snowflake-data-migration-orchestrator 1.3.3__tar.gz

snowflake_data_migration_orchestrator-1.3.3/.coveragerc

@@ -0,0 +1,23 @@
+[run]
+source = src
+omit =
+    */__init__.py
+    */__about__.py
+
+[report]
+exclude_lines =
+    pragma: no cover
+    def __repr__
+    raise NotImplementedError
+    if __name__ == .__main__.:
+    pass
+    raise ImportError
+
+[html]
+directory = tests/outcome/unit-coverage-html
+
+[xml]
+output = tests/outcome/unit-coverage.xml
+
+[json]
+output = tests/outcome/unit-coverage.json

snowflake_data_migration_orchestrator-1.3.3/.dockerignore

@@ -0,0 +1,18 @@
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+.hatch/
+*.egg-info/
+dist/
+build/
+.git/
+.gitignore
+tests/
+*.md
+!README.md
+.env
+.venv
+venv/
+scripts

snowflake_data_migration_orchestrator-1.3.3/.env.example

@@ -0,0 +1,13 @@
+# Snowflake Connection Configuration
+# Copy this file to .env and fill in your actual values
+
+# Required: Basic Snowflake credentials
+SNOWFLAKE_ACCOUNT=your_account
+SNOWFLAKE_USER=your_user
+SNOWFLAKE_PASSWORD=your_password
+
+# Optional: Connection settings
+SNOWFLAKE_WAREHOUSE=your_warehouse
+SNOWFLAKE_DATABASE=your_database
+SNOWFLAKE_SCHEMA=your_schema
+SNOWFLAKE_ROLE=your_role

snowflake_data_migration_orchestrator-1.3.3/.gitignore

@@ -0,0 +1,207 @@
+# DS_Store
+.DS_Store
+**/.DS_Store
+
+# version
+!__version__.py
+!**/__version__.py
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Sphinx documentation
+docs/build/
+docs/source/**/_autosummary
+
+
+# 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/
+
+# pytest outcome
+*/tests/outcome/
+tests/outcome/**
+test-results.xml
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+logs/
+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
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.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/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# 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/
+
+# PyPI configuration file
+.pypirc
+
+# ruff cache
+.ruff_cache
+
+# Requirements file generated by pip-compile
+requirements.txt
+
+# Data Exchange Agent
+data-exchange-agent/src/mocked_api/*
+.vscode
+
+# Rye lock files (not committed for library projects)
+requirements.lock
+requirements-dev.lock
+
+# Temporary files
+temp/

snowflake_data_migration_orchestrator-1.3.3/CONTRIBUTING.md

@@ -0,0 +1,73 @@
+# CONTRIBUTING
+
+## Code Organization
+Data Migration Orchestrator is organized in these main modules:
+- `utils`: Utils that can be imported from anywhere.
+- `cloud_core`: Core for Cloud operations, which includes definitions for Workflows and Tasks.
+- `data_migration_core`: Core for Data Migration, which includes platform-agnostic logic.
+- `data_migration_cloud`: Workflows Initializers, Task, and Task Handlers for Data Migration Workflows.  
+- `cloud_orchestrator`: The Orchestrator itself, which consumes the other modules to support the execution of Workflows of any kind.
+
+These modules follow a layered architecture with strict import rules. An arrow from module A to module B means that A can import from B. Colors represent the architecture layers:
+- 🔵 **Blue**: Orchestration layer (`cloud_orchestrator`)
+- 🟢 **Green**: Migration logic layer (`data_migration_cloud`)
+- 🟠 **Orange**: Core components layer (`cloud_core`, `data_migration_core`)
+- 🟣 **Purple**: Foundation layer (`utils`)
+
+![Module Dependencies](docs/diagrams/module-dependencies.png)
+
+## Type Errors, Lint Errors, Import Errors & Tests
+We try to keep a high bar for code quality in this project. This includes having a linter and type-safe code. These commands can help you navigate the codebase and check that your work is fulfilling those expectations:
+- Check (and fix) linter errors: `ruff check --fix`
+- Check that you're not violating the rules of the dependencies between the main modules described in [Code Organization](#code-organization): `./scripts/validate_imports.py`
+- Check type safety: `hatch run types:check-ty`
+- Run all tests: `hatch run test:unit`
+
+## Keeping Documentation up to Date
+When adding/modifying features, we should be careful with updating the corresponding documentation (including this file, the README.md and the files in the `docs` directory). This is particularly relevant for the `user-guide.md`.
+There are also Cursor rules that we should keep synchronized with the docs (including this doc).
+
+## Development Patterns
+### Task Model
+In the **Data Migration Orchestrator** we distribute work by converting workflows into sequences of many tasks:
+- Distributing the work in tasks help us achieve fault-tolerance, distribute the workload across several workers, and have "resumability".
+- These tasks can have successors/predecessors and be executed by different components of the architecture.
+- We strive for tasks to be idempotent, retryable, and moderately "quick" to execute. This might not always be achievable.
+- No specific executor is assigned to a task, although a specific executor type will be assigned depending on the kind of the task.
+- Each task has a payload that depends on the kind of the task. There are no guarantees on the time at which a task will be executed. Because of that, we can't assume that a sucessor task will be executed immediately after its predecessor (hours/days could have passed since).
+
+When adding features to the Orchestrator, consider this task model. For more information, you can visit the `task-model.md` document.
+
+### Creating/Queuing Tasks
+Create tasks using the `TaskBuilder` class and then queue them using the `TaskQueue`. When creating sequences of dependent tasks, you can use the `push_task_chain` method of the `TaskQueue`.
+
+### Manipulating Stage Paths
+We constantly are putting data/metadata into files in different paths of stages and then reading that data/metadata (or copying it into tables). For example, the default internal stage is `SNOWCONVERT_AI.DATA_MIGRATION.TASK_RESULTS` and we normally upload metadata/data of the tables we're moving.
+
+We try to avoid passing stage paths through task payloads. Instead, we try to have a standardize pattern for stage paths. For example, if you want to access the path at which the schema information for a table was uploaded, then it might look something like this: `<stage-id>/workflows/<workflow-id>/table/<table-metadata-id>/schema/`.
+
+### Scopes
+Scopes are described in detail in the `scopes.md` doc. Those are useful for understanding what is the purpose of each task and to what "domain" it applies.
+
+When creating scopes, we should use the `ScopeBuilder`. There are other helper functions that can be used when creating scopes (specially if the scope is very commonly created).
+
+### Changing Configuration
+When changing configuration models (by adding or modifying properties or configuration sections) or configuration behavior, we should update the corresponding documentation (the `user-guide.md` and also the examples of configuration).
+
+### Schema Migrations
+When changing the schema (tables in the `SNOWCONVERT_AI.DATA_MIGRATION` schema, for example), we should do it through schema migrations. Check the `schema-migrations.md` doc for more information about this topic.
+
+## Anti-patterns
+1. We want to avoid having duplicated dataclasses (or dataclasses that are almost equivalent) without a good reason.
+2. We do not want to rely too much on magic strings. In cases where we are dealing with categories/kinds, we should prefer to create a `StrEnum`.
+3. We want to avoid "carrying" too much information across tasks, particularly if you are sending a piece of information that is not meant for a task, but rather for a future task that might be created by the immediate task you are creating. We should strive to read configuration values from the TABLE_METADATA configuration column, for example. This also applies to the PARTITION_METADATA synchronization data, for example.
+4. We want to avoid using `Any` if possible. In general, we try to keep the code as type-safe as possible.
+5. We want to avoid complex types without a meaningful name. For example, types like `dict[str, dict[str, str]]` might be complex to understand when reading the code. A type alias or a dedicated class can help here.
+6. Let's not make non-deterministic tests, or unit tests that can take a lot of time. Running all tests should be matter of less than 10 seconds.
+
+## How to add a new platform?
+### Basic Integration
+TODO
+
+### Optimizations
+TODO

snowflake_data_migration_orchestrator-1.3.3/Dockerfile

@@ -0,0 +1,30 @@
+# Use Python 3.11 slim image
+FROM python:3.11-slim
+
+# Set working directory
+WORKDIR /app
+
+# Copy shared directory from parent context (required by pyproject.toml force-include)
+COPY shared /shared
+
+# Copy project files
+COPY data-migration-orchestrator/pyproject.toml data-migration-orchestrator/README.md ./
+COPY data-migration-orchestrator/src/ ./src/
+
+# Install the package and dependencies
+RUN pip install --no-cache-dir -e .
+# TODO(SNOW-2860314): move dependency installation before the part in which we copy the source code to leverage Docker layer caching
+
+# Set the Python path
+ENV PYTHONPATH=/app/src
+
+# Disable Python output buffering to see logs in real-time
+ENV PYTHONUNBUFFERED=1
+
+# Create non-root user and pre-create writable dirs
+RUN groupadd --system appgroup && useradd --system --gid appgroup appuser \
+    && mkdir -p /app/logs && chown appuser:appgroup /app/logs
+USER appuser
+
+# Run the main module
+CMD ["python", "-u", "-m", "data_migration_orchestrator"]

snowflake_data_migration_orchestrator-1.3.3/Jenkinsfile-push-image

@@ -0,0 +1,235 @@
+@Library('pipeline-utils')
+
+import com.snowflake.DevEnvUtils
+
+String prodServerUrl = 'ci-prod-200'
+String devServerUrl = 'sql-001'
+String prodArtifactoryRepo = 'internal-production-docker-data_migration-local'
+String devArtifactoryRepo = 'internal-development-docker-data_migration-local'
+Boolean isProdServer
+Boolean isDevServer
+String artifactoryRepo
+String imageName = 'data-migration-orchestrator'
+String version
+String imageTagAmd64
+String imageTagArm64
+
+pipeline {
+    agent {
+        label 'small-node-snowos'
+    }
+    options {
+        skipDefaultCheckout()
+    }
+    stages {
+        stage("Detect Environment") {
+            steps {
+                script {
+                    isProdServer = env.JENKINS_URL?.contains(prodServerUrl) ?: false
+                    isDevServer = env.JENKINS_URL?.contains(devServerUrl) ?: false
+
+                    if (isProdServer) {
+                        echo "Running on PRODUCTION server: ${env.JENKINS_URL}"
+                        artifactoryRepo = prodArtifactoryRepo
+                    } else if (isDevServer) {
+                        echo "Running on DEV server: ${env.JENKINS_URL}"
+                        artifactoryRepo = devArtifactoryRepo
+                    } else {
+                        error("Unknown server: ${env.JENKINS_URL}. Expected ${prodServerUrl} or ${devServerUrl}")
+                    }
+
+                    echo "Using Artifactory repository: ${artifactoryRepo}"
+                }
+            }
+        }
+
+        stage("Checkout") {
+            steps {
+                script {
+                    checkout([
+                        $class: 'GitSCM',
+                        branches: scm.branches,
+                        extensions: [],
+                        userRemoteConfigs: [[
+                            url: scm.userRemoteConfigs[0].url,
+                            credentialsId: 'jenkins-snowflake-github-app-2-emu'
+                        ]]
+                    ])
+                }
+            }
+        }
+
+        stage("Set Environment") {
+            steps {
+                script {
+                    echo "Extracting version from __version__.py..."
+                    version = sh(
+                        script: "grep -oP '__version__\\s*=\\s*\"\\K[^\"]+' __version__.py",
+                        returnStdout: true
+                    ).trim()
+
+                    // Set image tags
+                    imageTagAmd64 = "${imageName}:${version}"
+                    imageTagArm64 = "${imageName}-arm64:${version}"
+
+                    echo "Environment validation passed."
+                    echo "Version from __version__.py: ${version}"
+                    echo "Image tag (AMD64): ${imageTagAmd64}"
+                    echo "Image tag (ARM64): ${imageTagArm64}"
+                }
+            }
+        }
+
+        stage("Build Docker Images") {
+            steps {
+                script {
+                    sh """
+                        echo "=== Setting up Docker Buildx for multi-platform builds ==="
+                        # Install QEMU emulation for ARM64 builds
+                        docker run --rm --privileged multiarch/qemu-user-static --reset -p yes
+
+                        # Create and use a new buildx builder instance for multi-platform support
+                        docker buildx create --name multiplatform-builder --use --bootstrap
+
+                        echo "=== Building Docker Image (AMD64) ==="
+                        docker buildx build --platform linux/amd64 --load \
+                            -t "${imageTagAmd64}" \
+                            -f "data-migration-orchestrator/Dockerfile" \
+                            .
+                        echo "=== Docker Build Complete (AMD64) ==="
+
+                        echo "=== Building Docker Image (ARM64) ==="
+                        docker buildx build --platform linux/arm64 --load \
+                            -t "${imageTagArm64}" \
+                            -f "data-migration-orchestrator/Dockerfile" \
+                            .
+                        echo "=== Docker Build Complete (ARM64) ==="
+                    """
+                }
+            }
+        }
+
+        stage("Validate Local Images") {
+            steps {
+                script {
+                    // Function to check if image exists locally
+                    def checkLocalImageExists = { imageTag ->
+                        return sh(
+                            script: "docker images --format '{{.Repository}}:{{.Tag}}' | grep -q '^${imageTag}\$'",
+                            returnStatus: true
+                        )
+                    }
+
+                    echo "Validating Docker images exist..."
+                    def imageExistsAmd64 = checkLocalImageExists(imageTagAmd64)
+                    def imageExistsArm64 = checkLocalImageExists(imageTagArm64)
+
+                    if (imageExistsAmd64 != 0) {
+                        error("Docker image '${imageTagAmd64}' not found. Please ensure the image was built and tagged correctly.")
+                    }
+
+                    if (imageExistsArm64 != 0) {
+                        error("Docker image '${imageTagArm64}' not found. Please ensure the ARM64 image was built and tagged correctly.")
+                    }
+
+                    echo "All images validated successfully. Available Docker images:"
+                    sh "docker images | grep ${imageName}"
+                }
+            }
+        }
+
+        stage("Check Artifactory Repository") {
+            steps {
+                script {
+                    new DevEnvUtils().withSfCli {
+                        echo "Authenticating with OCI registry..."
+                        sh "sf artifact oci auth"
+                        echo "Authentication complete."
+
+                        // Function to check if image exists in remote repository
+                        def checkRemoteImageExists = { imagePath ->
+                            return sh(
+                                script: """
+                                    sf artifact container-images exists \\
+                                        --repository ${artifactoryRepo} \\
+                                        --name ${imagePath} \\
+                                        --tag ${version}
+                                """,
+                                returnStatus: true
+                            )
+                        }
+
+                        echo "Checking if AMD64 image already exists in remote repository..."
+                        def remoteImageExistsAmd64 = checkRemoteImageExists(imageName)
+
+                        if (remoteImageExistsAmd64 == 0) {
+                            error("Image '${imageName}:${version}' already exists in repository '${artifactoryRepo}'. Cannot push duplicate version.")
+                        }
+
+                        echo "Checking if ARM64 image already exists in remote repository..."
+                        def remoteImageExistsArm64 = checkRemoteImageExists("${imageName}-arm64")
+
+                        if (remoteImageExistsArm64 == 0) {
+                            error("Image '${imageName}-arm64:${version}' already exists in repository '${artifactoryRepo}'. Cannot push duplicate version.")
+                        }
+
+                        echo "All images validated - none exist in remote repository. Ready to push."
+                    }
+                }
+            }
+        }
+
+        stage("Push AMD64 Image to Artifactory") {
+            steps {
+                script {
+                    new DevEnvUtils().withSfCli {
+                        echo "Pushing AMD64 image to repository: ${artifactoryRepo}"
+
+                        sh """
+                            sf artifact container-images push \\
+                                --image ${imageTagAmd64} \\
+                                --name ${imageName} \\
+                                --repository ${artifactoryRepo} \\
+                                --tag ${version}
+                        """
+                        echo "AMD64 image push complete."
+                    }
+                }
+            }
+        }
+
+        stage("Push ARM64 Image to Artifactory") {
+            steps {
+                script {
+                    new DevEnvUtils().withSfCli {
+                        echo "Pushing ARM64 image to repository: ${artifactoryRepo}"
+
+                        sh """
+                            sf artifact container-images push \\
+                                --image ${imageTagArm64} \\
+                                --name ${imageName}-arm64 \\
+                                --repository ${artifactoryRepo} \\
+                                --tag ${version}
+                        """
+                        echo "ARM64 image push complete."
+
+                        echo "All images pushed successfully to Artifactory!"
+                    }
+                }
+            }
+        }
+    }
+    post {
+        always {
+            script {
+                // Clean up the buildx builder
+                sh """
+                    echo "=== Cleaning up Docker Buildx ==="
+                    docker buildx rm multiplatform-builder || true
+                    echo "=== Buildx cleanup complete ==="
+                """
+            }
+            cleanWs()
+        }
+    }
+}