nbwipers 0.3.3

Wipe clean your Jupyter Notebooks!
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
141
142
143
144
145
146
147
148
149
150

use std::{fmt::Display, path::Path};

use crate::{
    extra_keys::partition_extra_keys, files::NBReadError, schema::RawNotebook, settings::Settings,
    utils::get_value_child,
};
use serde::Serialize;
use serde_json::Value;

#[derive(Clone, Debug, Serialize, PartialEq, Eq)]
#[serde(tag = "type")]
pub enum CheckResult {
    IOError {
        error: String,
    },
    InvalidNotebook {
        error: String,
    },
    StripMeta {
        extra_key: String,
    },
    DropCells {
        cell_number: usize,
    },
    ClearOutput {
        cell_number: usize,
    },
    ClearCount {
        cell_number: usize,
    },
    ClearId {
        cell_number: usize,
    },
    CellStripMeta {
        cell_number: usize,
        extra_key: String,
    },
}
impl From<NBReadError> for CheckResult {
    fn from(value: NBReadError) -> Self {
        match value {
            NBReadError::IO(e) => Self::IOError {
                error: e.to_string(),
            },
            NBReadError::Serde(e) => Self::InvalidNotebook {
                error: e.to_string(),
            },
        }
    }
}

#[derive(Clone, Debug, Serialize, PartialEq, Eq)]
pub struct PathCheckResult<'a> {
    pub path: &'a Path,
    #[serde(flatten)]
    pub result: &'a CheckResult,
}

impl Display for CheckResult {
    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
        match self {
            CheckResult::IOError { error } => write!(f, "IO Error: {error}"),
            CheckResult::InvalidNotebook { error } => write!(f, "Invalid notebook: {error}"),
            CheckResult::DropCells { cell_number } => {
                write!(f, "cell: {cell_number}: Found cell to be dropped")
            }
            CheckResult::StripMeta { extra_key } => {
                write!(f, "Found notebook metadata: {extra_key}")
            }

            CheckResult::CellStripMeta {
                cell_number,
                extra_key,
            } => write!(f, "cell {cell_number}: Found cell metadata {extra_key}"),
            CheckResult::ClearCount { cell_number } => {
                write!(f, "cell {cell_number}: Found cell with execution count")
            }
            CheckResult::ClearId { cell_number } => {
                write!(f, "cell {cell_number}: Found cell with Id")
            }
            CheckResult::ClearOutput { cell_number } => {
                write!(f, "cell {cell_number}: Found cell with output")
            }
        }
    }
}

pub fn check_nb(nb: &RawNotebook, settings: &Settings) -> Vec<CheckResult> {
    let (cell_keys, meta_keys) = partition_extra_keys(&settings.extra_keys);
    let mut out = vec![];
    let nb_keep_output = get_value_child(&nb.metadata, &["keep_output"])
        .and_then(Value::as_bool)
        .unwrap_or(false);
    let drop_output = settings.drop_output && !nb_keep_output;

    meta_keys
        .iter()
        .filter(|k| get_value_child(&nb.metadata, k.get_parts()).is_some())
        .for_each(|extra_key| {
            out.push(CheckResult::StripMeta {
                extra_key: extra_key.to_string(),
            });
        });

    nb.cells
        .iter()
        .enumerate()
        .filter(|(_i, c)| c.should_drop(settings.drop_empty_cells, &settings.drop_tagged_cells))
        .for_each(|(cell_number, _c)| out.push(CheckResult::DropCells { cell_number }));

    if drop_output {
        nb.cells
            .iter()
            .enumerate()
            .filter_map(|(i, c)| c.as_codecell().map(|c| (i, c)))
            .filter(|(_i, c)| {
                !c.is_clear_outputs()
                    && c.should_clear_output(drop_output, settings.strip_init_cell)
            })
            .for_each(|(cell_number, _)| out.push(CheckResult::ClearOutput { cell_number }));
    }
    if settings.drop_count {
        nb.cells
            .iter()
            .enumerate()
            .filter_map(|(i, c)| c.as_codecell().map(|c| (i, c)))
            .filter(|(_i, c)| !c.is_clear_exec_count())
            .for_each(|(cell_number, _)| out.push(CheckResult::ClearCount { cell_number }));
    }
    if settings.drop_id {
        nb.cells
            .iter()
            .enumerate()
            .filter(|(i, c)| !c.is_clear_id(*i))
            .for_each(|(cell_number, _)| out.push(CheckResult::ClearId { cell_number }));
    }
    for (cell_number, cell) in nb.cells.iter().enumerate() {
        cell_keys
            .iter()
            .filter(|k| get_value_child(cell.get_metadata(), k.get_parts()).is_some())
            .for_each(|k| {
                out.push(CheckResult::CellStripMeta {
                    cell_number,
                    extra_key: k.to_string(),
                });
            });
    }

    out
}