libis-tools 0.9.65 → 1.0.0

data/lib/libis/tools/metadata/parsers.rb

@@ -1,12 +0,0 @@
-module Libis
-  module Tools
-    module Metadata
-
-      autoload :BasicParser, 'libis/tools/metadata/parser/basic_parser'
-      autoload :DublinCoreParser, 'libis/tools/metadata/parser/dublin_core_parser'
-      autoload :Marc21Parser, 'libis/tools/metadata/parser/marc21_parser'
-      autoload :SubfieldCriteriaParser, 'libis/tools/metadata/parser/subfield_criteria_parser'
-
-    end
-  end
-end

data/lib/libis/tools/metadata/sharepoint_mapping.rb

@@ -1,119 +0,0 @@
-# coding: utf-8
-
-require 'csv'
-require 'yaml'
-
-require 'libis/tools/extend/hash'
-
-module Libis
-  module Tools
-
-    # Copy of old Sharepoint mapping class. Needs inspection and probably a mayor update.
-    class SharepointMapping < Hash
-
-      def initialize(mapping_file)
-
-
-        CSV.foreach(mapping_file, headers: true, skip_blanks: true) do |row|
-          next unless row[1]
-          # next unless (row[2] || row[3])
-
-          # compensation for bug in library that reads the Excel data
-          0.upto(5) { |i| row[i] = row[i].gsub(/_x005F(_x[0-9a-fA-F]{4}_)/, '\1') if row[i] }
-
-          name = row[0] ? row[0].strip : nil
-          label = row[1].strip.to_sym
-          dc_tag = row[2] ? row[2].strip : ''
-          db_column = row[3] ? row[3].strip : nil
-          db_datatype = row[4] ? row[4].strip.upcase.to_sym : nil
-          db_valuemask = row[5] ? row[5] : nil
-          #      scope_tag = row[6] ? row[6].strip : nil
-          #      scope_id = (row[7] and row[7] =~ /[0-9]+/ ? Integer(row[7].strip) : nil)
-
-
-          mapping = {}
-          mapping[:fancy_name] = name if name
-          mapping[:db_column] = db_column if db_column
-          mapping[:db_datatype] = :STRING
-          mapping[:db_datatype] = db_datatype if db_datatype
-          mapping[:db_valuemask] = (mapping[:db_datatype] == :STRING ? "'@@'" : '@@')
-          mapping[:db_valuemask] = db_valuemask if db_valuemask
-          #      mapping[:scope_tag] = scope_tag if scope_tag
-          #      mapping[:scope_id] = scope_id if scope_id
-
-          if dc_tag.match(/^\s*"(.*)"\s*(<.*)$/)
-            mapping[:dc_prefix] = $1
-            dc_tag = $2
-          end
-
-          if dc_tag.match(/^\s*<dc:[^.]+\.([^.>]+)>(.*)$/)
-            mapping[:dc_tag] = "dcterms:#{$1}"
-            dc_tag = $2
-
-          elsif dc_tag.match(/^\s*<dc:([^.>]+)>(.*)$/)
-            mapping[:dc_tag] = "dc:#{$1}"
-            dc_tag = $2
-          end
-
-          if dc_tag.match(/^\s*"(.*)"\s*$/)
-            mapping[:dc_postfix] = $1
-          end
-
-          self[label] = mapping.empty? ? nil : mapping
-
-        end
-
-        File.open('mapping.yml', 'wt') { |fp|
-          fp.puts self.to_yaml
-        }
-        super nil
-
-      end
-
-      def name(label)
-        mapping = self[label]
-        mapping = mapping[:fancy_name] if mapping
-        mapping || label
-      end
-
-      def fancy_label(label)
-        mapping = self[label]
-        mapping = mapping[:fancy_name] if mapping
-        "#{label}#{mapping ? '(' + mapping + ')' : ''}"
-      end
-
-      def dc_tag(label)
-        mapping = self[label]
-        mapping = mapping[:dc_tag] if mapping
-        mapping
-      end
-
-      def dc_prefix(label)
-        mapping = self[label]
-        mapping = mapping[:dc_prefix] if mapping
-        mapping
-      end
-
-      def dc_postfix(label)
-        mapping = self[label]
-        mapping = mapping[:dc_postfix] if mapping
-        mapping
-      end
-
-      def db_column(label)
-        mapping = self[label]
-        mapping = mapping[:db_column] if mapping
-        mapping
-      end
-
-      def db_value(label, value)
-        mapping = self[label]
-        return nil unless mapping
-        mask = mapping[:db_valuemask]
-        mask.gsub('@@', value.to_s)
-      end
-
-    end
-
-  end
-end

data/lib/libis/tools/metadata/sharepoint_record.rb

@@ -1,262 +0,0 @@
-# coding: utf-8
-
-require 'uri'
-
-require 'libis/tools/extend/hash'
-require 'libis/tools/xml_document'
-
-module Libis
-  module Tools
-
-    # noinspection RubyTooManyMethodsInspection
-
-    # Copy of the old SharepointRecord class. Needs inspection and probably a mayor update.
-    class SharepointRecord < Hash
-
-      attr_accessor :node
-
-      def initialize
-        @node = nil
-        self[:label_prefix] = ''
-        super nil
-      end
-
-      def label_prefix
-        self[:label_prefix]
-      end
-
-      def label_prefix=(value)
-        self[:label_prefix] = value
-      end
-
-      def label
-        (self[:ows_Title1] || self[:ows_BaseName] || file_name).to_s
-      end
-
-      def title
-        self[:label_prefix] + ' ' + self.label
-      end
-
-      def content_type
-        self[:ows_ContentType]
-      end
-
-      def file_name
-        self[:ows_FileLeafRef]
-      end
-
-      def file_path
-        self[:ows_FileRef]
-      end
-
-      def file_size
-        self[:ows_FileSizeDisplay]
-      end
-
-      def url
-#    self[:ows_EncodedAbsUrl]
-#    'https://www.groupware.kuleuven.be' + URI.escape(self[:ows_ServerUrl], Regexp.new("[^#{URI::PATTERN::UNRESERVED}]"))
-#    'https://www.groupware.kuleuven.be' + URI.escape(self[:ows_ServerUrl])
-        URI.escape(URI.unescape(self[:ows_EncodedAbsUrl]))
-      end
-
-      def relative_path
-        return file_path.gsub(/^sites\/lias\/Gedeelde documenten\//, '') if file_path
-        nil
-      end
-
-      def local_path(sub_dir)
-        return relative_path unless sub_dir
-        sub_dir += '/' unless sub_dir[-1] == '/'
-        return relative_path.gsub(/^#{sub_dir}/, '') if relative_path
-        nil
-      end
-
-      def is_file?
-        return true if [:file, :mfile].include? simple_content_type
-        false
-      end
-
-      def is_described?
-=begin
-    self[:ows_Title1] and
-        (   self[:ows_Creation_x0020_date_x0028_s_x0029_] or
-            self[:ows_Startdate] or
-            self[:ows_Enddate]
-        )
-=end
-        self[:ows_Unit_of_description]
-      end
-
-      def simple_content_type
-        case content_type
-          when /^Archief/i
-            return :archive
-          when /^Bestanddeel \(folder\)/i
-            return :map
-          when /^Bestanddeel of stuk \(document\)/i
-            return :file
-          when /^Meervoudige beschrijving \(folder\)/i
-            return :mmap
-          when /^Meervoudige beschrijving \(document\)/i
-            return :mfile
-          when /^Tussenniveau/i
-            return :map
-          when /^Film/i
-            return :file
-          when /^Object/i
-            return :file
-          when /^Document/i
-            return :file
-          else
-            # type code here
-        end
-        :unknown
-      end
-
-      def content_code
-        case simple_content_type
-          when :archive
-            'a'
-          when :map
-            'm'
-          when :file
-            'f'
-          when :mmap
-            'v'
-          when :mfile
-            '<'
-          when :unknown
-            '-'
-          else
-            ' '
-        end + (is_described? ? '*' : ' ')
-      end
-
-      def ingest_model
-        return self[:ows_Ingestmodel] if self[:ows_Ingestmodel]
-        return self.node.parent.content.ingest_model if node and node.parent and node.parent.content
-        nil
-      end
-
-      def accessright_model
-        return self[:ows_Access_x0020_rights_x0020_model] if self[:ows_Access_x0020_rights_x0020_model]
-        return self.node.parent.content.accessright_model if node and node.parent and node.parent.content
-        nil
-      end
-
-      def to_raw
-        self
-      end
-
-      def to_xml
-
-        xml_doc = Libis::Tools::XmlDocument.new
-
-        xml_doc.root = xml_doc.create_node('record')
-
-        self.each do |label, value|
-
-          unless label == :node
-            #noinspection RubyResolve
-            xml_doc.root << xml_doc.create_text_node(label.to_s, value.to_s)
-          end
-
-        end
-
-        xml_doc
-
-      end
-
-      def self.from_xml(xml_node)
-
-        record = Libis::Tools::SharepointRecord.new
-
-        xml_node.element_children.each do |node|
-          record[node.name.to_sym] = node.content
-        end
-
-        record
-
-      end
-
-      # @param [Libis::Tools::SharepointMapping] mapping
-      def to_dc(mapping)
-
-        return nil unless mapping and mapping.is_a? Hash
-
-        xml_doc = Libis::Tools::XmlDocument.new
-
-        #noinspection RubyStringKeysInHashInspection
-        xml_doc.root = xml_doc.create_node(
-            'record',
-            namespaces: {
-                'dc' => 'http://purl.org/dc/elements/1.1/',
-                'xsi' => 'http://www.w3.org/2001/XMLSchema-instance',
-                'dcterms' => 'http://purl.org/dc/terms/'})
-
-        self.each do |label, value|
-          dc_tag = mapping.dc_tag(label)
-          next unless dc_tag
-          dc_value = (mapping.dc_prefix(label) || '') + value.to_s + (mapping.dc_postfix(label) || '')
-          #noinspection RubyResolve
-          xml_doc.root << xml_doc.create_text_node(dc_tag, dc_value)
-        end
-
-        if xml_doc.xpath('//dc:title').size == 0
-          xml_doc.root << xml_doc.create_text_node('dc:title', self[:ows_BaseName])
-        end
-
-        xml_doc
-
-      end
-
-      # @param [Libis::Tools::SharepointMapping] mapping
-      def to_sql(mapping)
-        sql_fields = []
-        sql_values = []
-
-        self.each do |label, value|
-          db_column = mapping.db_column(label)
-          next unless db_column
-          db_value = mapping.db_value(label, value)
-          next unless db_value and db_value != "''"
-          sql_fields << db_column
-          sql_values << db_value.escape_for_sql
-        end
-
-        sql_fields.each_with_index { |element, index| (index % 10 == 0) && (sql_fields[index] = "\n    " + element)
-        }
-        sql_values.each_with_index { |element, index| (index % 10 == 0) && (sql_values[index] = "\n    " + element)
-        }
-
-        'INSERT INTO @TABLE_NAME@ (' + sql_fields.join(',') + ")\n  VALUES (" + sql_values.join(',') + ');'
-
-      end
-
-      def create_dc(dir, mapping)
-        xml_doc = to_dc mapping
-        dc_file = "#{dir}/dc_#{self[:index].to_s}.xml"
-        xml_doc.save dc_file
-        dc_file
-      end
-
-      def to_s
-        super
-      end
-
-      def print_metadata(f, mapping)
-        f.printf "%6d -------------------------------------------------------------------------\n", self[:index].to_i
-        self.each do |label, value|
-          next if label == :node
-#      next if label == :index
-          name = mapping.fancy_label(label)
-          f.printf " %40s : %s\n", name, value
-        end
-
-      end
-
-    end
-
-  end
-end

data/lib/libis/tools/metadata/var_field.rb

@@ -1,242 +0,0 @@
-# coding: utf-8
-
-require 'libis/tools/assert'
-
-require_relative 'parser/subfield_criteria_parser'
-
-module Libis
-  module Tools
-    module Metadata
-
-      # Helper class implementing a variable field for MARC
-      class VarField
-
-        attr_reader :tag
-        attr_reader :ind1
-        attr_reader :ind2
-        attr_reader :subfield_data
-
-        # Create new variable field with given tag and indicators
-        # @param [String] tag tag
-        # @param [String] ind1 first indicator. nil will be translated into empty string.
-        # @param [String] ind2 second indicator. nil will be translated into empty string.
-        def initialize(tag, ind1, ind2)
-          @tag = tag
-          @ind1 = ind1 || ''
-          @ind2 = ind2 || ''
-          @subfield_data = Hash.new { |h, k| h[k] = Array.new   }
-        end
-
-        # Add subfield to variable field
-        # @param [String] name subfield indicator without '$'
-        # @param [String] value content of the subfield
-        def add_subfield(name, value)
-          @subfield_data[name] << value
-        end
-
-        # dump the contents
-        #
-        # @return [String] debug output to inspect the contents of the VarField
-        def dump
-          output = "#{@tag}:#{@ind1}:#{@ind2}:\n"
-          @subfield_data.each { |s, t| output += "\t#{s}:#{t}\n" }
-          output
-        end
-
-        # dump the contents
-        #
-        # @return [String] debug output to inspect the contents of the VarField - Single line version
-        def dump_line
-          output = "#{@tag}:#{@ind1}:#{@ind2}:"
-          @subfield_data.each { |s, t| output += "$#{s}#{t}" }
-          output
-        end
-
-        # list the subfield codes
-        #
-        # @return [Array] a list of all subfield codes
-        def keys
-          @subfield_data.keys
-        end
-
-        # get the first (or only) subfield value for the given code
-        #
-        # @return [String] the first or only entry of a subfield or nil if not present
-        # @param s [Character] the subfield code
-        def subfield(s)
-          subfield_array(s).first
-        end
-
-        # get a list of all subfield values for a given code
-        #
-        # @return [Array] all the entries of a repeatable subfield
-        # @param s [Character] the subfield code
-        def subfield_array(s)
-          assert(s.is_a?(String) && (s =~ /^[\da-z]$/) == 0, 'method expects a lower case alphanumerical char')
-          @subfield_data.has_key?(s) ? @subfield_data[s].dup : []
-        end
-
-        # get a list of the first subfield values for all the codes in the given string
-        #
-        # @return [Array] list of the first or only entries of all subfield codes in the input string
-        # @param s [String] subfield code specification (see match)
-        #
-        # The subfield codes are cleaned (see criteria_to_array)
-        def subfields(s)
-          assert(s.is_a?(String), 'method expects a string')
-          return [] unless (match_array = match(s))
-          criteria_to_array(match_array.join(' ')).collect { |i| send(:subfield, i) }.flatten.compact
-        end
-
-        # get a list of all the subfield values for all the codes in the given string
-        #
-        # @return [Array] list of the all the entries of all subfield codes in the input string
-        # @param s [String] subfield code criteria (see match)
-        #
-        # The subfield codes are cleaned (see criteria_to_array)
-
-        def subfields_array(s)
-          assert(s.is_a?(String), 'method expects a string')
-          return [] unless (match_array = match(s))
-          criteria_to_array(match_array.join(' ')).collect { |i| send(:subfield_array, i) }.flatten.compact
-        end
-
-        # check if the current VarField matches the given subfield criteria.
-        #
-        # @return [String] The matching part(s) of the criteria or nil if no match
-        # @param criteria [String] subfield criteria: sequence of alternative set of subfield codes that should-shouldn't be present
-        #
-        # The subfield criteria consists of groups of characters. At least one of these groups should match for the test to succeed
-        # Within the group sets of codes may be divided by a hyphen (-). The first set of codes must all be present;
-        # the second set of codes must all <b>not</b> be present. Either set may be empty.
-        #
-        # Examples:
-        #   'ab'      matches '$a...$b...'            => ['ab']
-        #                     '$a...$b...$c...'       => ['ab']
-        #             but not '$a...'                 => nil      # ($b missing)
-        #                     '$b...'                 => nil      # ($a missing)
-        #   'a b'     matches '$a...'                 => ['a']
-        #                     '$b...'                 => ['b']
-        #                     '$a...$b...'            => ['a', 'b']
-        #                     '$a...$b...$c...'       => ['a', 'b']
-        #             but not '$c...'                 => nil      # ($a or $b must be present)
-        #   'abc-d'   matches '$a..,$b...$c...'       => ['abc-d']
-        #                     '$a..,$b...$c...$e...'  => ['abc-d']
-        #             but not '$a...$b...$e...'       => nil      # ($c missing)
-        #                     '$a...$b...$c...$d...'  => nil      # ($d should not be present)
-        #   'a-b b-a' matches '$a...'                 => ['a-b']
-        #                     '$a...$c...'            => ['a-b']
-        #                     '$b...'                 => ['b-a']
-        #                     '$b...$c...'            => ['b-a']
-        #             but not '$a...$b...'            => nil
-        #   'a-b c-d' matches '$a...'                 => ['a-b']
-        #                     '$a...$c...'            => ['a-b', 'c-d']
-        #                     '$a...$b...$c...'       => ['c-d']
-        #                     '$b...$c...'            => ['c-d']
-        #             but not '$a...$b...'            => nil
-        #                     '$c...$d...'            => nil
-        #                     '$b...$c...$d...'       => nil
-        #                     '$a...$b...$c...$d...'  => nil
-        def match(criteria)
-          begin
-            parser = Libis::Tools::Metadata::SubfieldCriteriaParser.new
-            tree = parser.parse(criteria)
-            return [] if tree.is_a? String
-            tree = [tree] unless tree.is_a? Array
-            result = tree.map do |selection|
-              next unless parser.match_selection(selection, keys)
-              parser.selection_to_s(selection)
-            end.compact
-            return nil if result.empty?
-            result
-          rescue Parslet::ParseFailed => failure
-            failure.cause.set_label(criteria)
-            raise failure
-          end
-        end
-
-        private
-
-        # @return [Array] cleaned up version of the input string
-        # @param subfields [String] subfield code specification
-        # cleans the subfield code specification and splits it into an array of characters
-        # Duplicates will be removed from the array and the order will be untouched.
-        def criteria_to_array(subfields)
-
-          # note that we remove the '-xxx' part as it is only required for matching
-          subfields.gsub(/ |-\w*/, '').split('').uniq
-        end
-
-        def sort_helper(x)
-          # make sure that everything below 'A' is higher than 'z'
-          # note that this only works for numbers, but that is fine in our case.
-          x < 'A' ? (x.to_i + 123).chr : x
-        end
-
-        # implementation for methods for retrieving subfield values
-        #
-        # The methods start with a single character: the operation
-        # 'f' for retrieving only the first occurence of the subfield
-        # 'a' for retrieving all the subfield values for each of the given subfields
-        # if omitted, 'f' is assumed
-        #
-        # Then a '_' acts as a subdivider between the operation and the subfield(s). It must always be present, even
-        # if the operation is omitted.
-        #
-        # The last past is a sequence of subfield codes that should be used for selecting the values. The order in which the
-        # subfields are listed is respected in the resulting array of values.
-        #
-        # Examples:
-        #
-        #   t = VarField.new('100', '', '',
-        #                    { 'a' => %w'Name NickName',
-        #                      'b' => %w'LastName MaidenName',
-        #                      'c' => %w'eMail',
-        #                      '1' => %w'Age',
-        #                      '9' => %w'Score'})
-        #
-        #   # >> 100##$aName$aNickName$bLastName$bMaidenName$ceMail$1Age$9Score <<
-        #
-        #   t._1ab => ['Age', 'Name', 'LastName']
-        #   # equivalent to: t.f_1av or t.fields('1ab')
-        #
-        #   t.a_9ab => ['Score', 'Name', 'NickName', 'LastName', 'MaidenName']
-        #   # equivalent to: t.fields_array('9ab')
-        #
-        # Note that it is not possible to use a fieldspec for the sequence of subfield codes. Spaces and '-' are not allowed
-        # in method calls. If you want this, use the #subfield(s) and #subfield(s)_array methods.
-        #
-        def method_missing(name, *args)
-          operation, subfields = name.to_s.split('_')
-          assert(subfields.size > 0, 'need to specify at least one subfield')
-          operation = 'f' if operation.empty?
-          # convert subfield list to fieldspec
-          subfields = subfields.split('').join(' ')
-          case operation
-            when 'f'
-              if subfields.size > 1
-                operation = :subfields
-              else
-                operation = :subfield
-              end
-            when 'a'
-              if subfields.size > 1
-                operation = :subfields_array
-              else
-                operation = :subfield_array
-              end
-            else
-              throw "Unknown method invocation: '#{name}' with: #{args}"
-          end
-          send(operation, subfields)
-        end
-
-        def to_ary
-          nil
-        end
-
-      end
-
-    end
-  end
-end