initial commit

.editorconfig

@@ -0,0 +1,15 @@
+root = true
+
+[*]
+end_of_line = lf
+charset = utf-8
+insert_final_newline = true
+trim_trailing_whitespace = true
+
+[*.{md}]
+indent_size = 2
+indent_style = space
+
+[*.{cfg,py,sh}]
+indent_size = 4
+indent_style = space

.gitignore

@@ -0,0 +1,269 @@
+
+# Created by https://www.toptal.com/developers/gitignore/api/pycharm+all,python,vim
+# Edit at https://www.toptal.com/developers/gitignore?templates=pycharm+all,python,vim
+
+### PyCharm+all ###
+# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio, WebStorm and Rider
+# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
+
+# User-specific stuff
+.idea/**/workspace.xml
+.idea/**/tasks.xml
+.idea/**/usage.statistics.xml
+.idea/**/dictionaries
+.idea/**/shelf
+
+# AWS User-specific
+.idea/**/aws.xml
+
+# Generated files
+.idea/**/contentModel.xml
+
+# Sensitive or high-churn files
+.idea/**/dataSources/
+.idea/**/dataSources.ids
+.idea/**/dataSources.local.xml
+.idea/**/sqlDataSources.xml
+.idea/**/dynamic.xml
+.idea/**/uiDesigner.xml
+.idea/**/dbnavigator.xml
+
+# Gradle
+.idea/**/gradle.xml
+.idea/**/libraries
+
+# Gradle and Maven with auto-import
+# When using Gradle or Maven with auto-import, you should exclude module files,
+# since they will be recreated, and may cause churn.  Uncomment if using
+# auto-import.
+# .idea/artifacts
+# .idea/compiler.xml
+# .idea/jarRepositories.xml
+# .idea/modules.xml
+# .idea/*.iml
+# .idea/modules
+# *.iml
+# *.ipr
+
+# CMake
+cmake-build-*/
+
+# Mongo Explorer plugin
+.idea/**/mongoSettings.xml
+
+# File-based project format
+*.iws
+
+# IntelliJ
+out/
+
+# mpeltonen/sbt-idea plugin
+.idea_modules/
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# Cursive Clojure plugin
+.idea/replstate.xml
+
+# SonarLint plugin
+.idea/sonarlint/
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+fabric.properties
+
+# Editor-based Rest Client
+.idea/httpRequests
+
+# Android studio 3.1+ serialized cache file
+.idea/caches/build_file_checksums.ser
+
+### PyCharm+all Patch ###
+# Ignore everything but code style settings and run configurations
+# that are supposed to be shared within teams.
+
+.idea/*
+
+!.idea/codeStyles
+!.idea/runConfigurations
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  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/
+
+### Vim ###
+# Swap
+[._]*.s[a-v][a-z]
+!*.svg  # comment out if you don't need vector files
+[._]*.sw[a-p]
+[._]s[a-rt-v][a-z]
+[._]ss[a-gi-z]
+[._]sw[a-p]
+
+# Session
+Session.vim
+Sessionx.vim
+
+# Temporary
+.netrwhist
+*~
+# Auto-generated tag files
+tags
+# Persistent undo
+[._]*.un~
+
+# End of https://www.toptal.com/developers/gitignore/api/pycharm+all,python,vim
+

celery_aws_xray_sdk_extension/__init__.py

@@ -0,0 +1 @@
+__version__ = '0.1.0'

celery_aws_xray_sdk_extension/handlers.py

@@ -0,0 +1,49 @@
+from aws_xray_sdk.core import xray_recorder
+from aws_xray_sdk.core.utils import stacktrace
+from aws_xray_sdk.ext.util import construct_xray_header, inject_trace_header
+
+__all__ = (
+    'xray_after_task_publish',
+    'xray_before_task_publish',
+    'xray_task_failure',
+    'xray_task_postrun',
+    'xray_task_prerun',
+)
+
+CELERY_NAMESPACE = 'celery'
+
+
+def xray_before_task_publish(sender=None, headers=None, **kwargs):
+    headers = headers if headers else {}
+    task_id = headers.get('id')
+
+    subsegment = xray_recorder.begin_subsegment(name=sender, namespace='remote')
+    if not subsegment:
+        return
+
+    subsegment.put_metadata('task_id', task_id, namespace=CELERY_NAMESPACE)
+    inject_trace_header(headers, subsegment)
+
+
+def xray_after_task_publish(**kwargs):
+    xray_recorder.end_subsegment()
+
+
+def xray_task_prerun(task_id=None, task=None, **kwargs):
+    xray_header = construct_xray_header(task.request)
+    segment = xray_recorder.begin_segment(name=task.name, traceid=xray_header.root, parent_id=xray_header.parent)
+    segment.save_origin_trace_header(xray_header)
+    segment.put_annotation('routing_key', task.request.properties["delivery_info"]["routing_key"])
+    segment.put_annotation('task_name', task.name)
+    segment.put_metadata('task_id', task_id, namespace=CELERY_NAMESPACE)
+
+
+def xray_task_postrun(**kwargs):
+    xray_recorder.end_segment()
+
+
+def xray_task_failure(exception=None, **kwargs):
+    segment = xray_recorder.current_segment()
+    if exception:
+        stack = stacktrace.get_stacktrace(limit=xray_recorder._max_trace_back)
+        segment.add_exception(exception, stack)

example/readme.md

@@ -0,0 +1,37 @@
+# Example for celery-aws-xray-sdk-extension
+
+## Installation
+
+[Docker](https://www.docker.com/) is required for this example setup.
+
+1. Create an empty [virtualenv](https://virtualenv.pypa.io/en/latest/) in this directory and activate it.
+2. Run `pip install -e .`in this directory.
+3. Set environment variables to your testing AWS account (`AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY` and `AWS_SESSION_TOKEN`).
+4. Run `./run_xray_daemon.sh`. This starts in background a Docker container with AWS X-Ray daemon using latest version on port 2000.
+5. Run `./run.sh`. This starts the Celery worker with AWS X-Ray SDK patch for `httplib`.
+
+## Running demo Celery tasks
+
+This demo project contains 3 Celery tasks: `add`, `power_2` and `complex`.
+
+### Task `add`
+
+`celery -A tasks call -a '[2, 2]' tasks.add`
+
+Simply adds together two numbers. 
+
+### Task `power_2`
+
+`celery -A tasks call -a '[4]' tasks.power_2`
+
+Returns second power of a number.
+
+### Task `complex`
+
+`celery -A tasks call -a '[2, 2]' tasks.complex`
+
+Sends a HTTP request to [example.com](https://example.com/) and returns a second power of sum of two numbers.
+
+`celery -A tasks call -a '[2, 2]' -k '{"fail": true}' tasks.complex`
+
+You can optionally make it fail by providing `fail` kwarg set to `True`.

example/requirements.txt

@@ -0,0 +1,4 @@
+-e ..
+aws-xray-sdk>=2.9.0,<3
+celery[redis]>=5,<6
+requests<3

example/run.sh

@@ -0,0 +1,4 @@
+#!/bin/sh
+docker run --rm -d -p 6379:6379 --name celery-aws-xray-sdk-extension redis:alpine
+celery -A tasks worker -n celery-aws-xray-sdk-extension-example -E -Q xray-demo -l INFO
+docker stop celery-aws-xray-sdk-extension

example/run_xray_daemon.sh

@@ -0,0 +1,2 @@
+#!/bin/sh
+docker run --name aws-xray-daemon --rm -d -p 2000:2000 -e AWS_ACCESS_KEY_ID=${AWS_ACCESS_KEY_ID} -e AWS_SECRET_ACCESS_KEY=${AWS_SECRET_ACCESS_KEY} -e AWS_SESSION_TOKEN=${AWS_SESSION_TOKEN} --network host public.ecr.aws/xray/aws-xray-daemon:latest -o -n eu-central-1