Resolves #3 adding gene expr correlation with str length in crc suppo…

…rt + docker-compose + alembic migrations (optional)

.devcontainer/devcontainer.json

@@ -0,0 +1,29 @@
+// For format details, see https://aka.ms/devcontainer.json. For config options, see the
+// README at: https:/devcontainers/templates/tree/main/src/docker-existing-dockerfile
+{
+ "name": "Existing Dockerfile",
+ "build": {
+ // Sets the run context to one level up instead of the .devcontainer folder.
+ "context": "..",
+ // Update the 'dockerFile' property if you aren't using the standard 'Dockerfile' filename.
+ "dockerfile": "../Dockerfile"
+ },
+ "features": {
+ "ghcr.io/devcontainers/features/python:1": {}
+ }
+
+ // Features to add to the dev container. More info: https://containers.dev/features.
+ // "features": {},
+
+ // Use 'forwardPorts' to make a list of ports inside the container available locally.
+ // "forwardPorts": [],
+
+ // Uncomment the next line to run commands after the container is created.
+ // "postCreateCommand": "cat /etc/os-release",
+
+ // Configure tool-specific properties.
+ // "customizations": {},
+
+ // Uncomment to connect as an existing user other than the container default. More info: https://aka.ms/dev-containers-non-root.
+ // "remoteUser": "devcontainer"
+}

.dockerignore

@@ -0,0 +1,28 @@
+**/__pycache__
+**/.venv
+**/.classpath
+**/.dockerignore
+**/.env
+**/.git
+**/.gitignore
+**/.project
+**/.settings
+**/.toolstarget
+**/.vs
+**/.vscode
+**/*.*proj.user
+**/*.dbmdl
+**/*.jfm
+**/bin
+**/charts
+**/docker-compose*
+**/compose*
+**/Dockerfile*
+**/node_modules
+**/npm-debug.log
+**/obj
+**/secrets.dev.yaml
+**/values.dev.yaml
+**/db/
+LICENSE
+README.md

.env.example

@@ -0,0 +1,7 @@
+# Rename this file to .env and docker compose wil automatically use envornment variables fro it
+DATABASE_URL=postgresql://webstr:webstr@webstr_db:5432/webstr
+# DATABASE_URL=sqlite:///db/debug.sqlite
+PYTHONPATH="./" 
+WEBSTR_DATABASE_DATA=True
+WEBSTR_DEVELOPMENT=False
+WEBSTR_SOURCE_MOUNT_PATH=/temp/src #/usr/src/strs

.gitignore

@@ -4,4 +4,8 @@
 
 strAPI/local_queries.ipynb
 data/repeats
+db/docker_data/
 .venv/
+db/debug.db
+
+*/migrations/versions0/*

.vscode/launch.json

@@ -0,0 +1,46 @@
+{
+ "configurations": [
+ {
+ "name": "Python: main",
+ "type": "python",
+ "request": "launch",
+ "program": "strAPI/main.py",
+ "cwd": "${workspaceFolder}",
+ "console": "integratedTerminal",
+ "justMyCode": true,
+ "env": {
+ // "PYTHONPATH": "${workspaceFolder}/strAPI/"
+ }
+ },
+ {
+ "name": "Docker: Python - Fastapi",
+ "type": "docker",
+ "request": "launch",
+ "preLaunchTask": "docker-run: debug",
+ "python": {
+ "pathMappings": [
+ {
+ "localRoot": "${workspaceFolder}",
+ "remoteRoot": "/usr/src/strs"
+ }
+ ],
+ "projectType": "fastapi"
+ },
+ },
+ {
+ "name": "Python: Remote Attach 5000",
+ "type": "python",
+ "request": "attach",
+ "connect": {
+ "host": "0.0.0.0",
+ "port": 5000
+ },
+ "pathMappings": [
+ {
+ "localRoot": "${workspaceFolder}",
+ "remoteRoot": "/usr/src/app"
+ }
+ ]
+ }
+ ]
+}

.vscode/tasks.json

@@ -0,0 +1,43 @@
+{
+ "version": "2.0.0",
+ "tasks": [
+ {
+ "type": "docker-build",
+ "label": "docker-build",
+ "platform": "python",
+ "dockerBuild": {
+ "tag": "webstrapi:latest",
+ "dockerfile": "${workspaceFolder}/Dockerfile",
+ "context": "${workspaceFolder}",
+ "pull": true,
+ }
+ },
+ {
+ "type": "docker-run",
+ "label": "docker-run: debug",
+ "dependsOn": [
+ "docker-build"
+ ],
+ "dockerRun": {
+ "env": {
+ "DATABASE_URL": "sqlite:///db/debug.db",
+ "WEBSTR_DATABAS_UPGRADE": "True"
+ },
+ "mounts": [
+ "source=${workspaceFolder},target=/app,type=bind,consistency=cached"
+ ],
+ },
+ "python": {
+ "args": [
+ "strAPI.main:app",
+ "--host",
+ "0.0.0.0",
+ "--port",
+ "5000",
+ "--reload"
+ ],
+ "module": "uvicorn",
+ }
+ }
+ ]
+}

Dockerfile

@@ -1,18 +1,33 @@
-FROM python:3.8-slim-buster
+FROM python:3.8-slim-buster as base
 LABEL maintainer="merenlin -- follow me on medium https://medium.com/@merenlin"
 
-RUN apt-get update && apt-get install -y python3-dev build-essential
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV PYTHONUNBUFFERED=1
 
 RUN mkdir -p /usr/src/strs
 WORKDIR /usr/src/strs
 
 COPY requirements.txt .
-RUN pip3 install -r requirements.txt
+
+RUN apt-get update && \
+ apt-get install -y gcc python3-dev build-essential && \
+ python -m pip install -r requirements.txt --no-cache-dir && \
+ apt-get remove -y gcc python3-dev build-essential && \
+ apt-get clean && rm -rf /var/lib/apt/lists/*
+
+ENV DATABASE_URL=sqlite:///db/debug.db
+
+FROM base as prod
+LABEL maintainer="merenlin -- follow me on medium https://medium.com/@merenlin"
+
+RUN adduser -u 1000 --disabled-password --gecos "" appuser && chown -R appuser /usr/src/strs
+USER appuser
 
 COPY . .
 
-EXPOSE 5000
+ARG PORT=5000
+EXPOSE $PORT
 
-CMD uvicorn strAPI.main:app --host=0.0.0.0 --port=${PORT:-5000}
+CMD bash entrypoint.sh
 
 

README.md

@@ -76,3 +76,13 @@ Explore "database_setup" directory for different utilities to import data into t
 * If you would like **to import a new reference panel** we recommend making a csv corresponding to the repeats table structure and importing it directly to SQL to save time. Alternatively see ` insert_repeats.py ` and 
 ` import_data_ensembltrs.py ` utilities that we made for repeats data coming in different formats. Feel free to contact us for more details if you would like to make your own reference STR panel. 
 
+
+
+## DOCKER COMPOSE
+
+### How to run a debug container with database (for testing of migrations for example)
+
+```
+docker compose up -d webstr_debug
+docker exec -it webstr_debug bash
+```

alembic.ini

@@ -0,0 +1,110 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts
+script_location = database_setup/migrations
+
+# template used to generate migration file names; The default value is %%(rev)s_%%(slug)s
+# Uncomment the line below if you want the files to be prepended with date and time
+# see https://alembic.sqlalchemy.org/en/latest/tutorial.html#editing-the-ini-file
+# for all available tokens
+file_template = %%(year)d_%%(month).2d_%%(day).2d_%%(hour).2d%%(minute).2d-%%(rev)s_%%(slug)s
+
+# sys.path path, will be prepended to sys.path if present.
+# defaults to the current working directory.
+prepend_sys_path = .
+
+# timezone to use when rendering the date within the migration file
+# as well as the filename.
+# If specified, requires the python-dateutil library that can be
+# installed by adding `alembic[tz]` to the pip requirements
+# string value is passed to dateutil.tz.gettz()
+# leave blank for localtime
+# timezone =
+
+# max length of characters to apply to the
+# "slug" field
+# truncate_slug_length = 40
+
+# set to 'true' to run the environment during
+# the 'revision' command, regardless of autogenerate
+# revision_environment = false
+
+# set to 'true' to allow .pyc and .pyo files without
+# a source .py file to be detected as revisions in the
+# versions/ directory
+# sourceless = false
+
+# version location specification; This defaults
+# to migrations/versions. When using multiple version
+# directories, initial revisions must be specified with --version-path.
+# The path separator used here should be the separator specified by "version_path_separator" below.
+# version_locations = %(here)s/bar:%(here)s/bat:migrations/versions
+
+# version path separator; As mentioned above, this is the character used to split
+# version_locations. The default within new alembic.ini files is "os", which uses os.pathsep.
+# If this key is omitted entirely, it falls back to the legacy behavior of splitting on spaces and/or commas.
+# Valid values for version_path_separator are:
+#
+# version_path_separator = :
+# version_path_separator = ;
+# version_path_separator = space
+version_path_separator = os # Use os.pathsep. Default configuration used for new projects.
+
+# set to 'true' to search source files recursively
+# in each "version_locations" directory
+# new in Alembic version 1.10
+# recursive_version_locations = false
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+sqlalchemy.url = sqlite:///db/debug.sqlite
+
+
+[post_write_hooks]
+# post_write_hooks defines scripts or Python functions that are run
+# on newly generated revision scripts. See the documentation for further
+# detail and examples
+
+# format using "black" - use the console_scripts runner, against the "black" entrypoint
+# hooks = black
+# black.type = console_scripts
+# black.entrypoint = black
+# black.options = -l 79 REVISION_SCRIPT_FILENAME
+
+# Logging configuration
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARN
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARN
+handlers =
+qualname = sqlalchemy.engine
+
+[logger_alembic]
+level = INFO
+handlers =
+qualname = alembic
+
+[handler_console]
+class = StreamHandler
+args = (sys.stderr,)
+level = NOTSET
+formatter = generic
+
+[formatter_generic]
+format = %(levelname)-5.5s [%(name)s] %(message)s
+datefmt = %H:%M:%S