gared 0.0.23 → 0.0.27

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: cd1e7f535a0650e0251fec57b3572e49dda88b189b96fe1d1b630acc5e147bb4
-  data.tar.gz: b606f6169bdf2cac88f5d29cec6bf4e5464a639bc73b655a24c61aecf7593cd1
+  metadata.gz: e8dcff1820d0b68f25346b0899c3417eb0aa758ef282c65bf008aa0c36e5dd2a
+  data.tar.gz: 21277a0b51dbd03c75598e1d5ca37c09875d32e62e668facec2c82f335f3c78c
 SHA512:
-  metadata.gz: b5c082ab85a8a7fb4cf5c23af7ebc35584751ebcaf88defc1b4f8c8d808d5cb3ff5d213db4b07687bfae49fda11b12f6963c9c6d2bd2e6b1d2e5edcc487e6e4b
-  data.tar.gz: a4415463242669077a504252094c2e93f63469fe6fcd4faeeee7a5cceb852b5325608dd5255991c79f04d725856ac61296023301c39af0a4f48288dbe1ddad70
+  metadata.gz: d37c27081fb9385373d0336ac2d8d3f270e35c520ae180bfcea85e51f5fe13ae157fe6c2d8c97407890f0a4f899c8f416a757941470e3cc0cb8471e65ce22cca
+  data.tar.gz: 86f92c9ca4609bdeb31180bc6e63f46c76f212bc5665b3acd6997510cb91459b5a11356b44be07f707a626d512074f19c466d9cc085caf38f2e8fde0230a2604

data/lib/gared/googlebooks.rb

@@ -5,9 +5,13 @@ module Gared
     def initialize(api_key, page_size = '40')
       @options = {api_key: api_key, maxResults: page_size}
     end
-
+    def uri_escape(s)
+      p = URI::Parser.new
+      return p.escape(s)
+    end
+  
     def query_publications_by_person(person, ctx = nil)
-      url = "https://www.googleapis.com/books/v1/volumes?q=inauthor:#{URI.escape(person)}&filter=full&key=#{@options[:api_key]}&maxResults=#{@options[:maxResults]}"
+      url = "https://www.googleapis.com/books/v1/volumes?q=inauthor:#{uri_escape(person)}&filter=full&key=#{@options[:api_key]}&maxResults=#{@options[:maxResults]}"
       resp = JSON.parse(RestClient.get(url))
     
       total = resp['totalItems']

data/lib/gared/nli_api.rb

@@ -5,7 +5,11 @@ module Gared
     def initialize(url, api_key)
       @options = {url: url, api_key: api_key}
     end
-
+    def uri_escape(s)
+      p = URI::Parser.new
+      return p.escape(s)
+    end
+  
     def query_persons(q)
     end
 
@@ -36,15 +40,15 @@ module Gared
       ret = []
       begin
         # first run obtain counts for the query
-        escaped_person = URI.escape(person)
-        url = @options[:url]+"?api_key=#{@options[:api_key]}&query=creator,contains,#{escaped_person},AND;language,exact,heb&sort_field=title&material_type=books&count_mode=true"
+        escaped_person = uri_escape(person)
+        url = @options[:url]+"?api_key=#{@options[:api_key]}&query=creator,contains,#{escaped_person},AND;language,exact,heb&sort_field=title&material_type=book&count_mode=true"
         json = JSON.parse(RestClient::Resource.new(url,verify_ssl: OpenSSL::SSL::VERIFY_NONE).get)
         total = json['countInfos']['total']
         # then start loading the results
         result_page = 1
         recs = []
         while recs.length < total
-          url = @options[:url]+"?api_key=#{@options[:api_key]}&query=creator,contains,#{escaped_person},AND;language,exact,heb&sort_field=title&material_type=books&result_page=#{result_page}"
+          url = @options[:url]+"?api_key=#{@options[:api_key]}&query=creator,contains,#{escaped_person},AND;language,exact,heb&sort_field=title&material_type=book&result_page=#{result_page}"
           puts "DBG: retrieving results page #{result_page}"
           json = JSON.parse(RestClient::Resource.new(url,verify_ssl: OpenSSL::SSL::VERIFY_NONE).get)
           recs += json
@@ -79,7 +83,7 @@ module Gared
           end
         end
         # TODO: also collect IIIF links for the *subset* of titles that have them, using the availability_type param.  No way to get that in the above query -- the fields are not emitted.
-        # the URL is like https://api.nli.org.il/openlibrary/search?api_key=(((KEY)))&query=title,contains,querystring&availability_type=online_and_api_access&material_type=books
+        # the URL is like https://api.nli.org.il/openlibrary/search?api_key=(((KEY)))&query=title,contains,querystring&availability_type=online_and_api_access&material_type=book
       rescue Exception
         puts $!
       end

data/lib/gared/primo.rb

@@ -6,7 +6,11 @@ module Gared
     def initialize(url, institution)
       @options = {url: url, institution: institution}
     end
-
+    def uri_escape(s)
+      p = URI::Parser.new
+      return p.escape(s)
+    end
+  
     def query_persons(q)
     end
 
@@ -23,14 +27,14 @@ 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"
+        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
         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 = @options[:url]+"?institution=#{@options[:institution]}&query=creator,contains,#{uri_escape(person)}&indx=#{start_at}&bulkSize=50&query=facet_rtype,exact,books&json=true"
           json = JSON.parse(RestClient.get(url))
           recs += json['SEGMENTS']['JAGROOT']['RESULT']['DOCSET']['DOC']
           sleep 1 # respect the server and avoid flood-blocking

data/lib/gared.rb

@@ -9,5 +9,4 @@ module Gared
   require 'gared/googlebooks'
   require 'gared/nli_api'
   # ...
-
 end

data/test/test_gared.rb

@@ -4,44 +4,40 @@ require 'gared'
 
 class GaredTest < Minitest::Test
 
-  def test_nli_api_query_publicatios_by_person
+  def test_nli_api_query_publications_by_person
     if ENV['NLI_API_KEY'].nil?
       puts "skipping NLI API test because NLI_API_KEY envvar is not set"
       return
     end
     puts "Testing NLI API"
+    byebug
     nli = Gared::Nli_Api.new('https://api.nli.org.il/openlibrary/search', ENV['NLI_API_KEY'])
     refute_nil nli
-    recs = nli.query_publications_by_person('ביאליק')
-    #recs = nli.query_publications_by_person('אילנאה')
+    #recs = nli.query_publications_by_person('ביאליק')
+    recs = nli.query_publications_by_person('אילנאה')
     refute_nil recs
     refute_empty(recs)
     refute_empty(recs[0].title)
   end
 
-  def test_primo_query_publicatios_by_person
-    puts "Testing Primo"
-    primo = Gared::Primo.new('http://primo.nli.org.il/PrimoWebServices/xservice/search/brief', 'NNL')
-    refute_nil primo
-    recs = primo.query_publications_by_person('אילנאה')
-    refute_nil recs
-    refute_empty(recs)
-    refute_empty(recs[0].title)
-  end
+# 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://primo.nli.org.il/PrimoWebServices/xservice/search/brief', 'NNL')
+#    refute_nil primo
+#    recs = primo.query_publications_by_person('אילנאה')
+#    refute_nil recs
+#    refute_empty(recs)
+#    refute_empty(recs[0].title)
+#  end
 
-  def test_aleph_query_publicatios_by_person
-    puts "Testing Aleph"
-    aleph = Gared::Aleph.new('aleph.nli.org.il', 9991, 'NNL01')
-    refute_nil aleph
-    recs = aleph.query_publications_by_person('אילנאה')
-    refute_nil recs
-    refute_empty(recs)
-    refute_empty(recs[0].title)
-  end
-
-  def test_googlebooks_query_publicatios_by_person
+  def test_googlebooks_query_publications_by_person
+    if ENV['GOOGLE_API_KEY'].nil?
+      puts "skipping Google Books API test because GOOGLE_API_KEY envvar is not set"
+      return
+    end
     puts "Testing Google Books"
-    gb = Gared::Googlebooks.new('AIzaSyCE2WFqTPdxAz1wv2f33hMfPWIF4tcocgM') # a key I made just for testing this gem. Please do not abuse.
+    gb = Gared::Googlebooks.new(ENV['GOOGLE_API_KEY'])
     refute_nil gb
     recs = gb.query_publications_by_person('מנדלי')
     refute_nil recs
@@ -49,7 +45,7 @@ class GaredTest < Minitest::Test
     refute_empty(recs[0].title)
   end
 
-  def test_hebrewbooks_query_publicatios_by_person
+  def test_hebrewbooks_query_publications_by_person
     skip("Skipping testing Hebrewbooks because chromedriver not found") unless `chromedriver -v` =~ /ChromeDriver/
     puts "Testing Hebrewbooks"
     hb = Gared::Hebrewbooks.new
@@ -60,7 +56,7 @@ class GaredTest < Minitest::Test
     refute_empty(recs[0].title)
   end
 
-  def test_idea_query_publicatios_by_person
+  def test_idea_query_publications_by_person
     skip("Skipping testing IDEA because chromedriver not found") unless `chromedriver -v` =~ /ChromeDriver/
     puts "Testing IDEA"
     idea = Gared::Idea.new('http://infocenters.co.il/RAANANA/')
@@ -74,4 +70,4 @@ class GaredTest < Minitest::Test
     assert_empty(recs)
   end
 
-end
+end

metadata

@@ -1,29 +1,15 @@
 --- !ruby/object:Gem::Specification
 name: gared
 version: !ruby/object:Gem::Version
-  version: 0.0.23
+  version: 0.0.27
 platform: ruby
 authors:
 - Asaf Bartov
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2021-05-13 00:00:00.000000000 Z
+date: 2023-01-28 00:00:00.000000000 Z
 dependencies:
-- !ruby/object:Gem::Dependency
-  name: zoom
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0.5'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0.5'
 - !ruby/object:Gem::Dependency
   name: watir
   requirement: !ruby/object:Gem::Requirement
@@ -87,7 +73,6 @@ extensions: []
 extra_rdoc_files: []
 files:
 - lib/gared.rb
-- lib/gared/aleph.rb
 - lib/gared/googlebooks.rb
 - lib/gared/hebrewbooks.rb
 - lib/gared/holding.rb
@@ -102,7 +87,7 @@ homepage: https://gitlab.com/abartov/gared
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -117,8 +102,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.1.4
-signing_key: 
+rubygems_version: 3.2.32
+signing_key:
 specification_version: 4
 summary: Scrape Hebrew bibliography sources
 test_files:

data/lib/gared/aleph.rb

@@ -1,80 +0,0 @@
-# Z39.50 values according to https://www.loc.gov/z3950/agency/bib1.html
-# and NLI info according to http://web.nli.org.il/sites/NLI/Hebrew/infochannels/librarians/Pages/Z39.50.aspx 
-# Name of Database: NNL01
-# Host name: aleph.nli.org.il
-# IP address: 192.114.7.200
-# Port: 9991
-# Character-set: UTF-8
-# We support the following record syntaxes:
-# USMARC, OPAC, XML
-# We support the following word searches:
-# 1016, 1017, 1,1003, 1004,4,21,30,31,7,12,1007,1031,1007,5028,1033
-# We support the following phrase searches:
-# 7,12,1,1003,1004,4,21,15
-# We support the following sorts:
-# 1,4,30,31,1003
-
-module Gared
-  require 'zoom'
-  require 'nokogiri'
-  class Aleph
-    def initialize(host, port, database, syntax = 'USMARC')
-      @options = {host: host, port: port, database: database, syntax: syntax}
-    end
-    def query_persons(q)
-    end
-
-    def query_person(person)
-    end
-
-    def query_publications(q)
-    end
-
-    def query_publication(publication)
-    end
-
-    def query_publications_by_person(person, ctx = nil)
-      ZOOM::Connection.open(@options[:host], @options[:port]) do |conn|
-        conn.database_name = @options[:database] # 'aleph.nli.org.il',9991
-        conn.preferred_record_syntax = @options[:syntax]
-        rset = conn.search("@attr 1=1003 @attr 2=3 @attr 4=1 \"#{person}\"")
-        rr = rset.records
-        return nil if rr.nil? or rr.empty?
-        ret = []
-        rr.each do |r|
-          xml = Nokogiri::Slop(r.xml)
-          xml.remove_namespaces! # keeps biting me :)
-          # these scrapes are based on the National Library of Israel usage. No attempt to make it generic. :)
-          p = Publication.new(ctx)
-          begin
-            p.author_line = xml.xpath('//datafield[@tag=\'100\']/subfield[@code=\'a\']')[0].text
-            # puts "author: #{p.author_line}" # DEBUG
-          rescue
-            nil
-          end
-          begin
-            p.title = xml.xpath('//datafield[@tag=\'245\']/subfield[@code=\'a\']')[0].text
-            # puts "title: #{p.title}" # DEBUG
-          rescue
-            nil
-          end
-          begin
-            p.notes = xml.xpath('//datafield[@tag=\'500\']/subfield[@code=\'a\']').collect{|note| note.text}.join("\n")
-          rescue
-            nil
-          end
-          begin
-            h = Holding.new
-            h.source_id = xml.xpath('//datafield[@tag=\'090\']/subfield[@code=\'a\']')[0].text
-            h.source_name = @options[:database]
-            p.add_holding(h)
-            ret << p
-          rescue
-            nil # ignore records with no holdings; they may be archival files or other non-publications
-          end # 
-        end
-        return ret
-      end
-    end
-  end
-end