mirror of
https://github.com/storytold/pdfcraft.git
synced 2026-10-29 12:38:58 -06:00
aiongg
467c8556ec
Office export encoded and kept a separate copy of an image for every place a page drew it, so a short content stream repeating Do on one large image multiplied it into gigabytes before the writers' limits applied. Each image object is now encoded once and its bytes shared (pdfcraft_export::Image holds an Arc<[u8]>), distinct pictures share a 512 MiB budget whose overflow lists the page as truncated, and RTF, which leaves pictures out, prepares none.
44 lines
1.9 KiB
Rust
44 lines
1.9 KiB
Rust
//! Office export of pages that draw one image many times.
|
|
|
|
use std::sync::Arc;
|
|
|
|
use pdfcraft_engine::Session;
|
|
|
|
fn pdf(objects: &[String]) -> Vec<u8> {
|
|
let mut out = b"%PDF-1.7\n".to_vec();
|
|
let mut offsets = Vec::new();
|
|
for (i, o) in objects.iter().enumerate() {
|
|
offsets.push(out.len());
|
|
out.extend_from_slice(format!("{} 0 obj\n{o}\nendobj\n", i + 1).as_bytes());
|
|
}
|
|
let xref = out.len();
|
|
out.extend_from_slice(format!("xref\n0 {}\n0000000000 65535 f \n", objects.len() + 1).as_bytes());
|
|
for o in offsets {
|
|
out.extend_from_slice(format!("{o:010} 00000 n \n").as_bytes());
|
|
}
|
|
out.extend_from_slice(format!("trailer\n<< /Size {} /Root 1 0 R >>\nstartxref\n{xref}\n%%EOF\n", objects.len() + 1).as_bytes());
|
|
out
|
|
}
|
|
|
|
/// One image drawn many times is prepared once: every placement shares its encoded bytes.
|
|
#[test]
|
|
fn an_image_drawn_many_times_is_encoded_once() {
|
|
let placements = 500;
|
|
let content = "q 10 0 0 10 0 0 cm /Im Do Q\n".repeat(placements);
|
|
let bytes = pdf(&[
|
|
"<< /Type /Catalog /Pages 2 0 R >>".into(),
|
|
"<< /Type /Pages /Kids [3 0 R] /Count 1 >>".into(),
|
|
"<< /Type /Page /Parent 2 0 R /MediaBox [0 0 200 200] /Contents 4 0 R /Resources << /XObject << /Im 5 0 R >> >> >>".into(),
|
|
format!("<< /Length {} >>\nstream\n{content}endstream", content.len()),
|
|
"<< /Type /XObject /Subtype /Image /Width 2 /Height 2 /ColorSpace /DeviceGray /BitsPerComponent 8 /Length 4 >>\nstream\n\u{0}\u{40}\u{80}\u{ff}\nendstream".into(),
|
|
]);
|
|
let mut s = Session::new();
|
|
let id = s.open("many.pdf", None, Arc::new(bytes), None).unwrap();
|
|
let pages = s.get(id).unwrap().export_pages();
|
|
let images = &pages[0].images;
|
|
assert_eq!(images.len(), placements);
|
|
let first = images[0].bytes.as_ptr();
|
|
assert!(!images[0].bytes.is_empty());
|
|
assert!(images.iter().all(|im| im.bytes.as_ptr() == first), "each placement holds its own copy of the image");
|
|
}
|