jsonschema check: allow for .values to be missing

see #16

api/LICENSE

@@ -1,4 +1,4 @@
-This licence applies to the file: event.schema.json
+This licence applies to the files: event.schema.json (and its derivatives)
 The source of this file is: https://raw.githubusercontent.com/getsentry/sentry-data-schemas/main/LICENSE
 
 Copyright (c) 2020 Sentry (https://sentry.io) and individual contributors.

api/README.md

@@ -40,12 +40,3 @@ In short, the more reasons to just use the "upstream" API.
 
 Said in another way: we act more as the "relay" than as "getsentry/sentry", because we do ingest straight in the main
 process. So we should adhere to the relay's spec.
-
-### Notes on use:
-
-Bugsink, as it stands, doesn't use event.schema.json much.
-
-* We have `--valid-only` as a param on `send_json`, but I appear to have used that only sporadically (back in nov 2023)
-* We _could_ at some point in the future [offer the option to] throw events through a validator before proceeding with
-  digesting. At that point we'll re-vendor event.schema.json (from the sentry-data-schemas repo)
-* Reading this file is useful, but we can do that straight from the source.

ingest/management/commands/fetch_event_schema_json.py

@@ -8,6 +8,20 @@ from django.conf import settings
 from django.core.management.base import BaseCommand
 
 
+def alter_schema(schema):
+    # alter the schema to make it fit what the actual documentation says; see issues/utils.py' get_values() for details
+
+    for key in ['exception', 'threads', 'breadcrumbs']:
+        # no idea why that anyOf[0] is there (since there's no anyOf[1]), but it's there.
+        definition = schema['anyOf'][0]['properties'][key]
+        schema['anyOf'][0]['properties'][key] = {
+            "anyOf": [
+                definition,
+                definition['properties']['values'],
+            ]
+        }
+
+
 class Command(BaseCommand):
     help = "Fetches the event schema JSON from the API and saves it to disk. Used during development."
 
@@ -26,7 +40,7 @@ class Command(BaseCommand):
         license_result.raise_for_status()
 
         with open(settings.BASE_DIR / "api/LICENSE", "w") as f:
-            f.write("""This licence applies to the file: event.schema.json
+            f.write("""This licence applies to the files: event.schema.json (and its derivatives)
 The source of this file is: %s
 
 """ % license_url)
@@ -35,13 +49,17 @@ The source of this file is: %s
         # Generate fastjsonschema code from the schema and save it to disk
         schema = json.loads(json_result.text)
 
+        alter_schema(schema)
+        with open(settings.BASE_DIR / "api/event.schema.altered.json", "w") as f:
+            json.dump(schema, f, indent=2)
+
         # use_formats=False for "uint64", see https://github.com/horejsek/python-fastjsonschema/issues/108
         # use_default=False to avoid fastjsonschema adding default values to the data it validates (bwegh)
         code = fastjsonschema.compile_to_code(schema, use_formats=False, use_default=False, detailed_exceptions=False)
 
         with open(settings.BASE_DIR / "bugsink/event_schema.py", "w") as f:
             f.write("""# This file is generated by fetch_event_schema_json.py
-# it is based on api/event.schema.json
+# it is based on api/event.schema.altered.json
 # the following license applies:
 """)
             f.write("\n".join("# " + line for line in license_result.text.splitlines()) + "\n\n")

ingest/management/commands/send_json.py

@@ -41,7 +41,7 @@ class Command(BaseCommand):
             del data["_meta"]
 
         try:
-            schema_filename = settings.BASE_DIR / 'api/event.schema.json'
+            schema_filename = settings.BASE_DIR / 'api/event.schema.altered.json'
             with open(schema_filename, 'r') as f:
                 schema = json.loads(f.read())
 

ingest/views.py

@@ -134,7 +134,7 @@ class BaseIngestAPIView(View):
         # exceptions, so you'd have that cost-of-rollback anyway.
 
         def get_schema():
-            schema_filename = settings.BASE_DIR / 'api/event.schema.json'
+            schema_filename = settings.BASE_DIR / 'api/event.schema.altered.json'
             with open(schema_filename, 'r') as f:
                 return json.loads(f.read())