gared 0.0.29 → 0.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 5a4f6f4cbc307c097bf84e4308d7cc76257583ba58f97d0c861ebd79e1e362e6
-  data.tar.gz: 83aca016e843de3bbdbdfbeecdf1b4b544a376d3205970a810c5076ce3d3466e
+  metadata.gz: ae6b9daf5b73b6ff01acc3f098ad45ae0dccac12ea146f6966d58e25c3d8a74e
+  data.tar.gz: 19396d2e5e6701a22dd7d27e49491a9bd816a60d48278ca5562843c305f88282
 SHA512:
-  metadata.gz: 686d91870739b68c421f68c3a55fd8443dec0f4747118137d0cd256758e67e223c9db5617c7cbd408a4295c32936741172f8865dd96c1303a318841ff4157a41
-  data.tar.gz: 85336cda8af09b48fa3515d90efb5898dbe28592282c17ce3f352cde96ba459aa50a9cab7c2b32c6d32df4afe52a547d7a999a02a19eb4c4edf28e5beff729fd
+  metadata.gz: c37a03e8f88f7c9b7d63761ced83736bfbedf55e3e94aee1c0fa9d53855d6d65a899a0e171d142ae46031dfd177fa3214e2cf8a4eb844f1f82db13b355ada1df
+  data.tar.gz: f4dd892a74e7fd1282e200f30ea1ab76bd87ebcd30629ec64a6c8c47a87d2d4eeef67481dd35454fe7f967a46b7a6da23bc3274ee7bf02c3fb87903a99720945

data/lib/gared/primo.rb

@@ -3,8 +3,8 @@ require 'rest-client'
 
 module Gared
   class Primo
-    def initialize(url, institution)
-      @options = {url: url, institution: institution}
+    def initialize(url, vid, scope, apikey)
+      @options = {url: url, vid: vid, scope: scope, apikey: apikey}
     end
     def uri_escape(s)
       p = URI::Parser.new
@@ -27,48 +27,50 @@ module Gared
     def query_publications_by_person(person, ctx = nil)
       ret = []
       begin
-        url = @options[:url]+"?institution=#{@options[:institution]}&query=creator,contains,#{uri_escape(person)}&indx=1&bulkSize=50&query=facet_rtype,exact,books&json=true"
-        json = JSON.parse(RestClient.get(url))
-        total = json['SEGMENTS']['JAGROOT']['RESULT']['DOCSET']['@TOTALHITS'].to_i
-        start_at = 1
-        recs = json['SEGMENTS']['JAGROOT']['RESULT']['DOCSET']['DOC'] # stash the records
+        base_url = "#{@options[:url]}?vid=#{@options[:vid]}&scope=#{@options[:scope]}&q=creator,contains,#{uri_escape(person)}&qInclude=facet_rtype,exact,books&apikey=#{@options[:apikey]}&limit=50"
+        json = JSON.parse(RestClient.get(base_url))
+        total = json['info']['total'].to_i
+        start_at = 0
+        recs = json['docs'] # stash the records
         while recs.length < total
           start_at += 50
-          url = @options[:url]+"?institution=#{@options[:institution]}&query=creator,contains,#{uri_escape(person)}&indx=#{start_at}&bulkSize=50&query=facet_rtype,exact,books&json=true"
+          url = base_url+"&offset=#{start_at}"
           json = JSON.parse(RestClient.get(url))
-          recs += json['SEGMENTS']['JAGROOT']['RESULT']['DOCSET']['DOC']
-          sleep 1 # respect the server and avoid flood-blocking
+          recs += json['docs']
+          sleep 0.5 # respect the server and avoid flood-blocking
         end
         recs.each do |r|
           begin
-            deets = r['PrimoNMBib']['record']['display']
+            deets = r['pnx']['display'] # the fields inside are now always an array!
             p = Publication.new(ctx)
-            p.title = deets['title']
-            p.author_line = deets['creator']
-            p.language = deets['language']
-            p.notes = "#{deets['format']}\n#{deets['subject']}"
-            p.publisher_line = deets['publisher']
-            p.pub_year = deets['creationdate']
-            p.source_id = r['PrimoNMBib']['record']['control']['sourcerecordid']
-            # collect additional URLS from record, for clients to be able to determine whether a scanned object exists
-            additional_urls = []
-            deets.keys.each do |key|
-              if deets[key].class == Array
-                deets[key].each do |kkey|
-                  additional_urls << kkey if kkey.class == String && kkey =~ /https?:[^\s]/
-                end
-              elsif deets[key].class == String
-                additional_urls << deets[key] if deets[key] =~ /https?:[^\s]/
-              end
-            end
-            p.additional_urls = additional_urls if additional_urls.length > 0
+            p.title = deets['title'].join('; ') 
+            p.author_line = deets['creator'].join('; ')
+            p.author_line += deets['contributor'].join('; ') if deets['contributor']
+            p.language = deets['language'].join('; ')
+            p.notes = deets['format'].join('; ')+r['pnx']['search']['subject'].join('; ') # "#{deets['format']}\n#{deets['subject']}"
+            p.publisher_line = deets['publisher'].join('; ')
+            p.pub_year = deets['creationdate'].join('; ')
+            p.source_id = r['pnx']['control']['sourcerecordid'].join('; ')
+            ## collect additional URLS from record, for clients to be able to determine whether a scanned object exists
+            # commented out for now, as it needs to be rewritten for the new Primo output structure
+            #additional_urls = []
+            #deets.keys.each do |key|
+            #  if deets[key].class == Array
+            #    deets[key].each do |kkey|
+            #      additional_urls << kkey if kkey.class == String && kkey =~ /https?:[^\s]/
+            #    end
+            #  elsif deets[key].class == String
+            #    additional_urls << deets[key] if deets[key] =~ /https?:[^\s]/
+            #  end
+            #end
+            #p.additional_urls = additional_urls if additional_urls.length > 0
             h = Holding.new
             h.source_id = p.source_id
-            h.source_name = 'Primo:'+@options[:institution]
+            h.source_name = 'Primo:'+@options[:vid]
             
             begin
-              h.location = r['LIBRARIES']['LIBRARY'][0].nil? ? r['LIBRARIES']['LIBRARY']['callNumber'] : r['LIBRARIES']['LIBRARY'][0]['callNumber'] # there seem to be two cases, different between NLI and TAU, for example; there also seems to not even be a LIBRARIES key for some electronic resources. We're skipping those.
-            rescue Exception
+              h.location = r['pnx']['search']['callnumber']
+            rescue Exception # We're skipping things without a callnumber, as they are not resources within the library itself.
               puts $!
             end
             p.add_holding(h)

data/test/test_gared.rb

@@ -1,6 +1,6 @@
-require 'minitest/byebug' if ENV['DEBUG']
 require 'minitest/autorun'
 require 'gared'
+require 'minitest/debugger' if ENV['DEBUG']
 
 class GaredTest < Minitest::Test
 
@@ -22,8 +22,8 @@ class GaredTest < Minitest::Test
 
   # temporarily disabled until we find another Primo server to test against
   def test_primo_query_publications_by_person
-    puts "Testing Primo"
-    primo = Gared::Primo.new('http://tau-primo.hosted.exlibrisgroup.com/PrimoWebServices/xservice/search/brief', 'TAU')
+    puts "Testing Primo (did you remember to put a key in PRIMO_API_KEY?)"
+    primo = Gared::Primo.new('https://api-eu.hosted.exlibrisgroup.com/primo/v1/search', 'HAU', 'books_and_more', ENV['PRIMO_API_KEY'])
     refute_nil primo
     recs = primo.query_publications_by_person('אילנאה')
     refute_nil recs

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: gared
 version: !ruby/object:Gem::Version
-  version: 0.0.29
+  version: 0.1.0
 platform: ruby
 authors:
 - Asaf Bartov
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-04-06 00:00:00.000000000 Z
+date: 2024-02-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: watir
@@ -102,7 +102,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.4.10
+rubygems_version: 3.5.1
 signing_key:
 specification_version: 4
 summary: Scrape Hebrew bibliography sources