wayfarer 0.4.6 → 0.4.8
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/.env +17 -0
- data/.github/workflows/lint.yaml +27 -0
- data/.github/workflows/release.yaml +30 -0
- data/.github/workflows/tests.yaml +21 -0
- data/.gitignore +5 -1
- data/.rubocop.yml +36 -0
- data/.vale.ini +8 -0
- data/.yardopts +1 -3
- data/Dockerfile +6 -4
- data/Gemfile +24 -0
- data/Gemfile.lock +274 -164
- data/Rakefile +7 -51
- data/bin/wayfarer +1 -1
- data/docker-compose.yml +23 -13
- data/docs/cookbook/consent_screen.md +2 -2
- data/docs/cookbook/executing_javascript.md +3 -3
- data/docs/cookbook/navigation.md +12 -12
- data/docs/cookbook/querying_html.md +3 -3
- data/docs/cookbook/screenshots.md +2 -2
- data/docs/guides/callbacks.md +25 -125
- data/docs/guides/cli.md +71 -0
- data/docs/guides/configuration.md +10 -35
- data/docs/guides/development.md +67 -0
- data/docs/guides/handlers.md +60 -0
- data/docs/guides/index.md +1 -0
- data/docs/guides/jobs.md +142 -31
- data/docs/guides/navigation.md +1 -1
- data/docs/guides/networking/capybara.md +13 -22
- data/docs/guides/networking/custom_adapters.md +103 -41
- data/docs/guides/networking/ferrum.md +4 -4
- data/docs/guides/networking/http.md +9 -13
- data/docs/guides/networking/selenium.md +10 -11
- data/docs/guides/pages.md +78 -10
- data/docs/guides/redis.md +10 -0
- data/docs/guides/routing.md +156 -0
- data/docs/guides/tasks.md +53 -9
- data/docs/guides/tutorial.md +66 -0
- data/docs/guides/user_agents.md +115 -0
- data/docs/index.md +17 -40
- data/lib/wayfarer/base.rb +125 -46
- data/lib/wayfarer/batch_completion.rb +60 -0
- data/lib/wayfarer/callbacks.rb +22 -48
- data/lib/wayfarer/cli/route_printer.rb +85 -89
- data/lib/wayfarer/cli.rb +103 -0
- data/lib/wayfarer/gc.rb +18 -6
- data/lib/wayfarer/handler.rb +15 -7
- data/lib/wayfarer/kv.rb +28 -0
- data/lib/wayfarer/logging.rb +38 -0
- data/lib/wayfarer/middleware/base.rb +2 -0
- data/lib/wayfarer/middleware/batch_completion.rb +19 -0
- data/lib/wayfarer/middleware/chain.rb +7 -1
- data/lib/wayfarer/middleware/content_type.rb +59 -0
- data/lib/wayfarer/middleware/controller.rb +19 -15
- data/lib/wayfarer/middleware/dedup.rb +22 -13
- data/lib/wayfarer/middleware/dispatch.rb +17 -4
- data/lib/wayfarer/middleware/normalize.rb +7 -14
- data/lib/wayfarer/middleware/redis.rb +15 -0
- data/lib/wayfarer/middleware/router.rb +33 -35
- data/lib/wayfarer/middleware/stage.rb +5 -5
- data/lib/wayfarer/middleware/uri_parser.rb +31 -0
- data/lib/wayfarer/middleware/user_agent.rb +49 -0
- data/lib/wayfarer/networking/capybara.rb +1 -1
- data/lib/wayfarer/networking/context.rb +14 -3
- data/lib/wayfarer/networking/ferrum.rb +1 -4
- data/lib/wayfarer/networking/follow.rb +14 -7
- data/lib/wayfarer/networking/http.rb +1 -1
- data/lib/wayfarer/networking/pool.rb +23 -13
- data/lib/wayfarer/networking/selenium.rb +15 -7
- data/lib/wayfarer/networking/strategy.rb +2 -2
- data/lib/wayfarer/page.rb +34 -14
- data/lib/wayfarer/parsing/xml.rb +6 -6
- data/lib/wayfarer/parsing.rb +21 -0
- data/lib/wayfarer/redis/barrier.rb +26 -21
- data/lib/wayfarer/redis/counter.rb +18 -9
- data/lib/wayfarer/redis/pool.rb +1 -1
- data/lib/wayfarer/redis/resettable.rb +19 -0
- data/lib/wayfarer/routing/dsl.rb +166 -30
- data/lib/wayfarer/routing/hash_stack.rb +33 -0
- data/lib/wayfarer/routing/matchers/custom.rb +8 -5
- data/lib/wayfarer/routing/matchers/{suffix.rb → empty_params.rb} +2 -6
- data/lib/wayfarer/routing/matchers/host.rb +15 -9
- data/lib/wayfarer/routing/matchers/path.rb +11 -31
- data/lib/wayfarer/routing/matchers/query.rb +41 -17
- data/lib/wayfarer/routing/matchers/result.rb +12 -0
- data/lib/wayfarer/routing/matchers/scheme.rb +13 -5
- data/lib/wayfarer/routing/matchers/url.rb +13 -5
- data/lib/wayfarer/routing/path_consumer.rb +130 -0
- data/lib/wayfarer/routing/path_finder.rb +151 -23
- data/lib/wayfarer/routing/result.rb +1 -1
- data/lib/wayfarer/routing/root_route.rb +17 -1
- data/lib/wayfarer/routing/route.rb +66 -19
- data/lib/wayfarer/routing/serializable.rb +28 -0
- data/lib/wayfarer/routing/sub_route.rb +53 -0
- data/lib/wayfarer/routing/target_route.rb +17 -1
- data/lib/wayfarer/stringify.rb +21 -30
- data/lib/wayfarer/task.rb +9 -17
- data/lib/wayfarer/uri/normalization.rb +120 -0
- data/lib/wayfarer.rb +72 -5
- data/mise.toml +2 -0
- data/mkdocs.yml +44 -8
- data/rake/docs.rake +26 -0
- data/rake/lint.rake +9 -0
- data/rake/release.rake +23 -0
- data/rake/tests.rake +32 -0
- data/requirements.txt +1 -1
- data/spec/factories/job.rb +8 -0
- data/spec/factories/middleware.rb +2 -2
- data/spec/factories/path_finder.rb +11 -0
- data/spec/factories/redis.rb +19 -0
- data/spec/factories/task.rb +46 -2
- data/spec/spec_helpers.rb +55 -51
- data/spec/support/active_job_helpers.rb +8 -0
- data/spec/support/integration_helpers.rb +21 -0
- data/spec/support/redis_helpers.rb +9 -0
- data/spec/support/test_app.rb +66 -37
- data/spec/wayfarer/base_spec.rb +200 -0
- data/spec/wayfarer/batch_completion_spec.rb +142 -0
- data/spec/wayfarer/cli/job_spec.rb +88 -0
- data/spec/wayfarer/cli/routing_spec.rb +322 -0
- data/spec/{cli → wayfarer/cli}/version_spec.rb +1 -1
- data/spec/wayfarer/gc_spec.rb +29 -0
- data/spec/wayfarer/handler_spec.rb +9 -0
- data/spec/wayfarer/integration/callbacks_spec.rb +200 -0
- data/spec/wayfarer/integration/content_type_spec.rb +37 -0
- data/spec/wayfarer/integration/custom_routing_spec.rb +51 -0
- data/spec/wayfarer/integration/gc_spec.rb +40 -0
- data/spec/wayfarer/integration/handler_spec.rb +65 -0
- data/spec/wayfarer/integration/page_spec.rb +79 -0
- data/spec/wayfarer/integration/params_spec.rb +64 -0
- data/spec/wayfarer/integration/parsing_spec.rb +99 -0
- data/spec/wayfarer/integration/retry_spec.rb +112 -0
- data/spec/wayfarer/integration/stage_spec.rb +58 -0
- data/spec/wayfarer/middleware/batch_completion_spec.rb +33 -0
- data/spec/{middleware → wayfarer/middleware}/chain_spec.rb +24 -19
- data/spec/wayfarer/middleware/content_type_spec.rb +83 -0
- data/spec/{middleware → wayfarer/middleware}/controller_spec.rb +24 -22
- data/spec/wayfarer/middleware/dedup_spec.rb +66 -0
- data/spec/wayfarer/middleware/normalize_spec.rb +32 -0
- data/spec/wayfarer/middleware/router_spec.rb +102 -0
- data/spec/wayfarer/middleware/stage_spec.rb +63 -0
- data/spec/wayfarer/middleware/uri_parser_spec.rb +63 -0
- data/spec/wayfarer/middleware/user_agent_spec.rb +158 -0
- data/spec/wayfarer/networking/capybara_spec.rb +13 -0
- data/spec/{networking → wayfarer/networking}/context_spec.rb +46 -38
- data/spec/wayfarer/networking/ferrum_spec.rb +13 -0
- data/spec/{networking → wayfarer/networking}/follow_spec.rb +11 -6
- data/spec/wayfarer/networking/http_spec.rb +12 -0
- data/spec/{networking → wayfarer/networking}/pool_spec.rb +16 -14
- data/spec/wayfarer/networking/selenium_spec.rb +12 -0
- data/spec/{networking → wayfarer/networking}/strategy.rb +33 -54
- data/spec/wayfarer/page_spec.rb +69 -0
- data/spec/{parsing → wayfarer/parsing}/json_spec.rb +1 -1
- data/spec/wayfarer/parsing/xml_parse_spec.rb +25 -0
- data/spec/wayfarer/redis/barrier_spec.rb +39 -0
- data/spec/wayfarer/redis/counter_spec.rb +34 -0
- data/spec/{redis → wayfarer/redis}/pool_spec.rb +4 -3
- data/spec/{routing → wayfarer/routing}/dsl_spec.rb +12 -22
- data/spec/wayfarer/routing/hash_stack_spec.rb +63 -0
- data/spec/wayfarer/routing/integration_spec.rb +101 -0
- data/spec/wayfarer/routing/matchers/custom_spec.rb +39 -0
- data/spec/wayfarer/routing/matchers/host_spec.rb +56 -0
- data/spec/wayfarer/routing/matchers/matcher.rb +17 -0
- data/spec/wayfarer/routing/matchers/path_spec.rb +43 -0
- data/spec/wayfarer/routing/matchers/query_spec.rb +123 -0
- data/spec/wayfarer/routing/matchers/scheme_spec.rb +45 -0
- data/spec/wayfarer/routing/matchers/url_spec.rb +33 -0
- data/spec/wayfarer/routing/path_consumer_spec.rb +123 -0
- data/spec/wayfarer/routing/path_finder_spec.rb +409 -0
- data/spec/wayfarer/routing/root_route_spec.rb +51 -0
- data/spec/wayfarer/routing/route_spec.rb +74 -0
- data/spec/wayfarer/routing/sub_route_spec.rb +103 -0
- data/spec/wayfarer/task_spec.rb +13 -0
- data/spec/wayfarer/uri/normalization_spec.rb +98 -0
- data/spec/wayfarer_spec.rb +2 -2
- data/wayfarer.gemspec +18 -28
- metadata +797 -265
- data/.github/workflows/ci.yaml +0 -32
- data/.rbenv-gemsets +0 -1
- data/.ruby-version +0 -1
- data/RELEASING.md +0 -17
- data/docs/cookbook/user_agent.md +0 -7
- data/docs/guides/error_handling.md +0 -53
- data/docs/guides/networking.md +0 -94
- data/docs/guides/performance.md +0 -130
- data/docs/guides/reliability.md +0 -41
- data/docs/guides/routing/steering.md +0 -30
- data/docs/reference/api/base.md +0 -48
- data/docs/reference/cli.md +0 -61
- data/docs/reference/configuration_keys.md +0 -43
- data/docs/reference/environment_variables.md +0 -83
- data/lib/wayfarer/cli/base.rb +0 -45
- data/lib/wayfarer/cli/generate.rb +0 -17
- data/lib/wayfarer/cli/job.rb +0 -56
- data/lib/wayfarer/cli/route.rb +0 -29
- data/lib/wayfarer/cli/runner.rb +0 -34
- data/lib/wayfarer/cli/templates/Gemfile.tt +0 -5
- data/lib/wayfarer/cli/templates/job.rb.tt +0 -10
- data/lib/wayfarer/config/capybara.rb +0 -10
- data/lib/wayfarer/config/ferrum.rb +0 -11
- data/lib/wayfarer/config/networking.rb +0 -29
- data/lib/wayfarer/config/redis.rb +0 -14
- data/lib/wayfarer/config/root.rb +0 -11
- data/lib/wayfarer/config/selenium.rb +0 -21
- data/lib/wayfarer/config/strconv.rb +0 -45
- data/lib/wayfarer/config/struct.rb +0 -72
- data/lib/wayfarer/middleware/fetch.rb +0 -56
- data/lib/wayfarer/redis/connection.rb +0 -13
- data/lib/wayfarer/redis/version.rb +0 -19
- data/lib/wayfarer/routing/router.rb +0 -28
- data/spec/base_spec.rb +0 -224
- data/spec/callbacks_spec.rb +0 -102
- data/spec/cli/generate_spec.rb +0 -39
- data/spec/cli/job_spec.rb +0 -78
- data/spec/config/capybara_spec.rb +0 -18
- data/spec/config/ferrum_spec.rb +0 -24
- data/spec/config/networking_spec.rb +0 -73
- data/spec/config/redis_spec.rb +0 -32
- data/spec/config/root_spec.rb +0 -31
- data/spec/config/selenium_spec.rb +0 -56
- data/spec/config/strconv_spec.rb +0 -58
- data/spec/config/struct_spec.rb +0 -66
- data/spec/fixtures/dummy_job.rb +0 -7
- data/spec/gc_spec.rb +0 -59
- data/spec/handler_spec.rb +0 -11
- data/spec/integration/callbacks_spec.rb +0 -85
- data/spec/integration/page_spec.rb +0 -62
- data/spec/integration/params_spec.rb +0 -56
- data/spec/integration/stage_spec.rb +0 -51
- data/spec/integration/steering_spec.rb +0 -57
- data/spec/middleware/dedup_spec.rb +0 -88
- data/spec/middleware/dispatch_spec.rb +0 -43
- data/spec/middleware/fetch_spec.rb +0 -155
- data/spec/middleware/normalize_spec.rb +0 -29
- data/spec/middleware/router_spec.rb +0 -105
- data/spec/middleware/stage_spec.rb +0 -62
- data/spec/networking/capybara_spec.rb +0 -12
- data/spec/networking/ferrum_spec.rb +0 -12
- data/spec/networking/http_spec.rb +0 -12
- data/spec/networking/selenium_spec.rb +0 -12
- data/spec/page_spec.rb +0 -47
- data/spec/parsing/xml_spec.rb +0 -25
- data/spec/redis/barrier_spec.rb +0 -78
- data/spec/redis/counter_spec.rb +0 -32
- data/spec/redis/version_spec.rb +0 -13
- data/spec/routing/integration_spec.rb +0 -110
- data/spec/routing/matchers/custom_spec.rb +0 -31
- data/spec/routing/matchers/host_spec.rb +0 -49
- data/spec/routing/matchers/path_spec.rb +0 -43
- data/spec/routing/matchers/query_spec.rb +0 -137
- data/spec/routing/matchers/scheme_spec.rb +0 -25
- data/spec/routing/matchers/suffix_spec.rb +0 -41
- data/spec/routing/matchers/uri_spec.rb +0 -27
- data/spec/routing/path_finder_spec.rb +0 -33
- data/spec/routing/root_route_spec.rb +0 -29
- data/spec/routing/route_spec.rb +0 -43
- data/spec/routing/router_spec.rb +0 -24
- data/spec/task_spec.rb +0 -34
- data/spec/{stringify_spec.rb → wayfarer/stringify_spec.rb} +2 -2
@@ -3,20 +3,18 @@
|
|
3
3
|
require "spec_helpers"
|
4
4
|
|
5
5
|
describe Wayfarer::Middleware::Controller do
|
6
|
+
subject(:controller) { Class.new.include(described_class) }
|
7
|
+
|
6
8
|
let(:task) { build(:task) }
|
7
9
|
|
8
10
|
let(:middleware) do
|
9
|
-
Class.new do
|
10
|
-
extend
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
def call(task); end
|
11
|
+
Class.new.tap do |klass|
|
12
|
+
klass.extend(Wayfarer::Middleware::Base)
|
13
|
+
klass.define_method(:call, &->(_) {})
|
14
|
+
klass.const_set("API", Module.new)
|
15
15
|
end
|
16
16
|
end
|
17
17
|
|
18
|
-
subject(:controller) { Class.new.include(described_class) }
|
19
|
-
|
20
18
|
describe "::use" do
|
21
19
|
it "adds middleware" do
|
22
20
|
expect {
|
@@ -28,7 +26,7 @@ describe Wayfarer::Middleware::Controller do
|
|
28
26
|
controller.use(middleware)
|
29
27
|
expect(controller.chain.middlewares.last).to be_a(Wayfarer::Middleware::Lazy)
|
30
28
|
expect(controller.chain.middlewares.last.klass).to be(middleware)
|
31
|
-
expect_any_instance_of(middleware).to receive(:call).with(task)
|
29
|
+
expect_any_instance_of(middleware).to receive(:call).with(task) # rubocop:disable RSpec/AnyInstance
|
32
30
|
controller.new.call(task)
|
33
31
|
end
|
34
32
|
end
|
@@ -42,45 +40,49 @@ describe Wayfarer::Middleware::Controller do
|
|
42
40
|
end
|
43
41
|
|
44
42
|
describe "#call" do
|
45
|
-
|
43
|
+
let(:instance) { controller.new }
|
46
44
|
|
47
45
|
it "assigns the task" do
|
48
46
|
expect {
|
49
|
-
|
50
|
-
}.to change
|
47
|
+
instance.call(task)
|
48
|
+
}.to change(instance, :task).to(task)
|
51
49
|
end
|
52
50
|
|
53
51
|
context "without job assigned" do
|
54
52
|
it "assigns itself" do
|
55
53
|
expect {
|
56
|
-
|
57
|
-
}.to change { task
|
54
|
+
instance.call(task)
|
55
|
+
}.to change { task[:job] }.to(instance)
|
58
56
|
end
|
59
57
|
end
|
60
58
|
|
61
59
|
context "with job assigned" do
|
62
|
-
before { task
|
60
|
+
before { task[:job] = Object.new }
|
63
61
|
|
64
62
|
it "does not override the job" do
|
65
63
|
expect {
|
66
|
-
|
67
|
-
}.not_to(change { task
|
64
|
+
instance.call(task)
|
65
|
+
}.not_to(change { task[:job] })
|
68
66
|
end
|
69
67
|
end
|
70
68
|
|
71
69
|
it "assigns itself as controller" do
|
72
70
|
expect {
|
73
|
-
|
74
|
-
}.to change { task
|
71
|
+
instance.call(task)
|
72
|
+
}.to change { task[:controller] }.to(instance)
|
75
73
|
end
|
76
74
|
|
77
75
|
it "calls the chain" do
|
78
|
-
|
79
|
-
|
76
|
+
chain = instance.class.chain
|
77
|
+
allow(chain).to receive(:call)
|
78
|
+
|
79
|
+
instance.call(task)
|
80
|
+
|
81
|
+
expect(chain).to have_received(:call)
|
80
82
|
end
|
81
83
|
|
82
84
|
it "yields" do
|
83
|
-
expect { |spy|
|
85
|
+
expect { |spy| instance.call(task, &spy) }.to yield_control
|
84
86
|
end
|
85
87
|
end
|
86
88
|
end
|
@@ -0,0 +1,66 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require_relative "../../spec_helpers"
|
4
|
+
|
5
|
+
RSpec.describe Wayfarer::Middleware::Dedup, :redis do
|
6
|
+
subject(:middleware) { described_class.new }
|
7
|
+
|
8
|
+
let(:job) { build(:job, executions: 1) }
|
9
|
+
let(:controller) { job }
|
10
|
+
let(:task) { build(:task, :normalized, :barrier, job: job, controller: controller, url: "http://example.com/") }
|
11
|
+
let(:barrier) { task[:barrier] }
|
12
|
+
|
13
|
+
context "with unseen URL" do
|
14
|
+
specify do
|
15
|
+
expect { |block| middleware.call(task, &block) }.to yield_control
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
19
|
+
context "with seen URL" do
|
20
|
+
before { barrier.check!(task[:uri].to_s) }
|
21
|
+
|
22
|
+
specify do
|
23
|
+
expect { |block| middleware.call(task, &block) }.not_to yield_control
|
24
|
+
end
|
25
|
+
|
26
|
+
context "when task is rerouted" do
|
27
|
+
let(:controller) { Class.new.include(Wayfarer::Handler) }
|
28
|
+
|
29
|
+
specify do
|
30
|
+
expect { |block| middleware.call(task, &block) }.to yield_control
|
31
|
+
end
|
32
|
+
end
|
33
|
+
|
34
|
+
context "with retry" do
|
35
|
+
let(:job) { build(:job, executions: 3) }
|
36
|
+
|
37
|
+
specify do
|
38
|
+
expect { |block| middleware.call(task, &block) }.to yield_control
|
39
|
+
end
|
40
|
+
end
|
41
|
+
end
|
42
|
+
|
43
|
+
describe "cache keys" do
|
44
|
+
before do
|
45
|
+
task[:barrier] = spy
|
46
|
+
end
|
47
|
+
|
48
|
+
specify do
|
49
|
+
middleware.call(task)
|
50
|
+
|
51
|
+
expect(task[:barrier]).to have_received(:check!).with(task[:uri].to_s)
|
52
|
+
end
|
53
|
+
|
54
|
+
context "with custom key" do
|
55
|
+
before do
|
56
|
+
Wayfarer.config[:deduplication][:key] = ->(task) { Digest::MD5.base64digest(task[:uri]) }
|
57
|
+
end
|
58
|
+
|
59
|
+
specify do
|
60
|
+
middleware.call(task)
|
61
|
+
|
62
|
+
expect(task[:barrier]).to have_received(:check!).with("qbnwQzbOAYGgjndOARE7MQ==")
|
63
|
+
end
|
64
|
+
end
|
65
|
+
end
|
66
|
+
end
|
@@ -0,0 +1,32 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require "spec_helpers"
|
4
|
+
|
5
|
+
describe Wayfarer::Middleware::Normalize do
|
6
|
+
subject(:middleware) { described_class.new }
|
7
|
+
|
8
|
+
let(:task) { build(:task, :uri, url: "http://example.com/") }
|
9
|
+
|
10
|
+
context "with assigned URI" do
|
11
|
+
specify do
|
12
|
+
expect { |spy| middleware.call(task, &spy) }.to yield_control
|
13
|
+
end
|
14
|
+
|
15
|
+
specify do
|
16
|
+
expect { middleware.call(task) }.to(change { task[:uri] })
|
17
|
+
end
|
18
|
+
end
|
19
|
+
|
20
|
+
context "with invalid URL" do
|
21
|
+
before do
|
22
|
+
allow(Wayfarer::URI::Normalization)
|
23
|
+
.to receive(:canonical!)
|
24
|
+
.with(task[:uri])
|
25
|
+
.and_raise(Wayfarer::URI::Normalization::InvalidURIError)
|
26
|
+
end
|
27
|
+
|
28
|
+
specify do
|
29
|
+
expect { |spy| middleware.call(task, &spy) }.not_to yield_control
|
30
|
+
end
|
31
|
+
end
|
32
|
+
end
|
@@ -0,0 +1,102 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require "spec_helpers"
|
4
|
+
|
5
|
+
describe Wayfarer::Middleware::Router do
|
6
|
+
subject(:middleware) { described_class.new }
|
7
|
+
|
8
|
+
let(:task) { build(:task, :uri) }
|
9
|
+
|
10
|
+
describe "#call" do
|
11
|
+
let(:controller) do
|
12
|
+
Struct.new(:task).include(described_class::API).new(task)
|
13
|
+
end
|
14
|
+
|
15
|
+
before do
|
16
|
+
allow(controller.class.route).to receive(:invoke)
|
17
|
+
.with(task)
|
18
|
+
.and_return(result)
|
19
|
+
task[:controller] = controller
|
20
|
+
end
|
21
|
+
|
22
|
+
context "with matching route" do
|
23
|
+
let(:action) { :action }
|
24
|
+
let(:params) { { "foo" => "bar" } }
|
25
|
+
let(:result) do
|
26
|
+
Wayfarer::Routing::Result::Match.new(action, params)
|
27
|
+
end
|
28
|
+
|
29
|
+
it "assigns the action" do
|
30
|
+
expect {
|
31
|
+
middleware.call(task)
|
32
|
+
}.to change { task[:action] }.to(action)
|
33
|
+
end
|
34
|
+
|
35
|
+
it "merges params" do
|
36
|
+
task[:params] = ActiveSupport::HashWithIndifferentAccess.new("bar" => "qux")
|
37
|
+
|
38
|
+
expect {
|
39
|
+
middleware.call(task)
|
40
|
+
}.to change { task[:params] }.to("foo" => "bar", "bar" => "qux")
|
41
|
+
end
|
42
|
+
|
43
|
+
specify do
|
44
|
+
expect { |spy| middleware.call(task, &spy) }.to yield_control
|
45
|
+
end
|
46
|
+
|
47
|
+
specify do
|
48
|
+
# rubocop:disable RSpec/MessageSpies
|
49
|
+
expect(Wayfarer::Logging.logger).to receive(:add).with(Logger::INFO, kind_of(String))
|
50
|
+
# rubocop:enable RSpec/MessageSpies
|
51
|
+
|
52
|
+
middleware.call(task)
|
53
|
+
end
|
54
|
+
end
|
55
|
+
|
56
|
+
context "without matching route" do
|
57
|
+
let(:result) { Wayfarer::Routing::Result::Mismatch.instance }
|
58
|
+
|
59
|
+
it "does not assign the action" do
|
60
|
+
expect {
|
61
|
+
middleware.call(task)
|
62
|
+
}.not_to(change { task[:action] })
|
63
|
+
end
|
64
|
+
|
65
|
+
it "does not alter params" do
|
66
|
+
task[:params] = ActiveSupport::HashWithIndifferentAccess.new("bar" => "qux")
|
67
|
+
|
68
|
+
expect {
|
69
|
+
middleware.call(task)
|
70
|
+
}.not_to(change { task[:params] })
|
71
|
+
end
|
72
|
+
|
73
|
+
specify do
|
74
|
+
expect { |spy| middleware.call(task, &spy) }.not_to yield_control
|
75
|
+
end
|
76
|
+
|
77
|
+
specify do
|
78
|
+
# rubocop:disable RSpec/MessageSpies
|
79
|
+
expect(Wayfarer::Logging.logger).to receive(:add).with(Logger::INFO, kind_of(String))
|
80
|
+
# rubocop:enable RSpec/MessageSpies
|
81
|
+
|
82
|
+
middleware.call(task)
|
83
|
+
end
|
84
|
+
end
|
85
|
+
end
|
86
|
+
|
87
|
+
describe described_class::API do
|
88
|
+
subject(:controller) { Struct.new(:task).include(described_class).new(task) }
|
89
|
+
|
90
|
+
describe "::route" do
|
91
|
+
it "returns a root route" do
|
92
|
+
expect(controller.class.route).to be_a(Wayfarer::Routing::RootRoute)
|
93
|
+
end
|
94
|
+
|
95
|
+
it "adds a routing block" do
|
96
|
+
expect {
|
97
|
+
controller.class.route.to(:index)
|
98
|
+
}.to change { controller.class.route.children.count }.by(1)
|
99
|
+
end
|
100
|
+
end
|
101
|
+
end
|
102
|
+
end
|
@@ -0,0 +1,63 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require "spec_helpers"
|
4
|
+
|
5
|
+
describe Wayfarer::Middleware::Stage do
|
6
|
+
subject(:middleware) { described_class.new }
|
7
|
+
|
8
|
+
let(:task) { build(:task) }
|
9
|
+
|
10
|
+
describe "#call" do
|
11
|
+
it "assigns an empty set" do
|
12
|
+
middleware.call(task)
|
13
|
+
expect(task[:staged_urls]).to eq(SortedSet.new)
|
14
|
+
end
|
15
|
+
|
16
|
+
it "yields" do
|
17
|
+
expect { |spy| middleware.call(task, &spy) }.to yield_control
|
18
|
+
end
|
19
|
+
|
20
|
+
it "enqueues tasks" do
|
21
|
+
job = double(crawl: nil) # rubocop:disable RSpec/VerifiedDoubles
|
22
|
+
urls = [test_app_path("/alpha"), test_app_path("/beta")]
|
23
|
+
|
24
|
+
task[:job] = instance_spy(Object, class: job)
|
25
|
+
|
26
|
+
middleware.call(task) do
|
27
|
+
task[:staged_urls] = SortedSet.new(urls)
|
28
|
+
end
|
29
|
+
|
30
|
+
expect(job).to have_received(:crawl).with(urls.first, batch: task.batch).ordered
|
31
|
+
expect(job).to have_received(:crawl).with(urls.second, batch: task.batch).ordered
|
32
|
+
end
|
33
|
+
|
34
|
+
it "resets staged URLs" do
|
35
|
+
task[:staged_urls] = SortedSet.new([test_app_path("/foo")])
|
36
|
+
|
37
|
+
expect {
|
38
|
+
middleware.call(task)
|
39
|
+
}.to change { task[:staged_urls].count }.to(0)
|
40
|
+
end
|
41
|
+
end
|
42
|
+
|
43
|
+
describe described_class::API do
|
44
|
+
subject(:controller) do
|
45
|
+
Struct.new(:task).include(described_class).new(task)
|
46
|
+
end
|
47
|
+
|
48
|
+
describe "#stage" do
|
49
|
+
before { task[:staged_urls] = SortedSet.new }
|
50
|
+
|
51
|
+
it "stages URLs" do
|
52
|
+
expect {
|
53
|
+
controller.stage(test_app_path("/foo"))
|
54
|
+
}.to change { task[:staged_urls].count }.by(1)
|
55
|
+
end
|
56
|
+
|
57
|
+
it "converts to strings" do
|
58
|
+
controller.stage(Addressable::URI.parse(test_app_path("/foo")))
|
59
|
+
expect(task[:staged_urls].to_a.first).to be_a(String)
|
60
|
+
end
|
61
|
+
end
|
62
|
+
end
|
63
|
+
end
|
@@ -0,0 +1,63 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require "spec_helpers"
|
4
|
+
|
5
|
+
describe Wayfarer::Middleware::UriParser do
|
6
|
+
subject(:middleware) { described_class.new }
|
7
|
+
|
8
|
+
let(:task) { build(:task) }
|
9
|
+
|
10
|
+
it "parses URLs" do
|
11
|
+
expect { middleware.call(task) }.to change { task[:uri] }.to(Addressable::URI.parse(task.url))
|
12
|
+
end
|
13
|
+
|
14
|
+
specify do
|
15
|
+
expect { |spy| middleware.call(task, &spy) }.to yield_control
|
16
|
+
end
|
17
|
+
|
18
|
+
context "with already parsed URI" do
|
19
|
+
before do
|
20
|
+
task[:uri] = Addressable::URI.parse("http://example.com")
|
21
|
+
end
|
22
|
+
|
23
|
+
specify do
|
24
|
+
expect { |spy| middleware.call(task, &spy) }.to yield_control
|
25
|
+
end
|
26
|
+
|
27
|
+
specify do
|
28
|
+
expect { middleware.call(task) }.not_to(change { task[:uri] })
|
29
|
+
end
|
30
|
+
end
|
31
|
+
|
32
|
+
context "with invalid URL" do
|
33
|
+
let(:task) { build(:task, url: "ht%0atp://localhost/") }
|
34
|
+
|
35
|
+
specify do
|
36
|
+
expect { |spy| middleware.call(task, &spy) }.not_to yield_control
|
37
|
+
end
|
38
|
+
|
39
|
+
specify do
|
40
|
+
expect(Wayfarer::Logging.logger)
|
41
|
+
.to receive(:add) # rubocop:disable RSpec/MessageSpies
|
42
|
+
.with(Logger::INFO, "Not processing invalid URL (Invalid scheme format: 'ht%0atp')")
|
43
|
+
|
44
|
+
middleware.call(task)
|
45
|
+
end
|
46
|
+
end
|
47
|
+
|
48
|
+
describe described_class::API do
|
49
|
+
subject(:controller) do
|
50
|
+
Struct.new(:task).include(described_class).new(task)
|
51
|
+
end
|
52
|
+
|
53
|
+
describe "#uri" do
|
54
|
+
let(:uri) { Addressable::URI.parse(task.url) }
|
55
|
+
|
56
|
+
before { task[:uri] = uri }
|
57
|
+
|
58
|
+
specify do
|
59
|
+
expect(controller.uri).to be(uri)
|
60
|
+
end
|
61
|
+
end
|
62
|
+
end
|
63
|
+
end
|
@@ -0,0 +1,158 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require "spec_helpers"
|
4
|
+
|
5
|
+
describe Wayfarer::Middleware::UserAgent do
|
6
|
+
subject(:middleware) { described_class.new }
|
7
|
+
|
8
|
+
let(:task) { build(:task, :staged_urls) }
|
9
|
+
let(:page) { instance_double(Wayfarer::Page) }
|
10
|
+
let(:agent) { Object.new }
|
11
|
+
let(:result) { Wayfarer::Networking::Result::Success.new(page) }
|
12
|
+
let(:context) do
|
13
|
+
instance_spy(Wayfarer::Networking::Context, instance: agent).tap do |context|
|
14
|
+
allow(context).to receive(:fetch).with(task.url).and_return(result)
|
15
|
+
end
|
16
|
+
end
|
17
|
+
|
18
|
+
before { task[:controller] = controller }
|
19
|
+
|
20
|
+
describe "#call" do
|
21
|
+
let(:controller) do
|
22
|
+
Struct.new(:task).include(Wayfarer::Middleware::Stage::API).new(task)
|
23
|
+
end
|
24
|
+
|
25
|
+
before do
|
26
|
+
allow(controller).to receive(:run_callbacks).with(:fetch).and_yield
|
27
|
+
|
28
|
+
spy.tap do |pool|
|
29
|
+
allow(pool).to receive(:with).and_yield(context)
|
30
|
+
allow(middleware).to receive(:pool).and_return(pool) # rubocop:disable RSpec/SubjectStub
|
31
|
+
end
|
32
|
+
end
|
33
|
+
|
34
|
+
context "with page assigned" do
|
35
|
+
before { task[:page] = page }
|
36
|
+
|
37
|
+
specify do
|
38
|
+
expect {
|
39
|
+
middleware.call(task)
|
40
|
+
}.not_to(change { task[:page] })
|
41
|
+
end
|
42
|
+
|
43
|
+
specify do
|
44
|
+
expect { |spy| middleware.call(task, &spy) }.to yield_control
|
45
|
+
end
|
46
|
+
end
|
47
|
+
|
48
|
+
specify do
|
49
|
+
middleware.call(task)
|
50
|
+
|
51
|
+
expect(controller).to have_received(:run_callbacks).with(:fetch)
|
52
|
+
end
|
53
|
+
|
54
|
+
specify do
|
55
|
+
middleware.call(task)
|
56
|
+
|
57
|
+
expect(context).to have_received(:fetch).with(task.url)
|
58
|
+
end
|
59
|
+
|
60
|
+
context "with Redirect" do
|
61
|
+
let(:redirect_url) { test_app_path("/foobar") }
|
62
|
+
let(:result) { Wayfarer::Networking::Result::Redirect.new(page) }
|
63
|
+
|
64
|
+
specify do
|
65
|
+
expect {
|
66
|
+
middleware.call(task)
|
67
|
+
}.to change { task[:staged_urls].count }.by(1)
|
68
|
+
end
|
69
|
+
|
70
|
+
specify do
|
71
|
+
expect { |spy| middleware.call(task, &spy) }.not_to yield_control
|
72
|
+
end
|
73
|
+
end
|
74
|
+
|
75
|
+
context "with Success" do
|
76
|
+
specify do
|
77
|
+
expect {
|
78
|
+
middleware.call(task)
|
79
|
+
}.to change { task[:context] }.to(context)
|
80
|
+
end
|
81
|
+
|
82
|
+
specify do
|
83
|
+
expect {
|
84
|
+
middleware.call(task)
|
85
|
+
}.to change { task[:page] }.to(result.page)
|
86
|
+
end
|
87
|
+
|
88
|
+
specify do
|
89
|
+
expect { |spy| middleware.call(task, &spy) }.to yield_control
|
90
|
+
end
|
91
|
+
end
|
92
|
+
end
|
93
|
+
|
94
|
+
describe described_class::API do
|
95
|
+
subject(:controller) do
|
96
|
+
Struct.new(:task).include(described_class).new(task)
|
97
|
+
end
|
98
|
+
|
99
|
+
describe "#user_agent" do
|
100
|
+
before { task[:context] = context }
|
101
|
+
|
102
|
+
specify do
|
103
|
+
expect(controller.user_agent).to be(context.instance)
|
104
|
+
end
|
105
|
+
end
|
106
|
+
|
107
|
+
describe "#page" do
|
108
|
+
before { task[:page] = page }
|
109
|
+
|
110
|
+
specify do
|
111
|
+
expect(controller.page).to be(task[:page])
|
112
|
+
end
|
113
|
+
|
114
|
+
context "with live keyword" do
|
115
|
+
before { task[:context] = context }
|
116
|
+
|
117
|
+
context "with stateful agent" do
|
118
|
+
before do
|
119
|
+
result.page = Object.new
|
120
|
+
allow(context).to receive(:live).and_return(result)
|
121
|
+
end
|
122
|
+
|
123
|
+
it "replaces the page" do
|
124
|
+
expect {
|
125
|
+
controller.page(live: true)
|
126
|
+
}.to change { task[:page] }.to(result.page)
|
127
|
+
end
|
128
|
+
end
|
129
|
+
|
130
|
+
context "with stateless agent" do
|
131
|
+
before { allow(context).to receive(:live).and_return(nil) }
|
132
|
+
|
133
|
+
it "does not alter the page" do
|
134
|
+
expect {
|
135
|
+
controller.page(live: true)
|
136
|
+
}.not_to(change { task[:page] })
|
137
|
+
end
|
138
|
+
end
|
139
|
+
end
|
140
|
+
end
|
141
|
+
|
142
|
+
describe "#fetch" do
|
143
|
+
subject(:page) { controller.fetch(url) }
|
144
|
+
|
145
|
+
let(:url) { test_app_path("/redirect?times=3") }
|
146
|
+
|
147
|
+
it { is_expected.to be_a(Wayfarer::Page) }
|
148
|
+
|
149
|
+
context "with reries exhausted" do
|
150
|
+
let(:url) { test_app_path("/redirect?times=4") }
|
151
|
+
|
152
|
+
specify do
|
153
|
+
expect { page }.to raise_error(Wayfarer::Networking::Follow::RedirectsExhaustedError)
|
154
|
+
end
|
155
|
+
end
|
156
|
+
end
|
157
|
+
end
|
158
|
+
end
|
@@ -0,0 +1,13 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require "spec_helpers"
|
4
|
+
require_relative "strategy"
|
5
|
+
|
6
|
+
describe Wayfarer::Networking::Capybara, :ferrum do
|
7
|
+
it_behaves_like "Network strategy", strategy: described_class,
|
8
|
+
browser: true,
|
9
|
+
request_headers: false,
|
10
|
+
response_headers: true,
|
11
|
+
status_code: true,
|
12
|
+
raises_on_error_response: true # uses Ferrum
|
13
|
+
end
|