chore(dep): remove jsonschema dependency from package [backport 1.16] (#6295)

Backport 578e85b from #6292 to 1.16.

We have had issues recently with newer versions of `jsonschema`. Most
importantly, it caused issues with our build/release process (mainly
`rpds-py` which is a dependency of `jsonschema`s):
https://github.com/DataDog/dd-trace-py/actions/runs/5476876584/jobs/9975064818

Looking over the usage of `jsonschema`, there isn't much it is really
doing for us. This PR attempts to replace the usage with other/similar
manual checks.

If the existing test cases/edge cases continue to pass, then we have
successfully replaced `jsonschema`.

The risk with this change is a user ends up with an opaque error
message. Instead of getting a message saying `max_per_second` must be an
integer, they might instead get an operation error when trying to
multiply `None` (or some non-integer value) against another number. We
can consider adding more/additional checks.

## Checklist

- [x] Change(s) are motivated and described in the PR description.
- [x] Testing strategy is described if automated tests are not included
in the PR.
- [x] Risk is outlined (performance impact, potential for breakage,
maintainability, etc).
- [x] Change is maintainable (easy to change, telemetry, documentation).
- [x] [Library release note
guidelines](https://ddtrace.readthedocs.io/en/stable/releasenotes.html)
are followed. If no release note is required, add label
`changelog/no-changelog`.
- [x] Documentation is included (in-code, generated user docs, [public
corp docs](https://github.com/DataDog/documentation/)).
- [x] Backport labels are set (if
[applicable](https://ddtrace.readthedocs.io/en/latest/contributing.html#backporting))

## Reviewer Checklist

- [x] Title is accurate.
- [x] No unnecessary changes are introduced.
- [x] Description motivates each change.
- [x] Avoids breaking
[API](https://ddtrace.readthedocs.io/en/stable/versioning.html#interfaces)
changes unless absolutely necessary.
- [x] Testing strategy adequately addresses listed risk(s).
- [x] Change is maintainable (easy to change, telemetry, documentation).
- [x] Release note makes sense to a user of the library.
- [x] Reviewer has explicitly acknowledged and discussed the performance
implications of this PR as reported in the benchmarks PR comment.
- [x] Backport labels are set in a manner that is consistent with the
[release branch maintenance
policy](https://ddtrace.readthedocs.io/en/latest/contributing.html#backporting)

Co-authored-by: Brett Langdon <[email protected]>

Author: github-actions[bot]

ddtrace/internal/sampling.py

@@ -72,18 +72,6 @@ class SamplingMechanism(object):
     total=False,
 )
 
-SPAN_SAMPLING_JSON_SCHEMA = {
-    "type": "array",
-    "items": {
-        "type": "object",
-        "anyOf": [
-            {"properties": {"service": {"type": "string"}}, "required": ["service"]},
-            {"properties": {"name": {"type": "string"}}, "required": ["name"]},
-        ],
-        "properties": {"max_per_second": {"type": "integer"}, "sample_rate": {"type": "number"}},
-    },
-}
-
 
 def _set_trace_tag(
     context,  # type: Context
@@ -223,16 +211,16 @@ def apply_span_sampling_tags(self, span):
 def get_span_sampling_rules():
     # type: () -> List[SpanSamplingRule]
     json_rules = _get_span_sampling_json()
-    if json_rules:
-        from jsonschema import validate
-
-        validate(json_rules, SPAN_SAMPLING_JSON_SCHEMA)
     sampling_rules = []
     for rule in json_rules:
         # If sample_rate not specified default to 100%
         sample_rate = rule.get("sample_rate", 1.0)
         service = rule.get("service")
         name = rule.get("name")
+
+        if not service and not name:
+            raise ValueError("Sampling rules must supply at least 'service' or 'name', got {}".format(json.dumps(rule)))
+
         # If max_per_second not specified default to no limit
         max_per_second = rule.get("max_per_second", _SINGLE_SPAN_SAMPLING_MAX_PER_SEC_NO_LIMIT)
         if service:

setup.py

@@ -481,7 +481,6 @@ def get_ddup_ext():
         "typing_extensions",
         "importlib_metadata; python_version<'3.8'",
         "pathlib2; python_version<'3.5'",
-        "jsonschema",
         "xmltodict>=0.12",
         "ipaddress; python_version<'3.7'",
         "envier",

tests/tracer/test_single_span_sampling_rules.py

@@ -1,6 +1,5 @@
 import sys
 
-from jsonschema import ValidationError
 import pytest
 
 from ddtrace import Tracer
@@ -65,7 +64,7 @@ def test_sampling_rule_init_via_env():
 
     # Testing error thrown when neither name nor service is set
     with override_env(dict(DD_SPAN_SAMPLING_RULES='[{"sample_rate":1.0}]')):
-        with pytest.raises(ValidationError):
+        with pytest.raises(ValueError):
             sampling_rules = get_span_sampling_rules()
 
     # Testing exception thrown when service pattern contains unsupported char