mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-29 05:24:28 +00:00
Code Issues Packages Projects Releases Wiki Activity
69e0123213
docling/tests/data_scanned/groundtruth/docling_v2/ocr_test.pages.json
Ubuntu 547ce26702 Update test GT (from linux CPU) 
Signed-off-by: Ubuntu <ubuntu@ip-172-31-30-253.eu-central-1.compute.internal>
2025-07-23 12:32:30 +00:00

447 lines
12 KiB
JSON
Vendored
Raw Blame History

[
{
"page_no": 0,
"size": {
"width": 595.2,
"height": 841.92
},
"parsed_page": {
"dimension": {
"angle": 0.0,
"rect": {
"r_x0": 0.0,
"r_y0": 0.0,
"r_x1": 595.2,
"r_y1": 0.0,
"r_x2": 595.2,
"r_y2": 841.92,
"r_x3": 0.0,
"r_y3": 841.92,
"coord_origin": "BOTTOMLEFT"
},
"boundary_type": "crop_box",
"art_bbox": {
"l": 0.0,
"t": 841.92,
"r": 595.2,
"b": 0.0,
"coord_origin": "BOTTOMLEFT"
},
"bleed_bbox": {
"l": 0.0,
"t": 841.92,
"r": 595.2,
"b": 0.0,
"coord_origin": "BOTTOMLEFT"
},
"crop_bbox": {
"l": 0.0,
"t": 841.92,
"r": 595.2,
"b": 0.0,
"coord_origin": "BOTTOMLEFT"
},
"media_bbox": {
"l": 0.0,
"t": 841.92,
"r": 595.2,
"b": 0.0,
"coord_origin": "BOTTOMLEFT"
},
"trim_bbox": {
"l": 0.0,
"t": 841.92,
"r": 595.2,
"b": 0.0,
"coord_origin": "BOTTOMLEFT"
}
},
"bitmap_resources": [],
"char_cells": [],
"word_cells": [],
"textline_cells": [
{
"index": 0,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 72.73,
"r_y0": 96.34,
"r_x1": 505.27,
"r_y1": 96.34,
"r_x2": 505.27,
"r_y2": 75.97,
"r_x3": 72.73,
"r_y3": 75.97,
"coord_origin": "TOPLEFT"
},
"text": "Docling bundles PDF document conversion to",
"orig": "Docling bundles PDF document conversion to",
"text_direction": "left_to_right",
"confidence": 0.998,
"from_ocr": true
},
{
"index": 1,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 71.03,
"r_y0": 123.92,
"r_x1": 505.7,
"r_y1": 123.92,
"r_x2": 505.7,
"r_y2": 102.7,
"r_x3": 71.03,
"r_y3": 102.7,
"coord_origin": "TOPLEFT"
},
"text": "JSON and Markdown in an easy self contained",
"orig": "JSON and Markdown in an easy self contained",
"text_direction": "left_to_right",
"confidence": 0.995,
"from_ocr": true
},
{
"index": 2,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 71.03,
"r_y0": 154.06,
"r_x1": 152.64,
"r_y1": 154.06,
"r_x2": 152.64,
"r_y2": 130.29,
"r_x3": 71.03,
"r_y3": 130.29,
"coord_origin": "TOPLEFT"
},
"text": "package",
"orig": "package",
"text_direction": "left_to_right",
"confidence": 0.998,
"from_ocr": true
}
],
"has_chars": false,
"has_words": false,
"has_lines": true,
"image": null,
"lines": []
},
"predictions": {
"layout": {
"clusters": [
{
"id": 0,
"label": "text",
"bbox": {
"l": 71.03,
"t": 75.97,
"r": 505.7,
"b": 154.06,
"coord_origin": "TOPLEFT"
},
"confidence": 0.862,
"cells": [
{
"index": 0,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 72.73,
"r_y0": 96.34,
"r_x1": 505.27,
"r_y1": 96.34,
"r_x2": 505.27,
"r_y2": 75.97,
"r_x3": 72.73,
"r_y3": 75.97,
"coord_origin": "TOPLEFT"
},
"text": "Docling bundles PDF document conversion to",
"orig": "Docling bundles PDF document conversion to",
"text_direction": "left_to_right",
"confidence": 0.998,
"from_ocr": true
},
{
"index": 1,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 71.03,
"r_y0": 123.92,
"r_x1": 505.7,
"r_y1": 123.92,
"r_x2": 505.7,
"r_y2": 102.7,
"r_x3": 71.03,
"r_y3": 102.7,
"coord_origin": "TOPLEFT"
},
"text": "JSON and Markdown in an easy self contained",
"orig": "JSON and Markdown in an easy self contained",
"text_direction": "left_to_right",
"confidence": 0.995,
"from_ocr": true
},
{
"index": 2,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 71.03,
"r_y0": 154.06,
"r_x1": 152.64,
"r_y1": 154.06,
"r_x2": 152.64,
"r_y2": 130.29,
"r_x3": 71.03,
"r_y3": 130.29,
"coord_origin": "TOPLEFT"
},
"text": "package",
"orig": "package",
"text_direction": "left_to_right",
"confidence": 0.998,
"from_ocr": true
}
],
"children": []
}
]
},
"tablestructure": {
"table_map": {}
},
"figures_classification": null,
"equations_prediction": null,
"vlm_response": null
},
"assembled": {
"elements": [
{
"label": "text",
"id": 0,
"page_no": 0,
"cluster": {
"id": 0,
"label": "text",
"bbox": {
"l": 71.03,
"t": 75.97,
"r": 505.7,
"b": 154.06,
"coord_origin": "TOPLEFT"
},
"confidence": 0.862,
"cells": [
{
"index": 0,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 72.73,
"r_y0": 96.34,
"r_x1": 505.27,
"r_y1": 96.34,
"r_x2": 505.27,
"r_y2": 75.97,
"r_x3": 72.73,
"r_y3": 75.97,
"coord_origin": "TOPLEFT"
},
"text": "Docling bundles PDF document conversion to",
"orig": "Docling bundles PDF document conversion to",
"text_direction": "left_to_right",
"confidence": 0.998,
"from_ocr": true
},
{
"index": 1,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 71.03,
"r_y0": 123.92,
"r_x1": 505.7,
"r_y1": 123.92,
"r_x2": 505.7,
"r_y2": 102.7,
"r_x3": 71.03,
"r_y3": 102.7,
"coord_origin": "TOPLEFT"
},
"text": "JSON and Markdown in an easy self contained",
"orig": "JSON and Markdown in an easy self contained",
"text_direction": "left_to_right",
"confidence": 0.995,
"from_ocr": true
},
{
"index": 2,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 71.03,
"r_y0": 154.06,
"r_x1": 152.64,
"r_y1": 154.06,
"r_x2": 152.64,
"r_y2": 130.29,
"r_x3": 71.03,
"r_y3": 130.29,
"coord_origin": "TOPLEFT"
},
"text": "package",
"orig": "package",
"text_direction": "left_to_right",
"confidence": 0.998,
"from_ocr": true
}
],
"children": []
},
"text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"
}
],
"body": [
{
"label": "text",
"id": 0,
"page_no": 0,
"cluster": {
"id": 0,
"label": "text",
"bbox": {
"l": 71.03,
"t": 75.97,
"r": 505.7,
"b": 154.06,
"coord_origin": "TOPLEFT"
},
"confidence": 0.862,
"cells": [
{
"index": 0,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 72.73,
"r_y0": 96.34,
"r_x1": 505.27,
"r_y1": 96.34,
"r_x2": 505.27,
"r_y2": 75.97,
"r_x3": 72.73,
"r_y3": 75.97,
"coord_origin": "TOPLEFT"
},
"text": "Docling bundles PDF document conversion to",
"orig": "Docling bundles PDF document conversion to",
"text_direction": "left_to_right",
"confidence": 0.998,
"from_ocr": true
},
{
"index": 1,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 71.03,
"r_y0": 123.92,
"r_x1": 505.7,
"r_y1": 123.92,
"r_x2": 505.7,
"r_y2": 102.7,
"r_x3": 71.03,
"r_y3": 102.7,
"coord_origin": "TOPLEFT"
},
"text": "JSON and Markdown in an easy self contained",
"orig": "JSON and Markdown in an easy self contained",
"text_direction": "left_to_right",
"confidence": 0.995,
"from_ocr": true
},
{
"index": 2,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 71.03,
"r_y0": 154.06,
"r_x1": 152.64,
"r_y1": 154.06,
"r_x2": 152.64,
"r_y2": 130.29,
"r_x3": 71.03,
"r_y3": 130.29,
"coord_origin": "TOPLEFT"
},
"text": "package",
"orig": "package",
"text_direction": "left_to_right",
"confidence": 0.998,
"from_ocr": true
}
],
"children": []
},
"text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"
}
],
"headers": []
}
}
]
Reference in New Issue View Git Blame Copy Permalink