ahda 0.1.0

Pseudoalignment compression and conversion between formats.
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
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207

// ahda: Pseudoalignment compression and conversion between formats.
//
// Copyright 2025 Tommi Mäklin [tommi@maklin.fi].
//
// Copyrights in this project are retained by contributors. No copyright assignment
// is required to contribute to this project.
//
// Except as otherwise noted (below and/or in individual files), this
// project is licensed under the Apache License, Version 2.0
// <LICENSE-APACHE> or <http://www.apache.org/licenses/LICENSE-2.0> or
// the MIT license, <LICENSE-MIT> or <http://opensource.org/licenses/MIT>,
// at your option.
//
use std::path::PathBuf;

use clap::{Parser, Subcommand};

#[derive(Parser)]
#[command(version)]
#[command(propagate_version = true)]
pub struct Cli {
    #[command(subcommand)]
    pub command: Option<Commands>,
}

#[derive(Subcommand)]
pub enum Commands {
    // Encode pseudoalignment data in .ahda format
    #[command(name = "encode", about = "Compress plain text data")]
    Encode {
        // Input fasta or fastq sequence file(s)
        #[arg(group = "input", required = false, help = "Input file")]
        input_file: Option<PathBuf>,

        // FastX file used to generate the alignment
        #[arg(short = 'q', long = "query", help_heading = "Inputs", help = "Query .fastX file")]
        query_file: Option<PathBuf>,

        // File listing target sequence names in the order they appear in the index
        #[arg(short = 't', long = "targets", help_heading = "Inputs", help = "File listing target sequence names")]
        target_list: Option<PathBuf>,

        // Sample name
        #[arg(short = 'n', long = "name", help_heading = "Inputs", help = "Sample name (default: .fastX file path)")]
        sample_name: Option<String>,

        // Override input format detection
        #[arg(short = 'F', long = "format", help_heading = "Inputs", help = "Force input format for plain text parser")]
        input_format: Option<ahda::Format>,

        // Write to stdout
        #[arg(short = 'c', long = "stdout", default_value_t = false, help = "Write to stdout, keep original file")]
        stdout: bool,

        // Overwrite output file
        #[arg(short = 'f', long = "force", default_value_t = false, help = "Force overwriting")]
        force: bool,

        // Overwrite query names
        #[arg(long = "rename", default_value_t = false, help = "Overwrite query names with `sample_name`.`query_id`")]
        rename: bool,

        // Keep original file
        #[arg(short = 'k', long = "keep", default_value_t = false, help = "Don't delete input file after finishing")]
        keep: bool,

        // Verbosity
        #[arg(short = 'v', long = "verbose", default_value_t = false, help = "Print extra information")]
        verbose: bool,
    },

    // Decode .ahda format
    #[command(name = "decode", about = "Decompress binary data")]
    Decode {
        // Input file
        #[arg(group = "input", required = false, help = "Input file(s)")]
        input_file: Option<PathBuf>,

        // Output format, defaults to Themisto
        #[arg(short = 'F', long = "format", required = false, help = "Output plain text format")]
        format: Option<ahda::Format>,

        // Write to stdout
        #[arg(short = 'c', long = "stdout", default_value_t = false, help = "Write to stdout, keep original file")]
        stdout: bool,

        // Overwrite output file
        #[arg(short = 'f', long = "force", default_value_t = false, help = "Force overwriting")]
        force: bool,

        // Keep original file
        #[arg(short = 'k', long = "keep", default_value_t = false, help = "Don't delete input file after finishing")]
        keep: bool,

        // Verbosity
        #[arg(short = 'v', long = "verbose", default_value_t = false, help = "Print extra information")]
        verbose: bool,
    },

    // Convert plaintext to another plaintext format
    #[command(name = "convert", about = "Convert between plain text formats")]
    Convert {
        // Input fasta or fastq sequence file(s)
        #[arg(group = "input", required = false, help = "Input file")]
        input_file: Option<PathBuf>,

        // FastX file used to generate the alignment
        #[arg(short = 'q', long = "query", help_heading = "Inputs", help = "Query .fastX file")]
        query_file: Option<PathBuf>,

        // File listing target sequence names in the order they appear in the index
        #[arg(short = 't', long = "targets", help_heading = "Inputs", help = "File listing target sequence names")]
        target_list: Option<PathBuf>,

        // Output file name
        #[arg(short = 'o', long = "output", help_heading = "Outputs", help = "Output to file, keep original file")]
        output_file: Option<PathBuf>,

        // Output format, defaults to Themisto
        #[arg(short = 'F', long = "format", required = false, help_heading = "Outputs", help = "Output plain text format")]
        format: Option<ahda::Format>,

        // Sample name
        #[arg(short = 'n', long = "name", help_heading = "Inputs", help = "Sample name (default: .fastX file path)")]
        sample_name: Option<String>,

        // Write to stdout
        #[arg(short = 'c', long = "stdout", default_value_t = false, help = "Write to stdout, keep original file")]
        stdout: bool,

        // Overwrite output file
        #[arg(short = 'f', long = "force", default_value_t = false, help = "Force overwriting")]
        force: bool,

        // Keep original file
        #[arg(short = 'k', long = "keep", default_value_t = false, help = "Don't delete input file after finishing")]
        keep: bool,

        // Verbosity
        #[arg(short = 'v', long = "verbose", default_value_t = false, help = "Print extra information")]
        verbose: bool,
    },

    // Concatenate encoded data
    #[command(name = "cat", about = "Concatenate binary data")]
    Cat {
        // Input files
        #[arg(group = "input", required = true, help = "Input file(s)")]
        input_files: Vec<PathBuf>,

        // Output file name
        #[arg(short = 'o', long = "output", help_heading = "Outputs", help = "Output to file")]
        output_file: Option<PathBuf>,

        // Write to stdout
        #[arg(short = 'c', long = "stdout", default_value_t = false, help = "Write to stdout, keep original file")]
        stdout: bool,

        // Overwrite output file
        #[arg(short = 'f', long = "force", default_value_t = false, help = "Force overwriting")]
        force: bool,

        // Verbosity
        #[arg(short = 'v', long = "verbose", default_value_t = false, help = "Print extra information")]
        verbose: bool,
    },

    // Set operations on .ahda files
    #[command(name = "set", about = "Set operations on binary data")]
    Set {
        // Input files
        #[arg(group = "input", required = true, help = "Input file(s)")]
        input_files: Vec<PathBuf>,

        // Output file name
        #[arg(short = 'o', long = "output", help_heading = "Outputs", help = "Output to file")]
        output_file: Option<PathBuf>,

        // Merge operation
        #[arg(short = 'm', long = "mode", default_value = "union", help = "Merge operation")]
        operation: Option<ahda::MergeOp>,

        // Write to stdout
        #[arg(short = 'c', long = "stdout", default_value_t = false, help = "Write to stdout, keep original file")]
        stdout: bool,

        // Overwrite output file
        #[arg(short = 'f', long = "force", default_value_t = false, help = "Force overwriting")]
        force: bool,

        // Overwrite query names
        #[arg(long = "rename", default_value_t = false, help = "Overwrite query names with `sample_name`.`query_id`")]
        rename: bool,

        // Remove query names from block flags
        #[arg(long = "strip-names", default_value_t = false, help = "Strip query names from block flags.")]
        strip_names: bool,

        // Sample name
        #[arg(short = 'n', long = "name", help = "Overwrite sample name (default: clone from first input)")]
        sample_name: Option<String>,

        // Verbosity
        #[arg(short = 'v', long = "verbose", default_value_t = false, help = "Print extra information")]
        verbose: bool,
    },
}