kafka2s3

kafka2s3/.gitignore

@@ -0,0 +1,289 @@
+# Logs
+logs
+*.log
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+lerna-debug.log*
+.pnpm-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
+
+# Microbundle cache
+.rpt2_cache/
+.rts2_cache_cjs/
+.rts2_cache_es/
+.rts2_cache_umd/
+
+# Optional REPL history
+.node_repl_history
+
+# Output of 'npm pack'
+*.tgz
+
+# Yarn Integrity file
+.yarn-integrity
+
+# dotenv environment variable files
+.env
+.env.development.local
+.env.test.local
+.env.production.local
+.env.local
+
+# parcel-bundler cache (https://parceljs.org/)
+.cache
+.parcel-cache
+
+# Next.js build output
+.next
+out
+
+# Nuxt.js build / generate output
+.nuxt
+dist
+
+# 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
+
+# Docusaurus cache and generated files
+.docusaurus
+
+# Serverless directories
+.serverless/
+
+# FuseBox cache
+.fusebox/
+
+# DynamoDB Local files
+.dynamodb/
+
+# TernJS port file
+.tern-port
+
+# Stores VSCode versions used for testing VSCode extensions
+.vscode-test
+
+# yarn v2
+.yarn/cache
+.yarn/unplugged
+.yarn/build-state.yml
+.yarn/install-state.gz
+.pnp.*
+
+# 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
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__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/
+
+
+secret*
+
+.tinyb

kafka2s3/Makefile

@@ -0,0 +1,109 @@
+
+include .env
+
+# crypto_raw_array:
+# 	decodable stream create \
+# 		--name crypto_raw_array \
+# 		--field records="ARRAY<ROW<id STRING, currency STRING, symbol STRING, name STRING, logo_url STRING, status STRING, price double, price_date STRING, price_timestamp STRING, circulating_supply STRING, max_supply STRING, market_cap STRING, market_cap_dominance STRING, >>"
+
+crypto_desc:
+	decodable stream create \
+		--name crypto_desc \
+		--field id="STRING primary key" \
+		--field currency=STRING
+
+crypto_raw:
+	decodable stream create \
+		--name crypto_raw \
+		--field id=STRING \
+		--field currency=STRING \
+		--field symbol=STRING \
+		--field name=STRING \
+		--field logo_url=STRING \
+		--field status=STRING \
+		--field price=STRING \
+		--field price_date=STRING \
+		--field price_timestamp=STRING \
+		--field circulating_supply=STRING \
+		--field max_supply=STRING \
+		--field market_cap=STRING \
+		--field market_cap_dominance=STRING \
+		--field num_exchanges=STRING \
+		--field num_pairs=STRING \
+		--field num_pairs_unmapped=STRING \
+		--field first_candle=STRING \
+		--field first_trade=STRING \
+		--field first_order_book=STRING \
+		--field rank=STRING \
+		--field rank_delta=STRING \
+		--field high=STRING \
+		--field high_timestamp=STRING \
+		--field 1d="ROW<volume STRING, price_change STRING, price_change_pct STRING, volume_change STRING, volume_change_pct STRING, market_cap_change STRING, market_cap_change_pct STRING >" \
+		--field 30d="ROW<volume STRING, price_change STRING, price_change_pct STRING, volume_change STRING, volume_change_pct STRING, market_cap_change STRING, market_cap_change_pct STRING >"
+
+crypto_raw_table:
+	decodable stream create \
+		--name crypto_raw_table \
+		--field id="STRING primary key" \
+		--field currency=STRING \
+		--field symbol=STRING \
+		--field name=STRING \
+		--field logo_url=STRING \
+		--field status=STRING \
+		--field price=STRING \
+		--field price_date=STRING \
+		--field price_timestamp=STRING \
+		--field circulating_supply=STRING \
+		--field max_supply=STRING \
+		--field market_cap=STRING \
+		--field market_cap_dominance=STRING \
+		--field num_exchanges=STRING \
+		--field num_pairs=STRING \
+		--field num_pairs_unmapped=STRING \
+		--field first_candle=STRING \
+		--field first_trade=STRING \
+		--field first_order_book=STRING \
+		--field rank=STRING \
+		--field rank_delta=STRING \
+		--field high=STRING \
+		--field high_timestamp=STRING \
+		--field 1d="ROW<volume STRING, price_change STRING, price_change_pct STRING, volume_change STRING, volume_change_pct STRING, market_cap_change STRING, market_cap_change_pct STRING >" \
+		--field 30d="ROW<volume STRING, price_change STRING, price_change_pct STRING, volume_change STRING, volume_change_pct STRING, market_cap_change STRING, market_cap_change_pct STRING >"
+
+
+run:
+	python crypto.py
+
+copy.stream:
+	decodable stream get $(shell decodable stream list -o json | jq -sr '.[] |select(.name=="${STREAM}")|.id ' ) -o json | \
+		jq '.schema' | \
+
+
+postgres_cdc:
+	decodable conn create \
+		--name crypto_desc_postgres_cdc \
+		--connector postgres-cdc \
+		--type source \
+		--stream-id $(shell decodable stream list -o json | jq -sr '.[] |select(.name=="crypto_desc")|.id ' ) \
+		--prop database-name=postgres \
+		--prop decoding.plugin.name=pgoutput \
+		--prop hostname=hubert-demo.culgt83fyssj.us-west-2.rds.amazonaws.com \
+		--prop port=5432 \
+		--prop schema-name=public \
+		--prop table-name=crypto_desc \
+		--prop username=postgres \
+		--prop password=$(PG_PASSWORD)
+
+db:
+	psql -h $(PG_HOST) -d $(PG_DB) -U $(PG_USER) -W 
+
+list.topics:
+	kcat -L -b $(BOOTSTRAP)
+
+publish: kconfig # send data to kafka
+	# make publish JSON=<<path to JSON>> 
+	kcat -b $(BOOTSTRAP) -F config.properties -t $(TOPIC) -k $$RANDOM -P $(JSON)
+
+subscribe: kconfig
+	kcat -b $(BOOTSTRAP) -F config.properties -t $(TOPIC) -K :
+