Merge remote-tracking branch 'origin/main' into add-opentelemetry-support

Author: ctrl-schaff

.github/workflows/biothings_annotator_tests.yml

@@ -12,7 +12,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: [ "3.9", "3.10", "3.11", "3.12" ]
+        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13", "3.14"]
     steps:
       - name: Checkout biothings_annotator source
         uses: actions/checkout@v3

.gitignore

@@ -158,3 +158,151 @@ cython_debug/
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 #.idea/
+
+
+# Node configuration
+# Logs
+logs
+*.log
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+lerna-debug.log*
+
+# Diagnostic reports (https://nodejs.org/api/report.html)
+report.[0-9]*.[0-9]*.[0-9]*.[0-9]*.json
+
+# Runtime data
+pids
+*.pid
+*.seed
+*.pid.lock
+
+# Directory for instrumented libs generated by jscoverage/JSCover
+lib-cov
+
+# Coverage directory used by tools like istanbul
+coverage
+*.lcov
+
+# nyc test coverage
+.nyc_output
+
+# Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
+.grunt
+
+# Bower dependency directory (https://bower.io/)
+bower_components
+
+# node-waf configuration
+.lock-wscript
+
+# Compiled binary addons (https://nodejs.org/api/addons.html)
+build/Release
+
+# Dependency directories
+node_modules/
+jspm_packages/
+
+# Snowpack dependency directory (https://snowpack.dev/)
+web_modules/
+
+# TypeScript cache
+*.tsbuildinfo
+
+# Optional npm cache directory
+.npm
+
+# Optional eslint cache
+.eslintcache
+
+# Optional stylelint cache
+.stylelintcache
+
+# Optional REPL history
+.node_repl_history
+
+# Output of 'npm pack'
+*.tgz
+
+# Yarn Integrity file
+.yarn-integrity
+
+# dotenv environment variable files
+.env
+.env.*
+!.env.example
+
+# parcel-bundler cache (https://parceljs.org/)
+.cache
+.parcel-cache
+
+# Next.js build output
+.next
+out
+
+# Nuxt.js build / generate output
+.nuxt
+dist
+.output
+
+# Gatsby files
+.cache/
+# Comment in the public line in if your project uses Gatsby and not Next.js
+# https://nextjs.org/blog/next-9-1#public-directory-support
+# public
+
+# vuepress build output
+.vuepress/dist
+
+# vuepress v2.x temp and cache directory
+.temp
+.cache
+
+# Sveltekit cache directory
+.svelte-kit/
+
+# vitepress build output
+**/.vitepress/dist
+
+# vitepress cache directory
+**/.vitepress/cache
+
+# Docusaurus cache and generated files
+.docusaurus
+
+# Serverless directories
+.serverless/
+
+# FuseBox cache
+.fusebox/
+
+# DynamoDB Local files
+.dynamodb/
+
+# Firebase cache directory
+.firebase/
+
+# TernJS port file
+.tern-port
+
+# Stores VSCode versions used for testing VSCode extensions
+.vscode-test
+
+# yarn v3
+.pnp.*
+.yarn/*
+!.yarn/patches
+!.yarn/plugins
+!.yarn/releases
+!.yarn/sdks
+!.yarn/versions
+
+# Vite files
+vite.config.js.timestamp-*
+vite.config.ts.timestamp-*
+.vite/
+
+
+# local webapp
+biothings_annotator/webapp/*.sqlite3

biothings_annotator/annotator/annotator.py

@@ -94,10 +94,12 @@ async def annotate_curie(
         node_type, _id = parse_curie(curie)
         if not node_type:
             raise InvalidCurieError(curie)
+
         res = await self.query_biothings(node_type, [_id], fields=fields)
+
         if not raw:
             res = await self.transform(res, node_type)
-            # res = [self.transform(r) for r in res[_id]]
+
         if res and include_extra:
             await self.append_extra_annotations(res)
 
@@ -165,7 +167,7 @@ async def annotate_curie_list(
 
         if include_extra:
             # currently, we only need to append extra annotations for chem nodes
-            self.append_extra_annotations(node_d, node_id_subset=node_list_by_type.get("chem", []))
+            await self.append_extra_annotations(node_d, node_id_subset=node_list_by_type.get("chem", []))
         return node_d
 
     async def annotate_trapi(
@@ -215,14 +217,19 @@ async def annotate_trapi(
 
         if include_extra:
             # currently, we only need to append extra annotations for chem nodes
-            self.append_extra_annotations(_node_d, node_id_subset=node_list_by_type["chem"])
+            await self.append_extra_annotations(_node_d, node_id_subset=node_list_by_type["chem"])
 
         # place the annotation objects back to the original node_d as TRAPI attributes
         for node_id, res in _node_d.items():
             res = {
                 "attribute_type_id": "biothings_annotations",
                 "value": res,
             }
+
+            node_attributes = node_d[node_id].get("attributes", None)
+            if node_attributes is None:
+                node_d[node_id]["attributes"] = []
+
             if append:
                 # append annotations to existing "attributes" field
                 node_d[node_id]["attributes"].append(res)

biothings_annotator/annotator/transformer.py

@@ -7,7 +7,6 @@
 import logging
 from typing import Dict
 
-from biothings_annotator.annotator.settings import SERVICE_PROVIDER_API_HOST
 from biothings_annotator.annotator.utils import get_client
 
 logger = logging.getLogger(__name__)

biothings_annotator/annotator/utils.py

@@ -95,6 +95,7 @@ def parse_curie(curie: str, return_type: bool = True, return_id: bool = True):
     """
     if ":" not in curie:
         raise InvalidCurieError(curie)
+
     _prefix, _id = curie.split(":", 1)
     _type = BIOLINK_PREFIX_to_BioThings.get(_prefix, {}).get("type", None)
     if return_id:

biothings_annotator/application/__init__.py

@@ -1,7 +1,103 @@
+from typing import Dict
+import logging
 import pathlib
 
-APPLICATION_DIRECTORY = pathlib.Path(__file__).resolve().absolute().parent
-CLI_DIRECTORY = APPLICATION_DIRECTORY.joinpath("cli")
-CONFIGURATION_DIRECTORY = APPLICATION_DIRECTORY.joinpath("configuration")
-MIDDLEWARE_DIRECTORY = APPLICATION_DIRECTORY.joinpath("middleware")
-VIEWS_DIRECTORY = APPLICATION_DIRECTORY.joinpath("views")
+from sanic import Sanic
+
+from biothings_annotator.application.exceptions import build_exception_handers
+from biothings_annotator.application.middleware import build_middleware
+from biothings_annotator.application.static import build_static_routes, build_static_content
+from biothings_annotator.application.views import build_routes
+
+logging.basicConfig()
+logger = logging.getLogger("sanic-application")
+logger.setLevel(logging.DEBUG)
+
+
+def build_application(configuration: Dict = None) -> Sanic:
+    """
+    Generates and returns an instance of the sanic.app.Sanic application
+    for the web server
+
+    ***BEGIN IMPORTANT***
+    This must be kept separate from the AnnotatorCLI class methods. If you attempt
+    to leverage this as a class method, when the worker manager attempts to spawn
+    a process to call the partially initialized factory method, it will attempt
+    to pickle the instances of the class itself. So unless we take the effort
+    to make the class instance pickleable, we keep this target here for the moment
+    ***END IMPORTANT***
+
+    The sanic.web.Sanic application has the following constructor:
+    https://sanic.dev/api/sanic.app.html#getting-started
+    class Sanic(
+        name: str,
+        config: Optional[config_type] = None,
+        ctx: Optional[ctx_type] = None,
+        router: Optional[Router] = None,
+        signal_router: Optional[SignalRouter] = None,
+        error_handler: Optional[ErrorHandler] = None,
+        env_prefix: Optional[str] = SANIC_,
+        request_class: Optional[Type[Request]] = None,
+        strict_slashes: bool = False,
+        log_config: Optional[Dict[str, Any]] = None,
+        configure_logging: bool = True,
+        dumps: Optional[Callable[..., AnyStr]] = None,
+        loads: Optional[Callable[..., Any]] = None,
+        inspector: bool = False,
+        inspector_class: Optional[Type[Inspector]] = None,
+        certloader_class: Optional[Type[CertLoader]] = None
+    )
+
+    Loads the following additional aspects for the webserver:
+    > routes
+    > middleware
+    > exception handlers
+    """
+    application_configuration = configuration["application"]["configuration"]
+    extension_configuration = configuration["application"]["extension"]
+
+    configuration_settings = {}
+    configuration_settings.update(application_configuration)
+    configuration_settings.update(extension_configuration["cors"])
+
+    application = Sanic(name="biothings-annotator")
+    application.update_config(configuration_settings)
+
+    application_routes = build_routes()
+    static_routes = build_static_routes()
+    for route in (*application_routes, *static_routes):
+        try:
+            application.add_route(**route)
+        except Exception as gen_exc:
+            logger.exception(gen_exc)
+            logger.error("Unable to add route %s", route)
+            raise gen_exc
+
+    static_content = build_static_content()
+    for static_entry in static_content:
+        try:
+            application.static(static_entry[0], static_entry[1])
+        except Exception as gen_exc:
+            logger.exception(gen_exc)
+            logger.error("Unable to add static content %s", static_entry)
+            raise gen_exc
+
+    application_middleware = build_middleware()
+    for middleware in application_middleware:
+        try:
+            application.register_middleware(**middleware)
+        except Exception as gen_exc:
+            logger.exception(gen_exc)
+            logger.error("Unable to add middleware %s", middleware)
+            raise gen_exc
+
+    exception_handlers = build_exception_handers()
+    for exception_handler in exception_handlers:
+        try:
+            application.error_handler.add(**exception_handler)
+        except Exception as gen_exc:
+            logger.exception(gen_exc)
+            logger.error("Unable to add exception handler %s", exception_handler)
+            raise gen_exc
+
+    return application

biothings_annotator/application/cli/arguments.py

@@ -12,7 +12,7 @@
 from sanic.cli.arguments import Group
 from sanic_routing import __version__ as __routing_version__
 
-from biothings_annotator.application import CONFIGURATION_DIRECTORY
+from biothings_annotator.application.structure import CONFIGURATION_DIRECTORY
 
 logging.basicConfig()
 logger = logging.getLogger("sanic-application")

biothings_annotator/application/cli/interface.py

@@ -21,7 +21,7 @@
 from sanic.worker.loader import AppLoader
 
 from biothings_annotator.application.cli.arguments import build_annotator_argument_groups, load_configuration
-from biothings_annotator.application.cli.target import build_application
+from biothings_annotator.application import build_application
 
 logging.basicConfig()
 logger = logging.getLogger("sanic-application")