Merge pull request #2 from oracle-samples/fde

Utility for Downloading repository as zip and extracting them to AIDP…

Author: ahmedawan-oracle

aidp_migration/git_download_and_extract_to_aidp.ipynb

@@ -0,0 +1,130 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "id": "80e69eae-cd44-4046-9f24-4cde652dbc0f",
+      "metadata": {
+        "type": "markdown"
+      },
+      "source": [
+        "Oracle AI Data Platform v1.0\n",
+        "\n",
+        "Copyright © 2025, Oracle and/or its affiliates.\n",
+        "\n",
+        "Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "f2356308-64bd-4fcb-ae88-5869a227eb2a",
+      "metadata": {
+        "type": "markdown"
+      },
+      "source": [
+        "### Sample Code: Downloading Notebooks/Files from Git.\n",
+        "\n",
+        "This example demonstrates how to download notebook/files from Git as ZIP and extract them to AIDP Workspace. It uses requests python library.\n",
+        "\n",
+        "\n",
+        "**Note:** \n",
+        "\n",
+        "- Replace all placeholders (e.g., `<GIT_USERNAME>`, `<GIT_PAT>`, `<AIDP_WORKSPACE_PATH>`, `<GIT_REPO_NAME>`, `<GIT_BRANCH>`, `<IS_PRIVATE_REPO>`  etc.) with values specific to your environment before running the notebook. \n",
+        "- GIT_PAT is mandatory only for private repository.\n",
+        "- Use with caution: Notebook is designed for downloading all files from repo and unarchive to provided workspace path.\n",
+        "- This notebook should be executed from AIDP.\n",
+        "- Hardcoding Git token into the notebook leaves credentials vulnerable. It is strongly advised to manage the token securely by loading it dynamically from an environment variable, a secure configuration file, or a OCI Vault."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "065a7b5a-727d-4297-a502-e92c074f626f",
+      "metadata": {
+        "execution": {
+          "iopub.status.busy": "2025-11-04T14:37:15.709Z"
+        },
+        "trusted": true,
+        "type": "python"
+      },
+      "outputs": [],
+      "source": [
+        "# Username of Github\n",
+        "git_username = \"<GIT_USERNAME>\"\n",
+        "# Access Token of Github, needed for Private Repository.\n",
+        "git_pat = \"<GIT_PAT>\"\n",
+        "# AIDP Workspace path to download repository\n",
+        "aidp_path = \"<AIDP_WORKSPACE_PATH>\"\n",
+        "# Github Repository Name\n",
+        "git_repo_name = \"<GIT_REPO_NAME>\"\n",
+        "# Github Branch Name\n",
+        "git_branch = \"<GIT_BRANCH>\"\n",
+        "# Field 'is_private_repo' should be provided as a boolean (True/False).\n",
+        "is_private_repo = \"<IS_PRIVATE_REPO>\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "d730a44f-6582-40eb-8c72-f88519b01e23",
+      "metadata": {
+        "execution": {
+          "iopub.status.busy": "2025-11-04T14:37:29.146Z"
+        },
+        "trusted": true,
+        "type": "python"
+      },
+      "outputs": [],
+      "source": [
+        "import requests\n",
+        "import zipfile\n",
+        "import io\n",
+        "\n",
+        "zip_url = f\"https://api.github.com/repos/{git_username}/{git_repo_name}/zipball/{git_branch}\"\n",
+        "\n",
+        "try:\n",
+        "    headers = {\n",
+        "        \"Accept\": \"application/vnd.github.v3+json\"\n",
+        "    }\n",
+        "\n",
+        "    #Authorization requires only for Private Repo.\n",
+        "    if is_private_repo:\n",
+        "        if not git_pat:\n",
+        "            raise ValueError(\"GIT_PERSONAL_ACCESS_TOKEN not set\")\n",
+        "        headers[\"Authorization\"] = f\"token {git_pat}\"\n",
+        "        \n",
+        "    print(f\"Downloading ZIP from {zip_url}...\")\n",
+        "    response = requests.get(zip_url, headers=headers, stream=True)\n",
+        "    response.raise_for_status()\n",
+        "\n",
+        "    # Extract the ZIP content\n",
+        "    with zipfile.ZipFile(io.BytesIO(response.content)) as zip_ref:\n",
+        "        \n",
+        "        top_level_folder = os.path.commonprefix(zip_ref.namelist())\n",
+        "        # Extract all files\n",
+        "        zip_ref.extractall(aidp_path)\n",
+        "        print(\"Repository downloaded and extracted successfully.\")\n",
+        "\n",
+        "except requests.exceptions.RequestException as e:\n",
+        "    print(f\"Error downloading repository: {e}\")\n",
+        "except zipfile.BadZipFile:\n",
+        "    print(\"Downloaded file is not a valid ZIP file.\")\n",
+        "except Exception as e:\n",
+        "    print(f\"An unexpected error occurred: {e}\")"
+      ]
+    }
+  ],
+  "metadata": {
+    "Last_Active_Cell_Index": 2,
+    "kernelspec": {
+      "display_name": "python3",
+      "name": "notebook"
+    },
+    "language_info": {
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 5
+}