modsulator 0.0.6

data/lib/modsulator/modsulator.xsd

@@ -0,0 +1,35 @@
+<?xml version="1.0"?>
+<xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema" targetNamespace="http://library.stanford.edu/xmlDocs" xmlns="http://library.stanford.edu/xmlDocs" elementFormDefault="qualified" attributeFormDefault="unqualified">
+  <!-- This XML Schema Definition defines the "xmlDocs" vocabulary that is produced by the MODSulator. -->
+  <!-- The main content of xmlDocs is full MODS 3.5 XML, as defined by the Library of Congress. Import their schema definition. -->
+  <xs:import namespace="http://www.loc.gov/mods/v3" schemaLocation="mods-3-5.xsd"/>
+    
+  <xs:element name="xmlDocs">
+    <xs:complexType>
+      <xs:sequence minOccurs="0" maxOccurs="unbounded">
+        <xs:element name="xmlDoc"/>
+      </xs:sequence>
+      <xs:attributeGroup ref="docsAttributeGroup"/>
+    </xs:complexType>
+  </xs:element>
+
+  <xs:element name="xmlDoc">
+    <xs:complexType>
+      <xs:sequence>
+        <xs:element name="mods"/>
+      </xs:sequence>
+      <xs:attributeGroup ref="docAttributeGroup"/>
+    </xs:complexType>
+  </xs:element>
+
+  <xs:attributeGroup name="docsAttributeGroup">
+    <xs:attribute name="datetime" type="xs:string"/>
+    <xs:attribute name="sourceFile" type="xs:string"/>
+  </xs:attributeGroup>
+
+  <xs:attributeGroup name="docAttributeGroup">
+      <xs:attribute name="id" type="xs:string"/>
+      <xs:attribute name="objectId" type="xs:string"/>
+  </xs:attributeGroup>
+
+</xs:schema>

data/lib/modsulator/modsulator_sheet.rb

@@ -0,0 +1,62 @@
+# File "modsulator_sheet.rb" - a class to load and validate metadata spreadsheets (.xlsx or .csv) for input
+# to Modsulator.
+
+require 'json'
+require 'roo'
+
+# This class provides methods to parse Stanford's MODS spreadsheets into either an array of hashes, or a JSON string.
+class ModsulatorSheet
+  attr_reader :file, :filename
+
+  # Creates a new ModsulatorSheet. When called with temporary files, the filename must be specified separately, hence the
+  # second argument.
+  # @param [File]    file        The input spreadsheet
+  # @param [String]  filename    The filename of the input spreadsheet.
+  def initialize(file, filename)
+    @file = file
+    @filename = filename
+  end
+
+
+  # Loads the input spreadsheet into an array of hashes. This spreadsheet should conform to the Stanford MODS template format,
+  # which has three header rows. The first row is a kind of "super header", the second row is an intermediate header and the
+  # third row is the header row that names the fields. The data rows are in the fourth row onwards.
+  #
+  # @return [Array<Hash>]      An array with one entry per data row in the spreadsheet. Each entry is a hash, indexed by
+  #                            the spreadsheet headers.
+  def rows
+    # Parse the spreadsheet, automatically finding the header row by looking for "druid" and "sourceId" and leave the
+    # header row itself out of the resulting array. Everything preceding the header row is discarded. Would like to use
+    # clean: true here, but the latest release of Roo 1.13.2 crashes. 2.0.0beta1 seems to work though.
+    @rows ||= spreadsheet.parse(header_search: ['druid', 'sourceId']).drop(1)
+  end
+
+
+  # Opens a spreadsheet based on its filename extension.
+  #
+  # @return [Roo::CSV, Roo::Excel, Roo::Excelx]   A Roo object, whose type depends on the extension of the given filename.
+  def spreadsheet
+    @spreadsheet ||= case File.extname(@filename)
+                     when '.csv' then Roo::Spreadsheet.open(@file, extension: :csv)
+                     when '.xls' then Roo::Spreadsheet.open(@file, extension: :xls)
+                     when '.xlsx' then Roo::Spreadsheet.open(@file, extension: :xlsx)
+                     else fail "Unknown file type: #{@filename}"
+    end
+  end
+
+
+  # Get the headers used in the spreadsheet
+  def headers
+    rows.first.keys
+  end
+
+
+  # Convert the loaded spreadsheet to a JSON string.
+  # @return [String]  A JSON string.
+  def to_json
+    json_hash = {}
+    json_hash['filename'] = File.basename(filename)
+    json_hash['rows'] = rows
+    json_hash.to_json
+  end
+end

data/lib/modsulator/modsulator_template.xml

@@ -0,0 +1,198 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<mods xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://www.loc.gov/mods/v3" version="3.5" xsi:schemaLocation="http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-5.xsd">
+  <titleInfo authority="[[ti1:authority]]" valueURI="[[ti1:valueURI]]">
+    <nonSort>[[ti1:nonSort]]</nonSort>
+    <title>[[ti1:title]]</title>
+    <subTitle>[[ti1:subTitle]]</subTitle> 
+    <partNumber>[[ti1:partNumber]]</partNumber> 
+    <partName>[[ti1:partName]]</partName>
+  </titleInfo>
+  <titleInfo type="[[ti2:type]]" authority="[[ti2:authority]]" valueURI="[[ti2:valueURI]]">
+    <nonSort>[[ti2:nonSort]]</nonSort>
+    <title>[[ti2:title]]</title>
+    <subTitle>[[ti2:subTitle]]</subTitle> 
+    <partNumber>[[ti2:partNumber]]</partNumber> 
+    <partName>[[ti2:partName]]</partName>
+  </titleInfo>
+  <titleInfo type="[[ti3:type]]" authority="[[ti3:authority]]" valueURI="[[ti3:valueURI]]">
+    <nonSort>[[ti3:nonSort]]</nonSort>
+    <title>[[ti3:title]]</title>
+    <subTitle>[[ti3:subTitle]]</subTitle> 
+    <partNumber>[[ti3:partNumber]]</partNumber> 
+    <partName>[[ti3:partName]]</partName>
+  </titleInfo>
+  <name type="[[na1:type]]" authority="[[na1:authority]]" valueURI="[[na1:valueURI]]">
+    <namePart>[[na1:namePart]]</namePart>
+    <role>
+      <roleTerm type="code" authority="[[ro1:authority]]" valueURI="[[ro1:valueURI]]">[[ro1:roleCode]]</roleTerm>
+      <roleTerm type="text" authority="[[ro1:authority]]" valueURI="[[ro1:valueURI]]">[[ro1:roleText]]</roleTerm>
+    </role>
+  </name>
+  <name type="[[na2:type]]" authority="[[na2:authority]]" valueURI="[[na2:valueURI]]">
+    <namePart>[[na2:namePart]]</namePart>
+    <role>
+      <roleTerm type="code" authority="[[ro2:authority]]" valueURI="[[ro2:valueURI]]">[[ro2:roleCode]]</roleTerm>
+      <roleTerm type="text" authority="[[ro2:authority]]" valueURI="[[ro2:valueURI]]">[[ro2:roleText]]</roleTerm>
+    </role>
+  </name>
+  <name type="[[na3:type]]" authority="[[na3:authority]]" valueURI="[[na3:valueURI]]">
+    <namePart>[[na3:namePart]]</namePart>
+    <role>
+      <roleTerm type="code" authority="[[ro3:authority]]" valueURI="[[ro3:valueURI]]">[[ro3:roleCode]]</roleTerm>
+      <roleTerm type="text" authority="[[ro3:authority]]" valueURI="[[ro3:valueURI]]">[[ro3:roleText]]</roleTerm>
+    </role>
+  </name>
+  <name type="[[na4:type]]" authority="[[na4:authority]]" valueURI="[[na4:valueURI]]">
+    <namePart>[[na4:namePart]]</namePart>
+    <role>
+      <roleTerm type="code" authority="[[ro4:authority]]" valueURI="[[ro4:valueURI]]">[[ro4:roleCode]]</roleTerm>
+      <roleTerm type="text" authority="[[ro4:authority]]" valueURI="[[ro4:valueURI]]">[[ro4:roleText]]</roleTerm>
+    </role>
+  </name>
+  <name type="[[na5:type]]" authority="[[na5:authority]]" valueURI="[[na5:valueURI]]">
+    <namePart>[[na5:namePart]]</namePart>
+    <role>
+      <roleTerm type="code" authority="[[ro5:authority]]" valueURI="[[ro5:valueURI]]">[[ro5:roleCode]]</roleTerm>
+      <roleTerm type="text" authority="[[ro5:authority]]" valueURI="[[ro5:valueURI]]">[[ro5:roleText]]</roleTerm>
+    </role>
+  </name>
+  <typeOfResource manuscript="[[ty1:manuscript]]">[[ty1:typeOfResource]]</typeOfResource>
+  <typeOfResource>[[ty2:typeOfResource]]</typeOfResource>
+  <typeOfResource>[[ty3:typeOfResource]]</typeOfResource>
+  <genre type="[[ge1:type]]" authority="[[ge1:authority]]" valueURI="[[ge1:valueURI]]">[[ge1:genre]]</genre>
+  <genre type="[[ge2:type]]" authority="[[ge2:authority]]" valueURI="[[ge2:valueURI]]">[[ge2:genre]]</genre>
+  <genre type="[[ge3:type]]" authority="[[ge3:authority]]" valueURI="[[ge3:valueURI]]">[[ge3:genre]]</genre>
+  <originInfo>
+    <place>
+      <placeTerm type="code" authority="[[pl:authority]]" valueURI="[[pl:valueURI]]">[[pl:placeCode]]</placeTerm>
+      <placeTerm type="text" authority="[[pl:authority]]" valueURI="[[pl:valueURI]]">[[pl:placeText]]</placeTerm>
+    </place>
+    <publisher>[[or:publisher]]</publisher>
+    <dateCreated keyDate="yes" encoding="[[dt:encoding]]" qualifier="[[dt:qualifier]]" point="start">[[dt:dateCreated]]</dateCreated>
+    <dateCreated keyDate="yes" encoding="[[dt:encoding]]" qualifier="[[dt:qualifier]]" point="end">[[dt:dateCreated2]]</dateCreated>
+    <dateIssued keyDate="yes" encoding="[[dt:encoding]]" qualifier="[[dt:qualifier]]" point="start">[[dt:dateIssued]]</dateIssued>
+    <dateIssued keyDate="yes" encoding="[[dt:encoding]]" qualifier="[[dt:qualifier]]" point="end">[[dt:dateIssued2]]</dateIssued>
+  </originInfo>
+  <language>
+    <languageTerm authority="[[la1:authority]]" valueURI="[[la1:valueURI]]" type="code">[[la1:code]]</languageTerm>
+    <languageTerm authority="[[la1:authority]]" valueURI="[[la1:valueURI]]" type="text">[[la1:text]]</languageTerm>
+  </language>
+  <language>
+    <languageTerm authority="[[la2:authority]]" valueURI="[[la2:valueURI]]" type="code">[[la2:code]]</languageTerm>
+    <languageTerm authority="[[la2:authority]]" valueURI="[[la2:valueURI]]" type="text">[[la2:text]]</languageTerm>
+  </language>
+  <language>
+    <languageTerm authority="[[la3:authority]]" valueURI="[[la3:valueURI]]" type="code">[[la3:code]]</languageTerm>
+    <languageTerm authority="[[la3:authority]]" valueURI="[[la3:valueURI]]" type="text">[[la3:text]]</languageTerm>
+  </language>
+  <physicalDescription>
+    <form>[[ph1:form]]</form>
+    <extent>[[ph1:extent]]</extent>
+    <digitalOrigin>[[ph1:digitalOrigin]]</digitalOrigin>
+    <note displayLabel="[[ph1:displayLabel]]">[[ph1:note]]</note>
+  </physicalDescription>
+  <abstract displayLabel="[[ab:displayLabel]]">[[ab:abstract]]</abstract>
+  <tableOfContents displayLabel="[[tc:displayLabel]]">[[tc:tableOfContents]]</tableOfContents>
+  <note type="[[no1:type]]" displayLabel="[[no1:displayLabel]]">[[no1:note]]</note>
+  <note type="[[no2:type]]" displayLabel="[[no2:displayLabel]]">[[no2:note]]</note>
+  <note type="[[no3:type]]" displayLabel="[[no3:displayLabel]]">[[no3:note]]</note>
+  <note type="[[no4:type]]" displayLabel="[[no4:displayLabel]]">[[no4:note]]</note>
+  <note type="[[no5:type]]" displayLabel="[[no5:displayLabel]]">[[no5:note]]</note>
+  <subject authority="[[sn1:authority]]">
+    <name type="[[sn1:p1:nameType]]" authority="[[sn1:p1:authority]]" valueURI="[[sn1:p1:valueURI]]">
+      <namePart>[[sn1:p1:name]]</namePart>
+    </name>
+    <titleInfo>
+       <title>[[sn1:p1:title]]</title>
+    </titleInfo>
+    <[[sn1:p2:type]] authority="[[sn1:p2:authority]]" valueURI="[[sn1:p2:valueURI]]">[[sn1:p2:value]]</[[sn1:p2:type]]>
+    <[[sn1:p3:type]] authority="[[sn1:p3:authority]]" valueURI="[[sn1:p3:valueURI]]">[[sn1:p3:value]]</[[sn1:p3:type]]>
+  </subject>
+  <subject authority="[[sn2:authority]]">
+    <name type="[[sn2:p1:nameType]]" authority="[[sn2:p1:authority]]" valueURI="[[sn2:p1:valueURI]]">
+      <namePart>[[sn2:p1:name]]</namePart>
+    </name>
+    <titleInfo>
+       <title>[[sn2:p1:title]]</title>
+    </titleInfo>
+    <[[sn2:p2:type]] authority="[[sn2:p2:authority]]" valueURI="[[sn2:p2:valueURI]]">[[sn2:p2:value]]</[[sn2:p2:type]]>
+    <[[sn2:p3:type]] authority="[[sn2:p3:authority]]" valueURI="[[sn2:p3:valueURI]]">[[sn2:p3:value]]</[[sn2:p3:type]]>
+  </subject>
+  <subject authority="[[sn3:authority]]">
+    <name type="[[sn3:p1:nameType]]" authority="[[sn3:p1:authority]]" valueURI="[[sn3:p1:valueURI]]">
+      <namePart>[[sn3:p1:name]]</namePart>
+    </name>
+    <titleInfo>
+       <title>[[sn3:p1:title]]</title>
+    </titleInfo>
+    <[[sn3:p2:type]] authority="[[sn3:p2:authority]]" valueURI="[[sn3:p2:valueURI]]">[[sn3:p2:value]]</[[sn3:p2:type]]>
+    <[[sn3:p3:type]] authority="[[sn3:p3:authority]]" valueURI="[[sn3:p3:valueURI]]">[[sn3:p3:value]]</[[sn3:p3:type]]>
+  </subject>
+  <subject authority="[[sn4:authority]]">
+    <name type="[[sn4:p1:nameType]]" authority="[[sn4:p1:authority]]" valueURI="[[sn4:p1:valueURI]]">
+      <namePart>[[sn4:p1:name]]</namePart>
+    </name>
+    <titleInfo>
+       <title>[[sn4:p1:title]]</title>
+    </titleInfo>
+    <[[sn4:p2:type]] authority="[[sn4:p2:authority]]" valueURI="[[sn4:p2:valueURI]]">[[sn4:p2:value]]</[[sn4:p2:type]]>
+    <[[sn4:p3:type]] authority="[[sn4:p3:authority]]" valueURI="[[sn4:p3:valueURI]]">[[sn4:p3:value]]</[[sn4:p3:type]]>
+  </subject>
+  <subject authority="[[sn5:authority]]">
+    <name type="[[sn5:p1:nameType]]" authority="[[sn5:p1:authority]]" valueURI="[[sn5:p1:valueURI]]">
+      <namePart>[[sn5:p1:name]]</namePart>
+    </name>
+    <titleInfo>
+       <title>[[sn5:p1:title]]</title>
+    </titleInfo>
+    <[[sn5:p2:type]] authority="[[sn5:p2:authority]]" valueURI="[[sn5:p2:valueURI]]">[[sn5:p2:value]]</[[sn5:p2:type]]>
+    <[[sn5:p3:type]] authority="[[sn5:p3:authority]]" valueURI="[[sn5:p3:valueURI]]">[[sn5:p3:value]]</[[sn5:p3:type]]>
+  </subject>
+  <subject authority="[[su1:authority]]">
+    <[[su1:p1:type]] authority="[[su1:p1:authority]]" valueURI="[[su1:p1:valueURI]]">[[su1:p1:value]]</[[su1:p1:type]]>
+    <[[su1:p2:type]] authority="[[su1:p2:authority]]" valueURI="[[su1:p2:valueURI]]">[[su1:p2:value]]</[[su1:p2:type]]>
+    <[[su1:p3:type]] authority="[[su1:p3:authority]]" valueURI="[[su1:p3:valueURI]]">[[su1:p3:value]]</[[su1:p3:type]]>
+  </subject>
+  <subject authority="[[su2:authority]]">
+    <[[su2:p1:type]] authority="[[su2:p1:authority]]" valueURI="[[su2:p1:valueURI]]">[[su2:p1:value]]</[[su2:p1:type]]>
+    <[[su2:p2:type]] authority="[[su2:p2:authority]]" valueURI="[[su2:p2:valueURI]]">[[su2:p2:value]]</[[su2:p2:type]]>
+    <[[su2:p3:type]] authority="[[su2:p3:authority]]" valueURI="[[su2:p3:valueURI]]">[[su2:p3:value]]</[[su2:p3:type]]>
+  </subject>
+  <subject authority="[[su3:authority]]">
+    <[[su3:p1:type]] authority="[[su3:p1:authority]]" valueURI="[[su3:p1:valueURI]]">[[su3:p1:value]]</[[su3:p1:type]]>
+    <[[su3:p2:type]] authority="[[su3:p2:authority]]" valueURI="[[su3:p2:valueURI]]">[[su3:p2:value]]</[[su3:p2:type]]>
+    <[[su3:p3:type]] authority="[[su3:p3:authority]]" valueURI="[[su3:p3:valueURI]]">[[su3:p3:value]]</[[su3:p3:type]]>
+  </subject>
+  <subject authority="[[su4:authority]]">
+    <[[su4:p1:type]] authority="[[su4:p1:authority]]" valueURI="[[su4:p1:valueURI]]">[[su4:p1:value]]</[[su4:p1:type]]>
+    <[[su4:p2:type]] authority="[[su4:p2:authority]]" valueURI="[[su4:p2:valueURI]]">[[su4:p2:value]]</[[su4:p2:type]]>
+    <[[su4:p3:type]] authority="[[su4:p3:authority]]" valueURI="[[su4:p3:valueURI]]">[[su4:p3:value]]</[[su4:p3:type]]>
+  </subject>
+  <subject authority="[[su5:authority]]">
+    <[[su5:p1:type]] authority="[[su5:p1:authority]]" valueURI="[[su5:p1:valueURI]]">[[su5:p1:value]]</[[su5:p1:type]]>
+    <[[su5:p2:type]] authority="[[su5:p2:authority]]" valueURI="[[su5:p2:valueURI]]">[[su5:p2:value]]</[[su5:p2:type]]>
+    <[[su5:p3:type]] authority="[[su5:p3:authority]]" valueURI="[[su5:p3:valueURI]]">[[su5:p3:value]]</[[su5:p3:type]]>
+  </subject>
+  <subject>
+    <cartographics>
+      <scale>[[sc1:scale]]</scale>
+      <projection>[[sc1:projection]]</projection>
+      <coordinates>[[sc1:coordinates]]</coordinates>
+    </cartographics>
+  </subject>
+  <identifier type="[[id1:type]]" displayLabel="[[id1:displayLabel]]">[[id1:identifier]]</identifier>
+  <identifier type="[[id2:type]]" displayLabel="[[id2:displayLabel]]">[[id2:identifier]]</identifier>
+  <identifier type="[[id3:type]]" displayLabel="[[id3:displayLabel]]">[[id3:identifier]]</identifier>
+  <identifier type="[[id4:type]]" displayLabel="[[id4:displayLabel]]">[[id4:identifier]]</identifier>
+  <identifier type="[[id5:type]]" displayLabel="[[id5:displayLabel]]">[[id5:identifier]]</identifier>
+  <location>
+    <physicalLocation type="repository" authority="[[lo:authority]]" valueURI="[[lo:valueURI]]">[[lo:repository]]</physicalLocation>
+    <shelfLocator>[[lo:callNumber]]</shelfLocator>
+  </location>
+  <relatedItem type="[[ri1:type]]">
+    <titleInfo>
+      <title>[[ri1:title]]</title>
+    </titleInfo>
+    <url>[[ri1:url]]</url>
+  </relatedItem>
+</mods>

data/lib/modsulator/normalizer.rb

@@ -0,0 +1,218 @@
+# File "normalizer.rb" - defines a class for normalizing MODS XML according to the Stanford guidelines.
+
+require 'nokogiri'
+
+# This class provides methods to normalize MODS XML according to the Stanford guidelines.
+# @see https://consul.stanford.edu/display/chimera/MODS+validation+and+normalization Requirements (Stanford Consul page - requires login)
+class Normalizer
+  # Linefeed character entity reference
+  LINEFEED = '
'
+
+  # Checks if a node has attributes that we make exeptions for. There are two such exceptions.
+  #
+  # * A "collection" attribute with the value "yes" <em>on a typeOfResource tag</em>.
+  # * A "manuscript" attribute with the value "yes" <em>on a typeOfResource tag</em>.
+  #
+  # Nodes that fall under any of these exceptions should not be deleted, even if they have no content.
+  #
+  # @param  [Nokogiri::XML::Element]   node    An XML node.
+  # @return [Boolean]                  true if the node contains any of the exceptional attributes, false otherwise.
+  def exceptional?(node)
+    return false unless node != nil
+
+    tag = node.name
+    attributes = node.attributes
+
+    return false if(attributes.empty?)
+
+    attributes.each do |key, value|
+      if(tag == 'typeOfResource')  # Note that according to the MODS schema, any other value than 'yes' for these attributes is invalid
+        if((key == 'collection' && value.to_s.downcase == 'yes') ||
+           (key == 'manuscript' && value.to_s.downcase == 'yes'))
+          return true
+        end
+      end
+    end
+    return false
+  end
+
+
+  # Recursive helper method for {Normalizer#clean_linefeeds} to do string substitution.
+  #
+  # @param [Nokogiri::XML::Element]   node   An XML node
+  # @return [String]                  A string composed of the entire contents of the given node, with substitutions made as described for {#clean_linefeeds}.
+  def substitute_linefeeds(node)
+    new_text = String.new
+
+    # If we substitute in '&#10;' by itself, Nokogiri interprets that and then prints '&amp;#10;' when printing the document later. This
+    # is an ugly way to add linefeed characters in a way that we at least get well-formatted output in the end.
+    if(node.text?)
+      new_text = node.content.gsub(/\r\n/, Nokogiri::HTML(LINEFEED).text).gsub(/\n/, Nokogiri::HTML(LINEFEED).text).gsub(/\r/, Nokogiri::HTML(LINEFEED).text).gsub('\\n', Nokogiri::HTML(LINEFEED).text)
+    else
+      if(node.node_name == 'br')
+        new_text += Nokogiri::HTML(LINEFEED).text
+      elsif(node.node_name == 'p')
+        new_text += Nokogiri::HTML(LINEFEED).text + Nokogiri::HTML(LINEFEED).text
+      end
+
+      node.children.each do |c|
+        new_text += substitute_linefeeds(c)
+      end
+    end
+    return new_text
+  end
+
+
+  # Given the root of an XML document, replaces linefeed characters inside <tableOfContents>, <abstract> and <note> XML node by &#10;
+  # \n, \r, <br> and <br/> are all replaced by a single &#10;
+  # <p> is replaced by two &#10;
+  # </p> is removed
+  # \r\n is replaced by &#10;
+  # Any tags not listed above are removed. MODS 3.5 does not allow for anything other than text inside these three nodes.
+  #
+  # @param   [Nokogiri::XML::Element]    node  The root node of an XML document
+  # @return  [Void]                      This method doesn't return anything, but introduces UTF-8 linefeed characters in place, as described above.
+  def clean_linefeeds(node)
+    node_list = []
+    if(node.namespace.nil?)
+      node_list = node.xpath('//abstract | //tableOfContents | //note')
+    else
+      node_list = node.xpath('//ns:abstract | //ns:tableOfContents | //ns:note', 'ns' => node.namespace.href)
+    end
+
+    node_list.each do |current_node|
+      new_text = substitute_linefeeds(current_node)
+      current_node.children.remove
+      current_node.content = new_text
+    end
+  end
+
+
+  # Cleans up the text of a node:
+  #
+  # * Removes extra whitespace at the beginning and end.
+  # * Removes any consecutive whitespace within the string.
+  #
+  # @param [String]   s   The text of an XML node.
+  # @return [String]  The cleaned string, as described. Returns nil if the input is nil, or if the input is an empty string.
+  def clean_text(s)
+    return nil unless s != nil && s != ''
+    return s.gsub!(/\s+/, ' ').strip!
+  end
+
+
+  # Removes empty attributes from a given node.
+  #
+  # @param [Nokogiri::XML::Element]   node An XML node.
+  # @return [Void]                    This method doesn't return anything, but modifies the XML tree starting at the given node.
+  def remove_empty_attributes(node)
+    children = node.children
+    attributes = node.attributes
+
+    attributes.each do |key, value|
+      node.remove_attribute(key) if(value.to_s.strip.empty?)
+    end
+
+    children.each do |c|
+      remove_empty_attributes(c)
+    end
+  end
+
+
+  # Removes empty nodes from an XML tree. See {#exceptional?} for nodes that are kept even if empty.
+  #
+  # @param  [Nokogiri::XML::Element]   node An XML node.
+  # @return [Void]                     This method doesn't return anything, but modifies the XML tree starting at the given node.
+  def remove_empty_nodes(node)
+    children = node.children
+
+    if(node.text?)
+      if(node.to_s.strip.empty?)
+        node.remove
+      else
+        return
+      end
+    elsif(children.length > 0)
+      children.each do |c|
+        remove_empty_nodes(c)
+      end
+    end
+
+    if(!exceptional?(node) && (node.children.length == 0))
+      node.remove
+    end
+  end
+
+
+  # Removes leading and trailing spaces from a node.
+  #
+  # @param  [Nokogiri::XML::Element]  node An XML node.
+  # @return [Void]                    This method doesn't return anything, but modifies the entire XML tree starting at the
+  #                                   the given node, removing leading and trailing spaces from all text. If the input is nil,
+  #                                   an exception will be raised.
+  def trim_text(node)
+    children = node.children
+
+    if(node.text?)
+      node.parent.content = node.text.strip
+    else
+      children.each do |c|
+        trim_text(c)
+      end
+    end
+  end
+
+
+  # Removes the point attribute from single <dateCreated> and <dateIssued> elements.
+  #
+  # @param [Nokogiri::XML::Element]   root  The root of a MODS XML document.
+  # @return [Void]                    The given document is modified in place.
+  def clean_date_attributes(root)
+    
+    # Find all the <dateCreated> and <dateIssued> elements that are NOT immediately followed by another element with the same name
+    root.xpath('//mods:originInfo/mods:dateCreated[1][not(following-sibling::*[1][self::mods:dateCreated])] | //mods:originInfo/mods:dateIssued[1][not(following-sibling::*[1][self::mods:dateIssued])]', 'mods' => 'http://www.loc.gov/mods/v3').each do |current_element|
+      attributes = current_element.attributes
+      if(attributes.key?('point'))
+        current_element.remove_attribute('point')
+      end
+    end
+  end
+
+
+  # Sometimes there are spurious decimal digits within the date fields. This method removes any trailing decimal points within
+  # <dateCreated> and <dateIssued>.
+  #
+  # @param [Nokogiri::XML::Element]   root  The root of a MODS XML document.
+  # @return [Void]                    The given document is modified in place.
+  def clean_date_values(root)
+    root.xpath('//mods:dateCreated | //mods:dateIssued', 'mods' => 'http://www.loc.gov/mods/v3').each do |current_node|
+      current_node.content = current_node.content.sub(/(.*)\.\d+$/, '\1')
+    end
+  end
+
+
+  # Normalizes the given XML document according to the Stanford guidelines.
+  #
+  # @param  [Nokogiri::XML::Element]  root  The root of a MODS XML document.
+  # @return [Void]                    The given document is modified in place.
+  def normalize_document(root)
+    clean_linefeeds(root)   # Do this before deleting <br> and <p> with remove_empty_nodes()
+    remove_empty_attributes(root)
+    remove_empty_nodes(root)
+    trim_text(root)
+    clean_date_attributes(root)
+    clean_date_values(root)
+  end
+
+
+  # Normalizes the given XML document string according to the Stanford guidelines.
+  #
+  # @param  [String]   xml_string    An XML document
+  # @return [String]                 The XML string, with normalizations applied.
+  def normalize_xml_string(xml_string)
+    doc = Nokogiri::XML(xml_string)
+    normalize_document(doc.root)
+    doc.to_s
+  end
+end
+