bolognese 1.9.4 → 1.9.9

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f8f8cb84bf74f8a75d2469aa5a3e49dd4ba0adbd9b465d60e11bdbbd8252c267
-  data.tar.gz: 3fc9719de82891ce908fd4af271f05fc1f024442d0a1e6bc88b65db438118ab3
+  metadata.gz: fbe9e35e7353f028ff77b7265ebf35db75b6ca6827fd5e64fcbfc42c0ca04b0a
+  data.tar.gz: 734492dd88ddc4511a34c885a05431e31500fe422ed4bc642f06296177a9d824
 SHA512:
-  metadata.gz: 797b852b3dafd982249bb57a91dff364bd2dcc6d2b52cb50494dcc6a5cfec7a2fc714a27eed6cd46dde158c495ca93154a858ca0f1800a3990b3f6708878fcec
-  data.tar.gz: c19d5e7833401549a98b71a13e9063b52bbdfaaa70ff2165272aff311b2d3df6ae765ae79a4ad62ae45fb259520a3e3b39ada0dbef838cc602972ecdad50305b
+  metadata.gz: c72d97cc6f095710a6861188b5f6e6761813c67fbb3d7fa2ebd09586a427954d78997b4f9d1565b255a42646e48c0ead0a2f68319b38b79752924ce12774e852
+  data.tar.gz: 0d890b5b6572161d1596ad8641261e3d9d754613a18d66bf7b0406013b3d93308247fe8790022c3964295165cca51593314ec4b35e9ae4cdeb638330a035ea78

data/CHANGELOG.md

@@ -1,8 +1,41 @@
 # Changelog
 
-## [Unreleased](https://github.com/datacite/bolognese/tree/HEAD)
+## [1.9.8](https://github.com/datacite/bolognese/tree/1.9.8) (2021-06-08)
 
-[Full Changelog](https://github.com/datacite/bolognese/compare/1.9.3...HEAD)
+[Full Changelog](https://github.com/datacite/bolognese/compare/1.9.7...1.9.8)
+
+## [1.9.7](https://github.com/datacite/bolognese/tree/1.9.7) (2021-05-26)
+
+[Full Changelog](https://github.com/datacite/bolognese/compare/1.9.6...1.9.7)
+
+## [1.9.6](https://github.com/datacite/bolognese/tree/1.9.6) (2021-05-26)
+
+[Full Changelog](https://github.com/datacite/bolognese/compare/1.9.5...1.9.6)
+
+**Fixed bugs:**
+
+- Missing affiliationIdentiifer when used with schemaURI raises an error [\#116](https://github.com/datacite/bolognese/issues/116)
+- Optional numberType being treated as required generating error [\#112](https://github.com/datacite/bolognese/issues/112)
+
+**Closed issues:**
+
+- Book metadata seems to be ignored [\#113](https://github.com/datacite/bolognese/issues/113)
+- Namespaced XML Tags [\#109](https://github.com/datacite/bolognese/issues/109)
+- Funder DOI validation [\#108](https://github.com/datacite/bolognese/issues/108)
+
+**Merged pull requests:**
+
+- Fix missing affiliation identifier [\#117](https://github.com/datacite/bolognese/pull/117) ([richardhallett](https://github.com/richardhallett))
+- Add support for book title and additional metadata when reading Crossref Book Chapter DOI [\#115](https://github.com/datacite/bolognese/pull/115) ([prdanelli](https://github.com/prdanelli))
+- Valid Funder DOIs are being rejected for not starting with a 5 [\#114](https://github.com/datacite/bolognese/pull/114) ([prdanelli](https://github.com/prdanelli))
+
+## [1.9.5](https://github.com/datacite/bolognese/tree/1.9.5) (2021-04-20)
+
+[Full Changelog](https://github.com/datacite/bolognese/compare/1.9.4...1.9.5)
+
+## [1.9.4](https://github.com/datacite/bolognese/tree/1.9.4) (2021-04-13)
+
+[Full Changelog](https://github.com/datacite/bolognese/compare/1.9.3...1.9.4)
 
 **Implemented enhancements:**
 
@@ -535,6 +568,10 @@
 
 - Error when schema.org in put has array value for @type [\#66](https://github.com/datacite/bolognese/issues/66)
 
+**Merged pull requests:**
+
+- Default to `ScholarlyArticle` type for `citation` and `isBasedOn` relationships with datasets [\#64](https://github.com/datacite/bolognese/pull/64) ([chrisgorgo](https://github.com/chrisgorgo))
+
 ## [v.1.2.16](https://github.com/datacite/bolognese/tree/v.1.2.16) (2019-07-07)
 
 [Full Changelog](https://github.com/datacite/bolognese/compare/v.1.2.15...v.1.2.16)
@@ -633,7 +670,6 @@
 
 **Merged pull requests:**
 
-- Default to `ScholarlyArticle` type for `citation` and `isBasedOn` relationships with datasets [\#64](https://github.com/datacite/bolognese/pull/64) ([chrisgorgo](https://github.com/chrisgorgo))
 - When authors is a plain string, don't try to parse [\#60](https://github.com/datacite/bolognese/pull/60) ([richardhallett](https://github.com/richardhallett))
 
 ## [v.1.1.12](https://github.com/datacite/bolognese/tree/v.1.1.12) (2019-04-15)

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    bolognese (1.9.4)
+    bolognese (1.9.9)
       activesupport (>= 4.2.5)
       benchmark_methods (~> 0.7)
       bibtex-ruby (>= 5.1.0)
@@ -17,7 +17,7 @@ PATH
       json-ld-preloaded (~> 3.1, >= 3.1.3)
       jsonlint (~> 0.3.0)
       loofah (~> 2.0, >= 2.0.3)
-      maremma (>= 4.7, < 5)
+      maremma (>= 4.9.4, < 5)
       namae (~> 1.0)
       nokogiri (~> 1.11.2)
       oj (~> 3.10)
@@ -30,7 +30,7 @@ PATH
 GEM
   remote: https://rubygems.org/
   specs:
-    activesupport (6.1.3.1)
+    activesupport (6.1.3.2)
       concurrent-ruby (~> 1.0, >= 1.0.2)
       i18n (>= 1.6, < 2)
       minitest (>= 5.1)
@@ -38,6 +38,7 @@ GEM
       zeitwerk (~> 2.3)
     addressable (2.7.0)
       public_suffix (>= 2.0.2, < 5.0)
+    amazing_print (1.3.0)
     benchmark_methods (0.7)
     bibtex-ruby (6.0.0)
       latex-decode (~> 0.0)
@@ -48,21 +49,23 @@ GEM
       citeproc (~> 1.0, >= 1.0.9)
       csl (~> 1.5)
     colorize (0.8.1)
-    concurrent-ruby (1.1.8)
+    concurrent-ruby (1.1.9)
     crack (0.4.5)
       rexml
     crass (1.0.6)
     csl (1.5.2)
       namae (~> 1.0)
-    csl-styles (1.0.1.10)
+    csl-styles (1.0.1.11)
       csl (~> 1.0)
     diff-lcs (1.4.4)
-    docile (1.3.5)
-    ebnf (2.1.2)
+    docile (1.4.0)
+    ebnf (2.1.3)
+      amazing_print (~> 1.2)
       htmlentities (~> 4.3)
       rdf (~> 3.1)
       scanf (~> 1.0)
       sxp (~> 1.1)
+      unicode-types (~> 1.6)
     edtf (3.0.6)
       activesupport (>= 3.0, < 7.0)
     excon (0.71.1)
@@ -101,10 +104,10 @@ GEM
       optimist (~> 3)
     latex-decode (0.3.2)
     link_header (0.0.8)
-    loofah (2.9.1)
+    loofah (2.10.0)
       crass (~> 1.0.2)
       nokogiri (>= 1.5.9)
-    maremma (4.7.4)
+    maremma (4.9.4)
       activesupport (>= 4.2.5)
       addressable (>= 2.3.6)
       builder (~> 3.2, >= 3.2.2)
@@ -115,15 +118,15 @@ GEM
       nokogiri (~> 1.11.2)
       oj (>= 2.8.3)
       oj_mimic_json (~> 1.0, >= 1.0.1)
-    mini_portile2 (2.5.0)
+    mini_portile2 (2.5.3)
     minitest (5.14.4)
     multi_json (1.15.0)
     multipart-post (2.1.1)
     namae (1.1.1)
-    nokogiri (1.11.2)
+    nokogiri (1.11.7)
       mini_portile2 (~> 2.5.0)
       racc (~> 1.4)
-    oj (3.11.3)
+    oj (3.11.5)
     oj_mimic_json (1.0.1)
     optimist (3.0.1)
     postrank-uri (1.0.24)
@@ -136,7 +139,7 @@ GEM
     rack-test (0.8.3)
       rack (>= 1.0, < 3)
     rake (12.3.3)
-    rdf (3.1.13)
+    rdf (3.1.14)
       hamster (~> 3.0)
       link_header (~> 0.0, >= 0.0.8)
     rdf-aggregate-repo (3.1.0)
@@ -161,7 +164,7 @@ GEM
     rdf-xsd (3.1.1)
       rdf (~> 3.1)
       rexml (~> 3.2)
-    rexml (3.2.4)
+    rexml (3.2.5)
     rspec (3.10.0)
       rspec-core (~> 3.10.0)
       rspec-expectations (~> 3.10.0)
@@ -191,9 +194,10 @@ GEM
     tilt (2.0.10)
     tzinfo (2.0.4)
       concurrent-ruby (~> 1.0)
+    unicode-types (1.6.0)
     unicode_utils (1.4.0)
     vcr (3.0.3)
-    webmock (3.12.1)
+    webmock (3.13.0)
       addressable (>= 2.3.6)
       crack (>= 0.3.2)
       hashdiff (>= 0.4.0, < 2.0.0)
@@ -215,4 +219,4 @@ DEPENDENCIES
   webmock (~> 3.0, >= 3.0.1)
 
 BUNDLED WITH
-   2.2.16
+   2.2.19

data/bolognese.gemspec

@@ -16,7 +16,7 @@ Gem::Specification.new do |s|
   s.required_ruby_version = '~> 2.3'
 
   # Declare dependencies here, rather than in the Gemfile
-  s.add_dependency 'maremma', '>= 4.7', '< 5'
+  s.add_dependency 'maremma', '>= 4.9.4', '< 5'
   s.add_dependency 'faraday', '~> 0.17.3'
   s.add_dependency 'nokogiri', '~> 1.11.2'
   s.add_dependency 'loofah', '~> 2.0', '>= 2.0.3'

data/lib/bolognese/author_utils.rb

@@ -138,14 +138,19 @@ module Bolognese
 
     def get_affiliations(affiliations)
       Array.wrap(affiliations).map do |a|
+        affiliation_identifier = nil
         if a.is_a?(String)
           name = a.squish
-          affiliation_identifier = nil
           affiliation_identifier_scheme = nil
           scheme_uri = nil
         else
-          affiliation_identifier = a["affiliationIdentifier"]
-          affiliation_identifier = !affiliation_identifier.to_s.start_with?("https://") && a["schemeURI"].present? ? normalize_id(a["schemeURI"] + affiliation_identifier) : normalize_id(affiliation_identifier)
+          if a["affiliationIdentifier"].present?
+            affiliation_identifier = a["affiliationIdentifier"]
+            if a["schemeURI"].present?
+              schemeURI = a["schemeURI"].end_with?("/") ? a["schemeURI"] : a["schemeURI"] + "/"
+            end
+            affiliation_identifier = !affiliation_identifier.to_s.start_with?("https://") && schemeURI.present? ? normalize_id(schemeURI + affiliation_identifier) : normalize_id(affiliation_identifier)
+          end
           name = a["__content__"].to_s.squish.presence
           affiliation_identifier_scheme = a["affiliationIdentifierScheme"]
           scheme_uri = a["SchemeURI"]

data/lib/bolognese/doi_utils.rb

@@ -3,32 +3,33 @@
 module Bolognese
   module DoiUtils
     def validate_doi(doi)
-      doi = Array(/\A(?:(http|https):\/(\/)?(dx\.)?(doi.org|handle.test.datacite.org)\/)?(doi:)?(10\.\d{4,5}\/.+)\z/.match(doi)).last
+      doi = Array(/\A(?:(http|https):\/(\/)?(dx\.)?(doi.org|handle.stage.datacite.org|handle.test.datacite.org)\/)?(doi:)?(10\.\d{4,5}\/.+)\z/.match(doi)).last
       # remove non-printing whitespace and downcase
       doi.delete("\u200B").downcase if doi.present?
     end
 
     def validate_funder_doi(doi)
-      doi = Array(/\A(?:(http|https):\/(\/)?(dx\.)?(doi.org|handle.test.datacite.org)\/)?(doi:)?(10\.13039\/)?(5.+)\z/.match(doi)).last
+      doi = Array(/\A(?:(http|https):\/(\/)?(dx\.)?(doi.org|handle.stage.datacite.org|handle.test.datacite.org)\/)?(doi:)?(10\.13039\/)?([1-9]\d+)\z/.match(doi)).last
+
       # remove non-printing whitespace and downcase
       if doi.present?
-        doi.delete("\u200B").downcase 
+        doi.delete("\u200B").downcase
         "https://doi.org/10.13039/#{doi}"
       end
     end
 
     def validate_prefix(doi)
-      Array(/\A(?:(http|https):\/(\/)?(dx\.)?(doi.org|handle.test.datacite.org)\/)?(doi:)?(10\.\d{4,5}).*\z/.match(doi)).last
+      Array(/\A(?:(http|https):\/(\/)?(dx\.)?(doi.org|handle.stage.datacite.org|handle.test.datacite.org)\/)?(doi:)?(10\.\d{4,5}).*\z/.match(doi)).last
     end
 
     def doi_resolver(doi, options = {})
-      sandbox = Array(/handle.test.datacite.org/.match(doi)).last
-      sandbox.present? || options[:sandbox] ? "https://handle.test.datacite.org/" : "https://doi.org/"
+      sandbox = Array(/handle.stage.datacite.org/.match(doi)).last
+      sandbox.present? || options[:sandbox] ? "https://handle.stage.datacite.org/" : "https://doi.org/"
     end
 
     def doi_api_url(doi, options = {})
-      sandbox = Array(/handle.test.datacite.org/.match(doi)).last
-      sandbox.present? || options[:sandbox] ? "https://api.test.datacite.org/dois/#{doi_from_url(doi)}?include=media,client"  : "https://api.datacite.org/dois/#{doi_from_url(doi)}?include=media,client"
+      sandbox = Array(/handle.stage.datacite.org/.match(doi)).last
+      sandbox.present? || options[:sandbox] ? "https://api.stage.datacite.org/dois/#{doi_from_url(doi)}?include=media,client"  : "https://api.datacite.org/dois/#{doi_from_url(doi)}?include=media,client"
     end
 
     def normalize_doi(doi, options = {})
@@ -40,7 +41,7 @@ module Bolognese
     end
 
     def doi_from_url(url)
-      if /\A(?:(http|https):\/\/(dx\.)?(doi.org|handle.test.datacite.org)\/)?(doi:)?(10\.\d{4,5}\/.+)\z/.match(url)
+      if /\A(?:(http|https):\/\/(dx\.)?(doi.org|handle.stage.datacite.org|handle.test.datacite.org)\/)?(doi:)?(10\.\d{4,5}\/.+)\z/.match(url)
         uri = Addressable::URI.parse(url)
         uri.path.gsub(/^\//, '').downcase
       end

data/lib/bolognese/readers/crossref_reader.rb

@@ -9,7 +9,7 @@ module Bolognese
 
         doi = doi_from_url(id)
         url = "https://api.crossref.org/works/#{doi}/transform/application/vnd.crossref.unixsd+xml"
-        response = Maremma.get(url, accept: "text/xml", raw: true)
+        response = Maremma.get(url, accept: "text/xml;charset=utf-8", raw: true)
         string = response.body.fetch("data", nil)
         string = Nokogiri::XML(string, nil, 'UTF-8', &:noblanks).to_s if string.present?
 
@@ -56,10 +56,10 @@ module Bolognese
           #               book_series_metadata.dig("publisher", "publisher_name")
           #             end
         when "conference"
-          event_metadata = meta.dig("crossref", "conference", "event_metadata") || {}
+          event_metadata = meta.dig("crossref", "conference", "event_metadata") || {}
           bibliographic_metadata = meta.dig("crossref", "conference", "conference_paper").to_h
         when "journal"
-          journal_metadata = meta.dig("crossref", "journal", "journal_metadata") || {}
+          journal_metadata = meta.dig("crossref", "journal", "journal_metadata") || {}
           journal_issue = meta.dig("crossref", "journal", "journal_issue") || {}
           journal_article = meta.dig("crossref", "journal", "journal_article") || {}
           bibliographic_metadata = journal_article.presence || journal_issue.presence || journal_metadata
@@ -140,7 +140,8 @@ module Bolognese
         state = meta.present? || read_options.present? ? "findable" : "not_found"
 
         related_identifiers = Array.wrap(crossref_is_part_of(journal_metadata)) + Array.wrap(crossref_references(bibliographic_metadata))
-        container = if journal_metadata.present? || book_metadata.present?
+
+        container = if journal_metadata.present?
                       issn = normalize_issn(journal_metadata.to_h.fetch("issn", nil))
 
                       { "type" => "Journal",
@@ -151,6 +152,19 @@ module Bolognese
                         "issue" => parse_attributes(journal_issue.dig("issue")),
                         "firstPage" => bibliographic_metadata.dig("pages", "first_page") || parse_attributes(journal_article.to_h.dig("publisher_item", "item_number"), first: true),
                         "lastPage" => bibliographic_metadata.dig("pages", "last_page") }.compact
+
+                    # By using book_metadata, we can account for where resource_type is `BookChapter` and not assume its a whole book
+                    elsif book_metadata.present?
+                      identifiers = crossref_alternate_identifiers(book_metadata)
+
+                      {
+                        "type" => "Book",
+                        "title" => book_metadata.dig("titles", "title"),
+                        "firstPage" => bibliographic_metadata.dig("pages", "first_page"),
+                        "lastPage" => bibliographic_metadata.dig("pages", "last_page"),
+                        "identifiers" => identifiers,
+                      }.compact
+
                     elsif book_series_metadata.to_h.fetch("series_metadata", nil).present?
                       issn = normalize_issn(book_series_metadata.dig("series_metadata", "issn"))
 
@@ -162,7 +176,10 @@ module Bolognese
                     end
 
         id = normalize_doi(options[:doi] || options[:id] || bibliographic_metadata.dig("doi_data", "doi"))
-        identifiers = crossref_alternate_identifiers(bibliographic_metadata)
+
+        # Let sections override this in case of alternative metadata structures, such as book chapters, which
+        # have their meta inside `content_item`, but the main book indentifers inside of `book_metadata`
+        identifiers ||= crossref_alternate_identifiers(bibliographic_metadata)
 
         { "id" => id,
           "types" => types,

data/lib/bolognese/readers/datacite_reader.rb

@@ -7,7 +7,7 @@ module Bolognese
         return { "string" => nil, "state" => "not_found" } unless id.present?
 
         api_url = doi_api_url(id, options)
-        response = Maremma.get api_url
+        response = Maremma.get(api_url)
         attributes = response.body.dig("data", "attributes")
         return { "string" => nil, "state" => "not_found" } unless attributes.present?
 
@@ -203,6 +203,15 @@ module Bolognese
             "schemeType" => rii["schemeType"]
           }.compact
 
+          number = ri["number"]
+          if number.is_a?(String)
+            number = number
+            numberType = nil
+          else
+            number = ri.dig("number", "__content__")
+            numberType = ri.dig("number", "numberType")
+          end
+
           {
             "relationType" => ri["relationType"],
             "relatedItemType" => ri["relatedItemType"],
@@ -212,8 +221,8 @@ module Bolognese
             "publicationYear" => ri["publicationYear"],
             "volume" => ri["volume"],
             "issue" => ri["issue"],
-            "number" => ri.dig("number", "__content__"),
-            "numberType" => ri.dig("number", "numberType"),
+            "number" => number,
+            "numberType" => numberType,
             "firstPage" => ri["firstPage"],
             "lastPage" => ri["lastPage"],
             "publisher" => ri["publisher"],

data/lib/bolognese/readers/schema_org_reader.rb

@@ -26,8 +26,8 @@ module Bolognese
       def get_schema_org(id: nil, **options)
         return { "string" => nil, "state" => "not_found" } unless id.present?
 
-        id = normalize_id(id)
-        response = Maremma.get(id)
+        url = normalize_id(id)
+        response = Maremma.get(url)
         doc = Nokogiri::XML(response.body.fetch("data", nil), nil, 'UTF-8')
 
         # workaround for xhtml documents

data/lib/bolognese/utils.rb

@@ -499,7 +499,7 @@ module Bolognese
     def find_from_format_by_id(id)
       id = normalize_id(id)
 
-      if /\A(?:(http|https):\/(\/)?(dx\.)?(doi.org|handle.test.datacite.org)\/)?(doi:)?(10\.\d{4,5}\/.+)\z/.match(id)
+      if /\A(?:(http|https):\/(\/)?(dx\.)?(doi.org|handle.stage.datacite.org)\/)?(doi:)?(10\.\d{4,5}\/.+)\z/.match(id)
         ra = get_doi_ra(id)
         %w(DataCite Crossref mEDRA KISTI JaLC OP).include?(ra) ? ra.downcase : nil
       elsif /\A(?:(http|https):\/(\/)?orcid\.org\/)?(\d{4}-\d{4}-\d{4}-\d{3}[0-9X]+)\z/.match(id)
@@ -1306,8 +1306,8 @@ module Bolognese
         return [{
           "subject" => sanitize(hsh["__content__"] || hsh["subject"]),
           "subjectScheme" => hsh["subjectScheme"],
-          "schemeUri" => hsh["schemeURI"],
-          "valueUri" => hsh["valueURI"],
+          "schemeUri" => hsh["schemeURI"] || hsh["schemeUri"],
+          "valueUri" => hsh["valueURI"] || hsh["valueUri"],
           "classificationCode" => hsh["classificationCode"],
           "lang" => hsh["lang"] }.compact,
         {
@@ -1339,8 +1339,8 @@ module Bolognese
           "subject" => sanitize(hsh["__content__"] || hsh["subject"]),
           "subjectScheme" => hsh["subjectScheme"],
           "classificationCode" => hsh["classificationCode"],
-          "schemeUri" => hsh["schemeURI"],
-          "valueUri" => hsh["valueURI"],
+          "schemeUri" => hsh["schemeURI"] || hsh["schemeUri"],
+          "valueUri" => hsh["valueURI"] || hsh["valueUri"],
           "lang" => hsh["lang"] }.compact,
         {
           "subject" => "FOS: " + subject["fosLabel"],
@@ -1352,8 +1352,8 @@ module Bolognese
           "subject" => sanitize(hsh["__content__"] || hsh["subject"]),
           "subjectScheme" => hsh["subjectScheme"],
           "classificationCode" => hsh["classificationCode"],
-          "schemeUri" => hsh["schemeURI"],
-          "valueUri" => hsh["valueURI"],
+          "schemeUri" => hsh["schemeURI"] || hsh["schemeUri"],
+          "valueUri" => hsh["valueURI"] || hsh["valueUri"],
           "lang" => hsh["lang"] }.compact]
       end
     end

data/lib/bolognese/version.rb

@@ -1,3 +1,3 @@
 module Bolognese
-  VERSION = "1.9.4"
+  VERSION = "1.9.9"
 end

data/lib/bolognese/writers/jats_writer.rb

@@ -76,7 +76,9 @@ module Bolognese
       end
 
       def insert_source(xml)
-        if is_article? || is_data? || is_chapter?
+        if is_chapter?
+          xml.source(publisher)
+        elsif is_article? || is_data?
           xml.source(container && container["title"] || publisher)
         else
           xml.source(parse_attributes(titles, content: "title", first: true))