tables: add detectVectorGridInRegion napi export for region-scoped vector grid detection (#70)

* feat: add vector grid region detector napi export

Expose region-scoped vector PDF grid detection so TSR callers can reuse native geometry before model fallback.

Made-with: Cursor

* fix: address vector grid review feedback

Return null for rotated vector grids until the coordinate transform has coverage and reject out-of-crop cell boxes surfaced by real-PDF smoke testing.

Made-with: Cursor

* test: add crop bbox plausibility coverage

Cover in-crop, out-of-crop, slack-boundary, and non-positive DPI behavior for vector grid cell bbox validation.

Made-with: Cursor
This commit is contained in:
Abimael Martell
2026-04-28 17:20:15 -07:00
committed by GitHub
parent d196d435d1
commit c186a036fc
4 changed files with 894 additions and 4 deletions
+54
View File
@@ -99,6 +99,13 @@ pub struct PageRegionTexts {
pub regions: Vec<RegionText>,
}
/// Vector-grid detection result compatible with `extractTablesWithStructure*`.
#[napi(object)]
pub struct VectorGridDetectionJs {
pub structure_tokens: Vec<String>,
pub cell_bboxes: Vec<Vec<f64>>,
}
// ---------------------------------------------------------------------------
// Helpers
// ---------------------------------------------------------------------------
@@ -317,6 +324,53 @@ pub fn extract_tables_in_regions(
})
}
/// Detect a vector ruled-line / rectangle grid inside one page region.
///
/// Returns TSR-compatible structure tokens plus crop-pixel cell bboxes, or
/// `null` when the region does not contain a valid vector grid.
///
/// `pageIdx` is 0-indexed. `regionPdfPtBbox` is `[x1,y1,x2,y2]` in PDF
/// points with top-left origin. `renderDpi` is the DPI of the crop image that
/// will consume the returned cell bboxes.
#[napi]
pub fn detect_vector_grid_in_region(
buffer: Buffer,
page_idx: u32,
region_pdf_pt_bbox: Vec<f64>,
render_dpi: f64,
) -> Result<Option<VectorGridDetectionJs>> {
let bytes: Vec<u8> = buffer.to_vec();
let region = if region_pdf_pt_bbox.len() == 4 {
[
region_pdf_pt_bbox[0] as f32,
region_pdf_pt_bbox[1] as f32,
region_pdf_pt_bbox[2] as f32,
region_pdf_pt_bbox[3] as f32,
]
} else {
[0.0, 0.0, 0.0, 0.0]
};
catch_panic("detect_vector_grid_in_region", move || {
let result = pdf_inspector::detect_vector_grid_in_region_mem(
&bytes,
page_idx,
region,
render_dpi as f32,
)
.map_err(|e| to_napi_err(e, "detect_vector_grid_in_region"))?;
Ok(result.map(|r| VectorGridDetectionJs {
structure_tokens: r.structure_tokens,
cell_bboxes: r
.cell_bboxes
.into_iter()
.map(|bbox| bbox.into_iter().map(|v| v as f64).collect())
.collect(),
}))
})
}
/// One cropped table region plus its raw structure-recovery output, for
/// `extractTablesWithStructure`.
///