nb-fabric 1.0.0

CLI for managing Microsoft Fabric notebooks; create, edit cells, execute interactively, schedule, and query OneLake data
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140

// #region Imports
use base64::Engine;
use base64::engine::general_purpose::STANDARD as BASE64;
use serde_json::json;
// #endregion

// #region Functions

/// Generate an ipynb JSON structure for a new Fabric notebook.
///
/// Inputs:
///   - kernel: "python" or "pyspark"
///   - lakehouse_id: optional lakehouse GUID for default lakehouse
///   - lakehouse_name: optional lakehouse display name
///   - warehouse_id: optional warehouse GUID
///   - warehouse_name: optional warehouse display name
///   - workspace_id: workspace GUID (needed for trident references)
///
/// Returns: (ipynb_json_value, base64_encoded_string)
pub fn generate_ipynb(
    kernel: &str,
    lakehouse_id: Option<&str>,
    lakehouse_name: Option<&str>,
    warehouse_id: Option<&str>,
    warehouse_name: Option<&str>,
    workspace_id: &str,
) -> (serde_json::Value, String) {
    let (kernel_name, language_group, kernelspec_name, language) = match kernel {
        "pyspark" => (
            "synapse_pyspark",
            "synapse_pyspark",
            "python3",
            "python",
        ),
        _ => ("jupyter", "jupyter_python", "jupyter", "python"),
    };

    let kernelspec_display = if kernel == "python" { "Jupyter" } else { "Python 3" };

    let jupyter_kernel_name = if kernel == "python" {
        "python3.11"
    } else {
        "synapse_pyspark"
    };

    let mut metadata = json!({
        "kernel_info": {
            "name": kernel_name
        },
        "kernelspec": {
            "name": kernelspec_name,
            "display_name": kernelspec_display,
            "language": language
        },
        "language_info": {
            "name": language,
            "version": ""
        },
        "microsoft": {
            "language": language,
            "language_group": language_group,
            "ms_spell_check": {
                "ms_spell_check_language": "en"
            }
        },
        "nteract": {
            "version": "nteract-front-end@1.0.0"
        },
        "widgets": {},
        "spark_compute": {
            "compute_id": "/trident/default"
        }
    });

    // Add jupyter kernel_name for python kernels
    if kernel == "python" {
        metadata["kernel_info"]["jupyter_kernel_name"] = json!(jupyter_kernel_name);
    }

    // Build dependencies
    let mut dependencies = json!({});

    if let (Some(lh_id), Some(lh_name)) = (lakehouse_id, lakehouse_name) {
        dependencies["lakehouse"] = json!({
            "default_lakehouse": lh_id,
            "default_lakehouse_name": lh_name,
            "default_lakehouse_workspace_id": workspace_id,
            "known_lakehouses": [
                {
                    "id": lh_id
                }
            ]
        });
    }

    if let (Some(wh_id), Some(wh_name)) = (warehouse_id, warehouse_name) {
        dependencies["warehouse"] = json!({
            "default_warehouse": wh_id,
            "default_warehouse_name": wh_name,
            "default_warehouse_workspace_id": workspace_id,
            "known_warehouses": [
                {
                    "id": wh_id,
                    "type": "Datawarehouse"
                }
            ]
        });
    }

    if dependencies.as_object().map_or(false, |o| !o.is_empty()) {
        metadata["dependencies"] = dependencies;
    }

    let ipynb = json!({
        "nbformat": 4,
        "nbformat_minor": 5,
        "metadata": metadata,
        "cells": [
            {
                "cell_type": "code",
                "metadata": {
                    "microsoft": {
                        "language": language,
                        "language_group": language_group
                    }
                },
                "source": [""],
                "outputs": [],
                "execution_count": null
            }
        ]
    });

    let ipynb_str = serde_json::to_string_pretty(&ipynb).unwrap();
    let encoded = BASE64.encode(ipynb_str.as_bytes());

    (ipynb, encoded)
}

// #endregion