mirror of
https://github.com/storytold/pdfcraft.git
synced 2026-10-28 20:18:06 -06:00
NetterSilverandClaude Opus 5.5
37bf4ee986
Export > Image spent its time in the PNG, JPEG and TIFF encoders, one page after another: on a 55-page manual at 150 dpi, drawing every page took about 0.34 s and encoding it 1.1 s (PNG) to 2.0 s (JPEG). Exporter::images exports a list of pages, drawing and encoding several at once on worker threads, each with its own PageRenderer (as automation's extract_parallel does), and hands the files to a sink in page order on the calling thread. Workers draw at most one page ahead of the sink and fewer run when 1 GiB can't hold that many of the largest page. The first page or sink error stops the export with every earlier page handed over, as before. A page panic becomes that page's error, and a panicking sink stops the workers. One page, one core or wasm keeps the per-page loop. Export > Image and the doc_export_images tool use it. Files are byte-identical. One core is left for the interface (at most 8 workers). With examples/export_bench, on a Ryzen with 16 threads (shared), mean of two medians of 21 runs: PNG 150 dpi 1874 -> 340 ms (-82%) JPEG 150 dpi 2106 -> 340 ms (-84%) TIFF 150 dpi 2032 -> 375 ms (-82%) PNG 300 dpi 3804 -> 590 ms (-84%) Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
62 lines
2.6 KiB
Rust
62 lines
2.6 KiB
Rust
//! Times Export ▸ Image over every page of a PDF, for before and after comparisons.
|
|
//!
|
|
//! Usage: `export_bench FILE [DPI] [png|jpeg|tiff] [RUNS]` (defaults: 150 dpi, PNG, 7 runs). Each
|
|
//! run exports every page through [`Exporter::images`] from a fresh exporter, as Export ▸ Image
|
|
//! does, and prints its wall time; the summary gives the median and the minimum, the total size
|
|
//! and an FNV-1a hash of every file in page order. Equal hashes mean equal output. Build with
|
|
//! `--release`; timings are diagnostic, never a CI deadline.
|
|
|
|
use std::error::Error;
|
|
use std::sync::Arc;
|
|
use std::time::Instant;
|
|
|
|
use pdfcraft_engine::Session;
|
|
use pdfcraft_engine::export::{Exporter, ImageFormat};
|
|
|
|
const FNV_OFFSET: u64 = 0xcbf2_9ce4_8422_2325;
|
|
const FNV_PRIME: u64 = 0x0000_0100_0000_01b3;
|
|
|
|
fn main() -> Result<(), Box<dyn Error>> {
|
|
let mut args = std::env::args().skip(1);
|
|
let path = args.next().ok_or("usage: export_bench FILE [DPI] [png|jpeg|tiff] [RUNS]")?;
|
|
let dpi: f64 = args.next().map_or(Ok(150.0), |s| s.parse())?;
|
|
let format = match args.next().as_deref() {
|
|
None | Some("png") => ImageFormat::Png,
|
|
Some("jpeg" | "jpg") => ImageFormat::Jpeg { quality: 85 },
|
|
Some("tiff" | "tif") => ImageFormat::Tiff,
|
|
Some(other) => return Err(format!("unknown format {other:?}").into()),
|
|
};
|
|
let runs: usize = args.next().map_or(Ok(7), |s| s.parse())?;
|
|
let mut session = Session::new();
|
|
let id = session.open("bench.pdf", None, Arc::new(std::fs::read(&path)?), None)?;
|
|
let src = session.get(id).ok_or("the document did not open")?.export_source();
|
|
let pages: Vec<usize> = (0..src.pages).collect();
|
|
let mut times = Vec::new();
|
|
let mut summary = None;
|
|
for run in 0..runs {
|
|
let start = Instant::now();
|
|
let mut exporter = Exporter::from_source(src.clone());
|
|
let (mut hash, mut bytes) = (FNV_OFFSET, 0usize);
|
|
exporter.images(&pages, dpi, format, |_, file| {
|
|
bytes += file.len();
|
|
for b in file {
|
|
hash = (hash ^ u64::from(b)).wrapping_mul(FNV_PRIME);
|
|
}
|
|
Ok(())
|
|
})?;
|
|
let ms = start.elapsed().as_secs_f64() * 1000.0;
|
|
println!("run {}: {ms:.1} ms", run + 1);
|
|
times.push(ms);
|
|
summary = Some((bytes, hash));
|
|
}
|
|
times.sort_by(f64::total_cmp);
|
|
if let (Some(median), Some(min), Some((bytes, hash))) = (times.get(times.len() / 2), times.first(), summary) {
|
|
println!(
|
|
"{} pages, {} at {dpi} dpi: median {median:.1} ms, min {min:.1} ms ({runs} runs), {bytes} bytes, hash {hash:016x}",
|
|
pages.len(),
|
|
format.label()
|
|
);
|
|
}
|
|
Ok(())
|
|
}
|