mirror of
https://github.com/storytold/pdfcraft.git
synced 2026-10-25 02:29:31 -06:00
58795e9188
* cli: info names the standard a document declares A PDF/A file was summarised with no mention of PDF/A. `info` prints two dozen fields -- tagged, xfa, javascript, layers -- and said nothing about the standard, while the app's Standards panel reads the same declaration from the catalog's XMP and shows "PDF/A-2b" (#3319). `info` gains `pdfa` (the part and conformance together, e.g. "2B"), `pdfua` and `output_intents`, from `pdfcraft_preflight::declared` -- the call the Standards panel makes, so the two agree by construction rather than by a second reading of the metadata. A document that declares nothing leaves them null and empty. Read in the CLI rather than in `pdfcraft_render::Inspect`: render is layer 3 and preflight layer 4, so the summary struct can't reach it, while an app may depend on any layer. * cli: read the declaration from the bytes already in hand `Document::open_with_password` takes an `Arc<Vec<u8>>` and `info` already holds one, so `bytes.to_vec()` copied the whole file for every call -- a file-sized allocation on a large PDF, for nothing. Clone the `Arc` instead. * info: name the declared PDF/A level as the automation tools do (PDF/A-2b) Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> --------- Co-authored-by: Brandon Thomas <echelon@gmail.com> Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
88 lines
4.0 KiB
Rust
88 lines
4.0 KiB
Rust
//! `info` reports the standard a document declares, as the Standards panel does (#3319). A file
|
|
//! carrying `pdfaid:part` and `pdfaid:conformance` in its XMP metadata was summarised with no
|
|
//! mention of PDF/A at all, though the app reads the same declaration and shows it.
|
|
|
|
use std::process::Command;
|
|
|
|
const BIN: &str = env!("CARGO_BIN_EXE_pdfcraft-cli");
|
|
|
|
/// A one-page PDF, with `metadata` as the catalog's XMP stream when given.
|
|
fn fixture(metadata: Option<&str>) -> Vec<u8> {
|
|
let content = b"0 0 0 rg 10 10 40 20 re f";
|
|
let catalog = match metadata {
|
|
Some(_) => "<< /Type /Catalog /Pages 2 0 R /Metadata 5 0 R >>".to_string(),
|
|
None => "<< /Type /Catalog /Pages 2 0 R >>".to_string(),
|
|
};
|
|
let mut objs: Vec<Vec<u8>> = vec![
|
|
catalog.into_bytes(),
|
|
b"<< /Type /Pages /Kids [3 0 R] /Count 1 >>".to_vec(),
|
|
b"<< /Type /Page /Parent 2 0 R /MediaBox [0 0 120 60] /Contents 4 0 R >>".to_vec(),
|
|
format!("<< /Length {} >> stream\n", content.len()).into_bytes(),
|
|
];
|
|
objs[3].extend_from_slice(content);
|
|
objs[3].extend_from_slice(b"\nendstream");
|
|
if let Some(xmp) = metadata {
|
|
let mut stream = format!("<< /Type /Metadata /Subtype /XML /Length {} >> stream\n", xmp.len()).into_bytes();
|
|
stream.extend_from_slice(xmp.as_bytes());
|
|
stream.extend_from_slice(b"\nendstream");
|
|
objs.push(stream);
|
|
}
|
|
let mut out = b"%PDF-1.7\n".to_vec();
|
|
let mut offsets = Vec::new();
|
|
for (i, o) in objs.iter().enumerate() {
|
|
offsets.push(out.len());
|
|
out.extend_from_slice(format!("{} 0 obj\n", i + 1).as_bytes());
|
|
out.extend_from_slice(o);
|
|
out.extend_from_slice(b"\nendobj\n");
|
|
}
|
|
let xref = out.len();
|
|
out.extend_from_slice(format!("xref\n0 {}\n0000000000 65535 f \n", objs.len() + 1).as_bytes());
|
|
for off in &offsets {
|
|
out.extend_from_slice(format!("{off:010} 00000 n \n").as_bytes());
|
|
}
|
|
out.extend_from_slice(format!("trailer\n<< /Size {} /Root 1 0 R >>\nstartxref\n{xref}\n%%EOF\n", objs.len() + 1).as_bytes());
|
|
out
|
|
}
|
|
|
|
fn xmp(part: &str, conformance: &str) -> String {
|
|
format!(
|
|
"<?xpacket begin=\"\" id=\"W5M0MpCehiHzreSzNTczkc9d\"?>\n\
|
|
<x:xmpmeta xmlns:x=\"adobe:ns:meta/\">\n <rdf:RDF xmlns:rdf=\"http://www.w3.org/1999/02/22-rdf-syntax-ns#\">\n\
|
|
<rdf:Description rdf:about=\"\" xmlns:pdfaid=\"http://www.aiim.org/pdfa/ns/id/\">\n\
|
|
<pdfaid:part>{part}</pdfaid:part>\n <pdfaid:conformance>{conformance}</pdfaid:conformance>\n\
|
|
</rdf:Description>\n </rdf:RDF>\n</x:xmpmeta>\n<?xpacket end=\"w\"?>"
|
|
)
|
|
}
|
|
|
|
fn info_of(bytes: &[u8], name: &str) -> serde_json::Value {
|
|
let dir = std::env::temp_dir().join(format!("pdfcraft-info-standards-{}-{name}", std::process::id()));
|
|
std::fs::create_dir_all(&dir).unwrap();
|
|
let path = dir.join("f.pdf");
|
|
std::fs::write(&path, bytes).unwrap();
|
|
let out = Command::new(BIN).args(["info", path.to_str().unwrap()]).output().unwrap();
|
|
assert!(out.status.success(), "{}", String::from_utf8_lossy(&out.stderr));
|
|
let json = serde_json::from_slice(&out.stdout).expect("info prints JSON");
|
|
let _ = std::fs::remove_dir_all(&dir);
|
|
json
|
|
}
|
|
|
|
#[test]
|
|
fn info_names_the_declared_pdfa_level() {
|
|
let declared = info_of(&fixture(Some(&xmp("2", "B"))), "pdfa2b");
|
|
assert_eq!(declared["pdfa"], serde_json::json!("PDF/A-2b"), "{declared}");
|
|
assert_eq!(declared["pdfua"], serde_json::Value::Null);
|
|
assert_eq!(declared["output_intents"], serde_json::json!([]));
|
|
// Lower-case conformance in the file still reads as the level's own spelling.
|
|
assert_eq!(info_of(&fixture(Some(&xmp("3", "a"))), "pdfa3a")["pdfa"], serde_json::json!("PDF/A-3a"));
|
|
}
|
|
|
|
#[test]
|
|
fn info_declares_nothing_for_a_plain_pdf() {
|
|
let plain = info_of(&fixture(None), "plain");
|
|
assert_eq!(plain["pdfa"], serde_json::Value::Null, "{plain}");
|
|
assert_eq!(plain["pdfua"], serde_json::Value::Null);
|
|
// The rest of the summary is unaffected.
|
|
assert_eq!(plain["pages"], serde_json::json!(1));
|
|
assert_eq!(plain["pdf_version"], serde_json::json!("1.7"));
|
|
}
|