From d7b4d576a1a048ea63570c7ee074d31b43479d67 Mon Sep 17 00:00:00 2001 From: jonathanwxh-cell Date: Sun, 18 Oct 2026 08:16:58 +0800 Subject: [PATCH] fix(render): emit clip-only text (7 Tr) to devices for text extraction (#3109) --- crates/render/src/text.rs | 64 ++++++++++++++++++++ vendor/hayro-interpret/src/interpret/text.rs | 10 +++ 2 files changed, 74 insertions(+) diff --git a/crates/render/src/text.rs b/crates/render/src/text.rs index b767e2831..e163b204b 100644 --- a/crates/render/src/text.rs +++ b/crates/render/src/text.rs @@ -1740,6 +1740,70 @@ mod tests { } } + /// Issue #3109: text drawn in clipping mode (`7 Tr`) sets the clip for a subsequent fill, + /// shading or image without painting the glyphs directly, and must still reach `TextDevice` + /// with the same boxes and search ranges as modes 0–6. + #[test] + fn clipping_mode_text_is_extracted_and_searchable_like_other_rendering_modes() { + let fill_through = " 0 0 1 rg 0 0 300 300 re f"; + let mut pages: Vec = + (0..=7).map(|mode| format!("q BT /F1 24 Tf {mode} Tr 72 150 Td () Tj [(Hello) -200 (World)] TJ ET{fill_through} Q")).collect(); + // Page 8: /ActualText wrapping 7 Tr clip-only text. + pages.push(format!("q /Span <> BDC BT /F1 24 Tf 7 Tr 72 150 Td (Glyphs) Tj ET EMC{fill_through} Q")); + // Page 9: 0 Tr underpainting followed by 7 Tr at the same position (outline/gradient overlay) deduplicates. + pages.push(format!("BT /F1 24 Tf 0 Tr 72 150 Td (Hello World) Tj ET q BT /F1 24 Tf 7 Tr 72 150 Td (Hello World) Tj ET{fill_through} Q")); + // Page 10: 90° turned 7 Tr text. + pages.push(format!("q BT /F1 24 Tf 7 Tr 0 1 -1 0 150 100 Tm (Hello World) Tj ET{fill_through} Q")); + // Page 11: 7 Tr without any fill-through (visually blank, still extractable). + pages.push("BT /F1 24 Tf 7 Tr 72 150 Td (Hello World) Tj ET".into()); + + let refs: Vec<&str> = pages.iter().map(String::as_str).collect(); + let pdf = marked_pages(&refs); + let control = marked_text(&pdf, 0); + assert_eq!(control.plain_text(), "Hello World"); + let control_rects = control.line_rects(0..5); + assert_eq!(control_rects.len(), 1); + for mode in 0..=7 { + let text = marked_text(&pdf, mode); + assert_eq!(text.plain_text(), "Hello World", "mode {mode} Tr"); + assert_eq!(text.find("hello"), vec![0..5], "mode {mode} Tr"); + assert_eq!(text.find_opts("Hello", true, true), vec![0..5], "mode {mode} Tr"); + assert_eq!( + text.find_with(|chars| chars.starts_with(&['H', 'e', 'l', 'l', 'o']).then_some(0..5).into_iter().collect()), + vec![0..5], + "mode {mode} Tr" + ); + assert_eq!(text.line_rects(0..5), control_rects, "mode {mode} Tr"); + assert_eq!(text.glyphs, control.glyphs, "mode {mode} Tr"); + } + let actual = marked_text(&pdf, 8); + assert_eq!(actual.plain_text(), "Hello World"); + assert_eq!(actual.find("Hello"), vec![0..1]); + + let deduped = marked_text(&pdf, 9); + assert_eq!(deduped.plain_text(), "Hello World"); + + let turned = marked_text(&pdf, 10); + assert_eq!(turned.plain_text(), "Hello World"); + assert_eq!(turned.find("World"), vec![6..11]); + + let unfilled = marked_text(&pdf, 11); + assert_eq!(unfilled.plain_text(), "Hello World"); + + // Visual check: page 7 (`7 Tr` + blue fill-through) paints blue only inside the clipped + // glyph outlines, whereas page 11 (`7 Tr` alone) paints no ink at all. + let mut renderer = crate::PageRenderer::new(std::sync::Arc::new(pdf.data().as_ref().to_vec()), crate::RenderConfig::default()); + let filled_px = renderer.render(crate::RenderRequest { page: 7, kind: crate::RequestKind::Pixels, scale: 1.0, ..Default::default() }); + assert!(filled_px.error.is_none()); + let blue_pixels = filled_px.rgba.as_chunks::<4>().0.iter().filter(|p| p[0] < 32 && p[1] < 32 && p[2] > 200).count(); + let white_pixels = filled_px.rgba.as_chunks::<4>().0.iter().filter(|p| p[..3] == [255, 255, 255]).count(); + assert!(blue_pixels > 50 && white_pixels > 80_000, "blue={blue_pixels}, white={white_pixels}"); + + let unfilled_px = renderer.render(crate::RenderRequest { page: 11, kind: crate::RequestKind::Pixels, scale: 1.0, ..Default::default() }); + assert!(unfilled_px.error.is_none()); + assert!(unfilled_px.rgba.as_chunks::<4>().0.iter().all(|p| p[..3] == [255, 255, 255])); + } + /// One page per `(encoding, content)`, in Helvetica (`/F1`). fn encoded_pages(pages: &[(lopdf::Object, &[u8])]) -> Pdf { use lopdf::{Document, Object, Stream, dictionary}; diff --git a/vendor/hayro-interpret/src/interpret/text.rs b/vendor/hayro-interpret/src/interpret/text.rs index ddec0400e..8b80b4bdb 100644 --- a/vendor/hayro-interpret/src/interpret/text.rs +++ b/vendor/hayro-interpret/src/interpret/text.rs @@ -126,6 +126,16 @@ pub(crate) fn show_glyph<'a>( } TextRenderingMode::Clip => { clip_glyph(ctx, glyph, glyph_transform); + // PdfCraft patch: still call draw_glyph for clip-only text (`7 Tr`), as mode 3 does, + // so text extraction, search and search-redaction see text that is filled through its + // clipping path without rendering devices drawing it directly. + device.draw_glyph( + glyph, + ctx.get().ctm, + glyph_transform, + &get_paint(ctx, false), + &GlyphDrawMode::Invisible, + ); } TextRenderingMode::FillAndClip => { clip_glyph(ctx, glyph, glyph_transform);