datu 0.3.4

datu - a data file utility
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
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
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169

//! Contains shared types for the `datu` CLI and implementation.

pub mod repl;

use std::str::FromStr;

use clap::Args;

use crate::FileType;

/// Output format for schema, head, and tail commands (csv, json, json-pretty, yaml).
#[derive(Clone, Copy, Debug, Default, Eq, PartialEq)]
pub enum DisplayOutputFormat {
    #[default]
    Csv,
    Json,
    JsonPretty,
    Yaml,
}

impl TryFrom<&str> for DisplayOutputFormat {
    type Error = String;

    fn try_from(s: &str) -> Result<Self, Self::Error> {
        match s.to_lowercase().as_str() {
            "csv" => Ok(DisplayOutputFormat::Csv),
            "json" => Ok(DisplayOutputFormat::Json),
            "json-pretty" => Ok(DisplayOutputFormat::JsonPretty),
            "yaml" => Ok(DisplayOutputFormat::Yaml),
            _ => Err(format!(
                "unknown output type '{s}', expected csv, json, json-pretty, or yaml"
            )),
        }
    }
}

impl std::fmt::Display for DisplayOutputFormat {
    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
        match self {
            DisplayOutputFormat::Csv => write!(f, "csv"),
            DisplayOutputFormat::Json => write!(f, "json"),
            DisplayOutputFormat::JsonPretty => write!(f, "json-pretty"),
            DisplayOutputFormat::Yaml => write!(f, "yaml"),
        }
    }
}

impl FromStr for DisplayOutputFormat {
    type Err = String;

    fn from_str(s: &str) -> Result<Self, Self::Err> {
        Self::try_from(s)
    }
}

/// Arguments for the `datu schema` command.
#[derive(Args)]
pub struct SchemaArgs {
    /// Path to the Parquet, Avro, ORC, or CSV file
    pub input_path: String,
    #[arg(
        long,
        short = 'I',
        value_parser = clap::value_parser!(FileType),
        help = "Input file type (avro, csv, json, orc, parquet, xlsx, yaml). Overrides extension-based detection."
    )]
    pub input: Option<FileType>,
    #[arg(
        long,
        short,
        default_value_t = DisplayOutputFormat::Csv,
        value_parser = clap::value_parser!(DisplayOutputFormat),
        help = "Output format: csv, json, json-pretty, or yaml"
    )]
    pub output: DisplayOutputFormat,
    #[arg(
        long,
        default_value_t = true,
        help = "For JSON/YAML: omit keys with null/missing values. Default: true. Use --sparse=false to include default values."
    )]
    pub sparse: bool,
    #[arg(
        long,
        value_parser = clap::value_parser!(bool),
        num_args = 0..=1,
        default_missing_value = "true",
        help = "For CSV input: whether the first row is a header. Default: true when omitted. Use --input-headers=false for headerless CSV."
    )]
    pub input_headers: Option<bool>,
}

/// Arguments for the `datu count` command.
#[derive(Args)]
pub struct CountArgs {
    /// Path to the Parquet, Avro, ORC, or CSV file
    pub input_path: String,
    #[arg(
        long,
        short = 'I',
        value_parser = clap::value_parser!(FileType),
        help = "Input file type (avro, csv, json, orc, parquet, xlsx, yaml). Overrides extension-based detection."
    )]
    pub input: Option<FileType>,
    #[arg(
        long,
        value_parser = clap::value_parser!(bool),
        num_args = 0..=1,
        default_missing_value = "true",
        help = "For CSV input: whether the first row is a header. Default: true when omitted. Use --input-headers=false for headerless CSV."
    )]
    pub input_headers: Option<bool>,
}

/// Arguments for the `head`, `sample`, and `tail` commands.
#[derive(Args)]
pub struct HeadsOrTails {
    /// Path to the Parquet, Avro, ORC, or CSV file
    pub input_path: String,
    #[arg(
        long,
        short = 'I',
        value_parser = clap::value_parser!(FileType),
        help = "Input file type (avro, csv, json, orc, parquet, xlsx, yaml). Overrides extension-based detection."
    )]
    pub input: Option<FileType>,
    #[arg(
        short = 'n',
        long,
        default_value_t = 10,
        help = "Number of lines to print."
    )]
    pub number: usize,
    #[arg(
        long,
        short,
        default_value_t = DisplayOutputFormat::Csv,
        value_parser = clap::value_parser!(DisplayOutputFormat),
        help = "Output format: csv, json, json-pretty, or yaml"
    )]
    pub output: DisplayOutputFormat,
    #[arg(
        long,
        default_value_t = true,
        action = clap::ArgAction::Set,
        help = "For JSON/YAML: omit keys with null/missing values. Default: true. Use --sparse=false to include default values."
    )]
    pub sparse: bool,
    #[arg(
        long,
        help = "Columns to select. If not specified, all columns will be printed."
    )]
    pub select: Option<Vec<String>>,
    #[arg(
        long,
        value_parser = clap::value_parser!(bool),
        num_args = 0..=1,
        default_missing_value = "true",
        help = "For CSV input: whether the first row is a header. Default: true when omitted. Use --input-headers=false for headerless CSV."
    )]
    pub input_headers: Option<bool>,
    #[arg(
        long,
        value_parser = clap::value_parser!(bool),
        num_args = 0..=1,
        default_missing_value = "true",
        help = "For CSV output: whether to print column headers. Default: true when omitted. Use --output-headers=false to suppress headers."
    )]
    pub output_headers: Option<bool>,
}