mirror of
https://github.com/storytold/pdfcraft.git
synced 2026-11-09 12:32:52 +00:00
KenM76andClaude Opus 5.5
85df8ee668
An object whose load fails reads as null (ISO 32000-2 §7.3.10) and the
file opens, but nothing said so: the repair log records only
document-level repairs, so a file with an unparseable /Info showed no
repair and no reason for its missing title.
pdfcraft-cos Document now records each object whose load fails, with
its generation and the reason, in a set shared by clones and scans like
the object cache: at most 100, keyed by number, first reason kept, cut
to 160 characters, built only for an object not yet listed. It is reset
where the caches are (authenticate, reconstruct); edited objects drop
off a document's list. Document::unreadable_objects() gives neutral
lines ("object 4 0 could not be read: ..."), the engine passes them on,
and automation doc_info adds an unreadable_objects array, kept apart
from repairs so the "has been repaired" notice and the clean-file
checks keep their meaning.
Tests: a cos unit test for listing, dedup, clones, scans and edits; a
cos test for the 100 cap and the no-readable-copy reason; an end-to-end
doc_info test on a synthetic broken file. Each fails with the fix
reverted. The core.repair-log parity entry cites them and says what is
not listed.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SqmHYx8FiWM5PcsoiErgp9
65 lines
2.8 KiB
Rust
65 lines
2.8 KiB
Rust
//! `doc_info` lists the objects of a file that could not be read: each reads as null, so the file
|
|
//! opens, but what it held is lost and nothing was repaired.
|
|
|
|
use pdfcraft_automation::{Automation, Content};
|
|
use serde_json::{Value, json};
|
|
|
|
/// A one-page PDF whose document information dictionary (object 4) is `info`.
|
|
fn with_info(info: &str) -> Vec<u8> {
|
|
let bodies = [
|
|
"<< /Type /Catalog /Pages 2 0 R >>",
|
|
"<< /Type /Pages /Kids [3 0 R] /Count 1 >>",
|
|
"<< /Type /Page /Parent 2 0 R /MediaBox [0 0 200 200] >>",
|
|
info,
|
|
];
|
|
let mut out = b"%PDF-1.7\n".to_vec();
|
|
let mut offsets = Vec::new();
|
|
for (i, body) in bodies.iter().enumerate() {
|
|
offsets.push(out.len());
|
|
out.extend_from_slice(format!("{} 0 obj\n{body}\nendobj\n", i + 1).as_bytes());
|
|
}
|
|
let xref = out.len();
|
|
out.extend_from_slice(format!("xref\n0 {}\n0000000000 65535 f \n", bodies.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 /Info 4 0 R >>\nstartxref\n{xref}\n%%EOF\n", bodies.len() + 1).as_bytes());
|
|
out
|
|
}
|
|
|
|
fn info_of(a: &mut Automation, path: &str) -> Value {
|
|
let doc = match a.call("doc_open", &json!({ "path": path })).unwrap().remove(0) {
|
|
Content::Json(v) => v["doc"].as_u64().unwrap(),
|
|
other => panic!("expected JSON: {other:?}"),
|
|
};
|
|
match a.call("doc_info", &json!({ "doc": doc })).unwrap().remove(0) {
|
|
Content::Json(v) => v,
|
|
other => panic!("expected JSON: {other:?}"),
|
|
}
|
|
}
|
|
|
|
/// An unparseable `/Info` is listed with its number and why, the rest of the file reads, and
|
|
/// nothing is reported as repaired.
|
|
#[test]
|
|
fn doc_info_lists_an_object_that_could_not_be_read() {
|
|
let dir = std::env::temp_dir().join(format!("pdfcraft-unreadable-objects-{}", std::process::id()));
|
|
let _ = std::fs::remove_dir_all(&dir);
|
|
std::fs::create_dir_all(&dir).unwrap();
|
|
std::fs::write(dir.join("broken.pdf"), with_info("<< /Title (Report) /Author ) >>")).unwrap();
|
|
std::fs::write(dir.join("sound.pdf"), with_info("<< /Title (Report) >>")).unwrap();
|
|
let mut a = Automation::new().with_root(&dir).unwrap();
|
|
|
|
let info = info_of(&mut a, "broken.pdf");
|
|
let lines = info["unreadable_objects"].as_array().unwrap();
|
|
assert_eq!(lines.len(), 1, "{info}");
|
|
let line = lines[0].as_str().unwrap();
|
|
assert!(line.starts_with("object 4 0 could not be read: syntax error"), "{line}");
|
|
assert_eq!(info["repairs"], json!([]), "nothing was repaired");
|
|
assert_eq!(info["pages"].as_array().unwrap().len(), 1, "the rest of the file reads");
|
|
|
|
let info = info_of(&mut a, "sound.pdf");
|
|
assert_eq!(info["unreadable_objects"], json!([]), "{info}");
|
|
assert_eq!(info["title"], "Report");
|
|
let _ = std::fs::remove_dir_all(dir);
|
|
}
|