cbz2pdf/src/formats/cbz.rs

use std::ffi::OsStr;
use std::fs::File;
use std::io::Read;
use std::path::Path;

use anyhow::Result;
use rayon::prelude::*;
use zip::ZipArchive;

use crate::model::{Document, ImagePage};

use super::FormatReader;

pub struct CbzReader;

impl FormatReader for CbzReader {
    fn read(&self, input: &Path) -> Result<Document> {
        let mut zip = ZipArchive::new(File::open(input)?)?;
        let mut files: Vec<(String, Vec<u8>)> = Vec::new();
        for i in 0..zip.len() {
            let mut file = zip.by_index(i)?;
            let mut image_data = Vec::new();
            let name = file
                .enclosed_name()
                .expect("Failed to read file name")
                .to_owned();
            if name.extension() == Some(OsStr::new("jpg")) {
                file.read_to_end(&mut image_data)?;
                files.push((
                    name.file_name()
                        .expect("Failed to read file name")
                        .to_string_lossy()
                        .to_string(),
                    image_data,
                ));
            }
        }

        let mut pages: Vec<ImagePage> = Vec::new();
        files
            .par_iter()
            .map(|(name, data)| ImagePage {
                name: name.clone(),
                image: image::load_from_memory(data).expect("Failed to decode image"),
                jpeg_dct: Some(data.clone()),
            })
            .collect_into_vec(&mut pages);

        pages.par_sort_by_key(|p| p.name.clone());

        Ok(Document::new(pages))
    }
}