Struct PdfDocument 

pub struct PdfDocument {
    pub pages: Vec<PdfPage>,
}

A parsed PDF: per-page text cells and page images.

Fields

pages: Vec<PdfPage>

Implementations

impl PdfDocument

pub fn open(bytes: &[u8], password: Option<&str>) -> Result<Self, PdfiumError>

Parse a PDF from bytes, optionally decrypting with password.

Examples found in repository

examples/extract.rs (line 6)

fn main() {
    let path = std::env::args().nth(1).expect("usage: extract <file.pdf>");
    let bytes = std::fs::read(&path).expect("read pdf");
    match fleischwolf_pdf::PdfDocument::open(&bytes, None) {
        Ok(doc) => {
            for (i, page) in doc.pages.iter().enumerate() {
                println!(
                    "--- page {} ({:.0}x{:.0}, {} cells) ---",
                    i + 1,
                    page.width,
                    page.height,
                    page.cells.len()
                );
                for c in page.cells.iter().take(8) {
                    println!(
                        "  [{:.0},{:.0},{:.0},{:.0}] {:?}",
                        c.l, c.t, c.r, c.b, c.text
                    );
                }
            }
        }
        Err(e) => eprintln!("ERROR: {e}"),
    }
}

examples/layout.rs (line 10)

fn main() {
    let path = std::env::args().nth(1).expect("usage: layout <file.pdf>");
    let bytes = std::fs::read(&path).expect("read pdf");
    let doc = PdfDocument::open(&bytes, None).expect("open pdf");
    let mut model = LayoutModel::load().expect("load layout model");
    for (i, page) in doc.pages.iter().enumerate().take(1) {
        let regions = model
            .predict(&page.image, page.width, page.height)
            .expect("predict");
        println!(
            "page {} ({:.0}x{:.0}): {} regions",
            i + 1,
            page.width,
            page.height,
            regions.len()
        );
        let mut rs = regions.clone();
        rs.sort_by(|a, b| a.t.total_cmp(&b.t));
        for r in &rs {
            println!(
                "  {:<16} {:.2}  [{:.0},{:.0},{:.0},{:.0}]",
                r.label, r.score, r.l, r.t, r.r, r.b
            );
        }
    }
}