commonmeta-ruby 3.2.6 → 3.2.7

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 575100d8bef2d51a19423453d3a5c3d7129903d5d7d23da7e7ac3c6c24ceb52b
-  data.tar.gz: 9146bae365bf7f79c1f3ce05e781942749b29257433ed1d37196b3d0d1d2bf21
+  metadata.gz: 7a50ad8ff25b9ff753b60cc9a34f578ae064cedc2417a5db146898e8202f8dc3
+  data.tar.gz: cc7f32e49a6d0621a30884a8226a9dda04cd5b13ed6545aefc28fd8f19386acb
 SHA512:
-  metadata.gz: 82f95b057c1b28d1dd344f31207fc43d43f6db65705bbdc3609b02c90b9a4ed8ffd2d6a3538f090589c615e9207ad78046625344b99a1e592e9a4a624f414e4e
-  data.tar.gz: a6ff2bbe08b29b2641f35520e8fc46c8827f502e747b03b53f100235e7c0d639b8de4729ecfb6c7e41d1eee69e23fd9a6c0479e86471824797fe7bda1c78cc85
+  metadata.gz: 16d052d4e0dda3aed49235f43914f3d88e46627741500edb987cbf6dad00091234aa2304541f8ba6d713b05c9b158717d2c5632aa024e60dc694f7126752dda1
+  data.tar.gz: d6a7044f3b3722dc71f22f8c98e12d3f5c5e79b82bdf1aff745ccb74ecbd4febd2d53926924b635b97334c30df233dd793802dabfe0ea038f387488acf0ae4ef

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    commonmeta-ruby (3.2.6)
+    commonmeta-ruby (3.2.7)
       activesupport (>= 4.2.5, < 8.0)
       addressable (~> 2.8.1, < 2.8.2)
       base32-url (>= 0.5.0, < 1)
@@ -10,6 +10,7 @@ PATH
       citeproc-ruby (~> 2.0)
       csl-styles (~> 2.0)
       edtf (~> 3.0, >= 3.0.4)
+      feedparser (~> 2.2)
       gender_detector (~> 2.0)
       http (~> 5.1, >= 5.1.1)
       json-ld-preloaded (~> 3.2, >= 3.2.2)
@@ -57,7 +58,7 @@ GEM
     docile (1.4.0)
     domain_name (0.5.20190701)
       unf (>= 0.0.5, < 1.0.0)
-    ebnf (2.3.3)
+    ebnf (2.3.4)
       htmlentities (~> 4.3)
       rdf (~> 3.2)
       scanf (~> 1.0)
@@ -65,6 +66,9 @@ GEM
       unicode-types (~> 1.8)
     edtf (3.1.1)
       activesupport (>= 3.0, < 8.0)
+    feedparser (2.2.0)
+      logutils (>= 0.6.1)
+      textutils (>= 1.0.0)
     ffi (1.15.5)
     ffi-compiler (1.0.1)
       ffi (>= 1.0.0)
@@ -86,6 +90,7 @@ GEM
     http-form_data (2.3.0)
     i18n (1.14.1)
       concurrent-ruby (~> 1.0)
+    iniparser (1.0.1)
     json (2.6.3)
     json-canonicalization (0.3.2)
     json-ld (3.2.5)
@@ -110,6 +115,7 @@ GEM
     llhttp-ffi (0.4.0)
       ffi-compiler (~> 1.0)
       rake (~> 13.0)
+    logutils (0.6.1)
     loofah (2.21.3)
       crass (~> 1.0.2)
       nokogiri (>= 1.12.0)
@@ -129,6 +135,8 @@ GEM
       addressable (>= 2.4.0)
       nokogiri (>= 1.8.0)
       public_suffix (>= 4.0.0, < 5)
+    props (1.2.0)
+      iniparser (>= 0.1.0)
     public_suffix (4.0.7)
     racc (1.7.0)
     rack (3.0.7)
@@ -205,6 +213,7 @@ GEM
       rubocop-capybara (~> 2.17)
       rubocop-factory_bot (~> 2.22)
     ruby-progressbar (1.13.0)
+    rubyzip (2.3.2)
     scanf (1.0.0)
     simplecov (0.22.0)
       docile (~> 1.1)
@@ -218,6 +227,11 @@ GEM
       matrix (~> 0.4)
       rdf (~> 3.2)
     temple (0.10.2)
+    textutils (1.4.0)
+      activesupport
+      logutils (>= 0.6.1)
+      props (>= 1.1.2)
+      rubyzip (>= 1.0.0)
     thor (1.2.2)
     tilt (2.2.0)
     tzinfo (2.0.6)

data/commonmeta.gemspec

@@ -26,6 +26,7 @@ Gem::Specification.new do |s|
   s.add_dependency 'citeproc-ruby', '~> 2.0'
   s.add_dependency 'csl-styles', '~> 2.0'
   s.add_dependency 'edtf', '~> 3.0', '>= 3.0.4'
+  s.add_dependency 'feedparser', '~> 2.2'
   s.add_dependency 'gender_detector', '~> 2.0'
   s.add_dependency 'http', '~> 5.1', '>= 5.1.1'
   s.add_dependency 'json-ld-preloaded', '~> 3.2', '>= 3.2.2'

data/lib/commonmeta/author_utils.rb

@@ -24,6 +24,8 @@ module Commonmeta
       family_name = parse_attributes(author.fetch('familyName', nil)) ||
                     parse_attributes(author.fetch('family', nil))
 
+      name = cleanup_author(name)
+
       # parse author identifier
       id = parse_attributes(author.fetch('id', nil), first: true) ||
            parse_attributes(author.fetch('identifier', nil), first: true) ||
@@ -62,8 +64,6 @@ module Commonmeta
       # parse author contributor role
       contributor_type = parse_attributes(author.fetch('contributorType', nil))
 
-      name = cleanup_author(name)
-
       # split name for type Person into given/family name if not already provided
       if type == 'Person' && given_name.blank? && family_name.blank?
         Namae.options[:include_particle_in_family] = true
@@ -98,6 +98,19 @@ module Commonmeta
         author = author.gsub(/[[:space:]]([A-Z]\.)?(-?[A-Z]\.)$/, ', \1\2')
       end
 
+      # strip suffixes, e.g. "John Smith, MD" as the named parser doesn't handle them
+      author = author.split(',').first if %w[MD PhD].include? author.split(', ').last
+
+      # remove email addresses
+      email = validate_email(author)
+      author = author.gsub(email, '') if email.present?
+
+      # strip spaces at the beginning and end of string
+      author = author.strip
+
+      # remove parentheses around names
+      author = author[1..-2] if author[0] == '(' && author[-1] == ')'
+
       # remove spaces around hyphens
       author = author.gsub(' - ', '-')
 
@@ -113,12 +126,16 @@ module Commonmeta
       # check if a name has only one word, e.g. "FamousOrganization"
       return false if name.to_s.split(' ').size == 1
 
+      # check for suffixes, e.g. "John Smith, MD"
+      return true if %w[MD PhD].include? name.split(', ').last
+
       # check of name can be parsed into given/family name
       Namae.options[:include_particle_in_family] = true
       names = Namae.parse(name)
+
       parsed_name = names.first
       return true if parsed_name && parsed_name.given
-
+      
       false
     end
 

data/lib/commonmeta/cli.rb

@@ -82,8 +82,8 @@ module Commonmeta
 
     desc "", "json_feed"
 
-    def json_feed
-      puts get_json_feed
+    def json_feed_unregistered
+      puts get_json_feed_unregistered
     end
 
     default_task :convert

data/lib/commonmeta/crossref_utils.rb

@@ -61,7 +61,6 @@ module Commonmeta
           insert_crossref_publication_date(xml)
           insert_crossref_abstract(xml)
           insert_crossref_issn(xml)
-          insert_crossref_alternate_identifiers(xml)
           insert_crossref_access_indicators(xml)
           insert_doi_data(xml)
           insert_citation_list(xml)
@@ -78,8 +77,8 @@ module Commonmeta
         insert_crossref_titles(xml)
         insert_posted_date(xml)
         insert_institution(xml)
+        insert_publisher_item(xml)
         insert_crossref_abstract(xml)
-        insert_crossref_alternate_identifiers(xml)
         insert_crossref_access_indicators(xml)
         insert_doi_data(xml)
         insert_citation_list(xml)
@@ -132,13 +131,14 @@ module Commonmeta
       xml.citation_list do
         Array.wrap(references).each do |ref|
           xml.citation('key' => ref['key']) do
-            xml.journal_article(ref['journal_title'])
-            xml.author(ref['author'])
-            xml.volume(ref['volume'])
-            xml.first_page(ref['first_page'])
-            xml.cYear(ref['cYear'])
-            xml.article_title(ref['article_title'])
+            xml.journal_article(ref['journal_title']) if ref['journal_title'].present?
+            xml.author(ref['author']) if ref['author'].present?
+            xml.volume(ref['volume']) if ref['volume'].present?
+            xml.first_page(ref['first_page']) if ref['first_page'].present?
+            xml.cYear(ref['cYear']) if ref['cYear'].present?
+            xml.article_title(ref['article_title']) if ref['article_title'].present?
             xml.doi(ref['doi']) if ref['doi'].present?
+            xml.unstructured_citation(ref['url']) if ref['url'].present?
           end
         end
       end
@@ -159,16 +159,6 @@ module Commonmeta
     #     'resourceTypeGeneral' => types["resourceTypeGeneral"] || Metadata::SO_TO_DC_TRANSLATIONS[types["schemaOrg"]] || "Other")
     # end
 
-    def insert_crossref_alternate_identifiers(xml)
-      alternate_identifier = Array.wrap(alternate_identifiers).reject do |r|
-        %w[DOI, URL].include?(r['alternate_identifier_type'])
-      end.first
-      return xml if alternate_identifier.blank?
-
-      xml.item_number(alternate_identifier['alternateIdentifier'],
-                      'item_number_type' => alternate_identifier['alternateIdentifierType'])
-    end
-
     def insert_crossref_access_indicators(xml)
       return xml if license.blank?
 
@@ -265,6 +255,20 @@ module Commonmeta
       end
     end
 
+    def insert_publisher_item(xml)
+      return xml if alternate_identifiers.blank?
+
+      xml.publisher_item do
+        alternate_identifiers.each do |alternate_identifier|
+          attributes = {
+            'item_number_type' => alternate_identifier['alternateIdentifierType'] ? alternate_identifier['alternateIdentifierType'].downcase : nil
+          }.compact
+
+          xml.item_number(alternate_identifier['alternateIdentifier'], attributes)
+        end
+      end
+    end
+
     def insert_doi_data(xml)
       return xml if doi_from_url(id).blank? || url.blank?
 

data/lib/commonmeta/readers/json_feed_reader.rb

@@ -1,4 +1,5 @@
 # frozen_string_literal: true
+require "uri"
 
 module Commonmeta
   module Readers
@@ -58,6 +59,8 @@ module Commonmeta
 
           sum
         end
+        references = get_references(meta)
+        alternate_identifiers = [{ "alternateIdentifier" => meta["uuid"], "alternateIdentifierType" => "UUID" }]
 
         { "id" => id,
           "type" => type,
@@ -71,13 +74,35 @@ module Commonmeta
           "descriptions" => descriptions,
           "license" => license,
           "subjects" => subjects.presence,
+          "references" => references.presence,
+          "alternate_identifiers" => alternate_identifiers,
           "state" => state }.compact.merge(read_options)
       end
 
-      def get_json_feed
+      def get_references(meta)
+        # check that references resolve
+        Array.wrap(meta["references"]).reduce([]) do |sum, reference|
+          sum << reference if [200, 301, 302].include? HTTP.head(reference["doi"] || reference["url"]).status
+
+          sum
+        end
+      end
+
+      def get_json_feed_unregistered
         # get JSON Feed items not registered as DOIs
 
-        url = json_feed_url
+        url = json_feed_unregistered_url
+        response = HTTP.get(url)
+        return { "string" => nil, "state" => "not_found" } unless response.status.success?
+
+        posts = JSON.parse(response.body.to_s)
+        posts.map { |post| post["uuid"] }.first
+      end
+
+      def get_json_feed_updated
+        # get JSON Feed items updated since last check
+
+        url = json_feed_unregistered_url
         response = HTTP.get(url)
         return { "string" => nil, "state" => "not_found" } unless response.status.success?
 

data/lib/commonmeta/utils.rb

@@ -557,6 +557,12 @@ module Commonmeta
       end
     end
 
+    def validate_email(str)
+      email_regex = /\b[A-Z0-9._%+-]+@[A-Z0-9.-]+\.[A-Z]{2,4}\b/i
+      parsed_emails = str.scan(email_regex)
+      parsed_emails.first
+    end
+
     def parse_attributes(element, options = {})
       content = options[:content] || "__content__"
 
@@ -604,6 +610,12 @@ module Commonmeta
       # clean up URL
       uri.path = PostRank::URI.clean(uri.path)
 
+      # optionally remove query and fragment
+      if options[:remove_query_string]
+        uri.query = nil
+        uri.fragment = nil
+      end
+
       uri.to_s
     rescue Addressable::URI::InvalidURIError
       nil
@@ -1381,7 +1393,7 @@ module Commonmeta
       Base32::URL.decode(id)
     end
 
-    def json_feed_url
+    def json_feed_unregistered_url
       "https://rogue-scholar.org/api/posts/unregistered"
     end
   end

data/lib/commonmeta/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Commonmeta
-  VERSION = '3.2.6'
+  VERSION = '3.2.7'
 end

data/resources/crossref/common5.3.1.xsd

@@ -1,4 +1,9 @@
-<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:fr="http://www.crossref.org/fundref.xsd" xmlns:ct="http://www.crossref.org/clinicaltrials.xsd" xmlns:ai="http://www.crossref.org/AccessIndicators.xsd" xmlns:mml="http://www.w3.org/1998/Math/MathML"><!-- *************************************************************
+<xsd:schema xmlns:xsd="http://www.w3.org/2001/XMLSchema"
+   xmlns:fr="http://www.crossref.org/fundref.xsd"
+   xmlns:ct="http://www.crossref.org/clinicaltrials.xsd"
+   xmlns:ai="http://www.crossref.org/AccessIndicators.xsd"
+   xmlns:mml="http://www.w3.org/1998/Math/MathML">
+   <!--*************************************************************
 	Crossref Metadata Input Schema, common file v. 5.3.1
 	*************************************************************
 	
@@ -8,7 +13,7 @@ As of version 4.5.0 all changes are noted in the release notes for the schema re
 	
 Prior updates are noted as comments within previous schema versions.
 	
-   -->
+  -->
    <xsd:import namespace="http://www.w3.org/1998/Math/MathML" schemaLocation="http://www.w3.org/Math/XMLSchema/mathml3/mathml3.xsd"/>
    <xsd:import namespace="http://www.crossref.org/fundref.xsd" schemaLocation="fundref.xsd"/>
    <xsd:import namespace="http://www.crossref.org/AccessIndicators.xsd" schemaLocation="AccessIndicators.xsd"/>
@@ -20,7 +25,7 @@ Prior updates are noted as comments within previous schema versions.
    </xsd:complexType>
    <xsd:group name="face_markup">
       <xsd:annotation>
-         <xsd:documentation>The following are basic data types for face markup. Face markup that appears in the title, subtitle, and original_language_title elements should be retained when depositing metadata. Face markup in other elements (e.g. small caps in author names) must be dropped. Face markup support includes bold (b), italic (i), underline (u), over-line (ovl), superscript (sup), subscript (sub), small caps (scp), and typewriter text (tt). See https://support.crossref.org/hc/en-us/articles/214532023 MathML may also be included using the &apos;mml&apos; namespace prefix.</xsd:documentation>
+         <xsd:documentation>The following are basic data types for face markup. Face markup that appears in the title, subtitle, and original_language_title elements should be retained when depositing metadata. Face markup in other elements (e.g. small caps in author names) must be dropped. Face markup support includes bold (b), italic (i), underline (u), over-line (ovl), superscript (sup), subscript (sub), small caps (scp), and typewriter text (tt). See https://support.crossref.org/hc/en-us/articles/214532023 MathML may also be included using the 'mml' namespace prefix.</xsd:documentation>
       </xsd:annotation>
       <xsd:choice>
          <xsd:element ref="b"/>
@@ -50,7 +55,7 @@ Prior updates are noted as comments within previous schema versions.
    <xsd:element name="font" type="xrefFaces"/>
    <xsd:element name="a">
       <xsd:annotation>
-         <xsd:documentation> content is &quot;Inline&quot; except that anchors shouldn&apos;t be nested </xsd:documentation>
+         <xsd:documentation> content is "Inline" except that anchors shouldn't be nested			</xsd:documentation>
       </xsd:annotation>
       <xsd:complexType mixed="true">
          <xsd:simpleContent>
@@ -133,7 +138,7 @@ Prior updates are noted as comments within previous schema versions.
    </xsd:element>
    <xsd:element name="edition_number">
       <xsd:annotation>
-         <xsd:documentation>The edition number of a book. edition_number should include only a number and not additional text such as &quot;edition&quot;. For example, you should submit &quot;3&quot;, not &quot;third edition&quot; or &quot;3rd edition&quot;. Roman numerals are acceptable.</xsd:documentation>
+         <xsd:documentation>The edition number of a book. edition_number should include only a number and not additional text such as "edition". For example, you should submit "3", not "third edition" or "3rd edition". Roman numerals are acceptable.</xsd:documentation>
       </xsd:annotation>
       <xsd:simpleType>
          <xsd:restriction base="xsd:string">
@@ -141,11 +146,12 @@ Prior updates are noted as comments within previous schema versions.
             <xsd:minLength value="1"/>
          </xsd:restriction>
       </xsd:simpleType>
-   </xsd:element><!--  =============================================================
+   </xsd:element>
+   <!-- =============================================================
 
                           5. Journal elements
 
-     =============================================================  -->
+     ============================================================= -->
    <xsd:element name="issue">
       <xsd:annotation>
          <xsd:documentation>The issue number or name in which an article is published. The issue number takes precedence over any other name. For example, if an issue has only a seasonal name, then the season should be listed in issue.</xsd:documentation>
@@ -156,11 +162,12 @@ Prior updates are noted as comments within previous schema versions.
             <xsd:minLength value="1"/>
          </xsd:restriction>
       </xsd:simpleType>
-   </xsd:element><!--  =============================================================
+   </xsd:element>
+   <!-- =============================================================
 
        6. Elements shared by content types
 
-     =============================================================  -->
+     ============================================================= -->
    <xsd:element name="doi_data">
       <xsd:annotation>
          <xsd:documentation>The container for elements related directly to a DOI. </xsd:documentation>
@@ -203,10 +210,9 @@ Prior updates are noted as comments within previous schema versions.
    </xsd:simpleType>
    <xsd:element name="collection">
       <xsd:annotation>
-         <xsd:documentation>
-Container for item elements containing non-primary URIs associated with the item being registered. Collections are supported for the following (defined in the property attribute):
-<ul>
-               <li>list-based: Multiple Resolution, more info: https://www.crossref.org/education/content-registration/creating-and-managing-dois/multiple-resolution/</li>
+         <xsd:documentation>Container for item elements containing non-primary URIs associated with the item being registered. Collections are supported for the following (defined in the property attribute):				
+            <ul>
+               <li>list-based:  Multiple Resolution, more info: https://www.crossref.org/education/content-registration/creating-and-managing-dois/multiple-resolution/</li>
                <li>country-based: more info: https://www.crossref.org/education/content-registration/creating-and-managing-dois/multiple-resolution/#00130</li>
                <li>crawler-based: for Similarity Check URLs, more info: https://www.crossref.org/education/similarity-check/participate/urls-for-new-deposits/</li>
                <li>text-mining: supply specific URLs for text and data mining, more info: https://www.crossref.org/education/retrieve-metadata/rest-api/text-and-data-mining-for-members/</li>
@@ -540,7 +546,7 @@ Container for item elements containing non-primary URIs associated with the item
    </xsd:element>
    <xsd:attributeGroup name="reference_distribution_opts.att">
       <xsd:annotation>
-         <xsd:documentation>NOTE: not currently supported. Use to flag references for distribution. &quot;none&quot; is the default and follows current protocol - references are only distributed to everyone if the prefix level permission is set, otherwise reference distribution is limited to the DOI owner. Setting the value to &quot;query&quot; releases references to anyone making a query request (this overrides any established prefix level permission). Value &quot;any&quot; allows bulk distribution to anyone (using a Crossref query account) using the OAI-PMH protocol, and also releases references to anyone making a query request.</xsd:documentation>
+         <xsd:documentation>NOTE: not currently supported.				Use to flag references for distribution. "none" is the default and follows current protocol - references are only distributed to everyone if the prefix level permission is set, otherwise reference distribution is limited to the DOI owner. Setting the value to "query" releases references to anyone making a query request (this overrides any established prefix level permission). Value "any" allows bulk distribution to anyone (using a Crossref query account) using the OAI-PMH protocol, and also releases references to anyone making a query request.</xsd:documentation>
       </xsd:annotation>
       <xsd:attribute name="reference_distribution_opts" use="optional" default="none">
          <xsd:simpleType>
@@ -551,7 +557,9 @@ Container for item elements containing non-primary URIs associated with the item
             </xsd:restriction>
          </xsd:simpleType>
       </xsd:attribute>
-   </xsd:attributeGroup><!-- END NAME ELEMENTs --><!-- ============   end various dates ==========  -->
+   </xsd:attributeGroup>
+   <!--END NAME ELEMENTs-->
+   <!--============   end various dates ========== -->
    <xsd:simpleType name="doi_t">
       <xsd:restriction base="xsd:string">
          <xsd:maxLength value="2048"/>
@@ -703,7 +711,7 @@ Container for item elements containing non-primary URIs associated with the item
    </xsd:complexType>
    <xsd:element name="citation">
       <xsd:annotation>
-         <xsd:documentation>citation is used to deposit each reference in the reference list of the item for which the DOI is being deposited. For details see: https://www.crossref.org/education/metadata-stewardship/maintaining-your-metadata/add-references/ </xsd:documentation>
+         <xsd:documentation>citation is used to deposit each reference in the reference list of the item for which the DOI is being deposited. For details see:				https://www.crossref.org/education/metadata-stewardship/maintaining-your-metadata/add-references/ </xsd:documentation>
       </xsd:annotation>
       <xsd:complexType>
          <xsd:complexContent>
@@ -729,7 +737,7 @@ Container for item elements containing non-primary URIs associated with the item
    </xsd:attributeGroup>
    <xsd:element name="unstructured_citation">
       <xsd:annotation>
-         <xsd:documentation>A citation to an item that is not structured with the Crossref citation model. &apos;unstructured_citation&apos; supports deposit of references for which no structural information is available. </xsd:documentation>
+         <xsd:documentation>A citation to an item that is not structured with the Crossref citation model.  'unstructured_citation' supports deposit of references for which no structural information is available. </xsd:documentation>
       </xsd:annotation>
       <xsd:complexType mixed="true">
          <xsd:choice minOccurs="0" maxOccurs="unbounded">
@@ -783,7 +791,7 @@ Container for item elements containing non-primary URIs associated with the item
             <xsd:element ref="crossmark_domains" minOccurs="0" maxOccurs="unbounded"/>
             <xsd:element ref="crossmark_domain_exclusive" minOccurs="0">
                <xsd:annotation>
-                  <xsd:documentation>Some publishers encourage broad third party hosting of the publisher&apos;s content. Other publishers do not. And still others vary their policy depending on whether a particular article has been published under an OA policy or not. This boolean flag allows the publisher to indicate whether the Crossmarked content will only legitimately be updated on the Crossmark domain (true) or whether the publisher encourages updating the content on other sites as well (false).</xsd:documentation>
+                  <xsd:documentation>Some publishers encourage broad third party hosting of the publisher's content. Other publishers do not. And still others vary their policy depending on whether a particular article has been published under an OA policy or not. This boolean flag allows the publisher to indicate whether the Crossmarked content will only legitimately be updated on the Crossmark domain (true) or whether the publisher encourages updating the content on other sites as well (false).</xsd:documentation>
                </xsd:annotation>
             </xsd:element>
             <xsd:sequence minOccurs="0">
@@ -795,13 +803,13 @@ Container for item elements containing non-primary URIs associated with the item
    </xsd:element>
    <xsd:element name="crossmark_policy" type="doi_t">
       <xsd:annotation>
-         <xsd:documentation>A DOI which points to a publisher&apos;s CrossMark policy document. Publishers might have different policies for different publications.</xsd:documentation>
+         <xsd:documentation>A DOI which points to a publisher's CrossMark policy document. Publishers might have different policies for different publications.</xsd:documentation>
       </xsd:annotation>
    </xsd:element>
    <xsd:element name="crossmark_version" type="xsd:string"/>
    <xsd:element name="crossmark_domains">
       <xsd:annotation>
-         <xsd:documentation>Container element for crossmark_domain. A list of domains where the publisher maintains updates and corrections to their content. Minimally, one of these should include the Internet domain name of the publisher&apos;s web site(s), but the publisher might also decide to include 3rd party aggregators (e.g. Ebsco, IngentaConnect) or archives with which the publisher has agreements to update the content </xsd:documentation>
+         <xsd:documentation>Container element for crossmark_domain. A list of domains where the publisher maintains updates and corrections to their content. Minimally, one of these should include the Internet domain name of the publisher's web site(s), but the publisher might also decide to include 3rd party aggregators (e.g. Ebsco, IngentaConnect) or archives with which the publisher has agreements to update the content </xsd:documentation>
       </xsd:annotation>
       <xsd:complexType>
          <xsd:sequence>
@@ -811,7 +819,7 @@ Container for item elements containing non-primary URIs associated with the item
    </xsd:element>
    <xsd:element name="crossmark_domain">
       <xsd:annotation>
-         <xsd:documentation>This should be a simple Internet domain name or subdomain name (e.g. www.psychoceramics.org or psychoceramics.org). It is used to identify when a referring URL is coming from a Crossmark domain. A &quot;crossmark_domain&quot; is made up of two subelements; a &quot;domain&quot; and a &quot;filter&quot;. The filter is only needed for use in situations where content from multiple publishers/publications is on the same host with the same domain name (e.g. an aggregator) and one needs to use the referrer&apos;s URI &quot;path&quot; to further determine whether the content in a crossmark domain.</xsd:documentation>
+         <xsd:documentation>This should be a simple Internet domain name or subdomain name (e.g. www.psychoceramics.org or psychoceramics.org). It is used to identify when a referring URL is coming from a Crossmark domain. A "crossmark_domain" is made up of two subelements; a "domain" and a "filter". The filter is only needed for use in situations where content from multiple publishers/publications is on the same host with the same domain name (e.g. an aggregator) and one needs to use the referrer's URI "path" to further determine whether the content in a crossmark domain.</xsd:documentation>
       </xsd:annotation>
       <xsd:complexType>
          <xsd:sequence>
@@ -827,7 +835,7 @@ Container for item elements containing non-primary URIs associated with the item
    </xsd:element>
    <xsd:element name="filter" type="xsd:string">
       <xsd:annotation>
-         <xsd:documentation>The filter element is used to disambiguate content in situations where multiple publishers share the same host (e.g. when on an aggregated platform). It should contain a substring of the path that can be used to uniquely identify a publisher&apos;s or publication&apos;s content. For instance, using the string &quot;alpsp&quot; here would help the CrossMark system distinguish between ALPSP publications on the ingentaconnect host and other publications on the same host.</xsd:documentation>
+         <xsd:documentation>The filter element is used to disambiguate content in situations where multiple publishers share the same host (e.g. when on an aggregated platform). It should contain a substring of the path that can be used to uniquely identify a publisher's or publication's content. For instance, using the string "alpsp" here would help the CrossMark system distinguish between ALPSP publications on the ingentaconnect host and other publications on the same host.</xsd:documentation>
       </xsd:annotation>
    </xsd:element>
    <xsd:element name="crossmark_domain_exclusive" type="xsd:boolean"/>
@@ -843,16 +851,15 @@ Container for item elements containing non-primary URIs associated with the item
    </xsd:element>
    <xsd:element name="update">
       <xsd:annotation>
-         <xsd:documentation>The DOI of the content being updated (e.g. corrected, retracted, etc.) In the CrossMark Terms and Conditions &quot;updates&quot; are defined as changes that are likely to &quot;change the reader’s interpretation or crediting of the work.&quot; That is, *editorially significant* changes. &quot;Updates&quot; should not include minor changes to spelling, punctuation, formatting, etc. </xsd:documentation>
+         <xsd:documentation>The DOI of the content being updated (e.g. corrected, retracted, etc.) In the CrossMark Terms and Conditions "updates" are defined as changes that are likely to "change the reader’s interpretation or crediting of the work." That is, *editorially significant* changes. "Updates" should not include minor changes to spelling, punctuation, formatting, etc. </xsd:documentation>
       </xsd:annotation>
       <xsd:complexType mixed="true">
          <xsd:simpleContent>
             <xsd:extension base="doi_t">
                <xsd:attribute name="type" use="required" type="cm_update_type">
                   <xsd:annotation>
-                     <xsd:documentation>
-This attribute should be used to list the update type. Allowed update types are:
-<ul>
+                     <xsd:documentation>This attribute should be used to list the update type. Allowed update types are: 
+                        <ul>
                            <li>addendum</li>
                            <li>clarification</li>
                            <li>correction</li>
@@ -913,27 +920,27 @@ This attribute should be used to list the update type. Allowed update types are:
          </xsd:choice>
          <xsd:attribute name="explanation" type="xsd:anyURI">
             <xsd:annotation>
-               <xsd:documentation>If the publisher wants to provide a further explanation of what the particular &quot;assertion&quot; means, they can link to such an explanation by providing an appropriate url on the &quot;explanation&quot; attribute.</xsd:documentation>
+               <xsd:documentation>If the publisher wants to provide a further explanation of what the particular "assertion" means, they can link to such an explanation by providing an appropriate url on the "explanation" attribute.</xsd:documentation>
             </xsd:annotation>
          </xsd:attribute>
          <xsd:attribute name="group_label" type="cm_assertion_group_label">
             <xsd:annotation>
-               <xsd:documentation>This is the human-readable form of the &quot;group_name&quot; attribute. This is what will be displayed in the group headings on the Crossmark metadata record dialog.</xsd:documentation>
+               <xsd:documentation>This is the human-readable form of the "group_name" attribute. This is what will be displayed in the group headings on the Crossmark metadata record dialog.</xsd:documentation>
             </xsd:annotation>
          </xsd:attribute>
          <xsd:attribute name="group_name" type="cm_assertion_group_name">
             <xsd:annotation>
-               <xsd:documentation>Some assertions could be logically &quot;grouped&quot; together in the CrossMark dialog. For instance, if the publisher is recording several pieces of metadata related to funding sources (source name, percentage, grant number), they may want to make sure that these three assertions are grouped next to each-other in the CrossMark dialog. The group_name attribute is the machine-readable value that will be used for grouping such assertions.</xsd:documentation>
+               <xsd:documentation>Some assertions could be logically "grouped" together in the CrossMark dialog. For instance, if the publisher is recording several pieces of metadata related to funding sources (source name, percentage, grant number), they may want to make sure that these three assertions are grouped next to each-other in the CrossMark dialog. The group_name attribute is the machine-readable value that will be used for grouping such assertions.</xsd:documentation>
             </xsd:annotation>
          </xsd:attribute>
          <xsd:attribute name="label" type="cm_assertion_label">
             <xsd:annotation>
-               <xsd:documentation>This is the human-readable version of the name attribute which will be displayed in the CrossMark dialog. If this attribute is missing, then the value of the assertion will *not* be displayed in the dialog. Publishers may want to &quot;hide&quot; assertions this way in cases where the assertion value is too large or too complex to display in the dialog, but where the assertion is nonetheless valuable enough to include in API queries and metadata dumps (e.g. detailed licensing terms)</xsd:documentation>
+               <xsd:documentation>This is the human-readable version of the name attribute which will be displayed in the CrossMark dialog. If this attribute is missing, then the value of the assertion will *not* be displayed in the dialog. Publishers may want to "hide" assertions this way in cases where the assertion value is too large or too complex to display in the dialog, but where the assertion is nonetheless valuable enough to include in API queries and metadata dumps (e.g. detailed licensing terms)</xsd:documentation>
             </xsd:annotation>
          </xsd:attribute>
          <xsd:attribute name="name" use="required" type="cm_assertion_name">
             <xsd:annotation>
-               <xsd:documentation>This is the machine-readable name of the assertion. Use the &quot;label&quot; attribute to provide a human-readable version of the name.</xsd:documentation>
+               <xsd:documentation>This is the machine-readable name of the assertion. Use the "label" attribute to provide a human-readable version of the name.</xsd:documentation>
             </xsd:annotation>
          </xsd:attribute>
          <xsd:attribute name="order" type="xsd:integer">
@@ -1024,7 +1031,7 @@ This attribute should be used to list the update type. Allowed update types are:
    </xsd:element>
    <xsd:element name="std_family_designator" type="std_designator_t">
       <xsd:annotation>
-         <xsd:documentation>Provides for defining a DOI for a broad grouping of standards. </xsd:documentation>
+         <xsd:documentation>Provides for defining a DOI for a broad grouping of standards.			</xsd:documentation>
       </xsd:annotation>
    </xsd:element>
    <xsd:element name="std_set_designator">
@@ -1059,12 +1066,12 @@ This attribute should be used to list the update type. Allowed update types are:
    </xsd:element>
    <xsd:element name="std_adopted_from" type="std_designatorvalue_t">
       <xsd:annotation>
-         <xsd:documentation>Designator for standard from which the current deposit is adopted. </xsd:documentation>
+         <xsd:documentation>Designator for standard from which the current deposit is adopted.			</xsd:documentation>
       </xsd:annotation>
    </xsd:element>
    <xsd:element name="std_revision_of" type="std_designatorvalue_t">
       <xsd:annotation>
-         <xsd:documentation>Designator for the previous revision of the standard being deposited. (note: use alt_as_published for revisions within designators having common stem) </xsd:documentation>
+         <xsd:documentation>Designator for the previous revision of the standard being deposited. (note: use alt_as_published for revisions within designators having common stem)			</xsd:documentation>
       </xsd:annotation>
    </xsd:element>
    <xsd:element name="standards_body">
@@ -1103,7 +1110,8 @@ This attribute should be used to list the update type. Allowed update types are:
    </xsd:complexType>
    <xsd:element name="std_designator" type="std_designatorvalue_t"/>
    <xsd:element name="std_alt_script" type="std_designatorvalue_t"/>
-   <xsd:element name="std_variant_form" type="std_designatorvalue_t"/><!--  ================SCN policy =============================  -->
+   <xsd:element name="std_variant_form" type="std_designatorvalue_t"/>
+   <!-- ================SCN policy ============================= -->
    <xsd:element name="scn_policies">
       <xsd:annotation>
          <xsd:documentation>A wrapper for Scholarly Sharing Network (SCN) policy information</xsd:documentation>