rowboat 0.1.0

A package for working with row/column/cell structured data AKA dataframe.
Documentation 
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

use crate::dataframe::*;
use crate::format::*;
use crate::iterrows;
use crate::iterrows::*;
use crate::util::*;
use std::collections::HashMap;
use std::collections::HashSet;

#[derive(Debug, PartialEq)]
pub struct DataSlice<'a> {
    title: &'a str,
    columns: Vec<ColSlice<'a>>,
}

impl<'a> DataSlice<'a> {
    pub fn new(title: &'a str, columns: Vec<ColSlice<'a>>) -> Self {
        Self { title, columns }
    }
    pub fn print(&self) {
        TableFormatter::new().print(self);
    }
    pub fn title(&self) -> &'a str {
        self.title
    }

    pub fn length(&self) -> usize {
        if self.columns.len() == 0 {
            return 0;
        }
        self.columns[0].values().len()
    }
    pub fn col_names(&self) -> Vec<&str> {
        self.columns().iter().map(|col| col.name()).collect()
    }
    pub fn columns(&self) -> &Vec<ColSlice<'a>> {
        &self.columns
    }
    pub fn slice(&self, start: usize, stop: usize) -> Result<DataSlice, Error> {
        if start >= stop || stop > self.length() {
            return Err(Error::new("Invalid slice params".to_string()));
        }
        Ok(DataSlice {
            title: &self.title,
            columns: self
                .columns
                .iter()
                .map(|col| ColSlice::new(&col.name(), &col.values()[start..stop], &col.typed()))
                .collect(),
        })
    }
    pub fn col_slice(&self, cols: HashSet<&str>) -> Result<DataSlice, Error> {
        Ok(DataSlice {
            title: &self.title,
            columns: self
                .columns
                .iter()
                .filter(|col| cols.contains(col.name()))
                .map(|col| ColSlice::new(&col.name(), &col.values(), &col.typed()))
                .collect(),
        })
    }
    pub fn type_map(&self) -> HashMap<String, ()> {
        self.columns
            .iter()
            .map(|col| (format!("{}__{}", col.name(), col.typed().type_string()), ()))
            .collect()
    }
    pub fn match_count(&self, with: &Self) -> usize {
        let self_map = self.type_map();
        let with_map = with.type_map();
        self_map
            .iter()
            .filter(|(k, _)| match with_map.get(k.as_str()) {
                Some(_) => true,
                _ => false,
            })
            .collect::<HashMap<&String, &()>>()
            .len()
    }

    pub fn iter(self) -> Iterrows<'a> {
        iterrows::Iterrows::new(self)
    }

    pub fn to_sql(&self, table_name: &str) -> (String, Vec<String>) {
        let cols = self
            .col_names()
            .iter()
            .map(|name| format!("`{name}`"))
            .collect::<Vec<String>>()
            .join(", ");
        let mut args = vec![];
        let rows = (0..self.length())
            .map(|i| {
                let vals = self
                    .columns
                    .iter()
                    .map(|col| match col.values()[i] {
                        Cell::Str(_) => {
                            args.push(col.values()[i].as_string());
                            "?".to_string()
                        }
                        _ => col.values()[i].to_sql(),
                    })
                    .collect::<Vec<String>>()
                    .join(", ");
                format!("({vals})")
            })
            .collect::<Vec<String>>()
            .join(",\n\t");
        (
            format!("INSERT INTO `{table_name}` ({cols})\nVALUES\n\t{rows};"),
            args,
        )
    }
}

impl<'a> From<&'a Dataframe> for DataSlice<'a> {
    fn from(df: &'a Dataframe) -> Self {
        DataSlice {
            title: &df.title(),
            columns: df.columns().iter().map(|col| col.into()).collect(),
        }
    }
}