[0.2] Make elasticsearch the default value for output_sink (#176) (#205)

Backports the following commits to 0.2:
 - Make elasticsearch the default value for output_sink (#176)

Co-authored-by: Devesh Rahatekar <79015420+devesh-2002@users.noreply.github.com>

lib/crawler/api/config.rb

@@ -169,7 +169,7 @@ class Config # rubocop:disable Metrics/ClassLength
         binary_content_extraction_enabled: false,
         binary_content_extraction_mime_types: [],
 
-        output_sink: :console,
+        output_sink: :elasticsearch,
         url_queue: :memory_only,
         threads_per_crawl: 10,
 

spec/lib/crawler/api/config_spec.rb

@@ -30,15 +30,15 @@
       end.to raise_error(ArgumentError, /Unexpected configuration options.*fubar/)
     end
 
-    it 'can define a crawl with elasticsearch output' do
+    it 'can define a crawl with console output' do
       config = Crawler::API::Config.new(
         domains:,
-        output_sink: :elasticsearch
+        output_sink: :console
       )
 
       expect(config.domain_allowlist.map(&:to_s)).to match_array(expected_allowlist)
       expect(config.seed_urls.map(&:to_s).to_a).to match_array(expected_seed_urls)
-      expect(config.output_sink).to eq(:elasticsearch)
+      expect(config.output_sink).to eq(:console)
       expect(config.output_dir).to be_nil
     end
 
@@ -62,7 +62,7 @@
 
       expect(config.domain_allowlist.map(&:to_s)).to match_array(expected_allowlist)
       expect(config.seed_urls.map(&:to_s).to_a).to match_array(expected_seed_urls)
-      expect(config.output_sink).to eq(:console)
+      expect(config.output_sink).to eq(:elasticsearch)
       expect(config.output_dir).to be_nil
     end
 

spec/lib/crawler/api/crawl_spec.rb

@@ -14,7 +14,14 @@
     Crawler::API::Config.new(
       domains: [
         { url: }
-      ]
+      ],
+      output_sink: :elasticsearch,
+      output_index: 'some-index-name',
+      elasticsearch: {
+        host: 'http://localhost',
+        port: 1234,
+        api_key: 'key'
+      }
     )
   end
 
@@ -47,7 +54,7 @@
   #-------------------------------------------------------------------------------------------------
   it 'has a config' do
     expect(subject.config.seed_urls.map(&:to_s).to_a).to eq(["#{url}/"])
-    expect(subject.config.output_sink).to eq(:console)
+    expect(subject.config.output_sink).to eq(:elasticsearch)
   end
 
   it 'has a output sink' do

spec/lib/crawler/coordinator_spec.rb

@@ -140,7 +140,7 @@
         {
           domains:,
           results_collection:,
-          output_sink: 'console',
+          output_sink: :console,
           purge_crawl_enabled: true
         }
       end

spec/lib/crawler/output_sink_spec.rb

@@ -32,11 +32,17 @@
     it 'should return a new sink object of a correct type' do
       config = Crawler::API::Config.new(
         domains:,
-        output_sink: 'console'
+        output_sink: :elasticsearch,
+        output_index: 'some-index-name',
+        elasticsearch: {
+          host: 'http://localhost',
+          port: 1234,
+          api_key: 'key'
+        }
       )
 
       sink = Crawler::OutputSink.create(config)
-      expect(sink).to be_kind_of(Crawler::OutputSink::Console)
+      expect(sink).to be_kind_of(Crawler::OutputSink::Elasticsearch)
     end
   end
 end