Fix TSR cell assignment for overlapping table boxes (#62)
* feat: TSR-aware table extraction (extract_tables_with_structure_mem) New public function that consumes raw structure-recovery output (HTML structure tokens + per-cell bboxes from a model like SLANet) and assembles markdown tables by pulling cell text from the native PDF — no OCR, no geometry inference. Why: the existing extract_tables_in_regions_mem infers grid geometry from text positions only and can't distinguish merged cells from multiple narrow columns. Pairing structure recovery from a layout/TSR model with native PDF text gets perfect text quality with proper row/col/span structure. - New module src/tables/structured.rs: token state machine, polygon→AABB, crop-px→page-pt, rowspan/colspan-aware cell layout, markdown emitter. Accepts both 4-element rects and 8-element 4-corner polygons. - New public extract_tables_with_structure_mem in src/lib.rs that reuses extract_page_text_items, region_overlaps_item, and the shared region text-collection helper. No existing public function modified. - napi binding extractTablesWithStructure mirroring the existing extractTablesInRegions shape (f64 in JS → f32 internally). - 14 unit tests + 5 integration tests, including a real-PDF gold-standard match against bits_pilani_feedback.pdf. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * TSR follow-ups: header-aware separator, cells API, v1.6.0 - cells_to_markdown emits the separator after the LAST row that contains is_header=true cells, falling back to "after row 0" when no header is flagged. Multi-row theads now render correctly. Three new unit tests cover: multi-row header, header not on row 0, no headers (fallback). - New public extract_tables_with_structure_cells_mem returning Vec<Vec<StructuredCell>> so callers can drive their own rendering or debug overlays without re-doing the parse + extraction. The markdown variant now wraps it. The previously-unused page_pt_bbox field is surfaced through this API. - New napi binding extractTablesWithStructureCells + StructuredCellJs. - Bump @firecrawl/pdf-inspector to 1.6.0. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix TSR cell text assignment for overlapping bboxes Made-with: Cursor * bump npm package version to 1.6.1 Made-with: Cursor --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Opus 4.7
parent
f6d5e214f1
commit
3f8fb645c9
@@ -1484,6 +1484,82 @@ fn poly(x1: f32, y1: f32, x2: f32, y2: f32) -> Vec<f32> {
|
||||
vec![x1, y1, x2, y1, x2, y2, x1, y2]
|
||||
}
|
||||
|
||||
fn synthetic_dense_table_pdf() -> Vec<u8> {
|
||||
use lopdf::content::{Content, Operation};
|
||||
use lopdf::{dictionary, Document, Object, Stream};
|
||||
|
||||
let mut doc = Document::with_version("1.5");
|
||||
let pages_id = doc.new_object_id();
|
||||
let page_id = doc.new_object_id();
|
||||
let font_id = doc.new_object_id();
|
||||
let content_id = doc.new_object_id();
|
||||
|
||||
doc.objects.insert(
|
||||
font_id,
|
||||
dictionary! {
|
||||
"Type" => "Font",
|
||||
"Subtype" => "Type1",
|
||||
"BaseFont" => "Helvetica",
|
||||
}
|
||||
.into(),
|
||||
);
|
||||
|
||||
let operations = vec![
|
||||
Operation::new("BT", vec![]),
|
||||
Operation::new("Tf", vec!["F1".into(), 10.into()]),
|
||||
Operation::new("Td", vec![20.into(), 700.into()]),
|
||||
Operation::new("Tj", vec![Object::string_literal("Branch Name")]),
|
||||
Operation::new("Td", vec![100.into(), 0.into()]),
|
||||
Operation::new("Tj", vec![Object::string_literal("Deposits")]),
|
||||
Operation::new("Td", vec![Object::Integer(-100), Object::Real(-16.8)]),
|
||||
Operation::new("Tj", vec![Object::string_literal("Oak Street")]),
|
||||
Operation::new("Td", vec![100.into(), 0.into()]),
|
||||
Operation::new("Tj", vec![Object::string_literal("100")]),
|
||||
Operation::new("Td", vec![Object::Integer(-100), Object::Real(-16.8)]),
|
||||
Operation::new("Tj", vec![Object::string_literal("Boardwalk")]),
|
||||
Operation::new("Td", vec![100.into(), 0.into()]),
|
||||
Operation::new("Tj", vec![Object::string_literal("200")]),
|
||||
Operation::new("ET", vec![]),
|
||||
];
|
||||
let content = Content { operations }.encode().unwrap();
|
||||
doc.objects
|
||||
.insert(content_id, Stream::new(dictionary! {}, content).into());
|
||||
|
||||
doc.objects.insert(
|
||||
page_id,
|
||||
dictionary! {
|
||||
"Type" => "Page",
|
||||
"Parent" => pages_id,
|
||||
"MediaBox" => vec![0.into(), 0.into(), 200.into(), 800.into()],
|
||||
"Resources" => dictionary! {
|
||||
"Font" => dictionary! {
|
||||
"F1" => font_id,
|
||||
},
|
||||
},
|
||||
"Contents" => content_id,
|
||||
}
|
||||
.into(),
|
||||
);
|
||||
doc.objects.insert(
|
||||
pages_id,
|
||||
dictionary! {
|
||||
"Type" => "Pages",
|
||||
"Kids" => vec![page_id.into()],
|
||||
"Count" => 1,
|
||||
}
|
||||
.into(),
|
||||
);
|
||||
let catalog_id = doc.add_object(dictionary! {
|
||||
"Type" => "Catalog",
|
||||
"Pages" => pages_id,
|
||||
});
|
||||
doc.trailer.set("Root", catalog_id);
|
||||
|
||||
let mut bytes = Vec::new();
|
||||
doc.save_to(&mut bytes).unwrap();
|
||||
bytes
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_extract_tables_with_structure_real_pdf_bits_pilani() {
|
||||
use pdf_inspector::{extract_tables_with_structure_mem, TsrTableInput};
|
||||
@@ -1564,6 +1640,64 @@ fn test_extract_tables_with_structure_real_pdf_bits_pilani() {
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_extract_tables_with_structure_dense_overlapping_slanet_boxes() {
|
||||
use pdf_inspector::{extract_tables_with_structure_mem, TsrTableInput};
|
||||
|
||||
let buf = synthetic_dense_table_pdf();
|
||||
let tokens: Vec<String> = [
|
||||
"<table>",
|
||||
"<thead>",
|
||||
"<tr>",
|
||||
"<th></th>",
|
||||
"<th></th>",
|
||||
"</tr>",
|
||||
"</thead>",
|
||||
"<tbody>",
|
||||
"<tr>",
|
||||
"<td></td>",
|
||||
"<td></td>",
|
||||
"</tr>",
|
||||
"<tr>",
|
||||
"<td></td>",
|
||||
"<td></td>",
|
||||
"</tr>",
|
||||
"</tbody>",
|
||||
"</table>",
|
||||
]
|
||||
.into_iter()
|
||||
.map(String::from)
|
||||
.collect();
|
||||
|
||||
// Rows are spaced 16.8pt apart, while the SLANet-style boxes are 40pt
|
||||
// tall and overlap adjacent rows. Text must still land in only one row.
|
||||
let cell_bboxes = vec![
|
||||
poly(10.0, 72.0, 100.0, 112.0),
|
||||
poly(90.0, 72.0, 180.0, 112.0),
|
||||
poly(10.0, 88.8, 100.0, 128.8),
|
||||
poly(90.0, 88.8, 180.0, 128.8),
|
||||
poly(10.0, 105.6, 100.0, 145.6),
|
||||
poly(90.0, 105.6, 180.0, 145.6),
|
||||
];
|
||||
|
||||
let mds = extract_tables_with_structure_mem(
|
||||
&buf,
|
||||
&[TsrTableInput {
|
||||
page: 0,
|
||||
crop_pdf_pt_bbox: [0.0, 0.0, 200.0, 800.0],
|
||||
render_dpi: 72.0,
|
||||
structure_tokens: tokens,
|
||||
cell_bboxes,
|
||||
}],
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
let expected = "|Branch Name|Deposits|\n|---|---|\n|Oak Street|100|\n|Boardwalk|200|\n";
|
||||
assert_eq!(mds[0], expected);
|
||||
assert!(!mds[0].contains("Branch Name Oak Street"));
|
||||
assert!(!mds[0].contains("Oak Street Boardwalk"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_extract_tables_with_structure_input_order_preserved() {
|
||||
use pdf_inspector::{extract_tables_with_structure_mem, TsrTableInput};
|
||||
|
||||
Reference in New Issue
Block a user