fix(tracing): handle when origin is Py2 unicode (backport #4030) (#4044)

This is an automatic backport of pull request #4030 done by [Mergify](https://mergify.com).


---


<details>
<summary>Mergify commands and options</summary>

<br />

More conditions and actions can be found in the [documentation](https://docs.mergify.com/).

You can also trigger Mergify actions by commenting on this pull request:

- `@Mergifyio refresh` will re-evaluate the rules
- `@Mergifyio rebase` will rebase this PR on its base branch
- `@Mergifyio update` will merge the base branch into this PR
- `@Mergifyio backport <destination>` will backport this PR on `<destination>` branch

Additionally, on Mergify [dashboard](https://dashboard.mergify.com/) you can:

- look at your merge queues
- generate the Mergify configuration with the config editor.

Finally, you can contact us on https://mergify.com
</details>

Author: mergify[bot]

ddtrace/propagation/http.py

@@ -66,7 +66,7 @@ def _extract_header_value(possible_header_names, headers, default=None):
     # type: (FrozenSet[str], Dict[str, str], Optional[str]) -> Optional[str]
     for header in possible_header_names:
         if header in headers:
-            return headers[header]
+            return ensure_str(headers[header], errors="backslashreplace")
 
     return default
 

releasenotes/notes/fix-dd-origin-py2-7bb39ed9e45e2131.yaml

@@ -0,0 +1,4 @@
+---
+fixes:
+  - |
+    tracing: fix handling of unicode ``_dd.origin`` tag for Python 2

tests/contrib/django/test_django.py

@@ -1226,7 +1226,7 @@ def test_django_request_distributed(client, test_spans):
     headers = {
         get_wsgi_header(HTTP_HEADER_TRACE_ID): "12345",
         get_wsgi_header(HTTP_HEADER_PARENT_ID): "78910",
-        get_wsgi_header(HTTP_HEADER_SAMPLING_PRIORITY): USER_KEEP,
+        get_wsgi_header(HTTP_HEADER_SAMPLING_PRIORITY): str(USER_KEEP),
     }
     resp = client.get("/", **headers)
     assert resp.status_code == 200
@@ -1258,7 +1258,7 @@ def test_django_request_distributed_disabled(client, test_spans):
     headers = {
         get_wsgi_header(HTTP_HEADER_TRACE_ID): "12345",
         get_wsgi_header(HTTP_HEADER_PARENT_ID): "78910",
-        get_wsgi_header(HTTP_HEADER_SAMPLING_PRIORITY): USER_KEEP,
+        get_wsgi_header(HTTP_HEADER_SAMPLING_PRIORITY): str(USER_KEEP),
     }
     with override_config("django", dict(distributed_tracing_enabled=False)):
         resp = client.get("/", **headers)

tests/tracer/test_encoders.py

@@ -413,8 +413,12 @@ def test_encoder_propagates_dd_origin(Encoder, item):
             with tracer.trace("child"):
                 pass
     trace = tracer._writer.pop()
+    assert trace, "DummyWriter failed to encode the trace"
+
     encoder.put(trace)
     decoded_trace = decode(encoder.encode())
+    assert len(decoded_trace) == 1
+    assert decoded_trace[0]
 
     # Ensure encoded trace contains dd_origin tag in all spans
     assert all((_[item][_ORIGIN_KEY] == b"ciapp-test" for _ in decoded_trace[0]))

tests/tracer/test_propagation.py

@@ -174,6 +174,53 @@ def test_extract(tracer):
             }
 
 
+def test_extract_unicode(tracer):
+    """
+    When input data is unicode
+      we decode everything to str for Python2
+
+
+    Cython encoder expects `context.dd_origin` to be `str`
+    which for Python2 means only `str`, and `unicode` is
+    not accepted. If `context.dd_origin` is `unicode`
+    then trace encoding will fail and the trace will be
+    lost.
+    """
+    headers = {
+        u"x-datadog-trace-id": u"1234",
+        u"x-datadog-parent-id": u"5678",
+        u"x-datadog-sampling-priority": u"1",
+        u"x-datadog-origin": u"synthetics",
+        u"x-datadog-tags": u"_dd.p.test=value,any=tag",
+    }
+
+    context = HTTPPropagator.extract(headers)
+
+    tracer.context_provider.activate(context)
+
+    with tracer.trace("local_root_span") as span:
+        assert span.trace_id == 1234
+        assert span.parent_id == 5678
+        assert span.context.sampling_priority == 1
+
+        assert span.context.dd_origin == "synthetics"
+        assert type(span.context.dd_origin) is str
+
+        assert span.context._meta == {
+            "_dd.origin": "synthetics",
+            "_dd.p.test": "value",
+        }
+        with tracer.trace("child_span") as child_span:
+            assert child_span.trace_id == 1234
+            assert child_span.parent_id != 5678
+            assert child_span.context.sampling_priority == 1
+            assert child_span.context.dd_origin == "synthetics"
+            assert child_span.context._meta == {
+                "_dd.origin": "synthetics",
+                "_dd.p.test": "value",
+            }
+
+
 @pytest.mark.parametrize(
     "x_datadog_tags, expected_trace_tags",
     [