 0.1.0

data/lib/dcm_dict/xml/constant.rb

@@ -0,0 +1,38 @@
+#
+#  Copyright (C) 2014  Enrico Rivarola
+#
+#  This file is part of DcmDict gem (dcm_dict).
+#
+#  DcmDict is free software: you can redistribute it and/or modify
+#  it under the terms of the GNU General Public License as published by
+#  the Free Software Foundation, either version 3 of the License, or
+#  (at your option) any later version.
+#
+#  DcmDict is distributed in the hope that it will be useful,
+#  but WITHOUT ANY WARRANTY; without even the implied warranty of
+#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+#  GNU General Public License for more details.
+#
+#  You should have received a copy of the GNU General Public License
+#  along with DcmDict.  If not, see <http://www.gnu.org/licenses/>.
+#
+#  This software has neither been tested nor approved for clinical use
+#  or for incorporation in a medical device.
+#  It is the redistributor's or user's responsibility to comply with any
+#  applicable local, state, national or international regulations.
+#
+module DcmDict
+  module XML
+    DataElementNodeSetIdx = { tag_ps: 0,
+                              tag_name: 1,
+                              tag_key: 2,
+                              tag_vr: 3,
+                              tag_vm: 4,
+                              tag_note: 5 }.freeze
+
+    UidNodeSetIdx = { uid_value: 0,
+                      uid_name: 1,
+                      uid_type: 2}.freeze
+
+  end
+end

data/lib/dcm_dict/xml/field_data.rb

@@ -0,0 +1,47 @@
+#
+#  Copyright (C) 2014  Enrico Rivarola
+#
+#  This file is part of DcmDict gem (dcm_dict).
+#
+#  DcmDict is free software: you can redistribute it and/or modify
+#  it under the terms of the GNU General Public License as published by
+#  the Free Software Foundation, either version 3 of the License, or
+#  (at your option) any later version.
+#
+#  DcmDict is distributed in the hope that it will be useful,
+#  but WITHOUT ANY WARRANTY; without even the implied warranty of
+#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+#  GNU General Public License for more details.
+#
+#  You should have received a copy of the GNU General Public License
+#  along with DcmDict.  If not, see <http://www.gnu.org/licenses/>.
+#
+#  This software has neither been tested nor approved for clinical use
+#  or for incorporation in a medical device.
+#  It is the redistributor's or user's responsibility to comply with any
+#  applicable local, state, national or international regulations.
+#
+module DcmDict
+  module XML
+
+    # Base class to manage xml data
+    class FieldData
+      using DcmDict::Refine::Internal::StringRefineInternal
+
+      # Initialize object using +extract_proc+ as proc to extract data from xml element
+      def initialize(extract_proc)
+        @extract_proc = extract_proc
+      end
+
+      private
+      def extract_multiple_data(key, sep)
+        extract_content_data(key).split(sep)
+      end
+
+      def extract_content_data(key)
+        data = @extract_proc.call(key)
+        data ? data.dcm_unspace : ''
+      end
+    end
+  end
+end

data/lib/dcm_dict/xml/nokogiri_tool.rb

@@ -0,0 +1,108 @@
+#
+#  Copyright (C) 2014  Enrico Rivarola
+#
+#  This file is part of DcmDict gem (dcm_dict).
+#
+#  DcmDict is free software: you can redistribute it and/or modify
+#  it under the terms of the GNU General Public License as published by
+#  the Free Software Foundation, either version 3 of the License, or
+#  (at your option) any later version.
+#
+#  DcmDict is distributed in the hope that it will be useful,
+#  but WITHOUT ANY WARRANTY; without even the implied warranty of
+#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+#  GNU General Public License for more details.
+#
+#  You should have received a copy of the GNU General Public License
+#  along with DcmDict.  If not, see <http://www.gnu.org/licenses/>.
+#
+#  This software has neither been tested nor approved for clinical use
+#  or for incorporation in a medical device.
+#  It is the redistributor's or user's responsibility to comply with any
+#  applicable local, state, national or international regulations.
+#
+
+module DcmDict
+  module XML
+    @@nokogiri_enable = false
+
+    begin
+      #raise LoadError.new "Simulate LoadError to disable Nokogiri"
+      require 'nokogiri'
+      @@nokogiri_enable = true
+    rescue LoadError
+    end
+
+    # Check for Nokogiri gem
+    def self.nokogiri_enable?
+      @@nokogiri_enable
+    end
+
+    if @@nokogiri_enable
+      module NokogiriTool
+
+        # Extract data element data from a table row using +xml_tr_string+ as source string
+        def self.extract_data_element_field_from_xml_tr(xml_tr_string)
+          nodeset = extract_nokogiri_nodeset(xml_tr_string)
+          extract_data_element_field_from_tr_set(nodeset)
+        end
+
+        # Extract data element data from xml table row using +trset+ (NodeSet) as source
+        def self.extract_data_element_field_from_tr_set(trset)
+          proc = tag_field_extract_proc(trset)
+          TagFieldData.new(proc).data_element_data
+        end
+
+        # Extract uid data from a table row using +xml_tr_string+ as source string
+        def self.extract_uid_field_from_xml_tr(xml_tr_string)
+          nodeset = extract_nokogiri_nodeset(xml_tr_string)
+          extract_uid_field_from_tr_set(nodeset)
+        end
+
+        # Extract uid data from a table row using +trset+ (NodeSet) as source
+        def self.extract_uid_field_from_tr_set(trset)
+          proc = uid_field_extract_proc(trset)
+          UidFieldData.new(proc).uid_data
+        end
+
+        # Create XML root object from xml source string +xml_string+
+        def self.create_xml_doc(xml_string)
+          Nokogiri::XML(xml_string)
+        end
+
+        # Calls the given block from +doc+ once for each 'table row' identified by +xpath+
+        def self.each_tr_set(doc, xpath)
+          alltr = doc.xpath(xpath)
+          alltr.each do |tr|
+            trset = tr.xpath('xmlns:td')
+            yield trset if block_given?
+          end
+        end
+
+        private
+        def self.tag_field_extract_proc(node_set)
+          make_nokogiri_proc(node_set, DataElementNodeSetIdx)
+        end
+
+        def self.uid_field_extract_proc(node_set)
+          make_nokogiri_proc(node_set, UidNodeSetIdx)
+        end
+
+        def self.make_nokogiri_proc(node_set, node_set_idx)
+          Proc.new do |key|
+            idx = node_set_idx[key]
+            node_set[idx] ? node_set[idx].content.gsub(/ {2,}/, '') : ''
+          end
+        end
+
+        def self.extract_nokogiri_nodeset(xml_tr_string)
+          doc  = create_xml_doc(xml_tr_string)
+          each_tr_set(doc, '//xmlns:tr') do |tdset|
+            return tdset
+          end
+        end
+      end
+    end
+
+  end
+end

data/lib/dcm_dict/xml/rexml_tool.rb

@@ -0,0 +1,105 @@
+#
+#  Copyright (C) 2014  Enrico Rivarola
+#
+#  This file is part of DcmDict gem (dcm_dict).
+#
+#  DcmDict is free software: you can redistribute it and/or modify
+#  it under the terms of the GNU General Public License as published by
+#  the Free Software Foundation, either version 3 of the License, or
+#  (at your option) any later version.
+#
+#  DcmDict is distributed in the hope that it will be useful,
+#  but WITHOUT ANY WARRANTY; without even the implied warranty of
+#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+#  GNU General Public License for more details.
+#
+#  You should have received a copy of the GNU General Public License
+#  along with DcmDict.  If not, see <http://www.gnu.org/licenses/>.
+#
+#  This software has neither been tested nor approved for clinical use
+#  or for incorporation in a medical device.
+#  It is the redistributor's or user's responsibility to comply with any
+#  applicable local, state, national or international regulations.
+#
+require "rexml/document"
+
+module DcmDict
+  module XML
+
+    module RexmlTool
+
+      # Extract data element data from a table row using +xml_tr_string+ as source string
+      def self.extract_data_element_field_from_xml_tr(xml_tr_string)
+        nodeset = extract_rexml_nodeset(xml_tr_string)
+        extract_data_element_field_from_tr_set(nodeset)
+      end
+
+      # Extract data element data from xml table row using +trset+ (NodeSet) as source
+      def self.extract_data_element_field_from_tr_set(trset)
+        proc = tag_field_extract_proc(trset)
+        TagFieldData.new(proc).data_element_data
+      end
+
+      # Extract uid data from a table row using +xml_tr_string+ as source string
+      def self.extract_uid_field_from_xml_tr(xml_tr_string)
+        nodeset = extract_rexml_nodeset(xml_tr_string)
+        extract_uid_field_from_tr_set(nodeset)
+      end
+
+      # Extract uid data from a table row using +trset+ (XML Element) as source
+      def self.extract_uid_field_from_tr_set(trset)
+        proc = uid_field_extract_proc(trset)
+        UidFieldData.new(proc).uid_data
+      end
+
+      # Create XML root object from xml source string +xml_string+
+      def self.create_xml_doc(xml_string)
+        REXML::Document.new(xml_string)
+      end
+
+      # Calls the given block from +doc+ once for each 'table row' identified by +xpath+
+      def self.each_tr_set(doc, xpath)
+        alltr = REXML::XPath.match(doc, xpath)
+        alltr.each do |tr|
+          trset = tr.get_elements('xmlns:td')
+          yield trset if block_given?
+        end
+      end
+
+      private
+      def self.tag_field_extract_proc(node_set)
+        make_rexml_proc(node_set, DataElementNodeSetIdx)
+      end
+
+      def self.uid_field_extract_proc(node_set)
+        make_rexml_proc(node_set, UidNodeSetIdx)
+      end
+
+      def self.make_rexml_proc(node_set, node_set_idx)
+        Proc.new do |key|
+          element = node_set[node_set_idx[key]]
+          field = ''
+          if element
+            element.each_element_with_text do |txt1|
+              field << "\n"  unless field.nil_or_empty?
+              txt1.each_element_with_text do |txt2|
+                field << txt2.texts.map(&:value).join('')
+              end
+              field << txt1.texts.map(&:value).join('')
+            end
+          end
+          field
+        end
+      end
+
+      def self.extract_rexml_nodeset(xml_tr_string)
+        doc = create_xml_doc(xml_tr_string)
+        each_tr_set(doc, "//xmlns:tr") do |tdset|
+          return tdset
+        end
+      end
+
+    end
+
+  end
+end

data/lib/dcm_dict/xml/tag_field_data.rb

@@ -0,0 +1,96 @@
+#
+#  Copyright (C) 2014  Enrico Rivarola
+#
+#  This file is part of DcmDict gem (dcm_dict).
+#
+#  DcmDict is free software: you can redistribute it and/or modify
+#  it under the terms of the GNU General Public License as published by
+#  the Free Software Foundation, either version 3 of the License, or
+#  (at your option) any later version.
+#
+#  DcmDict is distributed in the hope that it will be useful,
+#  but WITHOUT ANY WARRANTY; without even the implied warranty of
+#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+#  GNU General Public License for more details.
+#
+#  You should have received a copy of the GNU General Public License
+#  along with DcmDict.  If not, see <http://www.gnu.org/licenses/>.
+#
+#  This software has neither been tested nor approved for clinical use
+#  or for incorporation in a medical device.
+#  It is the redistributor's or user's responsibility to comply with any
+#  applicable local, state, national or international regulations.
+#
+module DcmDict
+  module XML
+    MultiFieldSeparator = ' or '.freeze
+    DefaultMultiTagValue = '2'.freeze
+
+    # Class to handle data element data
+    class TagFieldData < FieldData
+      using DcmDict::Refine::Internal::StringRefineInternal
+      using DcmDict::Refine::Internal::HashRefineInternal
+
+      # Initialize object using +extract_proc+ as proc to extract data from xml element
+      def initialize(extract_proc)
+        super
+      end
+
+      # Extract and build data element data
+      def data_element_data
+        extract_base_data()
+        @data.check_base_data_tag_field!
+        extend_base_data()
+        @data
+      end
+
+      private
+      def extract_base_data()
+        @data = { :tag_ps =>  extract_content_data(:tag_ps),
+                  :tag_name =>  extract_content_data(:tag_name),
+                  :tag_key =>  extract_content_data(:tag_key),
+                  :tag_vr =>  extract_tag_vr(),
+                  :tag_vm =>  extract_tag_vm(),
+                  :tag_note => extract_content_data(:tag_note) }
+      end
+
+      def extract_tag_vr()
+        extract_multiple_data(:tag_vr, MultiFieldSeparator).map(&:to_sym)
+      end
+
+      def extract_tag_vm()
+        extract_multiple_data(:tag_vm, MultiFieldSeparator)
+      end
+
+      def extend_base_data
+        @data[:tag_str] = extract_tag_str_from_data
+        @data[:tag_sym] = extract_tag_sym_from_data
+        @data[:tag_ndm] = extract_tag_ndm_from_data
+        @data[:tag_ary] = extract_tag_ary_from_data
+        @data[:tag_multiple] = data_with_multiple_tag?
+      end
+
+      def extract_tag_str_from_data
+        @data[:tag_ps].gsub(/[xX|]/, DefaultMultiTagValue)
+      end
+
+      def data_with_multiple_tag?
+        @data[:tag_ps].index(/[xX|]/) ? true : false
+      end
+
+      def extract_tag_ary_from_data
+        @data[:tag_str].to_tag_ary
+      end
+
+      def extract_tag_ndm_from_data
+        @data[:tag_str].to_tag_ndm
+      end
+
+      def extract_tag_sym_from_data
+        @data[:tag_key].tag_key_to_sym
+      end
+
+    end
+
+  end
+end

data/lib/dcm_dict/xml/uid_field_data.rb

@@ -0,0 +1,49 @@
+#
+#  Copyright (C) 2014  Enrico Rivarola
+#
+#  This file is part of DcmDict gem (dcm_dict).
+#
+#  DcmDict is free software: you can redistribute it and/or modify
+#  it under the terms of the GNU General Public License as published by
+#  the Free Software Foundation, either version 3 of the License, or
+#  (at your option) any later version.
+#
+#  DcmDict is distributed in the hope that it will be useful,
+#  but WITHOUT ANY WARRANTY; without even the implied warranty of
+#  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+#  GNU General Public License for more details.
+#
+#  You should have received a copy of the GNU General Public License
+#  along with DcmDict.  If not, see <http://www.gnu.org/licenses/>.
+#
+#  This software has neither been tested nor approved for clinical use
+#  or for incorporation in a medical device.
+#  It is the redistributor's or user's responsibility to comply with any
+#  applicable local, state, national or international regulations.
+#
+module DcmDict
+  module XML
+
+    # Class to handle uid data
+    class UidFieldData < FieldData
+      using DcmDict::Refine::Internal::StringRefineInternal
+
+      # Initialize object using +extract_proc+ as proc to extract data from xml element
+      def initialize(extract_proc)
+        super
+      end
+
+      # Extract and build uid data
+      def uid_data
+        extract_base_data
+      end
+
+      private
+      def extract_base_data
+        { uid_value: extract_content_data(:uid_value),
+          uid_name: extract_content_data(:uid_name),
+          uid_type: extract_content_data(:uid_type).uid_type_to_sym}
+      end
+    end
+  end
+end