Merge main: test refreshes, nix workflow and the redaction audit fix

.github/workflows/nix.yml

@@ -0,0 +1,33 @@
+# Evaluates the Nix flake (no build, about a minute): `nix build` / `nix develop` stop at evaluation
+# when Cargo.lock gains something nix/package.nix can't vendor, and nothing else would notice.
+name: Nix
+
+on:
+  push:
+    branches: [main]
+    paths: ["flake.nix", "flake.lock", "nix/**", "Cargo.lock", ".github/workflows/nix.yml"]
+  pull_request:
+    paths: ["flake.nix", "flake.lock", "nix/**", "Cargo.lock", ".github/workflows/nix.yml"]
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+concurrency:
+  group: nix-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  eval:
+    runs-on: ubuntu-latest
+    timeout-minutes: 15
+    steps:
+      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+      - uses: cachix/install-nix-action@13d8dd58da0234aa297dedd986986ccb8e7f3e24 # v31.11.1
+      - name: nix flake check --no-build
+        run: |
+          if [ -f flake.nix ]; then
+            nix flake check --no-build --all-systems
+          else
+            echo "No flake.nix present in this repository; skipping check."
+          fi

crates/audit/README.md

@@ -16,9 +16,9 @@ It reports two kinds of finding:
 A properly applied redaction removes the text, so it never flags. Page backgrounds, table
 shading and highlights don't either: they're painted before the text, or light against it.
 
-A rectangle covers a text line when it hides at least 40% of the area of the words the line
-draws, or at least 40% of the line's box together with a positive-area intersection with one
-of its words. The gap an applied redaction leaves (a `TJ` adjustment where the text was) is in the line's box but
+A rectangle covers a text line when it hides at least half of one of the line's words, at
+least 40% of the area of the words the line draws, or at least 40% of the line's box together
+with a positive-area intersection with one of its words. The gap an applied redaction leaves (a `TJ` adjustment where the text was) is in the line's box but
 holds no word, so a redaction box over it alone does not count.
 
 Limits, by design and documented rather than hidden:
@@ -29,8 +29,8 @@ Limits, by design and documented rather than hidden:
 - covers inside form XObjects are found, but only text drawn directly in the page content is
   checked under them;
 - annotation rectangles are compared in unrotated user space, so `/Rotate` pages may misalign;
-- a cover that hides less than 40% of a line's box and less than 40% of its words (a short
-  value in the middle of a long line) is not flagged.
+- a cover that hides less than half of every word it touches, less than 40% of a line's box and
+  less than 40% of its words (a sliver of a long value) is not flagged.
 
 It fails closed: an undecodable content stream, malformed `/Annots`, form XObjects nested deeper
 than 32 or in a cycle, or a walk past the operator bound is an error, never "no findings".

crates/audit/src/lib.rs

@@ -87,6 +87,9 @@ pub enum AuditError {
 /// Fraction of a text line's ink (the area of its words), or of its box, that must lie under a
 /// cover to count as hidden (see [`covers`]).
 const COVER_FRACTION: f64 = 0.4;
+/// Fraction of one word's area that must lie under a cover to count as hidden on its own, however
+/// long the line around it (see [`covers`]).
+const WORD_FRACTION: f64 = 0.5;
 /// WCAG contrast ratio below which the text is unreadable against the cover.
 const COVER_CONTRAST: f64 = 3.0;
 
@@ -138,7 +141,10 @@ fn is_cover(rect: &cover::FilledRect, line: &TextLine) -> bool {
     rect.pos > line.paint_pos() && covers(&rect.rect, line) && contrast(line.color, rect.rgb) < COVER_CONTRAST
 }
 
-/// Does `cover` hide a substantial part of what `line` draws? Two ways, either is enough:
+/// Does `cover` hide a substantial part of what `line` draws? Three ways, any is enough:
+///
+/// - Half of one word lies under the cover. A box over one number in a long line hides a few
+///   percent of the line, and the number all the same (#2662).
 ///
 /// - 40% of the area of the line's words (its `ink`) lies under the cover. Measured on the words,
 ///   not the box: an applied redaction leaves a gap that draws nothing (a `TJ` adjustment where
@@ -155,6 +161,9 @@ fn covers(cover: &[f64; 4], line: &TextLine) -> bool {
         let total: f64 = boxes.iter().map(area).sum();
         if total > 0.0 { boxes.iter().map(hidden).sum::<f64>() / total } else { 0.0 }
     };
+    if line.ink.iter().any(|w| area(w) > 0.0 && hidden(w) / area(w) >= WORD_FRACTION) {
+        return true;
+    }
     let inked = fraction(&line.ink) >= COVER_FRACTION;
     let boxed = fraction(std::slice::from_ref(&line.rect)) >= COVER_FRACTION;
     let word_intersects = || line.ink.iter().any(|w| hidden(w) > 0.0);

crates/audit/src/tests.rs

@@ -175,6 +175,47 @@ fn unapplied_redact_mark_is_found() {
     assert!(findings[0].covered_text.contains("DO NOT SHARE"));
 }
 
+/// #2662: a box over one number of a long line hides a few percent of the line, and all of the
+/// number. Found as a cover, and as an unapplied mark over the same word.
+#[test]
+fn a_cover_over_one_word_of_a_long_line_is_found() {
+    // Helvetica 11: "The contract value is " ends near x 132, "98765" spans about 132-163.
+    let line = b"BT /F1 11 Tf 30 100 Td (The contract value is 98765 and the rest of this long line continues here.) Tj ET
+";
+    let mut content = line.to_vec();
+    content.extend_from_slice(
+        b"0 g
+131 96 33 14 re f
+",
+    );
+    let findings = audit_redactions(&open(one_page(&content, ""))).expect("audit must run");
+    assert_eq!(findings.len(), 1, "{findings:?}");
+    assert_eq!(findings[0].kind, FindingKind::CoveredText);
+    assert!(findings[0].covered_text.contains("98765"), "{findings:?}");
+
+    let mut b = Builder::new();
+    b.add("<< /Type /Catalog /Pages 2 0 R >>");
+    b.add("<< /Type /Pages /Kids [3 0 R] /Count 1 >>");
+    b.add("<< /Type /Page /Parent 2 0 R /MediaBox [0 0 612 792] /Contents 4 0 R /Resources << /Font << /F1 5 0 R >> >> /Annots [6 0 R] >>");
+    b.add_stream(line);
+    b.add(FONT);
+    b.add("<< /Type /Annot /Subtype /Redact /Rect [131 96 164 110] >>");
+    let findings = audit_redactions(&open(b.build())).expect("audit must run");
+    assert_eq!(findings.len(), 1, "{findings:?}");
+    assert_eq!(findings[0].kind, FindingKind::UnappliedMark);
+}
+
+/// A box that only grazes the words beside it (less than half of each) is not a cover.
+#[test]
+fn a_box_grazing_a_word_is_not_flagged() {
+    let content = b"BT /F1 11 Tf 30 100 Td (The contract value is 98765 and the rest of this long line continues here.) Tj ET
+0 g
+131 96 6 14 re f
+";
+    let findings = audit_redactions(&open(one_page(content, ""))).expect("audit must run");
+    assert!(findings.is_empty(), "{findings:?}");
+}
+
 #[test]
 fn background_before_text_is_not_flagged() {
     // An opaque dark rectangle painted *before* the text is a background, not a cover.
@@ -303,15 +344,17 @@ fn partial_value_is_found(rotated: bool) {
 /// Keep the historic detections with several covers, lines and text-spacing states.
 #[test]
 fn faux_redactions_with_multiple_covers_lines_and_spacing_are_found() {
-    let cases: [&[u8]; 4] = [
-        b"BT /F1 11 Tf 72 742 Td (Account: 123456789) Tj ET\n0 g\n72 738 65 16 re f\n140 738 40 16 re f\n",
-        b"BT /F1 11 Tf 72 742 Td (Account: 123456789) Tj 0 -15 Td (Account: 987654321) Tj ET\n0 g\n115 723 100 30 re f\n",
-        b"BT /F1 11 Tf 8 Tc 72 742 Td (Account: 1234) Tj ET\n0 g\n145 738 90 16 re f\n",
-        b"BT /F1 11 Tf 250 Tz 72 742 Td (Account: 1234) Tj ET\n0 g\n100 738 160 16 re f\n",
+    // The second box of the first case hides most of the number (less than 40% of the line): a
+    // finding of its own since covers are also measured per word (#2662).
+    let cases: [(&[u8], usize); 4] = [
+        (b"BT /F1 11 Tf 72 742 Td (Account: 123456789) Tj ET\n0 g\n72 738 65 16 re f\n140 738 40 16 re f\n", 2),
+        (b"BT /F1 11 Tf 72 742 Td (Account: 123456789) Tj 0 -15 Td (Account: 987654321) Tj ET\n0 g\n115 723 100 30 re f\n", 1),
+        (b"BT /F1 11 Tf 8 Tc 72 742 Td (Account: 1234) Tj ET\n0 g\n145 738 90 16 re f\n", 1),
+        (b"BT /F1 11 Tf 250 Tz 72 742 Td (Account: 1234) Tj ET\n0 g\n100 738 160 16 re f\n", 1),
     ];
-    for content in cases {
+    for (content, expected) in cases {
         let findings = audit_redactions(&open(one_page(content, ""))).expect("audit must run");
-        assert_eq!(findings.len(), 1, "{}: {findings:?}", String::from_utf8_lossy(content));
+        assert_eq!(findings.len(), expected, "{}: {findings:?}", String::from_utf8_lossy(content));
     }
 }
 

crates/automation/tests/batch.rs

@@ -11,7 +11,17 @@ fn result(auto: &mut Automation, args: Value) -> Value {
 
 // Fresh fixtures include the current timestamp; retain their bytes for output comparisons.
 fn pdf() -> Vec<u8> {
-    Session::new().create_from_text("Original", "Original text").unwrap().as_ref().clone()
+    // Reuse one synthetic document so byte comparisons cannot straddle the
+    // writer's modification-time clock. Each caller gets an independent buffer.
+    static PDF: std::sync::OnceLock<Vec<u8>> = std::sync::OnceLock::new();
+    PDF.get_or_init(|| Session::new().create_from_text("Original", "Original text").unwrap().as_ref().clone()).clone()
+}
+
+#[test]
+fn pdf_fixture_remains_identical_across_metadata_clock_tick() {
+    let before = pdf();
+    std::thread::sleep(std::time::Duration::from_millis(1100));
+    assert_eq!(before, pdf());
 }
 
 #[test]

crates/print/src/tests.rs

@@ -506,7 +506,8 @@ mod cups_options {
         let Some(record) = std::env::var_os(RECORD) else { return };
         let args: Vec<String> = std::env::args().skip_while(|a| a != "--").skip(1).collect();
         std::fs::write(std::path::Path::new(&record).join("args"), args.join("\n")).unwrap();
-        println!("{}", std::env::var(ANSWER).unwrap());
+        // Serial libtest prints its test label without a newline before this helper's stdout.
+        println!("\n{}", std::env::var(ANSWER).unwrap());
     }
 
     fn command(record: &std::path::Path, answer: &str) -> std::process::Command {

crates/ui-egui/src/open_worker_tests.rs

@@ -608,3 +608,65 @@ fn tool_picker_keeps_picked_recipient_when_other_open_is_ready() {
         }
     }
 }
+
+#[test]
+#[allow(clippy::expect_used, clippy::unwrap_used)]
+fn inline_tool_open_keeps_its_command_for_pdf_conversion_and_password_retry() {
+    for (name, bytes, encrypted) in
+        [("plain.pdf", fixture(1), false), ("converted.txt", b"Text to export".to_vec(), false), ("locked.pdf", encrypted_tool_fixture(), true)]
+    {
+        let path = std::env::temp_dir().join(format!("pdfcraft-inline-tool-{}-{name}", std::process::id()));
+        std::fs::write(&path, bytes).expect("write selected file");
+        let mut app = PdfCraftApp::new();
+        app.set_option("language", "en").expect("language preference");
+        assert!(app.ctx.is_none(), "this exercises the no-context inline path");
+        app.open_path_then(&path.to_string_lossy(), Some("export.text"));
+        if encrypted {
+            assert!(app.dialog.is_none());
+            assert_eq!(app.password_prompt.as_ref().expect("password prompt").then, Some("export.text"));
+            app.submit_password(Some("wrong".into()));
+            assert!(app.password_prompt.as_ref().expect("wrong-password prompt").error.is_some());
+            assert!(app.dialog.is_none());
+            app.submit_password(Some("tool-password".into()));
+        }
+        assert_eq!(app.views.len(), 1);
+        assert_eq!(app.active, Some(0));
+        assert!(matches!(app.dialog, Some(crate::Dialog::Export(_))), "the inline {name} retains its export command");
+        let _ = std::fs::remove_file(path);
+    }
+}
+
+#[test]
+#[allow(clippy::expect_used, clippy::panic, clippy::unwrap_used)]
+fn startup_files_wait_for_absolute_link_consent_and_preparation() {
+    let (mut h, _) = harness();
+    let source = h.state().views[0].id;
+    let path = std::env::temp_dir().join(format!("pdfcraft-open-consented-startup-{}.pdf", std::process::id()));
+    std::fs::write(&path, fixture(2)).expect("write linked PDF");
+    h.state_mut().open_remote_link(source, path.to_string_lossy().into_owned(), pdfcraft_render::RemoteDestination::Default);
+    h.state().startup_inbox.lock().expect("startup queue").push(("startup.pdf".into(), fixture(1)));
+    h.step();
+    assert!(h.state().pending_remote_link.is_some());
+    assert_eq!(h.state().startup_inbox.lock().expect("startup queue").len(), 1);
+    assert_eq!(h.state().views.len(), 1, "startup cannot replace the consent interaction");
+
+    let (gate, started, release, finished) = open_worker::prepare_gate();
+    h.state_mut().open_prepare_gate = Some(gate);
+    h.state_mut().resolve_pending_remote_link(true);
+    started.recv_timeout(Duration::from_secs(5)).expect("worker reached prepare barrier");
+    h.step();
+    let queued = h.state().startup_inbox.lock().expect("startup queue").len();
+    let visible = h.state().views.len();
+    // Always release before asserting: a failure must not strand the worker at the barrier.
+    release.send(()).expect("release prepare barrier");
+    finished.recv_timeout(Duration::from_secs(5)).expect("worker finished preparation");
+    assert_eq!(queued, 1, "startup bytes wait while the approved linked PDF prepares");
+    assert_eq!(visible, 1);
+    h.step();
+    let app = h.state();
+    assert_eq!(app.views.len(), 3);
+    assert_eq!(app.session.get(app.views[1].id).expect("linked document").path.as_deref(), path.to_str());
+    assert_eq!(app.session.get(app.views[2].id).expect("startup document").name, "startup.pdf");
+    assert_eq!(app.active, Some(1), "the user's approved navigation keeps focus");
+    let _ = std::fs::remove_file(path);
+}

parity/acrobat-features.toml

@@ -5812,8 +5812,8 @@ milestone = "M8"
 status = "partial"
 commands = []
 tools = ["doc_audit_redactions"]
-evidence = ["crates/audit/src/tests.rs::faux_redaction_is_found", "crates/audit/src/tests.rs::background_before_text_is_not_flagged", "crates/audit/src/tests.rs::light_shading_after_text_is_not_flagged", "crates/audit/src/tests.rs::graphics_state_carries_across_streams", "crates/audit/src/tests.rs::audit_fails_closed_on_undecodable_stream", "crates/audit/src/tests.rs::unapplied_redact_mark_is_found", "crates/audit/src/tests.rs::applied_redaction_at_the_end_of_a_line_is_not_flagged", "crates/audit/src/tests.rs::faux_redaction_at_the_end_of_a_line_is_found", "crates/audit/src/tests.rs::faux_redaction_over_a_short_value_after_a_long_label_is_found", "crates/audit/src/tests.rs::faux_redaction_over_mirrored_text_is_found", "crates/audit/src/tests.rs::faux_redaction_over_a_partial_value_after_a_long_label_is_found", "crates/audit/src/tests.rs::faux_redaction_over_a_partial_value_after_a_long_label_on_a_rotated_page_is_found", "crates/audit/src/tests.rs::faux_redactions_with_multiple_covers_lines_and_spacing_are_found", "crates/automation/tests/automation.rs::auditing_faux_redactions_through_tools", "crates/automation/tests/automation.rs::an_applied_redaction_at_the_end_of_a_line_audits_clean", "crates/audit/src/tests.rs::rectangle_drawn_as_a_path_covers_text_like_re", "crates/audit/src/tests.rs::non_rectangular_path_is_not_a_cover", "apps/pdfcraft-cli/tests/audit.rs::audit_rectangles_match_the_tool_in_top_left_points"]
-notes = "New pdfcraft-audit crate. A filled rectangle (re + fill, or a single m/l subpath whose corners form an axis-aligned rectangle, #1510; opaque) counts as a cover only when painted after the text it overlaps and dark enough to hide it (WCAG contrast < 3.0); page backgrounds, table shading and highlights are not flagged. Coverage is measured on the words a line draws, not its box, so the gap an applied redaction leaves is not counted as hidden text; a cover over 40% of the line's box still counts when it has a positive-area intersection with one word, so a short value after a long label is found. A cover over less than 40% of both a line's box and its words (a short value in the middle of a long line) is still not flagged. Graphics state carries across a page's content streams. Fails closed: undecodable content is an error, never a clean bill. Also flags /Redact annotations never applied. CLI: pdfcraft-cli audit (fails when findings exist). Tool and CLI report rectangles in points from the top-left of the displayed page, after /Rotate and rounded to 0.01 pt, like the other tools."
+evidence = ["crates/audit/src/tests.rs::faux_redaction_is_found", "crates/audit/src/tests.rs::background_before_text_is_not_flagged", "crates/audit/src/tests.rs::light_shading_after_text_is_not_flagged", "crates/audit/src/tests.rs::graphics_state_carries_across_streams", "crates/audit/src/tests.rs::audit_fails_closed_on_undecodable_stream", "crates/audit/src/tests.rs::unapplied_redact_mark_is_found", "crates/audit/src/tests.rs::applied_redaction_at_the_end_of_a_line_is_not_flagged", "crates/audit/src/tests.rs::faux_redaction_at_the_end_of_a_line_is_found", "crates/audit/src/tests.rs::faux_redaction_over_a_short_value_after_a_long_label_is_found", "crates/audit/src/tests.rs::faux_redaction_over_mirrored_text_is_found", "crates/audit/src/tests.rs::faux_redaction_over_a_partial_value_after_a_long_label_is_found", "crates/audit/src/tests.rs::faux_redaction_over_a_partial_value_after_a_long_label_on_a_rotated_page_is_found", "crates/audit/src/tests.rs::faux_redactions_with_multiple_covers_lines_and_spacing_are_found", "crates/audit/src/tests.rs::a_cover_over_one_word_of_a_long_line_is_found", "crates/audit/src/tests.rs::a_box_grazing_a_word_is_not_flagged", "crates/automation/tests/automation.rs::auditing_faux_redactions_through_tools", "crates/automation/tests/automation.rs::an_applied_redaction_at_the_end_of_a_line_audits_clean", "crates/audit/src/tests.rs::rectangle_drawn_as_a_path_covers_text_like_re", "crates/audit/src/tests.rs::non_rectangular_path_is_not_a_cover", "apps/pdfcraft-cli/tests/audit.rs::audit_rectangles_match_the_tool_in_top_left_points"]
+notes = "New pdfcraft-audit crate. A filled rectangle (re + fill, or a single m/l subpath whose corners form an axis-aligned rectangle, #1510; opaque) counts as a cover only when painted after the text it overlaps and dark enough to hide it (WCAG contrast < 3.0); page backgrounds, table shading and highlights are not flagged. Coverage is measured on the words a line draws, not its box, so the gap an applied redaction leaves is not counted as hidden text; a cover over 40% of the line's box still counts when it has a positive-area intersection with one word, so a short value after a long label is found. A cover hiding half of any one word counts too (#2662), so a box over one number in a long line, or an unapplied mark over it, is found; a sliver under half of every word it touches and under 40% of the line is not flagged. Graphics state carries across a page's content streams. Fails closed: undecodable content is an error, never a clean bill. Also flags /Redact annotations never applied. CLI: pdfcraft-cli audit (fails when findings exist). Tool and CLI report rectangles in points from the top-left of the displayed page, after /Rotate and rounded to 0.01 pt, like the other tools."
 
 [[feature]]
 id = "protect.remove-hidden-on-close"