From 106951e71ee74ce3e383e1a3d3182e9d9cec54a1 Mon Sep 17 00:00:00 2001 From: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com> Date: Wed, 28 May 2025 13:26:49 +0200 Subject: [PATCH] test: add missing ground truth files (#1667) Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com> --- .../docling_v2/example_08.html.itxt | 8 + .../docling_v2/example_08.html.json | 2008 +++++++++++++++++ .../groundtruth/docling_v2/example_08.html.md | 29 + .../groundtruth/docling_v2/textbox.docx.itxt | 94 + .../groundtruth/docling_v2/textbox.docx.json | 1470 ++++++++++++ .../groundtruth/docling_v2/textbox.docx.md | 46 + .../html/{example_8.html => example_08.html} | 0 7 files changed, 3655 insertions(+) create mode 100644 tests/data/groundtruth/docling_v2/example_08.html.itxt create mode 100644 tests/data/groundtruth/docling_v2/example_08.html.json create mode 100644 tests/data/groundtruth/docling_v2/example_08.html.md create mode 100644 tests/data/groundtruth/docling_v2/textbox.docx.itxt create mode 100644 tests/data/groundtruth/docling_v2/textbox.docx.json create mode 100644 tests/data/groundtruth/docling_v2/textbox.docx.md rename tests/data/html/{example_8.html => example_08.html} (100%) diff --git a/tests/data/groundtruth/docling_v2/example_08.html.itxt b/tests/data/groundtruth/docling_v2/example_08.html.itxt new file mode 100644 index 0000000..505408e --- /dev/null +++ b/tests/data/groundtruth/docling_v2/example_08.html.itxt @@ -0,0 +1,8 @@ +item-0 at level 0: unspecified: group _root_ + item-1 at level 1: section: group header-1 + item-2 at level 2: section_header: Pivot table with with 1 row header + item-3 at level 3: table with [6x4] + item-4 at level 2: section_header: Pivot table with 2 row headers + item-5 at level 3: table with [6x5] + item-6 at level 2: section_header: Equivalent pivot table + item-7 at level 3: table with [6x5] \ No newline at end of file diff --git a/tests/data/groundtruth/docling_v2/example_08.html.json b/tests/data/groundtruth/docling_v2/example_08.html.json new file mode 100644 index 0000000..085be7e --- /dev/null +++ b/tests/data/groundtruth/docling_v2/example_08.html.json @@ -0,0 +1,2008 @@ +{ + "schema_name": "DoclingDocument", + "version": "1.3.0", + "name": "example_08", + "origin": { + "mimetype": "text/html", + "binary_hash": 12799593797322619937, + "filename": "example_08.html" + }, + "furniture": { + "self_ref": "#/furniture", + "children": [], + "content_layer": "furniture", + "name": "_root_", + "label": "unspecified" + }, + "body": { + "self_ref": "#/body", + "children": [ + { + "$ref": "#/groups/0" + } + ], + "content_layer": "body", + "name": "_root_", + "label": "unspecified" + }, + "groups": [ + { + "self_ref": "#/groups/0", + "parent": { + "$ref": "#/body" + }, + "children": [ + { + "$ref": "#/texts/0" + }, + { + "$ref": "#/texts/1" + }, + { + "$ref": "#/texts/2" + } + ], + "content_layer": "body", + "name": "header-1", + "label": "section" + } + ], + "texts": [ + { + "self_ref": "#/texts/0", + "parent": { + "$ref": "#/groups/0" + }, + "children": [ + { + "$ref": "#/tables/0" + } + ], + "content_layer": "body", + "label": "section_header", + "prov": [], + "orig": "Pivot table with with 1 row header", + "text": "Pivot table with with 1 row header", + "level": 1 + }, + { + "self_ref": "#/texts/1", + "parent": { + "$ref": "#/groups/0" + }, + "children": [ + { + "$ref": "#/tables/1" + } + ], + "content_layer": "body", + "label": "section_header", + "prov": [], + "orig": "Pivot table with 2 row headers", + "text": "Pivot table with 2 row headers", + "level": 1 + }, + { + "self_ref": "#/texts/2", + "parent": { + "$ref": "#/groups/0" + }, + "children": [ + { + "$ref": "#/tables/2" + } + ], + "content_layer": "body", + "label": "section_header", + "prov": [], + "orig": "Equivalent pivot table", + "text": "Equivalent pivot table", + "level": 1 + } + ], + "pictures": [], + "tables": [ + { + "self_ref": "#/tables/0", + "parent": { + "$ref": "#/texts/0" + }, + "children": [], + "content_layer": "body", + "label": "table", + "prov": [], + "captions": [], + "references": [], + "footnotes": [], + "data": { + "table_cells": [ + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 0, + "end_row_offset_idx": 1, + "start_col_offset_idx": 0, + "end_col_offset_idx": 1, + "text": "Year", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 0, + "end_row_offset_idx": 1, + "start_col_offset_idx": 1, + "end_col_offset_idx": 2, + "text": "Month", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 0, + "end_row_offset_idx": 1, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "Revenue", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 0, + "end_row_offset_idx": 1, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "Cost", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 5, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 6, + "start_col_offset_idx": 0, + "end_col_offset_idx": 1, + "text": "2025", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 2, + "start_col_offset_idx": 1, + "end_col_offset_idx": 2, + "text": "January", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 2, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "$134", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 2, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "$162", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 2, + "end_row_offset_idx": 3, + "start_col_offset_idx": 1, + "end_col_offset_idx": 2, + "text": "February", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 2, + "end_row_offset_idx": 3, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "$150", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 2, + "end_row_offset_idx": 3, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "$155", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 3, + "end_row_offset_idx": 4, + "start_col_offset_idx": 1, + "end_col_offset_idx": 2, + "text": "March", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 3, + "end_row_offset_idx": 4, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "$160", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 3, + "end_row_offset_idx": 4, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "$143", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 4, + "end_row_offset_idx": 5, + "start_col_offset_idx": 1, + "end_col_offset_idx": 2, + "text": "April", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 4, + "end_row_offset_idx": 5, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "$210", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 4, + "end_row_offset_idx": 5, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "$150", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 5, + "end_row_offset_idx": 6, + "start_col_offset_idx": 1, + "end_col_offset_idx": 2, + "text": "May", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 5, + "end_row_offset_idx": 6, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "$280", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 5, + "end_row_offset_idx": 6, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "$120", + "column_header": false, + "row_header": false, + "row_section": false + } + ], + "num_rows": 6, + "num_cols": 4, + "grid": [ + [ + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 0, + "end_row_offset_idx": 1, + "start_col_offset_idx": 0, + "end_col_offset_idx": 1, + "text": "Year", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 0, + "end_row_offset_idx": 1, + "start_col_offset_idx": 1, + "end_col_offset_idx": 2, + "text": "Month", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 0, + "end_row_offset_idx": 1, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "Revenue", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 0, + "end_row_offset_idx": 1, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "Cost", + "column_header": true, + "row_header": false, + "row_section": false + } + ], + [ + { + "row_span": 5, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 6, + "start_col_offset_idx": 0, + "end_col_offset_idx": 1, + "text": "2025", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 2, + "start_col_offset_idx": 1, + "end_col_offset_idx": 2, + "text": "January", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 2, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "$134", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 2, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "$162", + "column_header": false, + "row_header": false, + "row_section": false + } + ], + [ + { + "row_span": 5, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 6, + "start_col_offset_idx": 0, + "end_col_offset_idx": 1, + "text": "2025", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 2, + "end_row_offset_idx": 3, + "start_col_offset_idx": 1, + "end_col_offset_idx": 2, + "text": "February", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 2, + "end_row_offset_idx": 3, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "$150", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 2, + "end_row_offset_idx": 3, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "$155", + "column_header": false, + "row_header": false, + "row_section": false + } + ], + [ + { + "row_span": 5, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 6, + "start_col_offset_idx": 0, + "end_col_offset_idx": 1, + "text": "2025", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 3, + "end_row_offset_idx": 4, + "start_col_offset_idx": 1, + "end_col_offset_idx": 2, + "text": "March", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 3, + "end_row_offset_idx": 4, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "$160", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 3, + "end_row_offset_idx": 4, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "$143", + "column_header": false, + "row_header": false, + "row_section": false + } + ], + [ + { + "row_span": 5, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 6, + "start_col_offset_idx": 0, + "end_col_offset_idx": 1, + "text": "2025", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 4, + "end_row_offset_idx": 5, + "start_col_offset_idx": 1, + "end_col_offset_idx": 2, + "text": "April", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 4, + "end_row_offset_idx": 5, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "$210", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 4, + "end_row_offset_idx": 5, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "$150", + "column_header": false, + "row_header": false, + "row_section": false + } + ], + [ + { + "row_span": 5, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 6, + "start_col_offset_idx": 0, + "end_col_offset_idx": 1, + "text": "2025", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 5, + "end_row_offset_idx": 6, + "start_col_offset_idx": 1, + "end_col_offset_idx": 2, + "text": "May", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 5, + "end_row_offset_idx": 6, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "$280", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 5, + "end_row_offset_idx": 6, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "$120", + "column_header": false, + "row_header": false, + "row_section": false + } + ] + ] + } + }, + { + "self_ref": "#/tables/1", + "parent": { + "$ref": "#/texts/1" + }, + "children": [], + "content_layer": "body", + "label": "table", + "prov": [], + "captions": [], + "references": [], + "footnotes": [], + "data": { + "table_cells": [ + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 0, + "end_row_offset_idx": 1, + "start_col_offset_idx": 0, + "end_col_offset_idx": 1, + "text": "Year", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 0, + "end_row_offset_idx": 1, + "start_col_offset_idx": 1, + "end_col_offset_idx": 2, + "text": "Quarter", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 0, + "end_row_offset_idx": 1, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "Month", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 0, + "end_row_offset_idx": 1, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "Revenue", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 0, + "end_row_offset_idx": 1, + "start_col_offset_idx": 4, + "end_col_offset_idx": 5, + "text": "Cost", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 6, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 7, + "start_col_offset_idx": 0, + "end_col_offset_idx": 1, + "text": "2025", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 3, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 4, + "start_col_offset_idx": 1, + "end_col_offset_idx": 2, + "text": "Q1", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 2, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "January", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 2, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "$134", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 2, + "start_col_offset_idx": 4, + "end_col_offset_idx": 5, + "text": "$162", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 2, + "end_row_offset_idx": 3, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "February", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 2, + "end_row_offset_idx": 3, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "$150", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 2, + "end_row_offset_idx": 3, + "start_col_offset_idx": 4, + "end_col_offset_idx": 5, + "text": "$155", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 3, + "end_row_offset_idx": 4, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "March", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 3, + "end_row_offset_idx": 4, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "$160", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 3, + "end_row_offset_idx": 4, + "start_col_offset_idx": 4, + "end_col_offset_idx": 5, + "text": "$143", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 2, + "col_span": 1, + "start_row_offset_idx": 4, + "end_row_offset_idx": 6, + "start_col_offset_idx": 1, + "end_col_offset_idx": 2, + "text": "Q2", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 4, + "end_row_offset_idx": 5, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "April", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 4, + "end_row_offset_idx": 5, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "$210", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 4, + "end_row_offset_idx": 5, + "start_col_offset_idx": 4, + "end_col_offset_idx": 5, + "text": "$150", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 5, + "end_row_offset_idx": 6, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "May", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 5, + "end_row_offset_idx": 6, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "$280", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 5, + "end_row_offset_idx": 6, + "start_col_offset_idx": 4, + "end_col_offset_idx": 5, + "text": "$120", + "column_header": false, + "row_header": false, + "row_section": false + } + ], + "num_rows": 6, + "num_cols": 5, + "grid": [ + [ + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 0, + "end_row_offset_idx": 1, + "start_col_offset_idx": 0, + "end_col_offset_idx": 1, + "text": "Year", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 0, + "end_row_offset_idx": 1, + "start_col_offset_idx": 1, + "end_col_offset_idx": 2, + "text": "Quarter", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 0, + "end_row_offset_idx": 1, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "Month", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 0, + "end_row_offset_idx": 1, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "Revenue", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 0, + "end_row_offset_idx": 1, + "start_col_offset_idx": 4, + "end_col_offset_idx": 5, + "text": "Cost", + "column_header": true, + "row_header": false, + "row_section": false + } + ], + [ + { + "row_span": 6, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 7, + "start_col_offset_idx": 0, + "end_col_offset_idx": 1, + "text": "2025", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 3, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 4, + "start_col_offset_idx": 1, + "end_col_offset_idx": 2, + "text": "Q1", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 2, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "January", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 2, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "$134", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 2, + "start_col_offset_idx": 4, + "end_col_offset_idx": 5, + "text": "$162", + "column_header": false, + "row_header": false, + "row_section": false + } + ], + [ + { + "row_span": 6, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 7, + "start_col_offset_idx": 0, + "end_col_offset_idx": 1, + "text": "2025", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 3, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 4, + "start_col_offset_idx": 1, + "end_col_offset_idx": 2, + "text": "Q1", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 2, + "end_row_offset_idx": 3, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "February", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 2, + "end_row_offset_idx": 3, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "$150", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 2, + "end_row_offset_idx": 3, + "start_col_offset_idx": 4, + "end_col_offset_idx": 5, + "text": "$155", + "column_header": false, + "row_header": false, + "row_section": false + } + ], + [ + { + "row_span": 6, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 7, + "start_col_offset_idx": 0, + "end_col_offset_idx": 1, + "text": "2025", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 3, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 4, + "start_col_offset_idx": 1, + "end_col_offset_idx": 2, + "text": "Q1", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 3, + "end_row_offset_idx": 4, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "March", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 3, + "end_row_offset_idx": 4, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "$160", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 3, + "end_row_offset_idx": 4, + "start_col_offset_idx": 4, + "end_col_offset_idx": 5, + "text": "$143", + "column_header": false, + "row_header": false, + "row_section": false + } + ], + [ + { + "row_span": 6, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 7, + "start_col_offset_idx": 0, + "end_col_offset_idx": 1, + "text": "2025", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 2, + "col_span": 1, + "start_row_offset_idx": 4, + "end_row_offset_idx": 6, + "start_col_offset_idx": 1, + "end_col_offset_idx": 2, + "text": "Q2", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 4, + "end_row_offset_idx": 5, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "April", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 4, + "end_row_offset_idx": 5, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "$210", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 4, + "end_row_offset_idx": 5, + "start_col_offset_idx": 4, + "end_col_offset_idx": 5, + "text": "$150", + "column_header": false, + "row_header": false, + "row_section": false + } + ], + [ + { + "row_span": 6, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 7, + "start_col_offset_idx": 0, + "end_col_offset_idx": 1, + "text": "2025", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 2, + "col_span": 1, + "start_row_offset_idx": 4, + "end_row_offset_idx": 6, + "start_col_offset_idx": 1, + "end_col_offset_idx": 2, + "text": "Q2", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 5, + "end_row_offset_idx": 6, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "May", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 5, + "end_row_offset_idx": 6, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "$280", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 5, + "end_row_offset_idx": 6, + "start_col_offset_idx": 4, + "end_col_offset_idx": 5, + "text": "$120", + "column_header": false, + "row_header": false, + "row_section": false + } + ] + ] + } + }, + { + "self_ref": "#/tables/2", + "parent": { + "$ref": "#/texts/2" + }, + "children": [], + "content_layer": "body", + "label": "table", + "prov": [], + "captions": [], + "references": [], + "footnotes": [], + "data": { + "table_cells": [ + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 0, + "end_row_offset_idx": 1, + "start_col_offset_idx": 0, + "end_col_offset_idx": 1, + "text": "Year", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 0, + "end_row_offset_idx": 1, + "start_col_offset_idx": 1, + "end_col_offset_idx": 2, + "text": "Quarter", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 0, + "end_row_offset_idx": 1, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "Month", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 0, + "end_row_offset_idx": 1, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "Revenue", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 0, + "end_row_offset_idx": 1, + "start_col_offset_idx": 4, + "end_col_offset_idx": 5, + "text": "Cost", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 7, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 8, + "start_col_offset_idx": 0, + "end_col_offset_idx": 1, + "text": "2025", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 3, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 4, + "start_col_offset_idx": 1, + "end_col_offset_idx": 2, + "text": "Q1", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 2, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "January", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 2, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "$134", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 2, + "start_col_offset_idx": 4, + "end_col_offset_idx": 5, + "text": "$162", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 2, + "end_row_offset_idx": 3, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "February", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 2, + "end_row_offset_idx": 3, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "$150", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 2, + "end_row_offset_idx": 3, + "start_col_offset_idx": 4, + "end_col_offset_idx": 5, + "text": "$155", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 3, + "end_row_offset_idx": 4, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "March", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 3, + "end_row_offset_idx": 4, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "$160", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 3, + "end_row_offset_idx": 4, + "start_col_offset_idx": 4, + "end_col_offset_idx": 5, + "text": "$143", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 2, + "col_span": 1, + "start_row_offset_idx": 4, + "end_row_offset_idx": 6, + "start_col_offset_idx": 1, + "end_col_offset_idx": 2, + "text": "Q2", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 4, + "end_row_offset_idx": 5, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "April", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 4, + "end_row_offset_idx": 5, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "$210", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 4, + "end_row_offset_idx": 5, + "start_col_offset_idx": 4, + "end_col_offset_idx": 5, + "text": "$150", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 5, + "end_row_offset_idx": 6, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "May", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 5, + "end_row_offset_idx": 6, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "$280", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 5, + "end_row_offset_idx": 6, + "start_col_offset_idx": 4, + "end_col_offset_idx": 5, + "text": "$120", + "column_header": false, + "row_header": false, + "row_section": false + } + ], + "num_rows": 6, + "num_cols": 5, + "grid": [ + [ + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 0, + "end_row_offset_idx": 1, + "start_col_offset_idx": 0, + "end_col_offset_idx": 1, + "text": "Year", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 0, + "end_row_offset_idx": 1, + "start_col_offset_idx": 1, + "end_col_offset_idx": 2, + "text": "Quarter", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 0, + "end_row_offset_idx": 1, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "Month", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 0, + "end_row_offset_idx": 1, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "Revenue", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 0, + "end_row_offset_idx": 1, + "start_col_offset_idx": 4, + "end_col_offset_idx": 5, + "text": "Cost", + "column_header": true, + "row_header": false, + "row_section": false + } + ], + [ + { + "row_span": 7, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 8, + "start_col_offset_idx": 0, + "end_col_offset_idx": 1, + "text": "2025", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 3, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 4, + "start_col_offset_idx": 1, + "end_col_offset_idx": 2, + "text": "Q1", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 2, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "January", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 2, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "$134", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 2, + "start_col_offset_idx": 4, + "end_col_offset_idx": 5, + "text": "$162", + "column_header": false, + "row_header": false, + "row_section": false + } + ], + [ + { + "row_span": 7, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 8, + "start_col_offset_idx": 0, + "end_col_offset_idx": 1, + "text": "2025", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 3, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 4, + "start_col_offset_idx": 1, + "end_col_offset_idx": 2, + "text": "Q1", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 2, + "end_row_offset_idx": 3, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "February", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 2, + "end_row_offset_idx": 3, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "$150", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 2, + "end_row_offset_idx": 3, + "start_col_offset_idx": 4, + "end_col_offset_idx": 5, + "text": "$155", + "column_header": false, + "row_header": false, + "row_section": false + } + ], + [ + { + "row_span": 7, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 8, + "start_col_offset_idx": 0, + "end_col_offset_idx": 1, + "text": "2025", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 3, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 4, + "start_col_offset_idx": 1, + "end_col_offset_idx": 2, + "text": "Q1", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 3, + "end_row_offset_idx": 4, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "March", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 3, + "end_row_offset_idx": 4, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "$160", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 3, + "end_row_offset_idx": 4, + "start_col_offset_idx": 4, + "end_col_offset_idx": 5, + "text": "$143", + "column_header": false, + "row_header": false, + "row_section": false + } + ], + [ + { + "row_span": 7, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 8, + "start_col_offset_idx": 0, + "end_col_offset_idx": 1, + "text": "2025", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 2, + "col_span": 1, + "start_row_offset_idx": 4, + "end_row_offset_idx": 6, + "start_col_offset_idx": 1, + "end_col_offset_idx": 2, + "text": "Q2", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 4, + "end_row_offset_idx": 5, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "April", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 4, + "end_row_offset_idx": 5, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "$210", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 4, + "end_row_offset_idx": 5, + "start_col_offset_idx": 4, + "end_col_offset_idx": 5, + "text": "$150", + "column_header": false, + "row_header": false, + "row_section": false + } + ], + [ + { + "row_span": 7, + "col_span": 1, + "start_row_offset_idx": 1, + "end_row_offset_idx": 8, + "start_col_offset_idx": 0, + "end_col_offset_idx": 1, + "text": "2025", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 2, + "col_span": 1, + "start_row_offset_idx": 4, + "end_row_offset_idx": 6, + "start_col_offset_idx": 1, + "end_col_offset_idx": 2, + "text": "Q2", + "column_header": true, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 5, + "end_row_offset_idx": 6, + "start_col_offset_idx": 2, + "end_col_offset_idx": 3, + "text": "May", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 5, + "end_row_offset_idx": 6, + "start_col_offset_idx": 3, + "end_col_offset_idx": 4, + "text": "$280", + "column_header": false, + "row_header": false, + "row_section": false + }, + { + "row_span": 1, + "col_span": 1, + "start_row_offset_idx": 5, + "end_row_offset_idx": 6, + "start_col_offset_idx": 4, + "end_col_offset_idx": 5, + "text": "$120", + "column_header": false, + "row_header": false, + "row_section": false + } + ] + ] + } + } + ], + "key_value_items": [], + "form_items": [], + "pages": {} +} \ No newline at end of file diff --git a/tests/data/groundtruth/docling_v2/example_08.html.md b/tests/data/groundtruth/docling_v2/example_08.html.md new file mode 100644 index 0000000..462a810 --- /dev/null +++ b/tests/data/groundtruth/docling_v2/example_08.html.md @@ -0,0 +1,29 @@ +## Pivot table with with 1 row header + +| Year | Month | Revenue | Cost | +|--------|----------|-----------|--------| +| 2025 | January | $134 | $162 | +| 2025 | February | $150 | $155 | +| 2025 | March | $160 | $143 | +| 2025 | April | $210 | $150 | +| 2025 | May | $280 | $120 | + +## Pivot table with 2 row headers + +| Year | Quarter | Month | Revenue | Cost | +|--------|-----------|----------|-----------|--------| +| 2025 | Q1 | January | $134 | $162 | +| 2025 | Q1 | February | $150 | $155 | +| 2025 | Q1 | March | $160 | $143 | +| 2025 | Q2 | April | $210 | $150 | +| 2025 | Q2 | May | $280 | $120 | + +## Equivalent pivot table + +| Year | Quarter | Month | Revenue | Cost | +|--------|-----------|----------|-----------|--------| +| 2025 | Q1 | January | $134 | $162 | +| 2025 | Q1 | February | $150 | $155 | +| 2025 | Q1 | March | $160 | $143 | +| 2025 | Q2 | April | $210 | $150 | +| 2025 | Q2 | May | $280 | $120 | \ No newline at end of file diff --git a/tests/data/groundtruth/docling_v2/textbox.docx.itxt b/tests/data/groundtruth/docling_v2/textbox.docx.itxt new file mode 100644 index 0000000..2933724 --- /dev/null +++ b/tests/data/groundtruth/docling_v2/textbox.docx.itxt @@ -0,0 +1,94 @@ +item-0 at level 0: unspecified: group _root_ + item-1 at level 1: paragraph: Chiayi County Shuishang Township ... mentary School Affiliated Kindergarten + item-2 at level 1: paragraph: Infectious Disease Reporting Pro ... r the 113th Academic Year Kindergarten + item-3 at level 1: paragraph: + item-4 at level 1: section: group textbox + item-5 at level 2: paragraph: Student falls ill + item-6 at level 2: paragraph: + item-7 at level 2: paragraph: + item-8 at level 2: list: group list + item-9 at level 3: list_item: Suggested Reportable Symptoms: +＊ ... sh +＊ Blisters +＊ Headache +＊ Sore throat + item-10 at level 1: list_item: + item-11 at level 1: paragraph: + item-12 at level 1: paragraph: + item-13 at level 1: section: group textbox + item-14 at level 2: paragraph: If a caregiver suspects that wit ... the same suggested reportable symptoms + item-15 at level 1: paragraph: + item-16 at level 1: paragraph: + item-17 at level 1: paragraph: + item-18 at level 1: paragraph: + item-19 at level 1: section: group textbox + item-20 at level 2: paragraph: Yes + item-21 at level 1: paragraph: + item-22 at level 1: paragraph: + item-23 at level 1: section: group textbox + item-24 at level 2: paragraph:  A report must be submitted wi ... saster Prevention Information Network. + item-25 at level 2: paragraph:  A report must also be submitt ... d Infectious Disease Reporting System. + item-26 at level 2: paragraph: + item-27 at level 2: paragraph: + item-28 at level 1: paragraph: + item-29 at level 1: paragraph: + item-30 at level 1: paragraph: + item-31 at level 1: paragraph: + item-32 at level 1: paragraph: + item-33 at level 1: paragraph: + item-34 at level 1: section: group textbox + item-35 at level 2: paragraph: Health Bureau: + item-36 at level 2: paragraph: Upon receiving a report from the ... rt to the Centers for Disease Control. + item-37 at level 2: list: group list + item-38 at level 3: list_item: If necessary, provide health edu ... vidual to undergo specimen collection. + item-39 at level 3: list_item: Implement appropriate epidemic p ... the Communicable Disease Control Act. + item-40 at level 2: paragraph: + item-41 at level 2: paragraph: + item-42 at level 1: list: group list + item-43 at level 2: list_item: + item-44 at level 1: paragraph: + item-45 at level 1: section: group textbox + item-46 at level 2: paragraph: Department of Education: +Collabo ... vention measures at all school levels. + item-47 at level 1: paragraph: + item-48 at level 1: paragraph: + item-49 at level 1: paragraph: + item-50 at level 1: paragraph: + item-51 at level 1: paragraph: + item-52 at level 1: paragraph: + item-53 at level 1: paragraph: + item-54 at level 1: section: group textbox + item-55 at level 2: inline: group group + item-56 at level 3: paragraph: The Health Bureau will handle + item-57 at level 3: paragraph: reporting and specimen collection + item-58 at level 3: paragraph: . + item-59 at level 2: paragraph: + item-60 at level 2: paragraph: + item-61 at level 1: paragraph: + item-62 at level 1: paragraph: + item-63 at level 1: paragraph: + item-64 at level 1: section: group textbox + item-65 at level 2: paragraph: Whether the epidemic has eased. + item-66 at level 2: paragraph: + item-67 at level 2: paragraph: + item-68 at level 1: paragraph: + item-69 at level 1: section: group textbox + item-70 at level 2: paragraph: Whether the test results are pos ... legally designated infectious disease. + item-71 at level 2: paragraph: No + item-72 at level 1: paragraph: + item-73 at level 1: paragraph: + item-74 at level 1: section: group textbox + item-75 at level 1: paragraph: + item-76 at level 1: section: group textbox + item-77 at level 1: paragraph: + item-78 at level 1: paragraph: + item-79 at level 1: section: group textbox + item-80 at level 2: paragraph: Case closed. + item-81 at level 2: paragraph: + item-82 at level 2: paragraph: + item-83 at level 2: paragraph: The Health Bureau will carry out ... ters for Disease Control if necessary. + item-84 at level 1: paragraph: + item-85 at level 1: section: group textbox + item-86 at level 1: paragraph: + item-87 at level 1: paragraph: + item-88 at level 1: paragraph: \ No newline at end of file diff --git a/tests/data/groundtruth/docling_v2/textbox.docx.json b/tests/data/groundtruth/docling_v2/textbox.docx.json new file mode 100644 index 0000000..c7985b2 --- /dev/null +++ b/tests/data/groundtruth/docling_v2/textbox.docx.json @@ -0,0 +1,1470 @@ +{ + "schema_name": "DoclingDocument", + "version": "1.3.0", + "name": "textbox", + "origin": { + "mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document", + "binary_hash": 830302052279341882, + "filename": "textbox.docx" + }, + "furniture": { + "self_ref": "#/furniture", + "children": [], + "content_layer": "furniture", + "name": "_root_", + "label": "unspecified" + }, + "body": { + "self_ref": "#/body", + "children": [ + { + "$ref": "#/texts/0" + }, + { + "$ref": "#/texts/1" + }, + { + "$ref": "#/texts/2" + }, + { + "$ref": "#/groups/0" + }, + { + "$ref": "#/texts/7" + }, + { + "$ref": "#/texts/8" + }, + { + "$ref": "#/texts/9" + }, + { + "$ref": "#/groups/2" + }, + { + "$ref": "#/texts/11" + }, + { + "$ref": "#/texts/12" + }, + { + "$ref": "#/texts/13" + }, + { + "$ref": "#/texts/14" + }, + { + "$ref": "#/groups/3" + }, + { + "$ref": "#/texts/16" + }, + { + "$ref": "#/texts/17" + }, + { + "$ref": "#/groups/4" + }, + { + "$ref": "#/texts/22" + }, + { + "$ref": "#/texts/23" + }, + { + "$ref": "#/texts/24" + }, + { + "$ref": "#/texts/25" + }, + { + "$ref": "#/texts/26" + }, + { + "$ref": "#/texts/27" + }, + { + "$ref": "#/groups/5" + }, + { + "$ref": "#/groups/7" + }, + { + "$ref": "#/texts/35" + }, + { + "$ref": "#/groups/8" + }, + { + "$ref": "#/texts/37" + }, + { + "$ref": "#/texts/38" + }, + { + "$ref": "#/texts/39" + }, + { + "$ref": "#/texts/40" + }, + { + "$ref": "#/texts/41" + }, + { + "$ref": "#/texts/42" + }, + { + "$ref": "#/texts/43" + }, + { + "$ref": "#/groups/9" + }, + { + "$ref": "#/texts/49" + }, + { + "$ref": "#/texts/50" + }, + { + "$ref": "#/texts/51" + }, + { + "$ref": "#/groups/11" + }, + { + "$ref": "#/texts/55" + }, + { + "$ref": "#/groups/12" + }, + { + "$ref": "#/texts/58" + }, + { + "$ref": "#/texts/59" + }, + { + "$ref": "#/groups/13" + }, + { + "$ref": "#/texts/60" + }, + { + "$ref": "#/groups/14" + }, + { + "$ref": "#/texts/61" + }, + { + "$ref": "#/texts/62" + }, + { + "$ref": "#/groups/15" + }, + { + "$ref": "#/texts/67" + }, + { + "$ref": "#/groups/16" + }, + { + "$ref": "#/texts/68" + }, + { + "$ref": "#/texts/69" + }, + { + "$ref": "#/texts/70" + } + ], + "content_layer": "body", + "name": "_root_", + "label": "unspecified" + }, + "groups": [ + { + "self_ref": "#/groups/0", + "parent": { + "$ref": "#/body" + }, + "children": [ + { + "$ref": "#/texts/3" + }, + { + "$ref": "#/texts/4" + }, + { + "$ref": "#/texts/5" + }, + { + "$ref": "#/groups/1" + } + ], + "content_layer": "body", + "name": "textbox", + "label": "section" + }, + { + "self_ref": "#/groups/1", + "parent": { + "$ref": "#/groups/0" + }, + "children": [ + { + "$ref": "#/texts/6" + } + ], + "content_layer": "body", + "name": "list", + "label": "list" + }, + { + "self_ref": "#/groups/2", + "parent": { + "$ref": "#/body" + }, + "children": [ + { + "$ref": "#/texts/10" + } + ], + "content_layer": "body", + "name": "textbox", + "label": "section" + }, + { + "self_ref": "#/groups/3", + "parent": { + "$ref": "#/body" + }, + "children": [ + { + "$ref": "#/texts/15" + } + ], + "content_layer": "body", + "name": "textbox", + "label": "section" + }, + { + "self_ref": "#/groups/4", + "parent": { + "$ref": "#/body" + }, + "children": [ + { + "$ref": "#/texts/18" + }, + { + "$ref": "#/texts/19" + }, + { + "$ref": "#/texts/20" + }, + { + "$ref": "#/texts/21" + } + ], + "content_layer": "body", + "name": "textbox", + "label": "section" + }, + { + "self_ref": "#/groups/5", + "parent": { + "$ref": "#/body" + }, + "children": [ + { + "$ref": "#/texts/28" + }, + { + "$ref": "#/texts/29" + }, + { + "$ref": "#/groups/6" + }, + { + "$ref": "#/texts/32" + }, + { + "$ref": "#/texts/33" + } + ], + "content_layer": "body", + "name": "textbox", + "label": "section" + }, + { + "self_ref": "#/groups/6", + "parent": { + "$ref": "#/groups/5" + }, + "children": [ + { + "$ref": "#/texts/30" + }, + { + "$ref": "#/texts/31" + } + ], + "content_layer": "body", + "name": "list", + "label": "list" + }, + { + "self_ref": "#/groups/7", + "parent": { + "$ref": "#/body" + }, + "children": [ + { + "$ref": "#/texts/34" + } + ], + "content_layer": "body", + "name": "list", + "label": "list" + }, + { + "self_ref": "#/groups/8", + "parent": { + "$ref": "#/body" + }, + "children": [ + { + "$ref": "#/texts/36" + } + ], + "content_layer": "body", + "name": "textbox", + "label": "section" + }, + { + "self_ref": "#/groups/9", + "parent": { + "$ref": "#/body" + }, + "children": [ + { + "$ref": "#/groups/10" + }, + { + "$ref": "#/texts/47" + }, + { + "$ref": "#/texts/48" + } + ], + "content_layer": "body", + "name": "textbox", + "label": "section" + }, + { + "self_ref": "#/groups/10", + "parent": { + "$ref": "#/groups/9" + }, + "children": [ + { + "$ref": "#/texts/44" + }, + { + "$ref": "#/texts/45" + }, + { + "$ref": "#/texts/46" + } + ], + "content_layer": "body", + "name": "group", + "label": "inline" + }, + { + "self_ref": "#/groups/11", + "parent": { + "$ref": "#/body" + }, + "children": [ + { + "$ref": "#/texts/52" + }, + { + "$ref": "#/texts/53" + }, + { + "$ref": "#/texts/54" + } + ], + "content_layer": "body", + "name": "textbox", + "label": "section" + }, + { + "self_ref": "#/groups/12", + "parent": { + "$ref": "#/body" + }, + "children": [ + { + "$ref": "#/texts/56" + }, + { + "$ref": "#/texts/57" + } + ], + "content_layer": "body", + "name": "textbox", + "label": "section" + }, + { + "self_ref": "#/groups/13", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "name": "textbox", + "label": "section" + }, + { + "self_ref": "#/groups/14", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "name": "textbox", + "label": "section" + }, + { + "self_ref": "#/groups/15", + "parent": { + "$ref": "#/body" + }, + "children": [ + { + "$ref": "#/texts/63" + }, + { + "$ref": "#/texts/64" + }, + { + "$ref": "#/texts/65" + }, + { + "$ref": "#/texts/66" + } + ], + "content_layer": "body", + "name": "textbox", + "label": "section" + }, + { + "self_ref": "#/groups/16", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "name": "textbox", + "label": "section" + } + ], + "texts": [ + { + "self_ref": "#/texts/0", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "Chiayi County Shuishang Township Nanjing Elementary School Affiliated Kindergarten", + "text": "Chiayi County Shuishang Township Nanjing Elementary School Affiliated Kindergarten", + "formatting": { + "bold": true, + "italic": false, + "underline": false, + "strikethrough": false + } + }, + { + "self_ref": "#/texts/1", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "Infectious Disease Reporting Procedure for the 113th Academic Year Kindergarten", + "text": "Infectious Disease Reporting Procedure for the 113th Academic Year Kindergarten", + "formatting": { + "bold": true, + "italic": false, + "underline": false, + "strikethrough": false + } + }, + { + "self_ref": "#/texts/2", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/3", + "parent": { + "$ref": "#/groups/0" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "Student falls ill", + "text": "Student falls ill", + "formatting": { + "bold": true, + "italic": false, + "underline": false, + "strikethrough": false + } + }, + { + "self_ref": "#/texts/4", + "parent": { + "$ref": "#/groups/0" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/5", + "parent": { + "$ref": "#/groups/0" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/6", + "parent": { + "$ref": "#/groups/1" + }, + "children": [], + "content_layer": "body", + "label": "list_item", + "prov": [], + "orig": "Suggested Reportable Symptoms:\n＊ Fever\n＊ Cough\n＊ Diarrhea\n＊ Vomiting\n＊ Rash\n＊ Blisters\n＊ Headache\n＊ Sore throat", + "text": "Suggested Reportable Symptoms:\n＊ Fever\n＊ Cough\n＊ Diarrhea\n＊ Vomiting\n＊ Rash\n＊ Blisters\n＊ Headache\n＊ Sore throat", + "formatting": { + "bold": false, + "italic": false, + "underline": false, + "strikethrough": false + }, + "enumerated": false, + "marker": "-" + }, + { + "self_ref": "#/texts/7", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "list_item", + "prov": [], + "orig": "", + "text": "", + "enumerated": false, + "marker": "-" + }, + { + "self_ref": "#/texts/8", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/9", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/10", + "parent": { + "$ref": "#/groups/2" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "If a caregiver suspects that within one week, a fifth of the class (for classes with more than 15 students) or more than three students (for classes with 15 or fewer students)\nshow the same suggested reportable symptoms", + "text": "If a caregiver suspects that within one week, a fifth of the class (for classes with more than 15 students) or more than three students (for classes with 15 or fewer students)\nshow the same suggested reportable symptoms", + "formatting": { + "bold": false, + "italic": false, + "underline": false, + "strikethrough": false + } + }, + { + "self_ref": "#/texts/11", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/12", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/13", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/14", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/15", + "parent": { + "$ref": "#/groups/3" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "Yes", + "text": "Yes", + "formatting": { + "bold": false, + "italic": false, + "underline": false, + "strikethrough": false + } + }, + { + "self_ref": "#/texts/16", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/17", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/18", + "parent": { + "$ref": "#/groups/4" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": " A report must be submitted within 24 hours via the Ministry of Education’s Campus Safety and Disaster Prevention Information Network.", + "text": " A report must be submitted within 24 hours via the Ministry of Education’s Campus Safety and Disaster Prevention Information Network.", + "formatting": { + "bold": false, + "italic": false, + "underline": false, + "strikethrough": false + } + }, + { + "self_ref": "#/texts/19", + "parent": { + "$ref": "#/groups/4" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": " A report must also be submitted within 48 hours through Chiayi County’s School Suspected Infectious Disease Reporting System.", + "text": " A report must also be submitted within 48 hours through Chiayi County’s School Suspected Infectious Disease Reporting System.", + "formatting": { + "bold": false, + "italic": false, + "underline": false, + "strikethrough": false + } + }, + { + "self_ref": "#/texts/20", + "parent": { + "$ref": "#/groups/4" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/21", + "parent": { + "$ref": "#/groups/4" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/22", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/23", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/24", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/25", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/26", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/27", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/28", + "parent": { + "$ref": "#/groups/5" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "Health Bureau:", + "text": "Health Bureau:", + "formatting": { + "bold": true, + "italic": false, + "underline": false, + "strikethrough": false + } + }, + { + "self_ref": "#/texts/29", + "parent": { + "$ref": "#/groups/5" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "Upon receiving a report from the kindergarten, conduct a preliminary assessment of the case, and depending on the situation and type of illness, carry out an epidemiological investigation and report to the Centers for Disease Control.", + "text": "Upon receiving a report from the kindergarten, conduct a preliminary assessment of the case, and depending on the situation and type of illness, carry out an epidemiological investigation and report to the Centers for Disease Control.", + "formatting": { + "bold": false, + "italic": false, + "underline": false, + "strikethrough": false + } + }, + { + "self_ref": "#/texts/30", + "parent": { + "$ref": "#/groups/6" + }, + "children": [], + "content_layer": "body", + "label": "list_item", + "prov": [], + "orig": "If necessary, provide health education and important reminders at the kindergarten, or notify the individual to undergo specimen collection.", + "text": "If necessary, provide health education and important reminders at the kindergarten, or notify the individual to undergo specimen collection.", + "formatting": { + "bold": false, + "italic": false, + "underline": false, + "strikethrough": false + }, + "enumerated": false, + "marker": "-" + }, + { + "self_ref": "#/texts/31", + "parent": { + "$ref": "#/groups/6" + }, + "children": [], + "content_layer": "body", + "label": "list_item", + "prov": [], + "orig": "Implement appropriate epidemic prevention measures in accordance with the Communicable Disease Control Act.", + "text": "Implement appropriate epidemic prevention measures in accordance with the Communicable Disease Control Act.", + "formatting": { + "bold": false, + "italic": false, + "underline": false, + "strikethrough": false + }, + "enumerated": false, + "marker": "-" + }, + { + "self_ref": "#/texts/32", + "parent": { + "$ref": "#/groups/5" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/33", + "parent": { + "$ref": "#/groups/5" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/34", + "parent": { + "$ref": "#/groups/7" + }, + "children": [], + "content_layer": "body", + "label": "list_item", + "prov": [], + "orig": "", + "text": "", + "enumerated": false, + "marker": "-" + }, + { + "self_ref": "#/texts/35", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/36", + "parent": { + "$ref": "#/groups/8" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "Department of Education:\nCollaborate with the Health Bureau in conducting epidemiological investigations and assist Health Bureau personnel in implementing necessary epidemic prevention measures at all school levels.", + "text": "Department of Education:\nCollaborate with the Health Bureau in conducting epidemiological investigations and assist Health Bureau personnel in implementing necessary epidemic prevention measures at all school levels.", + "formatting": { + "bold": false, + "italic": false, + "underline": false, + "strikethrough": false + } + }, + { + "self_ref": "#/texts/37", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/38", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/39", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/40", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/41", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/42", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/43", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/44", + "parent": { + "$ref": "#/groups/10" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "The Health Bureau will handle", + "text": "The Health Bureau will handle", + "formatting": { + "bold": false, + "italic": false, + "underline": false, + "strikethrough": false + } + }, + { + "self_ref": "#/texts/45", + "parent": { + "$ref": "#/groups/10" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "reporting and specimen collection", + "text": "reporting and specimen collection", + "formatting": { + "bold": true, + "italic": false, + "underline": false, + "strikethrough": false + } + }, + { + "self_ref": "#/texts/46", + "parent": { + "$ref": "#/groups/10" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": ".", + "text": ".", + "formatting": { + "bold": false, + "italic": false, + "underline": false, + "strikethrough": false + } + }, + { + "self_ref": "#/texts/47", + "parent": { + "$ref": "#/groups/9" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/48", + "parent": { + "$ref": "#/groups/9" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/49", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/50", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/51", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/52", + "parent": { + "$ref": "#/groups/11" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "Whether the epidemic has eased.", + "text": "Whether the epidemic has eased.", + "formatting": { + "bold": true, + "italic": false, + "underline": false, + "strikethrough": false + } + }, + { + "self_ref": "#/texts/53", + "parent": { + "$ref": "#/groups/11" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/54", + "parent": { + "$ref": "#/groups/11" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/55", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/56", + "parent": { + "$ref": "#/groups/12" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "Whether the test results are positive for a legally designated infectious disease.", + "text": "Whether the test results are positive for a legally designated infectious disease.", + "formatting": { + "bold": true, + "italic": false, + "underline": false, + "strikethrough": false + } + }, + { + "self_ref": "#/texts/57", + "parent": { + "$ref": "#/groups/12" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "No", + "text": "No", + "formatting": { + "bold": false, + "italic": false, + "underline": false, + "strikethrough": false + } + }, + { + "self_ref": "#/texts/58", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/59", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/60", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/61", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/62", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/63", + "parent": { + "$ref": "#/groups/15" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "Case closed.", + "text": "Case closed.", + "formatting": { + "bold": true, + "italic": false, + "underline": false, + "strikethrough": false + } + }, + { + "self_ref": "#/texts/64", + "parent": { + "$ref": "#/groups/15" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/65", + "parent": { + "$ref": "#/groups/15" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/66", + "parent": { + "$ref": "#/groups/15" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "The Health Bureau will carry out subsequent related epidemic prevention measures and follow-up, and will request assistance from the Centers for Disease Control if necessary.", + "text": "The Health Bureau will carry out subsequent related epidemic prevention measures and follow-up, and will request assistance from the Centers for Disease Control if necessary.", + "formatting": { + "bold": false, + "italic": false, + "underline": false, + "strikethrough": false + } + }, + { + "self_ref": "#/texts/67", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/68", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/69", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + }, + { + "self_ref": "#/texts/70", + "parent": { + "$ref": "#/body" + }, + "children": [], + "content_layer": "body", + "label": "paragraph", + "prov": [], + "orig": "", + "text": "" + } + ], + "pictures": [], + "tables": [], + "key_value_items": [], + "form_items": [], + "pages": {} +} \ No newline at end of file diff --git a/tests/data/groundtruth/docling_v2/textbox.docx.md b/tests/data/groundtruth/docling_v2/textbox.docx.md new file mode 100644 index 0000000..829abad --- /dev/null +++ b/tests/data/groundtruth/docling_v2/textbox.docx.md @@ -0,0 +1,46 @@ +**Chiayi County Shuishang Township Nanjing Elementary School Affiliated Kindergarten** + +**Infectious Disease Reporting Procedure for the 113th Academic Year Kindergarten** + +**Student falls ill** + +- Suggested Reportable Symptoms: +＊ Fever +＊ Cough +＊ Diarrhea +＊ Vomiting +＊ Rash +＊ Blisters +＊ Headache +＊ Sore throat + +If a caregiver suspects that within one week, a fifth of the class (for classes with more than 15 students) or more than three students (for classes with 15 or fewer students) +show the same suggested reportable symptoms + +Yes + + A report must be submitted within 24 hours via the Ministry of Education’s Campus Safety and Disaster Prevention Information Network. + + A report must also be submitted within 48 hours through Chiayi County’s School Suspected Infectious Disease Reporting System. + +**Health Bureau:** + +Upon receiving a report from the kindergarten, conduct a preliminary assessment of the case, and depending on the situation and type of illness, carry out an epidemiological investigation and report to the Centers for Disease Control. + +- If necessary, provide health education and important reminders at the kindergarten, or notify the individual to undergo specimen collection. +- Implement appropriate epidemic prevention measures in accordance with the Communicable Disease Control Act. + +Department of Education: +Collaborate with the Health Bureau in conducting epidemiological investigations and assist Health Bureau personnel in implementing necessary epidemic prevention measures at all school levels. + +The Health Bureau will handle **reporting and specimen collection** . + +**Whether the epidemic has eased.** + +**Whether the test results are positive for a legally designated infectious disease.** + +No + +**Case closed.** + +The Health Bureau will carry out subsequent related epidemic prevention measures and follow-up, and will request assistance from the Centers for Disease Control if necessary. \ No newline at end of file diff --git a/tests/data/html/example_8.html b/tests/data/html/example_08.html similarity index 100% rename from tests/data/html/example_8.html rename to tests/data/html/example_08.html