Extract span attrs from Tornado request (#3784)

Author: sentrivana

MIGRATION_GUIDE.md

@@ -32,6 +32,18 @@ Looking to upgrade from Sentry SDK 2.x to 3.x? Here's a comprehensive list of wh
   | `scheme`         | `url.scheme`                    |
   | full URL         | `url.full`                      |
 
+- If you're using the Tornado integration, the `sampling_context` argument of `traces_sampler` doesn't contain the `tornado_request` object anymore. Instead, some of the individual properties of the request are accessible, if available, as follows:
+
+  | Request property | Sampling context key(s)                             |
+  | ---------------- | --------------------------------------------------- |
+  | `path`           | `url.path`                                          |
+  | `query`          | `url.query`                                         |
+  | `protocol`       | `url.scheme`                                        |
+  | `method`         | `http.request.method`                               |
+  | `host`           | `server.address`, `server.port`                     |
+  | `version`        | `network.protocol.name`, `network.protocol.version` |
+  | full URL         | `url.full`                                          |
+
 - If you're using the generic WSGI integration, the `sampling_context` argument of `traces_sampler` doesn't contain the `wsgi_environ` object anymore. Instead, the individual properties of the environment are accessible, if available, as follows:
 
   | Env property      | Sampling context key(s)                           |

sentry_sdk/integrations/tornado.py

@@ -27,8 +27,9 @@
 
 try:
     from tornado import version_info as TORNADO_VERSION
-    from tornado.web import RequestHandler, HTTPError
     from tornado.gen import coroutine
+    from tornado.httputil import HTTPServerRequest
+    from tornado.web import RequestHandler, HTTPError
 except ImportError:
     raise DidNotEnable("Tornado not installed")
 
@@ -44,6 +45,14 @@
     from sentry_sdk._types import Event, EventProcessor
 
 
+REQUEST_PROPERTY_TO_ATTRIBUTE = {
+    "method": "http.request.method",
+    "path": "url.path",
+    "query": "url.query",
+    "protocol": "url.scheme",
+}
+
+
 class TornadoIntegration(Integration):
     identifier = "tornado"
     origin = f"auto.http.{identifier}"
@@ -124,7 +133,7 @@ def _handle_request_impl(self):
                 name="generic Tornado request",
                 source=TRANSACTION_SOURCE_ROUTE,
                 origin=TornadoIntegration.origin,
-                custom_sampling_context={"tornado_request": self.request},
+                attributes=_prepopulate_attributes(self.request),
             ):
                 yield
 
@@ -218,3 +227,36 @@ def files(self):
     def size_of_file(self, file):
         # type: (Any) -> int
         return len(file.body or ())
+
+
+def _prepopulate_attributes(request):
+    # type: (HTTPServerRequest) -> dict[str, Any]
+    # https://www.tornadoweb.org/en/stable/httputil.html#tornado.httputil.HTTPServerRequest
+    attributes = {}
+
+    for prop, attr in REQUEST_PROPERTY_TO_ATTRIBUTE.items():
+        if getattr(request, prop, None) is not None:
+            attributes[attr] = getattr(request, prop)
+
+    if getattr(request, "version", None):
+        try:
+            proto, version = request.version.split("/")
+            attributes["network.protocol.name"] = proto
+            attributes["network.protocol.version"] = version
+        except ValueError:
+            attributes["network.protocol.name"] = request.version
+
+    if getattr(request, "host", None) is not None:
+        try:
+            address, port = request.host.split(":")
+            attributes["server.address"] = address
+            attributes["server.port"] = port
+        except ValueError:
+            attributes["server.address"] = request.host
+
+    try:
+        attributes["url.full"] = request.full_url()
+    except Exception:
+        pass
+
+    return attributes

tests/integrations/tornado/test_tornado.py

@@ -1,4 +1,5 @@
 import json
+import re
 
 import pytest
 
@@ -450,3 +451,29 @@ def test_span_origin(tornado_testcase, sentry_init, capture_events):
     (_, event) = events
 
     assert event["contexts"]["trace"]["origin"] == "auto.http.tornado"
+
+
+def test_attributes_in_traces_sampler(tornado_testcase, sentry_init):
+    def traces_sampler(sampling_context):
+        assert sampling_context["url.query"] == "foo=bar"
+        assert sampling_context["url.path"] == "/hi"
+        assert sampling_context["url.scheme"] == "http"
+        assert re.match(
+            r"http:\/\/127\.0\.0\.1:[0-9]{4,5}\/hi\?foo=bar",
+            sampling_context["url.full"],
+        )
+        assert sampling_context["http.request.method"] == "GET"
+        assert sampling_context["server.address"] == "127.0.0.1"
+        assert sampling_context["server.port"].isnumeric()
+        assert sampling_context["network.protocol.name"] == "HTTP"
+        assert sampling_context["network.protocol.version"] == "1.1"
+
+        return True
+
+    sentry_init(
+        integrations=[TornadoIntegration],
+        traces_sampler=traces_sampler,
+    )
+
+    client = tornado_testcase(Application([(r"/hi", HelloHandler)]))
+    client.fetch("/hi?foo=bar")