purl_fetcher-client 0.5.0 → 1.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b80b63b29ffbed55055e58d2d063f4496f84015b1130a6908e82e4d91a18c94d
-  data.tar.gz: 3d9691d8e9939f17a8d4f3a66a03bb3644463a3ffcc9604b8558242614f4e0a6
+  metadata.gz: cade5ac0289e6a39d9d9dca571bea47032391fa774d1356e56dbada402e6bb5e
+  data.tar.gz: 043a7f61d74b733bf2fd12bf26704ff25af6539f10c5731ae4843f11c2376c1a
 SHA512:
-  metadata.gz: '0484a2254521f201fed8d95cf65ab85a3310111c6be46c6d13ecb4e7c40cec3d807861b42c47dc389f34c242918733dce7c21b66beb872d062112bbfe8674dd0'
-  data.tar.gz: ff5cdc4fe8d78eedeba1594e8aa47e87bfb6186337d4f1042f928a56f0a6b854487e7acfba5398e306401a123cb710ae0ac4bc6b9b11b157a81d20550b789570
+  metadata.gz: fa1bce8d7e6ef5090a19d8cf8ecf42eeeb24f2c5ef59345c77ded4b50752f01e1b18307dd65aafcd0aa8c4873210becf6fcdfacb5cdd6179034c023a609d3218
+  data.tar.gz: 8f76a7eecfff70435931364f827571733cc6f4d9e7cc90d8f65276580eab0dbcd5cd8eddd5a146b3e7fe016b2f4d69a3dff177e77e941ef7bbe47e49b975d3dc

data/.github/workflows/ruby.yml

@@ -2,9 +2,9 @@ name: CI
 
 on:
   push:
-    branches: [ master ]
+    branches: [ main ]
   pull_request:
-    branches: [ master ]
+    branches: [ main ]
 
 jobs:
   tests:

data/README.md

@@ -36,4 +36,4 @@ Bug reports and pull requests are welcome on GitHub at https://github.com/[USERN
 
 ## Code of Conduct
 
-Everyone interacting in the PurlFetcher::Client project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/[USERNAME]/purl_fetcher-client/blob/master/CODE_OF_CONDUCT.md).
+Everyone interacting in the PurlFetcher::Client project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/[USERNAME]/purl_fetcher-client/blob/main/CODE_OF_CONDUCT.md).

data/lib/purl_fetcher/client/reader.rb

@@ -1,77 +1,48 @@
 class PurlFetcher::Client::Reader
   include Enumerable
-  attr_reader :input_stream, :settings, :range
+  attr_reader :host, :conn, :range
 
-  def initialize(input_stream, settings = {})
-    @settings = settings
-    @input_stream = input_stream
+  def initialize(host: 'https://purl-fetcher.stanford.edu', conn: nil)
+    @host = host
+    @conn = conn || Faraday.new(host) do |f|
+              f.response :json
+            end
     @range = {}
   end
 
-  def each
-    return to_enum(:each) unless block_given?
-
-    changes(first_modified: first_modified, target: target).each do |change, meta|
-      next unless target.nil? || (change['true_targets'] && change['true_targets'].include?(target))
-
-      public_xml = PurlFetcher::Client::PublicXmlRecord.new(change['druid'].sub('druid:', ''), settings)
-
-      yield public_xml, change, self
-    end
-  end
-
   def collection_members(druid)
     return to_enum(:collection_members, druid) unless block_given?
 
-    paginated_get("/collections/druid:#{druid.sub(/^druid:/, '')}/purls", 'purls').each do |obj, _meta|
-      yield PurlFetcher::Client::PublicXmlRecord.new(obj['druid'].sub('druid:', ''), settings), obj, self
+    paginated_get("/collections/druid:#{druid.delete_prefix('druid:')}/purls", 'purls').each do |obj, _meta|
+      yield obj['druid'].delete_prefix('druid:')
     end
   end
 
   private
 
-  def first_modified
-    settings['purl_fetcher.first_modified']
-  end
-
-  def target
-    settings['purl_fetcher.target']
-  end
-
-  ##
-  # @return [Enumerator]
-  def changes(params = {})
-    paginated_get('/docs/changes', 'changes', params)
-  end
-
-  ##
-  # @return [Enumerator]
-  def deletes(params = {})
-    paginated_get('/docs/deletes', 'deletes', params)
-  end
-
   ##
   # @return [Hash] a parsed JSON hash
-  def get(path, params = {})
-    JSON.parse(fetch(settings.fetch('purl_fetcher.api_endpoint', 'https://purl-fetcher.stanford.edu') + path, params))
-  end
+  def fetch(path, params)
+    response = conn.get(path, params: params)
 
-  def fetch(url, params)
-    if defined?(Manticore)
-      Manticore.get(url, query: params).body
-    else
-      HTTP.get(url, params: params).body
+    unless response.success?
+      if defined?(Honeybadger)
+        Honeybadger.context({ path:, params:, response_code: response.code, body: response.body })
+      end
+      raise PurlFetcher::Client::ResponseError, "Unsuccessful response from purl-fetcher"
     end
+
+    response.body
   end
 
   ##
   # For performance, and enumberable object is returned.
   #
   # @example operating on each of the results as they come in
-  #   paginated_get('/docs/changes', 'changes').map { |v| puts v.inspect }
+  #   paginated_get('/docs/collections/druid:123', 'purls').map { |v| puts v.inspect }
   #
   # @example getting all of the results and converting to an array
-  #   paginated_get('/docs/changes', 'changes').to_a
+  #   paginated_get('/docs/collections/druid:123', 'purls').to_a
   #
   # @return [Enumerator] an enumberable object
   def paginated_get(path, accessor, options = {})
@@ -83,7 +54,7 @@ class PurlFetcher::Client::Reader
       total    = 0
 
       loop do
-        data = get(path, { per_page: per_page, page: page }.merge(params))
+        data = fetch(path, { per_page: per_page, page: page }.merge(params))
         @range = data['range']
 
         total += data[accessor].length

data/lib/purl_fetcher/client/version.rb

@@ -1,5 +1,5 @@
 module PurlFetcher
   module Client
-    VERSION = "0.5.0"
+    VERSION = "1.0.0"
   end
 end

data/lib/purl_fetcher/client.rb

@@ -1,15 +1,14 @@
 require "purl_fetcher/client/version"
-require 'http'
-begin
-  require 'manticore' if defined? JRUBY_VERSION
-rescue LoadError
-end
+require 'faraday'
 
 module PurlFetcher
   module Client
-    require 'purl_fetcher/client/public_xml_record'
     require 'purl_fetcher/client/reader'
-    require 'purl_fetcher/client/deletes_reader'
-    # Your code goes here...
+    
+    # General error originating in PurlFetcher::Client
+    class Error < StandardError; end
+
+    # Raised when the response from the server is not successful
+    class ResponseError < Error; end
   end
 end

data/purl_fetcher-client.gemspec

@@ -20,13 +20,11 @@ Gem::Specification.new do |spec|
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
   spec.require_paths = ["lib"]
 
-  spec.add_dependency 'http'
-  spec.add_dependency 'nokogiri'
-  spec.add_dependency 'stanford-mods'
-  spec.add_dependency 'dor-rights-auth'
-  spec.add_dependency 'mods_display', '>= 1.0.0.alpha1'
+  spec.add_dependency 'faraday', '~> 2.1'
 
   spec.add_development_dependency "bundler"
+  spec.add_development_dependency "debug"
   spec.add_development_dependency "rake"
   spec.add_development_dependency "rspec", "~> 3.0"
+  spec.add_development_dependency "webmock"
 end

metadata

@@ -1,37 +1,37 @@
 --- !ruby/object:Gem::Specification
 name: purl_fetcher-client
 version: !ruby/object:Gem::Version
-  version: 0.5.0
+  version: 1.0.0
 platform: ruby
 authors:
 - Chris Beer
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2022-01-13 00:00:00.000000000 Z
+date: 2024-04-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: http
+  name: faraday
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '2.1'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '2.1'
 - !ruby/object:Gem::Dependency
-  name: nokogiri
+  name: bundler
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-  type: :runtime
+  type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
@@ -39,13 +39,13 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: stanford-mods
+  name: debug
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-  type: :runtime
+  type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
@@ -53,13 +53,13 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: dor-rights-auth
+  name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-  type: :runtime
+  type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
@@ -67,35 +67,21 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: mods_display
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: 1.0.0.alpha1
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: 1.0.0.alpha1
-- !ruby/object:Gem::Dependency
-  name: bundler
+  name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '3.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - ">="
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: '0'
+        version: '3.0'
 - !ruby/object:Gem::Dependency
-  name: rake
+  name: webmock
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -108,20 +94,6 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-- !ruby/object:Gem::Dependency
-  name: rspec
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '3.0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '3.0'
 description:
 email:
 - cabeer@stanford.edu
@@ -139,8 +111,6 @@ files:
 - bin/console
 - bin/setup
 - lib/purl_fetcher/client.rb
-- lib/purl_fetcher/client/deletes_reader.rb
-- lib/purl_fetcher/client/public_xml_record.rb
 - lib/purl_fetcher/client/reader.rb
 - lib/purl_fetcher/client/version.rb
 - purl_fetcher-client.gemspec
@@ -162,7 +132,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.2.32
+rubygems_version: 3.4.19
 signing_key:
 specification_version: 4
 summary: Traject-compatible reader implementation for streaming data from purl-fetcher

data/lib/purl_fetcher/client/deletes_reader.rb

@@ -1,21 +0,0 @@
-class PurlFetcher::Client::DeletesReader < PurlFetcher::Client::Reader
-  # Enumerate objects that should be deleted.
-  def each
-    return to_enum(:each) unless block_given?
-
-    deletes(first_modified: first_modified).each do |change|
-
-      public_xml = PurlFetcher::Client::PublicXmlRecord.new(change['druid'].sub('druid:', ''), settings)
-
-      yield public_xml, change, self
-    end
-
-    changes(first_modified: first_modified, target: target).each do |change|
-      public_xml = PurlFetcher::Client::PublicXmlRecord.new(change['druid'].sub('druid:', ''), settings)
-
-      next unless target.nil? || (change['false_targets'] && change['false_targets'].include?(target)) || (settings['skip_if_catkey'] && record.catkey)
-
-      yield public_xml, change, self
-    end
-  end
-end

data/lib/purl_fetcher/client/public_xml_record.rb

@@ -1,205 +0,0 @@
-require 'nokogiri'
-require 'stanford-mods'
-require 'mods_display'
-require 'dor/rights_auth'
-
-module PurlFetcher::Client
-  class PublicXmlRecord
-    attr_reader :druid, :options
-
-    def self.fetch(url)
-      if defined?(JRUBY_VERSION)
-        response = Manticore.get(url)
-        response.body if response.code == 200
-      else
-        response = HTTP.get(url)
-        response.body if response.status.ok?
-      end
-    end
-
-    def initialize(druid, options = {})
-      @druid = druid
-      @options = options
-    end
-
-    def searchworks_id
-      catkey.nil? ? druid : catkey
-    end
-
-    # @return catkey value from the DOR identity_metadata, or nil if there is no catkey
-    def catkey
-      get_value(public_xml_doc.xpath("/publicObject/identityMetadata/otherId[@name='catkey']"))
-    end
-
-    # @return objectLabel value from the DOR identity_metadata, or nil if there is no barcode
-    def label
-      get_value(public_xml_doc.xpath('/publicObject/identityMetadata/objectLabel'))
-    end
-
-    def get_value(node)
-      (node && node.first) ? node.first.content : nil
-    end
-
-    def stanford_mods
-      @smods_rec ||= Stanford::Mods::Record.new.tap do |smods_rec|
-        smods_rec.from_str(mods.to_s)
-      end
-    end
-
-    def mods_display
-      @mods_display ||= ModsDisplay::HTML.new(stanford_mods)
-    end
-
-    def public_xml
-      @public_xml ||= self.class.fetch(purl_base_url + "/#{druid}.xml")
-    end
-
-    def public_xml?
-      !!public_xml
-    end
-
-    def public_xml_doc
-      @public_xml_doc ||= Nokogiri::XML(public_xml)
-    end
-
-    def mods
-      @mods ||= if public_xml_doc.xpath('/publicObject/mods:mods', mods: 'http://www.loc.gov/mods/v3').any?
-        public_xml_doc.xpath('/publicObject/mods:mods', mods: 'http://www.loc.gov/mods/v3').first
-      else
-        if defined?(Honeybadger)
-          Honeybadger.notify(
-            'Unable to find MODS in the public xml; falling back to stand-along mods document',
-            context: { druid: druid }
-          )
-        end
-
-        Nokogiri::XML(self.class.fetch(purl_base_url + "/#{druid}.mods"))
-      end
-    end
-
-    # @return true if the identityMetadata has <objectType>collection</objectType>, false otherwise
-    def is_collection
-      object_type_nodes = public_xml_doc.xpath('//objectType')
-      object_type_nodes.find_index { |n| %w(collection set).include? n.text.downcase }
-    end
-
-    # value is used to tell SearchWorks UI app of specific display needs for objects
-    # this comes from the <thumb> element in publicXML or the first image found (as parsed by discovery-indexer)
-    # @return [String] filename or nil if none found
-    def thumb
-      return if is_collection
-      encoded_thumb if %w(book image manuscript map webarchive-seed).include?(dor_content_type)
-    end
-
-    # the value of the type attribute for a DOR object's contentMetadata
-    #  more info about these values is here:
-    #    https://consul.stanford.edu/display/chimera/DOR+content+types%2C+resource+types+and+interpretive+metadata
-    #    https://consul.stanford.edu/display/chimera/Summary+of+Content+Types%2C+Resource+Types+and+their+behaviors
-    # @return [String]
-    def dor_content_type
-      public_xml_doc.xpath('//contentMetadata/@type').text
-    end
-
-    # the thumbnail in publicXML, falling back to the first image if no thumb node is found
-     # @return [String] thumb filename with druid prepended, e.g. oo000oo0001/filename withspace.jp2
-     def parse_thumb
-       unless public_xml_doc.nil?
-         thumb = public_xml_doc.xpath('//thumb')
-         # first try and parse what is in the thumb node of publicXML, but fallback to the first image if needed
-         if thumb.size == 1
-           thumb.first.content
-         elsif thumb.size == 0 && parse_sw_image_ids.size > 0
-           parse_sw_image_ids.first
-         else
-           nil
-         end
-       end
-     end
-
-     # the druid and id attribute of resource/file and objectId and fileId of the
-     # resource/externalFile elements that match the image, page, or thumb resource type, including extension
-     # Also, prepends the corresponding druid and / specifically for Searchworks use
-     # @return [Array<String>] filenames
-     def parse_sw_image_ids
-       public_xml_doc.xpath('//resource[@type="page" or @type="image" or @type="thumb"]').map do |node|
-         node.xpath('./file[@mimetype="image/jp2"]/@id').map{ |x| "#{@druid.gsub('druid:','')}/" + x } << node.xpath('./externalFile[@mimetype="image/jp2"]').map do |y|
-           "#{y.attributes['objectId'].text.split(':').last}" + "/" + "#{y.attributes['fileId']}"
-         end
-       end.flatten
-     end
-
-     def collections
-       @collections ||= predicate_druids('isMemberOfCollection').map do |druid|
-         PublicXmlRecord.new(druid, options)
-       end
-     end
-
-     def constituents
-       @constituents ||= predicate_druids('isConstituentOf').map do |druid|
-         PublicXmlRecord.new(druid, options)
-       end
-     end
-
-     def items(&block)
-       return [] unless is_collection
-
-       purl_fetcher_client.collection_members(druid, &block)
-     end
-
-     # the thumbnail in publicXML properly URI encoded, including the slash separator
-     # @return [String] thumb filename with druid prepended, e.g. oo000oo0001%2Ffilename%20withspace.jp2
-    def encoded_thumb
-      thumb=parse_thumb
-      return unless thumb
-      thumb_druid=thumb.split('/').first # the druid (before the first slash)
-      thumb_filename=thumb.split(/[a-zA-Z]{2}[0-9]{3}[a-zA-Z]{2}[0-9]{4}[\/]/).last # everything after the druid
-      "#{thumb_druid}%2F#{ERB::Util.url_encode(thumb_filename)}"
-    end
-
-    # get the druids from predicate relationships in rels-ext from public_xml
-    # @return [Array<String>, nil] the druids (e.g. ww123yy1234) from the rdf:resource of the predicate relationships, or nil if none
-    def predicate_druids(predicate, predicate_ns = 'info:fedora/fedora-system:def/relations-external#')
-      ns_hash = { 'rdf' => 'http://www.w3.org/1999/02/22-rdf-syntax-ns#', 'pred_ns' => predicate_ns }
-      xpth = "/publicObject/rdf:RDF/rdf:Description/pred_ns:#{predicate}/@rdf:resource"
-      pred_nodes = public_xml_doc.xpath(xpth, ns_hash)
-      pred_nodes.reject { |n| n.value.empty? }.map do |n|
-        n.value.split('druid:').last
-      end
-    end
-
-    def druid_tree
-      druid.match(/(..)(...)(..)(....)/).captures.join('/')
-    end
-
-    def rights_xml
-      @rights_xml ||= public_xml_doc.xpath('//rightsMetadata').to_s
-    end
-
-    def rights
-      @rights ||= ::Dor::RightsAuth.parse(rights_xml)
-    end
-
-    def public?
-      rights.world_unrestricted?
-    end
-
-    def stanford_only?
-      rights.stanford_only_unrestricted?
-    end
-
-    def purl_base_url
-      options[:purl_url]&.sub(%r{/$}, '') || 'https://purl.stanford.edu'
-    end
-
-    def purl_fetcher_api_endpoint
-      options[:purl_fetcher_url] || 'https://purl-fetcher.stanford.edu'
-    end
-
-    def purl_fetcher_client
-      @purl_fetcher_client ||= PurlFetcher::Client::Reader.new(
-        nil,
-        'purl_fetcher.api_endpoint' => purl_fetcher_api_endpoint
-      )
-    end
-  end
-end