mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-26 20:14:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

One more test fix

Browse Source 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer 2025-06-13 16:01:26 +02:00
parent d99080e036
commit 1c39dc93ab
1 changed files with 148 additions and 73 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

221
tests/data/webp/groundtruth/docling_v2/webp-test.pages.json vendored
View File

@ -5,84 +5,159 @@
"width": 2000.0, "width": 2000.0,
"height": 2829.0 "height": 2829.0
}, },
"cells": [ "parsed_page": {
{ "dimension": {
"index": 0, "angle": 0.0,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": { "rect": {
"r_x0": 246.4065456254215, "r_x0": 0.0,
"r_y0": 329.06770715202435, "r_y0": 0.0,
"r_x1": 1691.991797818404, "r_x1": 2000.0,
"r_y1": 329.06770715202435, "r_y1": 0.0,
"r_x2": 1691.991797818404, "r_x2": 2000.0,
"r_y2": 258.9040166758338, "r_y2": 2829.0,
"r_x3": 246.4065456254215, "r_x3": 0.0,
"r_y3": 258.9040166758338, "r_y3": 2829.0,
"coord_origin": "TOPLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"text": "Docling bundles PDF document conversion to", "boundary_type": "crop_box",
"orig": "Docling bundles PDF document conversion to", "art_bbox": {
"text_direction": "left_to_right", "l": 0.0,
"confidence": 1.0, "t": 2829.0,
"from_ocr": true "r": 2000.0,
"b": 0.0,
"coord_origin": "BOTTOMLEFT"
},
"bleed_bbox": {
"l": 0.0,
"t": 2829.0,
"r": 2000.0,
"b": 0.0,
"coord_origin": "BOTTOMLEFT"
},
"crop_bbox": {
"l": 0.0,
"t": 2829.0,
"r": 2000.0,
"b": 0.0,
"coord_origin": "BOTTOMLEFT"
},
"media_bbox": {
"l": 0.0,
"t": 2829.0,
"r": 2000.0,
"b": 0.0,
"coord_origin": "BOTTOMLEFT"
},
"trim_bbox": {
"l": 0.0,
"t": 2829.0,
"r": 2000.0,
"b": 0.0,
"coord_origin": "BOTTOMLEFT"
}
}, },
{ "bitmap_resources": [
"index": 1, {
"rgba": { "index": 0,
"r": 0, "rect": {
"g": 0, "r_x0": 0.0,
"b": 0, "r_y0": 0.0,
"a": 255 "r_x1": 2000.0,
"r_y1": 0.0,
"r_x2": 2000.0,
"r_y2": 2829.0,
"r_x3": 0.0,
"r_y3": 2829.0,
"coord_origin": "BOTTOMLEFT"
},
"uri": null
}
],
"char_cells": [],
"word_cells": [],
"textline_cells": [
{
"index": 0,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 246.4065456254215,
"r_y0": 329.06770715202435,
"r_x1": 1691.991797818404,
"r_y1": 329.06770715202435,
"r_x2": 1691.991797818404,
"r_y2": 258.9040166758338,
"r_x3": 246.4065456254215,
"r_y3": 258.9040166758338,
"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,
"from_ocr": true
}, },
"rect": { {
"r_x0": 234.08627147881114, "index": 1,
"r_y0": 419.5788697734327, "rgba": {
"r_x1": 1696.0985042090742, "r": 0,
"r_y1": 419.5788697734327, "g": 0,
"r_x2": 1696.0985042090742, "b": 0,
"r_y2": 349.4151792972422, "a": 255
"r_x3": 234.08627147881114, },
"r_y3": 349.4151792972422, "rect": {
"coord_origin": "TOPLEFT" "r_x0": 234.08627147881114,
"r_y0": 419.5788697734327,
"r_x1": 1696.0985042090742,
"r_y1": 419.5788697734327,
"r_x2": 1696.0985042090742,
"r_y2": 349.4151792972422,
"r_x3": 234.08627147881114,
"r_y3": 349.4151792972422,
"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,
"from_ocr": true
}, },
"text": "JSON and Markdown in an easy self contained", {
"orig": "JSON and Markdown in an easy self contained", "index": 2,
"text_direction": "left_to_right", "rgba": {
"confidence": 1.0, "r": 0,
"from_ocr": true "g": 0,
}, "b": 0,
{ "a": 255
"index": 2, },
"rgba": { "rect": {
"r": 0, "r_x0": 242.29979922858777,
"g": 0, "r_y0": 509.8779072023336,
"b": 0, "r_x1": 513.3470125989277,
"a": 255 "r_y1": 509.8779072023336,
}, "r_x2": 513.3470125989277,
"rect": { "r_y2": 439.9752910477536,
"r_x0": 242.29979922858777, "r_x3": 242.29979922858777,
"r_y0": 509.8779072023336, "r_y3": 439.9752910477536,
"r_x1": 513.3470125989277, "coord_origin": "TOPLEFT"
"r_y1": 509.8779072023336, },
"r_x2": 513.3470125989277, "text": "package",
"r_y2": 439.9752910477536, "orig": "package",
"r_x3": 242.29979922858777, "text_direction": "left_to_right",
"r_y3": 439.9752910477536, "confidence": 1.0,
"coord_origin": "TOPLEFT" "from_ocr": true
}, }
"text": "package", ],
"orig": "package", "has_chars": false,
"text_direction": "left_to_right", "has_words": false,
"confidence": 1.0, "has_lines": true,
"from_ocr": true "image": null,
} "lines": []
], },
"parsed_page": null,
"predictions": { "predictions": {
"layout": { "layout": {
"clusters": [ "clusters": [