mirror of
https://github.com/storytold/pdfcraft.git
synced 2026-10-27 11:37:59 -06:00
Brandon ThomasandClaude Opus 5.5
1449b71a19
Fuzzed inputs drove one check-one process to 2-6 GB (the 16 GB CI runner running two of them was killed every night). Three causes, each with a test: - lopdf (bootstrap inspector) sized PNG predictor rows from /Columns before reading data: /Columns 4294967295 allocated two 4 GiB rows. Vendored lopdf 0.45.0 refuses rows longer than the data (and uses saturating row widths); its load-time stream decoding also gets a 256 MiB limit (it had none). - hayro sized a tiling pattern's cell pixmap from /XStep x scale, bounded only by u16: a step far beyond /BBox allocated 2 GB. The vendored patch keeps the cell within 3000 px a side, lowering the resolution instead. - cos decoded cross-reference streams up to the general 1 GiB limit; they now stop at what 8,388,607 objects' rows can hold (~200 MB at most), and the section is reconstructed (logged) instead. On the nightly's seed (41) the worst captured input fell from 6.2 GB to 6 MB, and a 300 s fuzz run had no process above 300 MB (before: many at 2-5 GB). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
87 lines
2.7 KiB
Rust
87 lines
2.7 KiB
Rust
use lopdf::{Document, Object, SaveOptions, dictionary};
|
|
use std::io::Write;
|
|
|
|
fn main() {
|
|
println!("Debugging save_with_object_streams...\n");
|
|
|
|
// Create a simple document
|
|
let mut doc = Document::with_version("1.5");
|
|
|
|
// Add some simple objects that can be compressed
|
|
let obj1_id = doc.add_object(Object::Integer(42));
|
|
let obj2_id = doc.add_object(Object::String(b"Hello".to_vec(), lopdf::StringFormat::Literal));
|
|
let obj3_id = doc.add_object(dictionary! {
|
|
"Type" => "TestObject",
|
|
"Value" => 123
|
|
});
|
|
|
|
println!("Created objects:");
|
|
println!(" {} 0 R: Integer", obj1_id.0);
|
|
println!(" {} 0 R: String", obj2_id.0);
|
|
println!(" {} 0 R: Dictionary", obj3_id.0);
|
|
|
|
// Add required catalog structure
|
|
let pages_id = doc.add_object(dictionary! {
|
|
"Type" => "Pages",
|
|
"Kids" => vec![],
|
|
"Count" => 0
|
|
});
|
|
|
|
let catalog_id = doc.add_object(dictionary! {
|
|
"Type" => "Catalog",
|
|
"Pages" => pages_id
|
|
});
|
|
|
|
doc.trailer.set("Root", catalog_id);
|
|
|
|
println!("\nSaving with object streams...");
|
|
|
|
// Save with object streams
|
|
let options = SaveOptions {
|
|
use_object_streams: true,
|
|
..Default::default()
|
|
};
|
|
|
|
let mut buffer = Vec::new();
|
|
doc.save_with_options(&mut buffer, options).unwrap();
|
|
|
|
println!("Saved {} bytes", buffer.len());
|
|
|
|
// Write to file for inspection
|
|
let mut file = std::fs::File::create("debug_objstream_save.pdf").unwrap();
|
|
file.write_all(&buffer).unwrap();
|
|
|
|
// Load it back and check
|
|
println!("\nLoading back and analyzing...");
|
|
let loaded = Document::load_mem(&buffer).unwrap();
|
|
|
|
println!("Loaded {} objects", loaded.objects.len());
|
|
|
|
// Find object streams
|
|
for (id, obj) in &loaded.objects {
|
|
if let Object::Stream(stream) = obj
|
|
&& let Ok(type_obj) = stream.dict.get(b"Type")
|
|
&& let Ok(type_name) = type_obj.as_name()
|
|
&& type_name == b"ObjStm"
|
|
{
|
|
println!("\nFound object stream {} 0 R:", id.0);
|
|
println!(" Dictionary: {:?}", stream.dict);
|
|
println!(" Has Filter: {}", stream.dict.get(b"Filter").is_ok());
|
|
println!(" Content size: {} bytes", stream.content.len());
|
|
|
|
// Check if it looks compressed
|
|
let looks_compressed = stream.content.iter().take(10).any(|&b| !(32..=127).contains(&b));
|
|
println!(" Content looks compressed: {}", looks_compressed);
|
|
|
|
if !looks_compressed {
|
|
println!(
|
|
" First 50 bytes: {:?}",
|
|
&stream.content[..stream.content.len().min(50)]
|
|
);
|
|
}
|
|
}
|
|
}
|
|
|
|
println!("\nDone! Check debug_objstream_save.pdf");
|
|
}
|