mirror of
https://github.com/storytold/pdfcraft.git
synced 2026-10-24 10:23:02 +00:00
Brandon Thomas
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>
119 lines
3.4 KiB
Rust
119 lines
3.4 KiB
Rust
use lopdf::Document;
|
|
|
|
#[cfg(not(feature = "async"))]
|
|
fn main() {
|
|
// Test loading the encrypted.pdf file
|
|
println!("Loading encrypted.pdf...");
|
|
let doc = match Document::load("assets/encrypted.pdf") {
|
|
Ok(d) => d,
|
|
Err(e) => {
|
|
eprintln!("Failed to load encrypted.pdf: {:?}", e);
|
|
return;
|
|
}
|
|
};
|
|
|
|
println!("Document loaded successfully!");
|
|
println!("Is encrypted: {}", doc.is_encrypted());
|
|
|
|
// Try to get pages
|
|
let pages = doc.get_pages();
|
|
println!("Number of pages: {}", pages.len());
|
|
|
|
// Try to extract text
|
|
if !pages.is_empty() {
|
|
let page_numbers: Vec<u32> = pages.keys().cloned().collect();
|
|
match doc.extract_text(&page_numbers) {
|
|
Ok(text) => {
|
|
println!("Text extraction successful!");
|
|
println!(
|
|
"Text preview (first 200 chars): {}",
|
|
text.chars().take(200).collect::<String>()
|
|
);
|
|
}
|
|
Err(e) => {
|
|
println!("Text extraction failed: {:?}", e);
|
|
}
|
|
}
|
|
}
|
|
|
|
// Check if we can access objects
|
|
println!("\nChecking object access:");
|
|
let max_check = 10;
|
|
for i in 1..=max_check {
|
|
if doc.get_object((i, 0)).is_ok() {
|
|
println!(" Object ({}, 0) found", i);
|
|
}
|
|
}
|
|
|
|
// Check trailer
|
|
println!("\nTrailer entries:");
|
|
if let Ok(root) = doc.trailer.get(b"Root") {
|
|
println!(" Root: {:?}", root);
|
|
}
|
|
if let Ok(encrypt) = doc.trailer.get(b"Encrypt") {
|
|
println!(" Encrypt: {:?}", encrypt);
|
|
}
|
|
if let Ok(info) = doc.trailer.get(b"Info") {
|
|
println!(" Info: {:?}", info);
|
|
}
|
|
}
|
|
|
|
#[cfg(feature = "async")]
|
|
#[tokio::main]
|
|
async fn main() {
|
|
// Test loading the encrypted.pdf file
|
|
println!("Loading encrypted.pdf...");
|
|
let doc = match Document::load("assets/encrypted.pdf").await {
|
|
Ok(d) => d,
|
|
Err(e) => {
|
|
eprintln!("Failed to load encrypted.pdf: {:?}", e);
|
|
return;
|
|
}
|
|
};
|
|
|
|
println!("Document loaded successfully!");
|
|
println!("Is encrypted: {}", doc.is_encrypted());
|
|
|
|
// Try to get pages
|
|
let pages = doc.get_pages();
|
|
println!("Number of pages: {}", pages.len());
|
|
|
|
// Try to extract text
|
|
if !pages.is_empty() {
|
|
let page_numbers: Vec<u32> = pages.keys().cloned().collect();
|
|
match doc.extract_text(&page_numbers) {
|
|
Ok(text) => {
|
|
println!("Text extraction successful!");
|
|
println!(
|
|
"Text preview (first 200 chars): {}",
|
|
text.chars().take(200).collect::<String>()
|
|
);
|
|
}
|
|
Err(e) => {
|
|
println!("Text extraction failed: {:?}", e);
|
|
}
|
|
}
|
|
}
|
|
|
|
// Check if we can access objects
|
|
println!("\nChecking object access:");
|
|
let max_check = 10;
|
|
for i in 1..=max_check {
|
|
if doc.get_object((i, 0)).is_ok() {
|
|
println!(" Object ({}, 0) found", i);
|
|
}
|
|
}
|
|
|
|
// Check trailer
|
|
println!("\nTrailer entries:");
|
|
if let Ok(root) = doc.trailer.get(b"Root") {
|
|
println!(" Root: {:?}", root);
|
|
}
|
|
if let Ok(encrypt) = doc.trailer.get(b"Encrypt") {
|
|
println!(" Encrypt: {:?}", encrypt);
|
|
}
|
|
if let Ok(info) = doc.trailer.get(b"Info") {
|
|
println!(" Info: {:?}", info);
|
|
}
|
|
}
|