garf-executors 0.0.13__tar.gz → 0.1.2__tar.gz

{garf_executors-0.0.13 → garf_executors-0.1.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: garf-executors
-Version: 0.0.13
+Version: 0.1.2
 Summary: Executes queries against API and writes data to local/remote storage.
 Author-email: "Google Inc. (gTech gPS CSE team)" <no-reply@google.com>, Andrei Markin <andrey.markin.ppc@gmail.com>
 License: Apache 2.0
@@ -21,6 +21,8 @@ Requires-Dist: garf-core
 Requires-Dist: garf-io
 Requires-Dist: pyyaml
 Requires-Dist: pydantic
+Requires-Dist: opentelemetry-api
+Requires-Dist: opentelemetry-sdk
 Provides-Extra: bq
 Requires-Dist: garf-io[bq]; extra == "bq"
 Requires-Dist: pandas; extra == "bq"
@@ -30,6 +32,8 @@ Requires-Dist: garf-io[sqlalchemy]; extra == "sql"
 Requires-Dist: pandas; extra == "sql"
 Provides-Extra: server
 Requires-Dist: fastapi[standard]; extra == "server"
+Requires-Dist: opentelemetry-instrumentation-fastapi; extra == "server"
+Requires-Dist: opentelemetry-exporter-otlp; extra == "server"
 Provides-Extra: all
 Requires-Dist: garf-executors[bq,server,sql]; extra == "all"
 

{garf_executors-0.0.13 → garf_executors-0.1.2}/garf_executors/__init__.py

@@ -19,8 +19,10 @@ import importlib
 
 from garf_executors import executor, fetchers
 from garf_executors.api_executor import ApiExecutionContext, ApiQueryExecutor
+from garf_executors.telemetry import tracer
 
 
+@tracer.start_as_current_span('setup_executor')
 def setup_executor(
   source: str, fetcher_parameters: dict[str, str]
 ) -> type[executor.Executor]:
@@ -48,4 +50,4 @@ __all__ = [
   'ApiExecutionContext',
 ]
 
-__version__ = '0.0.13'
+__version__ = '0.1.2'

{garf_executors-0.0.13 → garf_executors-0.1.2}/garf_executors/api_executor.py

@@ -20,11 +20,14 @@ GarfReport and saving it to local/remote storage.
 
 from __future__ import annotations
 
+import asyncio
 import logging
 
 from garf_core import report_fetcher
+from opentelemetry import trace
 
 from garf_executors import exceptions, execution_context, executor, fetchers
+from garf_executors.telemetry import tracer
 
 logger = logging.getLogger(__name__)
 
@@ -75,8 +78,9 @@ class ApiQueryExecutor(executor.Executor):
     Returns:
       Result of writing the report.
     """
-    return await self.execute(query, context, title, context)
+    return await asyncio.to_thread(self.execute, query, title, context)
 
+  @tracer.start_as_current_span('api.execute')
   def execute(
     self,
     query: str,
@@ -96,7 +100,12 @@ class ApiQueryExecutor(executor.Executor):
     Raises:
       GarfExecutorError: When failed to execute query.
     """
+    span = trace.get_current_span()
+    span.set_attribute('fetcher', self.fetcher.__class__.__name__)
+    span.set_attribute('api_client', self.fetcher.api_client.__class__.__name__)
     try:
+      span.set_attribute('query_title', title)
+      span.set_attribute('query_text', query)
       logger.debug('starting query %s', query)
       results = self.fetcher.fetch(
         query_specification=query,

{garf_executors-0.0.13 → garf_executors-0.1.2}/garf_executors/bq_executor.py

@@ -31,6 +31,7 @@ from garf_core import query_editor, report
 from google.cloud import exceptions as google_cloud_exceptions
 
 from garf_executors import exceptions, execution_context, executor
+from garf_executors.telemetry import tracer
 
 logger = logging.getLogger(__name__)
 
@@ -72,6 +73,7 @@ class BigQueryExecutor(executor.Executor, query_editor.TemplateProcessorMixin):
     """Instantiates bigquery client."""
     return bigquery.Client(self.project_id)
 
+  @tracer.start_as_current_span('bq.execute')
   def execute(
     self,
     query: str,
@@ -119,6 +121,7 @@ class BigQueryExecutor(executor.Executor, query_editor.TemplateProcessorMixin):
     except google_cloud_exceptions.GoogleCloudError as e:
       raise BigQueryExecutorError(e) from e
 
+  @tracer.start_as_current_span('bq.create_datasets')
   def create_datasets(self, macros: dict | None) -> None:
     """Creates datasets in BQ based on values in a dict.
 

{garf_executors-0.0.13 → garf_executors-0.1.2}/garf_executors/entrypoints/cli.py

@@ -28,8 +28,13 @@ from garf_io import reader
 import garf_executors
 from garf_executors import config, exceptions
 from garf_executors.entrypoints import utils
+from garf_executors.entrypoints.tracer import initialize_tracer
+from garf_executors.telemetry import tracer
 
+initialize_tracer()
 
+
+@tracer.start_as_current_span('garf.entrypoints.cli')
 def main():
   parser = argparse.ArgumentParser()
   parser.add_argument('query', nargs='*')
@@ -49,7 +54,7 @@ def main():
   parser.add_argument('--dry-run', dest='dry_run', action='store_true')
   parser.add_argument('-v', '--version', dest='version', action='store_true')
   parser.add_argument(
-    '--parallel-threshold', dest='parallel_threshold', default=None, type=int
+    '--parallel-threshold', dest='parallel_threshold', default=10, type=int
   )
   parser.set_defaults(parallel_queries=True)
   parser.set_defaults(dry_run=False)
@@ -77,7 +82,7 @@ def main():
       args.source, context.fetcher_parameters
     )
     batch = {query: reader_client.read(query) for query in args.query}
-    query_executor.execute_batch(batch, context, args.parallel_queries)
+    query_executor.execute_batch(batch, context, args.parallel_threshold)
   else:
     extra_parameters = utils.ParamsParser(
       ['source', args.output, 'macro', 'template']
@@ -99,7 +104,7 @@ def main():
     if args.parallel_queries:
       logger.info('Running queries in parallel')
       batch = {query: reader_client.read(query) for query in args.query}
-      query_executor.execute_batch(batch, context, args.parallel_queries)
+      query_executor.execute_batch(batch, context, args.parallel_threshold)
     else:
       logger.info('Running queries sequentially')
       for query in args.query:

{garf_executors-0.0.13 → garf_executors-0.1.2}/garf_executors/entrypoints/server.py

@@ -20,9 +20,15 @@ import fastapi
 import pydantic
 import uvicorn
 from garf_io import reader
+from opentelemetry.instrumentation.fastapi import FastAPIInstrumentor
 
 import garf_executors
 from garf_executors import exceptions
+from garf_executors.entrypoints.tracer import initialize_tracer
+
+initialize_tracer()
+app = fastapi.FastAPI()
+FastAPIInstrumentor.instrument_app(app)
 
 
 class ApiExecutorRequest(pydantic.BaseModel):
@@ -40,7 +46,7 @@ class ApiExecutorRequest(pydantic.BaseModel):
   title: Optional[str] = None
   query: Optional[str] = None
   query_path: Optional[Union[str, list[str]]] = None
-  context: garf_executors.ApiExecutionContext
+  context: garf_executors.api_executor.ApiExecutionContext
 
   @pydantic.model_validator(mode='after')
   def check_query_specified(self):
@@ -67,10 +73,18 @@ class ApiExecutorResponse(pydantic.BaseModel):
   results: list[str]
 
 
-router = fastapi.APIRouter(prefix='/api')
+@app.get('/api/version')
+async def version() -> str:
+  return garf_executors.__version__
+
+
+@app.get('/api/fetchers')
+async def get_fetchers() -> list[str]:
+  """Shows all available API sources."""
+  return list(garf_executors.fetchers.find_fetchers())
 
 
-@router.post('/execute')
+@app.post('/api/execute')
 async def execute(request: ApiExecutorRequest) -> ApiExecutorResponse:
   query_executor = garf_executors.setup_executor(
     request.source, request.context.fetcher_parameters
@@ -79,8 +93,8 @@ async def execute(request: ApiExecutorRequest) -> ApiExecutorResponse:
   return ApiExecutorResponse(results=[result])
 
 
-@router.post('/execute:batch')
-async def execute_batch(request: ApiExecutorRequest) -> ApiExecutorResponse:
+@app.post('/api/execute:batch')
+def execute_batch(request: ApiExecutorRequest) -> ApiExecutorResponse:
   query_executor = garf_executors.setup_executor(
     request.source, request.context.fetcher_parameters
   )
@@ -91,6 +105,4 @@ async def execute_batch(request: ApiExecutorRequest) -> ApiExecutorResponse:
 
 
 if __name__ == '__main__':
-  app = fastapi.FastAPI()
-  app.include_router(router)
   uvicorn.run(app)

garf_executors-0.1.2/garf_executors/entrypoints/tracer.py

@@ -0,0 +1,42 @@
+# Copyright 2025 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import os
+
+from opentelemetry import trace
+from opentelemetry.exporter.otlp.proto.grpc.trace_exporter import (
+  OTLPSpanExporter,
+)
+from opentelemetry.sdk.resources import Resource
+from opentelemetry.sdk.trace import TracerProvider
+from opentelemetry.sdk.trace.export import (
+  BatchSpanProcessor,
+)
+
+DEFAULT_SERVICE_NAME = 'garf'
+
+
+def initialize_tracer():
+  resource = Resource.create(
+    {'service.name': os.getenv('OTLP_SERVICE_NAME', DEFAULT_SERVICE_NAME)}
+  )
+
+  tracer_provider = TracerProvider(resource=resource)
+
+  if otel_endpoint := os.getenv('OTEL_EXPORTER_OTLP_ENDPOINT'):
+    otlp_processor = BatchSpanProcessor(
+      OTLPSpanExporter(endpoint=otel_endpoint, insecure=True)
+    )
+    tracer_provider.add_span_processor(otlp_processor)
+  trace.set_tracer_provider(tracer_provider)

{garf_executors-0.0.13 → garf_executors-0.1.2}/garf_executors/executor.py

@@ -14,14 +14,18 @@
 
 """Defines common functionality between executors."""
 
-from concurrent import futures
+import asyncio
+
+from opentelemetry import trace
 
 from garf_executors import execution_context
+from garf_executors.telemetry import tracer
 
 
 class Executor:
   """Defines common functionality between executors."""
 
+  @tracer.start_as_current_span('api.execute_batch')
   def execute_batch(
     self,
     batch: dict[str, str],
@@ -38,17 +42,28 @@ class Executor:
     Returns:
       Results of execution.
     """
-    results = []
-    with futures.ThreadPoolExecutor(max_workers=parallel_threshold) as executor:
-      future_to_query = {
-        executor.submit(
-          self.execute,
-          query,
-          title,
-          context,
-        ): query
-        for title, query in batch.items()
-      }
-      for future in futures.as_completed(future_to_query):
-        results.append(future.result())
-    return results
+    span = trace.get_current_span()
+    span.set_attribute('api.parallel_threshold', parallel_threshold)
+    return asyncio.run(
+      self._run(
+        batch=batch, context=context, parallel_threshold=parallel_threshold
+      )
+    )
+
+  async def _run(
+    self,
+    batch: dict[str, str],
+    context: execution_context.ExecutionContext,
+    parallel_threshold: int,
+  ):
+    semaphore = asyncio.Semaphore(value=parallel_threshold)
+
+    async def run_with_semaphore(fn):
+      async with semaphore:
+        return await fn
+
+    tasks = [
+      self.aexecute(query=query, title=title, context=context)
+      for title, query in batch.items()
+    ]
+    return await asyncio.gather(*(run_with_semaphore(task) for task in tasks))

{garf_executors-0.0.13 → garf_executors-0.1.2}/garf_executors/fetchers.py

@@ -16,9 +16,13 @@ import inspect
 import sys
 from importlib.metadata import entry_points
 
-from garf_core import exceptions, report_fetcher
+from garf_core import report_fetcher
+from opentelemetry import trace
 
+from garf_executors.telemetry import tracer
 
+
+@tracer.start_as_current_span('find_fetchers')
 def find_fetchers() -> set[str]:
   """Identifiers all available report fetchers."""
   if entrypoints := _get_entrypoints('garf'):
@@ -26,6 +30,7 @@ def find_fetchers() -> set[str]:
   return set()
 
 
+@tracer.start_as_current_span('get_report_fetcher')
 def get_report_fetcher(source: str) -> type[report_fetcher.ApiReportFetcher]:
   """Loads report fetcher for a given source.
 
@@ -44,7 +49,9 @@ def get_report_fetcher(source: str) -> type[report_fetcher.ApiReportFetcher]:
   for fetcher in _get_entrypoints('garf'):
     if fetcher.name == source:
       try:
-        fetcher_module = fetcher.load()
+        with tracer.start_as_current_span('load_fetcher_module') as span:
+          fetcher_module = fetcher.load()
+          span.set_attribute('loaded_module', fetcher_module.__name__)
         for name, obj in inspect.getmembers(fetcher_module):
           if inspect.isclass(obj) and issubclass(
             obj, report_fetcher.ApiReportFetcher
@@ -52,7 +59,7 @@ def get_report_fetcher(source: str) -> type[report_fetcher.ApiReportFetcher]:
             return getattr(fetcher_module, name)
       except ModuleNotFoundError:
         continue
-  raise exceptions.ApiReportFetcherError(
+  raise report_fetcher.ApiReportFetcherError(
     f'No fetcher available for the source "{source}"'
   )
 

{garf_executors-0.0.13 → garf_executors-0.1.2}/garf_executors/sql_executor.py

@@ -28,8 +28,10 @@ import re
 
 import pandas as pd
 from garf_core import query_editor, report
+from opentelemetry import trace
 
 from garf_executors import exceptions, execution_context, executor
+from garf_executors.telemetry import tracer
 
 logger = logging.getLogger(__name__)
 
@@ -66,6 +68,7 @@ class SqlAlchemyQueryExecutor(
     engine = sqlalchemy.create_engine(connection_string)
     return cls(engine)
 
+  @tracer.start_as_current_span('sql.execute')
   def execute(
     self,
     query: str,
@@ -84,6 +87,7 @@ class SqlAlchemyQueryExecutor(
     Returns:
       Report with data if query returns some data otherwise empty Report.
     """
+    span = trace.get_current_span()
     logging.info('Executing script: %s', title)
     query_text = self.replace_params_template(query, context.query_parameters)
     with self.engine.begin() as conn:
@@ -115,4 +119,5 @@ class SqlAlchemyQueryExecutor(
         )
         logger.info('%s executed successfully', title)
         return writing_result
+      span.set_attribute('execute.num_results', len(results))
       return results

garf_executors-0.1.2/garf_executors/telemetry.py

@@ -0,0 +1,20 @@
+# Copyright 2025 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# pylint: disable=C0330, g-bad-import-order, g-multiple-import
+from opentelemetry import trace
+
+tracer = trace.get_tracer(
+  instrumenting_module_name='garf_executors',
+)

{garf_executors-0.0.13 → garf_executors-0.1.2}/garf_executors.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: garf-executors
-Version: 0.0.13
+Version: 0.1.2
 Summary: Executes queries against API and writes data to local/remote storage.
 Author-email: "Google Inc. (gTech gPS CSE team)" <no-reply@google.com>, Andrei Markin <andrey.markin.ppc@gmail.com>
 License: Apache 2.0
@@ -21,6 +21,8 @@ Requires-Dist: garf-core
 Requires-Dist: garf-io
 Requires-Dist: pyyaml
 Requires-Dist: pydantic
+Requires-Dist: opentelemetry-api
+Requires-Dist: opentelemetry-sdk
 Provides-Extra: bq
 Requires-Dist: garf-io[bq]; extra == "bq"
 Requires-Dist: pandas; extra == "bq"
@@ -30,6 +32,8 @@ Requires-Dist: garf-io[sqlalchemy]; extra == "sql"
 Requires-Dist: pandas; extra == "sql"
 Provides-Extra: server
 Requires-Dist: fastapi[standard]; extra == "server"
+Requires-Dist: opentelemetry-instrumentation-fastapi; extra == "server"
+Requires-Dist: opentelemetry-exporter-otlp; extra == "server"
 Provides-Extra: all
 Requires-Dist: garf-executors[bq,server,sql]; extra == "all"
 

{garf_executors-0.0.13 → garf_executors-0.1.2}/garf_executors.egg-info/SOURCES.txt

@@ -9,6 +9,7 @@ garf_executors/execution_context.py
 garf_executors/executor.py
 garf_executors/fetchers.py
 garf_executors/sql_executor.py
+garf_executors/telemetry.py
 garf_executors.egg-info/PKG-INFO
 garf_executors.egg-info/SOURCES.txt
 garf_executors.egg-info/dependency_links.txt
@@ -18,4 +19,5 @@ garf_executors.egg-info/top_level.txt
 garf_executors/entrypoints/__init__.py
 garf_executors/entrypoints/cli.py
 garf_executors/entrypoints/server.py
+garf_executors/entrypoints/tracer.py
 garf_executors/entrypoints/utils.py

{garf_executors-0.0.13 → garf_executors-0.1.2}/garf_executors.egg-info/requires.txt

@@ -2,6 +2,8 @@ garf-core
 garf-io
 pyyaml
 pydantic
+opentelemetry-api
+opentelemetry-sdk
 
 [all]
 garf-executors[bq,server,sql]
@@ -13,6 +15,8 @@ google-cloud-logging
 
 [server]
 fastapi[standard]
+opentelemetry-instrumentation-fastapi
+opentelemetry-exporter-otlp
 
 [sql]
 garf-io[sqlalchemy]

{garf_executors-0.0.13 → garf_executors-0.1.2}/pyproject.toml

@@ -9,6 +9,8 @@ dependencies = [
   "garf-io",
   "pyyaml",
   "pydantic",
+  "opentelemetry-api",
+  "opentelemetry-sdk",
 ]
 authors = [
   {name = "Google Inc. (gTech gPS CSE team)", email = "no-reply@google.com"},
@@ -48,6 +50,8 @@ sql=[
 ]
 server=[
   "fastapi[standard]",
+  "opentelemetry-instrumentation-fastapi",
+  "opentelemetry-exporter-otlp",
 ]
 all = [
   "garf-executors[bq,sql,server]"