Merge pull request #371 from DataDog/feature/quantize_http_query_strings

Add URL query string quantization to Rack

docs/GettingStarted.md

@@ -142,9 +142,44 @@ Where `options` is an optional `Hash` that accepts the following parameters:
 | ``service_name`` | Service name used when tracing application requests | rack |
 | ``distributed_tracing`` | Enables [distributed tracing](#Distributed_Tracing) so that this service trace is connected with a trace of another service if tracing headers are received | `false` |
 | ``middleware_names`` | Enable this if you want to use the middleware classes as the resource names for `rack` spans. Must provide the ``application`` option with it. | ``false`` |
+| ``quantize`` | Hash containing options for quantization. May include `:query` or `:fragment`. | {} |
+| ``quantize.query`` | Hash containing options for query portion of URL quantization. May include `:show` or `:exclude`. See options below. Option must be nested inside the `quantize` option. | {} |
+| ``quantize.query.show`` | Defines which values should always be shown. Shows no values by default. May be an Array of strings, or `:all` to show all values. Option must be nested inside the `query` option. | ``nil`` |
+| ``quantize.query.exclude`` | Defines which values should be removed entirely. Excludes nothing by default. May be an Array of strings, or `:all` to remove the query string entirely. Option must be nested inside the `query` option. | ``nil`` |
+| ``quantize.fragment`` | Defines behavior for URL fragments. Removes fragments by default. May be `:show` to show URL fragments. Option must be nested inside the `quantize` option. | ``nil`` |
 | ``application`` | Your Rack application. Necessary for enabling middleware resource names. | ``nil`` |
 | ``tracer`` | A ``Datadog::Tracer`` instance used to instrument the application. Usually you don't need to set that. | ``Datadog.tracer`` |
 
+Configuring URL quantization behavior:
+
+```
+Datadog.configure do |c|
+  # Default behavior: all values are quantized, fragment is removed.
+  # http://example.com/path?category_id=1&sort_by=asc#featured --> http://example.com/path?category_id&sort_by
+  # http://example.com/path?categories[]=1&categories[]=2 --> http://example.com/path?categories[]
+
+  # Show values for any query string parameter matching 'category_id' exactly
+  # http://example.com/path?category_id=1&sort_by=asc#featured --> http://example.com/path?category_id=1&sort_by
+  c.use :rack, quantize: { query: { show: ['category_id'] } }
+
+  # Show all values for all query string parameters
+  # http://example.com/path?category_id=1&sort_by=asc#featured --> http://example.com/path?category_id=1&sort_by=asc
+  c.use :rack, quantize: { query: { show: :all } }
+
+  # Totally exclude any query string parameter matching 'sort_by' exactly
+  # http://example.com/path?category_id=1&sort_by=asc#featured --> http://example.com/path?category_id
+  c.use :rack, quantize: { query: { exclude: ['sort_by'] } }
+
+  # Remove the query string entirely
+  # http://example.com/path?category_id=1&sort_by=asc#featured --> http://example.com/path
+  c.use :rack, quantize: { query: { exclude: :all } }
+
+  # Show URL fragments
+  # http://example.com/path?category_id=1&sort_by=asc#featured --> http://example.com/path?category_id&sort_by#featured
+  c.use :rack, quantize: { fragment: :show }
+end
+```
+
 ## Other libraries
 
 ### GraphQL

lib/ddtrace/contrib/rack/middlewares.rb

@@ -104,7 +104,8 @@ def set_request_tags!(request_span, env, status, headers, response, original_env
             request_span.set_tag(Datadog::Ext::HTTP::METHOD, env['REQUEST_METHOD'])
           end
           if request_span.get_tag(Datadog::Ext::HTTP::URL).nil?
-            request_span.set_tag(Datadog::Ext::HTTP::URL, url)
+            options = Datadog.configuration[:rack][:quantize]
+            request_span.set_tag(Datadog::Ext::HTTP::URL, Datadog::Quantization::HTTP.url(url, options))
           end
           if request_span.get_tag(Datadog::Ext::HTTP::BASE_URL).nil?
             request_obj = ::Rack::Request.new(env)

lib/ddtrace/contrib/rack/patcher.rb

@@ -8,6 +8,7 @@ module Patcher
         option :tracer, default: Datadog.tracer
         option :distributed_tracing, default: false
         option :middleware_names, default: false
+        option :quantize, default: {}
         option :application
         option :service_name, default: 'rack', depends_on: [:tracer] do |value|
           get_option(:tracer).set_service_info(value, 'rack', Ext::AppTypes::WEB)

test/contrib/rack/middleware_test.rb

@@ -64,6 +64,35 @@ def test_request_middleware_get_with_request_uri
     assert_equal('200', span.get_tag('http.status_code'))
     # Since REQUEST_URI is set (usually provided by WEBrick/Puma)
     # it uses REQUEST_URI, which has query string parameters.
+    # However, that query string will be quantized.
+    assert_equal('/success?foo', span.get_tag('http.url'))
+    assert_equal('http://example.org', span.get_tag('http.base_url'))
+    assert_equal(0, span.status)
+    assert_nil(span.parent)
+  end
+
+  def test_request_middleware_get_with_request_uri_and_quantize_option
+    Datadog.configure do |c|
+      c.use :rack, quantize: { query: { show: ['foo'] } }
+    end
+
+    # ensure the Rack request is properly traced
+    get '/success?foo=bar', {}, 'REQUEST_URI' => '/success?foo=bar'
+    assert last_response.ok?
+
+    spans = @tracer.writer.spans
+    assert_equal(1, spans.length)
+
+    span = spans[0]
+    assert_equal('rack.request', span.name)
+    assert_equal('http', span.span_type)
+    assert_equal('rack', span.service)
+    assert_equal('GET 200', span.resource)
+    assert_equal('GET', span.get_tag('http.method'))
+    assert_equal('200', span.get_tag('http.status_code'))
+    # Since REQUEST_URI is set (usually provided by WEBrick/Puma)
+    # it uses REQUEST_URI, which has query string parameters.
+    # However, that query string will be quantized.
     assert_equal('/success?foo=bar', span.get_tag('http.url'))
     assert_equal('http://example.org', span.get_tag('http.base_url'))
     assert_equal(0, span.status)