[go: up one dir, main page]

extractous 0.3.0

Extractous provides a fast and efficient way to extract content from all kind of file formats including PDF, Word, Excel CSV, Email etc... Internally it uses a natively compiled Apache Tika for formats are not supported natively by the Rust core
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

use criterion::{criterion_group, criterion_main, Criterion};

use extractous::Extractor;
use std::io::{BufReader, Read};

fn extract_to_stream(c: &mut Criterion) {
    let file_path = "../test_files/documents/2022_Q3_AAPL.pdf";
    let extractor = Extractor::new();

    c.bench_function("extract_to_stream", |b| {
        b.iter(|| {
            // Extract the provided file content to a stream
            let stream = extractor.extract_file(file_path).unwrap();
            // Because stream implements std::io::Read trait we can perform buffered reading
            // For example we can use it to create a BufReader
            let mut reader = BufReader::new(stream);
            let mut buffer = Vec::new();
            reader.read_to_end(&mut buffer).unwrap();
        })
    });
}

fn extract_to_string(c: &mut Criterion) {
    let file_path = "../test_files/documents/2022_Q3_AAPL.pdf";
    let extractor = Extractor::new();

    c.bench_function("extract_to_string", |b| {
        b.iter(|| {
            // Extract the provided file content to a string
            let _content = extractor.extract_file_to_string(file_path).unwrap();
        })
    });
}

criterion_group!(benches, extract_to_stream, extract_to_string);
criterion_main!(benches);