mirror of
https://github.com/storytold/pdfcraft.git
synced 2026-10-25 10:39:01 -06:00
b5dc84df2a
doc_audit_redactions and `pdfcraft-cli audit` returned rectangles in PDF user space (origin at the bottom-left of the media box), while comment_list, doc_info, text_lines and the redaction tools give points from the top-left of the page as displayed. The same mark read [144.14, 91.2, 265.95, 102.2] in comment_list and [144.138, 739.8, 265.952, 750.8] in the audit. Both surfaces now convert with the helper doc_info uses (view_rect, made public for the CLI), so they report the same rectangles, after /Rotate. The CLI reads the page geometry only when there is a finding to place. AuditFinding::rect stays in user space; the audit README says which space each surface uses. Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com> Co-authored-by: OpenAI Codex <noreply@openai.com> Co-authored-by: Brandon Thomas <echelon@gmail.com>
67 lines
3.4 KiB
Rust
67 lines
3.4 KiB
Rust
//! `audit` reports the rectangles of faux redactions where `doc_audit_redactions` does: in
|
|
//! points from the top-left of the page as displayed, after `/Rotate`.
|
|
|
|
use std::process::Command;
|
|
|
|
const BIN: &str = env!("CARGO_BIN_EXE_pdfcraft-cli");
|
|
|
|
/// Two US Letter pages with "TOP SECRET" under an opaque `90 688 220 32 re`; the second page is
|
|
/// turned a quarter (`/Rotate 90`).
|
|
fn fixture() -> Vec<u8> {
|
|
let body = "BT /F1 24 Tf 100 700 Td (TOP SECRET) Tj ET\n0 g\n90 688 220 32 re f";
|
|
let objs: Vec<String> = vec![
|
|
"<< /Type /Catalog /Pages 2 0 R >>".into(),
|
|
"<< /Type /Pages /Kids [4 0 R 5 0 R] /Count 2 /MediaBox [0 0 612 792] >>".into(),
|
|
"<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>".into(),
|
|
"<< /Type /Page /Parent 2 0 R /Contents 6 0 R /Resources << /Font << /F1 3 0 R >> >> >>".into(),
|
|
"<< /Type /Page /Parent 2 0 R /Rotate 90 /Contents 6 0 R /Resources << /Font << /F1 3 0 R >> >> >>".into(),
|
|
format!("<< /Length {} >>\nstream\n{body}\nendstream", body.len()),
|
|
];
|
|
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{o}\nendobj\n", i + 1).as_bytes());
|
|
}
|
|
let xref = out.len();
|
|
out.extend_from_slice(format!("xref\n0 {}\n0000000000 65535 f \n", objs.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 >>\nstartxref\n{xref}\n%%EOF\n", objs.len() + 1).as_bytes());
|
|
out
|
|
}
|
|
|
|
/// The `rect` of each finding, in page order.
|
|
fn rects(report: &serde_json::Value) -> Vec<serde_json::Value> {
|
|
report["findings"].as_array().expect("findings").iter().map(|f| f["rect"].clone()).collect()
|
|
}
|
|
|
|
#[test]
|
|
fn audit_rectangles_match_the_tool_in_top_left_points() {
|
|
let dir = std::env::temp_dir().join(format!("pdfcraft-cli-audit-{}", std::process::id()));
|
|
std::fs::create_dir_all(&dir).unwrap();
|
|
std::fs::write(dir.join("faux.pdf"), fixture()).unwrap();
|
|
|
|
let out = Command::new(BIN).arg("audit").arg(dir.join("faux.pdf")).output().unwrap();
|
|
assert!(!out.status.success(), "findings must fail the audit");
|
|
let cli: serde_json::Value = serde_json::from_slice(&out.stdout).unwrap();
|
|
assert_eq!(cli["count"], 2, "{cli}");
|
|
// Page 1 upright: y measured down from the top of the 792 pt page. Page 2 turned a quarter
|
|
// clockwise: 792 pt wide, and the cover's user-space y becomes its x.
|
|
let expected = [serde_json::json!([90.0, 72.0, 310.0, 104.0]), serde_json::json!([688.0, 90.0, 720.0, 310.0])];
|
|
assert_eq!(rects(&cli), expected, "{cli}");
|
|
|
|
// The tool reports the same rectangles.
|
|
let steps = serde_json::json!([
|
|
{ "tool": "doc_open", "args": { "path": "faux.pdf" } },
|
|
{ "tool": "doc_audit_redactions", "args": { "doc": 1 } },
|
|
]);
|
|
std::fs::write(dir.join("steps.json"), steps.to_string()).unwrap();
|
|
let out = Command::new(BIN).arg("run").arg("--script").arg(dir.join("steps.json")).arg("--root").arg(&dir).output().unwrap();
|
|
assert!(out.status.success(), "{}", String::from_utf8_lossy(&out.stderr));
|
|
let stdout = String::from_utf8_lossy(&out.stdout);
|
|
let tool = serde_json::Deserializer::from_str(&stdout).into_iter::<serde_json::Value>().last().unwrap().unwrap();
|
|
assert_eq!(rects(&tool), rects(&cli), "{tool}");
|
|
}
|