mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-09 05:08:14 +00:00
Code Issues Packages Projects Releases Wiki Activity

updated the ground-truth output

Browse Source 
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
This commit is contained in:
Peter Staar
2025-09-04 05:22:54 +02:00
parent cffa6e05d0
commit effd9de250
19 changed files with 459 additions and 5608511 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/data/webp/groundtruth/docling_v2/webp-test.doctags.txt vendored
View File

@@ -1,2 +1,2 @@
<doctag><text><loc_59><loc_46><loc_424><loc_90>Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package</text>
<doctag><text><loc_58><loc_42><loc_426><loc_92>Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package</text>
</doctag>

8
tests/data/webp/groundtruth/docling_v2/webp-test.json vendored
View File

@@ -39,10 +39,10 @@
{
"page_no": 1,
"bbox": {
"l": 234.09,
"t": 2570.1,
"r": 1696.1,
"b": 2319.12,
"l": 233.67,
"t": 2589.67,
"r": 1703.0,
"b": 2310.67,
"coord_origin": "BOTTOMLEFT"
},
"charspan": [

186
tests/data/webp/groundtruth/docling_v2/webp-test.pages.json vendored
View File

@@ -12,13 +12,13 @@
"id": 0,
"label": "text",
"bbox": {
"l": 234.09,
"t": 258.9,
"r": 1696.1,
"b": 509.88,
"l": 233.67,
"t": 239.33,
"r": 1703.0,
"b": 518.33,
"coord_origin": "TOPLEFT"
},
"confidence": 0.972,
"confidence": 0.88,
"cells": [
{
"index": 0,
@@ -29,20 +29,20 @@
"a": 255
},
"rect": {
"r_x0": 246.41,
"r_y0": 329.07,
"r_x1": 1691.99,
"r_y1": 329.07,
"r_x2": 1691.99,
"r_y2": 258.9,
"r_x3": 246.41,
"r_y3": 258.9,
"r_x0": 234.67,
"r_y0": 336.67,
"r_x1": 1703.0,
"r_y1": 336.67,
"r_x2": 1703.0,
"r_y2": 239.33,
"r_x3": 234.67,
"r_y3": 239.33,
"coord_origin": "TOPLEFT"
},
"text": "Docling bundles PDF document conversion to",
"orig": "Docling bundles PDF document conversion to",
"text_direction": "left_to_right",
"confidence": 1.0,
"confidence": 0.751,
"from_ocr": true
},
{
@@ -54,20 +54,20 @@
"a": 255
},
"rect": {
"r_x0": 234.09,
"r_y0": 419.58,
"r_x1": 1696.1,
"r_y1": 419.58,
"r_x2": 1696.1,
"r_y2": 349.42,
"r_x3": 234.09,
"r_y3": 349.42,
"r_x0": 233.67,
"r_y0": 425.33,
"r_x1": 1702.0,
"r_y1": 425.33,
"r_x2": 1702.0,
"r_y2": 339.67,
"r_x3": 233.67,
"r_y3": 339.67,
"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": 1.0,
"confidence": 0.832,
"from_ocr": true
},
{
@@ -79,14 +79,14 @@
"a": 255
},
"rect": {
"r_x0": 242.3,
"r_y0": 509.88,
"r_x1": 513.35,
"r_y1": 509.88,
"r_x2": 513.35,
"r_y2": 439.98,
"r_x3": 242.3,
"r_y3": 439.98,
"r_x0": 235.0,
"r_y0": 518.33,
"r_x1": 518.33,
"r_y1": 518.33,
"r_x2": 518.33,
"r_y2": 430.0,
"r_x3": 235.0,
"r_y3": 430.0,
"coord_origin": "TOPLEFT"
},
"text": "package",
@@ -117,13 +117,13 @@
"id": 0,
"label": "text",
"bbox": {
"l": 234.09,
"t": 258.9,
"r": 1696.1,
"b": 509.88,
"l": 233.67,
"t": 239.33,
"r": 1703.0,
"b": 518.33,
"coord_origin": "TOPLEFT"
},
"confidence": 0.972,
"confidence": 0.88,
"cells": [
{
"index": 0,
@@ -134,20 +134,20 @@
"a": 255
},
"rect": {
"r_x0": 246.41,
"r_y0": 329.07,
"r_x1": 1691.99,
"r_y1": 329.07,
"r_x2": 1691.99,
"r_y2": 258.9,
"r_x3": 246.41,
"r_y3": 258.9,
"r_x0": 234.67,
"r_y0": 336.67,
"r_x1": 1703.0,
"r_y1": 336.67,
"r_x2": 1703.0,
"r_y2": 239.33,
"r_x3": 234.67,
"r_y3": 239.33,
"coord_origin": "TOPLEFT"
},
"text": "Docling bundles PDF document conversion to",
"orig": "Docling bundles PDF document conversion to",
"text_direction": "left_to_right",
"confidence": 1.0,
"confidence": 0.751,
"from_ocr": true
},
{
@@ -159,20 +159,20 @@
"a": 255
},
"rect": {
"r_x0": 234.09,
"r_y0": 419.58,
"r_x1": 1696.1,
"r_y1": 419.58,
"r_x2": 1696.1,
"r_y2": 349.42,
"r_x3": 234.09,
"r_y3": 349.42,
"r_x0": 233.67,
"r_y0": 425.33,
"r_x1": 1702.0,
"r_y1": 425.33,
"r_x2": 1702.0,
"r_y2": 339.67,
"r_x3": 233.67,
"r_y3": 339.67,
"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": 1.0,
"confidence": 0.832,
"from_ocr": true
},
{
@@ -184,14 +184,14 @@
"a": 255
},
"rect": {
"r_x0": 242.3,
"r_y0": 509.88,
"r_x1": 513.35,
"r_y1": 509.88,
"r_x2": 513.35,
"r_y2": 439.98,
"r_x3": 242.3,
"r_y3": 439.98,
"r_x0": 235.0,
"r_y0": 518.33,
"r_x1": 518.33,
"r_y1": 518.33,
"r_x2": 518.33,
"r_y2": 430.0,
"r_x3": 235.0,
"r_y3": 430.0,
"coord_origin": "TOPLEFT"
},
"text": "package",
@@ -215,13 +215,13 @@
"id": 0,
"label": "text",
"bbox": {
"l": 234.09,
"t": 258.9,
"r": 1696.1,
"b": 509.88,
"l": 233.67,
"t": 239.33,
"r": 1703.0,
"b": 518.33,
"coord_origin": "TOPLEFT"
},
"confidence": 0.972,
"confidence": 0.88,
"cells": [
{
"index": 0,
@@ -232,20 +232,20 @@
"a": 255
},
"rect": {
"r_x0": 246.41,
"r_y0": 329.07,
"r_x1": 1691.99,
"r_y1": 329.07,
"r_x2": 1691.99,
"r_y2": 258.9,
"r_x3": 246.41,
"r_y3": 258.9,
"r_x0": 234.67,
"r_y0": 336.67,
"r_x1": 1703.0,
"r_y1": 336.67,
"r_x2": 1703.0,
"r_y2": 239.33,
"r_x3": 234.67,
"r_y3": 239.33,
"coord_origin": "TOPLEFT"
},
"text": "Docling bundles PDF document conversion to",
"orig": "Docling bundles PDF document conversion to",
"text_direction": "left_to_right",
"confidence": 1.0,
"confidence": 0.751,
"from_ocr": true
},
{
@@ -257,20 +257,20 @@
"a": 255
},
"rect": {
"r_x0": 234.09,
"r_y0": 419.58,
"r_x1": 1696.1,
"r_y1": 419.58,
"r_x2": 1696.1,
"r_y2": 349.42,
"r_x3": 234.09,
"r_y3": 349.42,
"r_x0": 233.67,
"r_y0": 425.33,
"r_x1": 1702.0,
"r_y1": 425.33,
"r_x2": 1702.0,
"r_y2": 339.67,
"r_x3": 233.67,
"r_y3": 339.67,
"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": 1.0,
"confidence": 0.832,
"from_ocr": true
},
{
@@ -282,14 +282,14 @@
"a": 255
},
"rect": {
"r_x0": 242.3,
"r_y0": 509.88,
"r_x1": 513.35,
"r_y1": 509.88,
"r_x2": 513.35,
"r_y2": 439.98,
"r_x3": 242.3,
"r_y3": 439.98,
"r_x0": 235.0,
"r_y0": 518.33,
"r_x1": 518.33,
"r_y1": 518.33,
"r_x2": 518.33,
"r_y2": 430.0,
"r_x3": 235.0,
"r_y3": 430.0,
"coord_origin": "TOPLEFT"
},
"text": "package",