
* Keep page.parsed_page.textline_cells and page.cells in sync, including OCR Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Make page.parsed_page the only source of truth for text cells Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Small fix Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Correctly compute PDF boxes from pymupdf Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Use different OCR engine order Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Add type hints and fix mypy Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * One more test fix Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Remove with pypdfium2_lock from caller sites Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Fix typing Signed-off-by: Christoph Auer <cau@zurich.ibm.com> --------- Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
463 lines
14 KiB
JSON
Vendored
463 lines
14 KiB
JSON
Vendored
[
|
|
{
|
|
"page_no": 0,
|
|
"size": {
|
|
"width": 2000.0,
|
|
"height": 2829.0
|
|
},
|
|
"parsed_page": {
|
|
"dimension": {
|
|
"angle": 0.0,
|
|
"rect": {
|
|
"r_x0": 0.0,
|
|
"r_y0": 0.0,
|
|
"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"
|
|
},
|
|
"boundary_type": "crop_box",
|
|
"art_bbox": {
|
|
"l": 0.0,
|
|
"t": 2829.0,
|
|
"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": 0,
|
|
"rect": {
|
|
"r_x0": 0.0,
|
|
"r_y0": 0.0,
|
|
"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
|
|
},
|
|
{
|
|
"index": 1,
|
|
"rgba": {
|
|
"r": 0,
|
|
"g": 0,
|
|
"b": 0,
|
|
"a": 255
|
|
},
|
|
"rect": {
|
|
"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
|
|
},
|
|
{
|
|
"index": 2,
|
|
"rgba": {
|
|
"r": 0,
|
|
"g": 0,
|
|
"b": 0,
|
|
"a": 255
|
|
},
|
|
"rect": {
|
|
"r_x0": 242.29979922858777,
|
|
"r_y0": 509.8779072023336,
|
|
"r_x1": 513.3470125989277,
|
|
"r_y1": 509.8779072023336,
|
|
"r_x2": 513.3470125989277,
|
|
"r_y2": 439.9752910477536,
|
|
"r_x3": 242.29979922858777,
|
|
"r_y3": 439.9752910477536,
|
|
"coord_origin": "TOPLEFT"
|
|
},
|
|
"text": "package",
|
|
"orig": "package",
|
|
"text_direction": "left_to_right",
|
|
"confidence": 1.0,
|
|
"from_ocr": true
|
|
}
|
|
],
|
|
"has_chars": false,
|
|
"has_words": false,
|
|
"has_lines": true,
|
|
"image": null,
|
|
"lines": []
|
|
},
|
|
"predictions": {
|
|
"layout": {
|
|
"clusters": [
|
|
{
|
|
"id": 0,
|
|
"label": "text",
|
|
"bbox": {
|
|
"l": 234.08627147881114,
|
|
"t": 258.9040166758338,
|
|
"r": 1696.0985042090742,
|
|
"b": 509.8779072023336,
|
|
"coord_origin": "TOPLEFT"
|
|
},
|
|
"confidence": 0.9721011519432068,
|
|
"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
|
|
},
|
|
{
|
|
"index": 1,
|
|
"rgba": {
|
|
"r": 0,
|
|
"g": 0,
|
|
"b": 0,
|
|
"a": 255
|
|
},
|
|
"rect": {
|
|
"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
|
|
},
|
|
{
|
|
"index": 2,
|
|
"rgba": {
|
|
"r": 0,
|
|
"g": 0,
|
|
"b": 0,
|
|
"a": 255
|
|
},
|
|
"rect": {
|
|
"r_x0": 242.29979922858777,
|
|
"r_y0": 509.8779072023336,
|
|
"r_x1": 513.3470125989277,
|
|
"r_y1": 509.8779072023336,
|
|
"r_x2": 513.3470125989277,
|
|
"r_y2": 439.9752910477536,
|
|
"r_x3": 242.29979922858777,
|
|
"r_y3": 439.9752910477536,
|
|
"coord_origin": "TOPLEFT"
|
|
},
|
|
"text": "package",
|
|
"orig": "package",
|
|
"text_direction": "left_to_right",
|
|
"confidence": 1.0,
|
|
"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": 234.08627147881114,
|
|
"t": 258.9040166758338,
|
|
"r": 1696.0985042090742,
|
|
"b": 509.8779072023336,
|
|
"coord_origin": "TOPLEFT"
|
|
},
|
|
"confidence": 0.9721011519432068,
|
|
"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
|
|
},
|
|
{
|
|
"index": 1,
|
|
"rgba": {
|
|
"r": 0,
|
|
"g": 0,
|
|
"b": 0,
|
|
"a": 255
|
|
},
|
|
"rect": {
|
|
"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
|
|
},
|
|
{
|
|
"index": 2,
|
|
"rgba": {
|
|
"r": 0,
|
|
"g": 0,
|
|
"b": 0,
|
|
"a": 255
|
|
},
|
|
"rect": {
|
|
"r_x0": 242.29979922858777,
|
|
"r_y0": 509.8779072023336,
|
|
"r_x1": 513.3470125989277,
|
|
"r_y1": 509.8779072023336,
|
|
"r_x2": 513.3470125989277,
|
|
"r_y2": 439.9752910477536,
|
|
"r_x3": 242.29979922858777,
|
|
"r_y3": 439.9752910477536,
|
|
"coord_origin": "TOPLEFT"
|
|
},
|
|
"text": "package",
|
|
"orig": "package",
|
|
"text_direction": "left_to_right",
|
|
"confidence": 1.0,
|
|
"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": 234.08627147881114,
|
|
"t": 258.9040166758338,
|
|
"r": 1696.0985042090742,
|
|
"b": 509.8779072023336,
|
|
"coord_origin": "TOPLEFT"
|
|
},
|
|
"confidence": 0.9721011519432068,
|
|
"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
|
|
},
|
|
{
|
|
"index": 1,
|
|
"rgba": {
|
|
"r": 0,
|
|
"g": 0,
|
|
"b": 0,
|
|
"a": 255
|
|
},
|
|
"rect": {
|
|
"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
|
|
},
|
|
{
|
|
"index": 2,
|
|
"rgba": {
|
|
"r": 0,
|
|
"g": 0,
|
|
"b": 0,
|
|
"a": 255
|
|
},
|
|
"rect": {
|
|
"r_x0": 242.29979922858777,
|
|
"r_y0": 509.8779072023336,
|
|
"r_x1": 513.3470125989277,
|
|
"r_y1": 509.8779072023336,
|
|
"r_x2": 513.3470125989277,
|
|
"r_y2": 439.9752910477536,
|
|
"r_x3": 242.29979922858777,
|
|
"r_y3": 439.9752910477536,
|
|
"coord_origin": "TOPLEFT"
|
|
},
|
|
"text": "package",
|
|
"orig": "package",
|
|
"text_direction": "left_to_right",
|
|
"confidence": 1.0,
|
|
"from_ocr": true
|
|
}
|
|
],
|
|
"children": []
|
|
},
|
|
"text": "Docling bundles PDF document conversion to JSON and Markdown in an easy self contained package"
|
|
}
|
|
],
|
|
"headers": []
|
|
}
|
|
}
|
|
] |