Initial Commit

.gitignore

@@ -0,0 +1,160 @@
+# 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/
+
+# 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/

Dockerfile

@@ -0,0 +1,10 @@
+FROM docker.co.clearstreet.io/clst/clst-python:3.9.5-slim-buster
+
+WORKDIR /usr/src/app
+
+COPY requirements.txt ./
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+CMD [ "python", "./main.py" ]

config/localkube.yaml

@@ -0,0 +1,5 @@
+---
+aws:
+  access_key: fake
+  secret_key: fake
+  endpoint_url: http://aws:4566

main.py

@@ -0,0 +1,129 @@
+import os
+
+import boto3
+
+from flask import Flask, send_file, render_template, redirect
+from gestalt import Gestalt
+
+from clearstreet.logger import create_logger
+
+
+def sanitize_key(key):
+    return key.replace("/", "-")
+
+
+def rebuild_key(key):
+    return key.replace("-", "/")
+
+
+def get_path(key):
+    s = key.split("/")
+    return "/".join(s[:len(s) - 1])
+
+
+def get_filename(key):
+    s = key.split("/")
+    return s[len(s) - 1]
+
+
+def build_s3_client(config: Gestalt):
+    session = boto3.Session()
+    access = config.get_string("aws.access_key")
+    secret = config.get_string("aws.secret_key")
+    url = config.get_string("aws.endpoint_url", 's3.amazonaws.com')
+    s3 = session.client(
+        service_name="s3",
+        aws_access_key_id=access,
+        aws_secret_access_key=secret,
+        endpoint_url=url,
+    )
+    return s3
+
+
+def list_buckets(client):
+    ret = []
+    list = client.list_buckets()['Buckets']
+    for bucket in list:
+        ret.append(bucket["Name"])
+    ret.sort()
+    return ret
+
+
+def list_in_bucket(client, bucket, prefix):
+    ret = []
+    items = []
+
+    if prefix is None or len(prefix) == 0:
+        items = client.list_objects_v2(Bucket=bucket, Delimiter="/")
+    else:
+        items = client.list_objects_v2(Bucket=bucket, Prefix=f"{prefix}/", Delimiter="/")
+
+    for item in items.get('Contents', []):
+        if item.get('Key', None) is not None:
+            ret.append(item['Key'])
+    ret.sort()
+
+    dirs = []
+    for item in items.get('CommonPrefixes', []):
+        if item.get('Prefix', None) is not None:
+            dirs.append(item['Prefix'])
+
+    dirs.sort()
+    return ret, dirs
+
+
+def download_object(client, bucket_name, key):
+    key = rebuild_key(key)
+    filename = "/tmp" + get_filename(key)
+    client.download_file(Bucket=bucket_name, Key=key, Filename=filename)
+    return filename
+
+
+env = os.environ.get('ENV', 'localkube')
+
+logger = create_logger("q1")
+
+app = Flask(__name__)
+
+logger.info("loading configurations", env=env)
+g = Gestalt()
+g.add_config_file(f'./config/{env}.yaml')
+g.build_config()
+g.auto_env()
+
+s3client = build_s3_client(g)
+
+
+@app.route('/download/<bucket>/<path:path>')
+def download(bucket, path):
+    global s3client
+    fname = download_object(s3client, bucket, path)
+    return send_file(fname, as_attachment=True)
+
+
+@app.route('/browse/<bucket>', defaults={'path': ''})
+@app.route('/browse/<bucket>/', defaults={'path': ''})
+@app.route('/browse/<bucket>/<path:path>')
+@app.route('/browse/<bucket>/<path:path>/')
+def withinBucket(bucket, path):
+    global s3client
+    logger.info("inside bucket", bucket=bucket, path=path)
+    items, dirs = list_in_bucket(s3client, bucket, path)
+    return render_template('browser.html', items=items, dirs=dirs, bucket=bucket, path=path)
+
+
+@app.route('/browse')
+@app.route('/browse/')
+def sendhome():
+    return redirect("/", code=302)
+
+
+@app.route('/')
+def root():
+    global s3client
+    buckets = list_buckets(s3client)
+    return render_template('index.html', buckets=buckets)
+
+
+if __name__ == "__main__":
+    app.run(host="0.0.0.0", port=8081, debug=True)

requirements.txt

@@ -0,0 +1,5 @@
+Flask==2.1.2
+clearstreet.logger==2.0.2
+boto3==1.24.47
+botocore==1.27.48
+gestalt-cfg==3.0.0

templates/browser.html

@@ -0,0 +1,31 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <!--Import Google Icon Font-->
+    <link href="https://fonts.googleapis.com/icon?family=Material+Icons" rel="stylesheet">
+    <!--Import materialize.css-->
+    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/materialize/1.0.0/css/materialize.min.css">
+
+    <!--Let browser know website is optimized for mobile-->
+    <meta name="viewport" content="width=device-width, initial-scale=1.0"/>
+    <title>Q1</title>
+</head>
+<body>
+    <h1>Q1: A Simple S3 Browser</h1>
+    <h3>Directories</h3>
+    <ul>
+    {% for item in dirs %}
+      <li><a href="/browse/{{bucket}}/{{item}}">{{item}}</a></li>
+    {% endfor %}
+    </ul>
+    <h3>Files</h3>
+    <ul>
+    {% for item in items %}
+      <li>{{item}} -- <a href="/download/{{bucket}}/{{item}}">Download</a></li>
+    {% endfor %}
+    </ul>
+    <a href="../"><b>Back</b></a>
+    <script type="text/javascript" src="js/materialize.min.js"></script>
+</body>
+</html> 

templates/index.html

@@ -0,0 +1,25 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+
+    <!--Import Google Icon Font-->
+    <link href="https://fonts.googleapis.com/icon?family=Material+Icons" rel="stylesheet">
+    <!--Import materialize.css-->
+    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/materialize/1.0.0/css/materialize.min.css">
+
+    <!--Let browser know website is optimized for mobile-->
+    <meta name="viewport" content="width=device-width, initial-scale=1.0"/>
+
+    <title>Q1</title>
+</head>
+<body>
+    <h1>Q1: A Simple S3 Browser</h1>
+    <ul>
+    {% for bucket in buckets %}
+      <li><a href="/browse/{{bucket}}">{{bucket}}</a></li>
+    {% endfor %}
+    </ul>
+    <script type="text/javascript" src="js/materialize.min.js"></script>
+</body>
+</html>