mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-10 05:38:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: Make Page.parsed_page the only source of truth for text cells, add OCR cells to it (#1745)

Browse Source 
* 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>
This commit is contained in:
Christoph Auer
2025-06-13 19:01:55 +02:00
committed by GitHub
parent 0432a31b2f
commit 7d3302cb48
50 changed files with 339091 additions and 330047 deletions
Download Patch File Download Diff File Expand all files Collapse all files

205
tests/data_scanned/groundtruth/docling_v2/ocr_test.pages.json vendored
View File

@@ -5,84 +5,143 @@
"width": 595.201171875,
"height": 841.9216918945312
},
"cells": [
{
"index": 0,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"parsed_page": {
"dimension": {
"angle": 0.0,
"rect": {
"r_x0": 73.34702132031646,
"r_y0": 97.99999977896755,
"r_x1": 503.64955224479564,
"r_y1": 97.99999977896755,
"r_x2": 503.64955224479564,
"r_y2": 76.99999977896756,
"r_x3": 73.34702132031646,
"r_y3": 76.99999977896756,
"coord_origin": "TOPLEFT"
"r_x0": 0.0,
"r_y0": 0.0,
"r_x1": 595.201171875,
"r_y1": 0.0,
"r_x2": 595.201171875,
"r_y2": 841.9216918945312,
"r_x3": 0.0,
"r_y3": 841.9216918945312,
"coord_origin": "BOTTOMLEFT"
},
"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
"boundary_type": "crop_box",
"art_bbox": {
"l": 0.0,
"t": 841.9216918945312,
"r": 595.201171875,
"b": 0.0,
"coord_origin": "BOTTOMLEFT"
},
"bleed_bbox": {
"l": 0.0,
"t": 841.9216918945312,
"r": 595.201171875,
"b": 0.0,
"coord_origin": "BOTTOMLEFT"
},
"crop_bbox": {
"l": 0.0,
"t": 841.9216918945312,
"r": 595.201171875,
"b": 0.0,
"coord_origin": "BOTTOMLEFT"
},
"media_bbox": {
"l": 0.0,
"t": 841.9216918945312,
"r": 595.201171875,
"b": 0.0,
"coord_origin": "BOTTOMLEFT"
},
"trim_bbox": {
"l": 0.0,
"t": 841.9216918945312,
"r": 595.201171875,
"b": 0.0,
"coord_origin": "BOTTOMLEFT"
}
},
{
"index": 1,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
"bitmap_resources": [],
"char_cells": [],
"word_cells": [],
"textline_cells": [
{
"index": 0,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 73.34702132031646,
"r_y0": 97.99999977896755,
"r_x1": 503.64955224479564,
"r_y1": 97.99999977896755,
"r_x2": 503.64955224479564,
"r_y2": 76.99999977896756,
"r_x3": 73.34702132031646,
"r_y3": 76.99999977896756,
"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": 69.6796630536824,
"r_y0": 124.83139494707741,
"r_x1": 504.8720051760782,
"r_y1": 124.83139494707741,
"r_x2": 504.8720051760782,
"r_y2": 104.00000011573796,
"r_x3": 69.6796630536824,
"r_y3": 104.00000011573796,
"coord_origin": "TOPLEFT"
{
"index": 1,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 69.6796630536824,
"r_y0": 124.83139494707741,
"r_x1": 504.8720051760782,
"r_y1": 124.83139494707741,
"r_x2": 504.8720051760782,
"r_y2": 104.00000011573796,
"r_x3": 69.6796630536824,
"r_y3": 104.00000011573796,
"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",
"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": 71.84193505100733,
"r_y0": 152.90926970226084,
"r_x1": 153.088934155825,
"r_y1": 152.90926970226084,
"r_x2": 153.088934155825,
"r_y2": 129.797125232046,
"r_x3": 71.84193505100733,
"r_y3": 129.797125232046,
"coord_origin": "TOPLEFT"
},
"text": "package",
"orig": "package",
"text_direction": "left_to_right",
"confidence": 1.0,
"from_ocr": true
}
],
"parsed_page": null,
{
"index": 2,
"rgba": {
"r": 0,
"g": 0,
"b": 0,
"a": 255
},
"rect": {
"r_x0": 71.84193505100733,
"r_y0": 152.90926970226084,
"r_x1": 153.088934155825,
"r_y1": 152.90926970226084,
"r_x2": 153.088934155825,
"r_y2": 129.797125232046,
"r_x3": 71.84193505100733,
"r_y3": 129.797125232046,
"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": [