NeoAnd/Docling
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(ocr): auto-detect rotated pages in Tesseract (#1167)

Browse Source 
* fix(ocr): tesseract support mis-oriented documents

Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>

* fix(ocr): update missing test data

Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>

* fix(ocr): rotate image to the natural orientation before layout prediction

Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>

* fix(ocr): move bounding bow rotation util to orientation.py

Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>

* fix(ocr): refactor rotation utilities

Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>

* chore(ocr): revert layout updates

Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>

* chore(ocr): update e2e OCR test data

Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>

* fix(ocr): avoid to swallow tesseract errors causing orientation detection failures

Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>

* chore(ocr): revert layout updates

Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>

* chore(ocr): update e2e OCR test data

* chore(ocr): proceed to OCR without rotation when OSD fails in `TesseractOcrCliModel`

* chore(ocr): proceed to OCR without rotation when OSD fails in `TesseractOcrModel`

* chore(ocr): default `TesseractOcrCliModel._is_auto` to `False`

* fix(ocr): fix `TesseractOcrCliModel._is_auto` computation

* chore(ocr): improve logging in case of OSD failure in `TesseractOcrCliModel` and `TesseractOcrModel`

---------

Signed-off-by: Clément Doumouro <clement.doumouro@gmail.com>
This commit is contained in:
Clément Doumouro
2025-05-21 18:12:33 +02:00
committed by GitHub
parent 90875247e5
commit 45265bf8b1
96 changed files with 9864 additions and 5258 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/data/groundtruth/docling_v1/2203.01017v2.json
+55 -55
View File
@@ -4913,9 +4913,9 @@
{
"bbox": [
315.65362548828125,
489.19854736328125,
489.1985778808594,
537.1475219726562,
563.2765655517578
563.276611328125
],
"page": 1,
"span": [
@@ -4979,9 +4979,9 @@
{
"bbox": [
312.10369873046875,
541.3901214599609,
541.3901519775391,
550.38916015625,
713.5591125488281
713.5591354370117
],
"page": 3,
"span": [
@@ -5003,7 +5003,7 @@
74.30525970458984,
608.2984924316406,
519.9801025390625,
714.0887908935547
714.0887985229492
],
"page": 5,
"span": [
@@ -5024,7 +5024,7 @@
"bbox": [
53.03328323364258,
284.3311462402344,
285.3731384277344,
285.3731689453125,
534.3346557617188
],
"page": 5,
@@ -5047,7 +5047,7 @@
49.97503662109375,
604.4210662841797,
301.6335754394531,
688.2873153686523
688.2873382568359
],
"page": 8,
"span": [
@@ -5066,7 +5066,7 @@
"prov": [
{
"bbox": [
305.58367919921875,
305.5836486816406,
611.3732452392578,
554.8258666992188,
693.3458404541016
@@ -5111,9 +5111,9 @@
{
"bbox": [
216.76925659179688,
348.6529541015625,
348.65301513671875,
375.7829284667969,
411.5093994140625
411.5093688964844
],
"page": 8,
"span": [
@@ -5132,10 +5132,10 @@
"prov": [
{
"bbox": [
383.1363830566406,
383.1364440917969,
349.2250671386719,
542.1131591796875,
410.7687072753906
542.1132202148438,
410.7686767578125
],
"page": 8,
"span": [
@@ -5220,7 +5220,7 @@
"prov": [
{
"bbox": [
51.153778076171875,
51.15378952026367,
447.09332275390625,
282.8598937988281,
687.6914825439453
@@ -5286,8 +5286,8 @@
"prov": [
{
"bbox": [
55.11635208129883,
542.6654968261719,
55.116363525390625,
542.6654510498047,
279.370849609375,
655.7449951171875
],
@@ -5375,9 +5375,9 @@
{
"bbox": [
323.46868896484375,
327.73956298828125,
327.739501953125,
525.9569091796875,
429.5492248535156
429.5491638183594
],
"page": 15,
"span": [
@@ -5421,7 +5421,7 @@
66.79948425292969,
293.8616027832031,
528.5565795898438,
538.3837127685547
538.3836822509766
],
"page": 16,
"span": [
@@ -5443,9 +5443,9 @@
{
"bbox": [
315.65362548828125,
489.19854736328125,
489.1985778808594,
537.1475219726562,
563.2765655517578
563.276611328125
],
"page": 1,
"span": [
@@ -6250,10 +6250,10 @@
"prov": [
{
"bbox": [
310.6757507324219,
310.67584228515625,
636.7794799804688,
542.9546508789062,
718.8061218261719
542.9547119140625,
718.8061141967773
],
"page": 4,
"span": [
@@ -9329,7 +9329,7 @@
332.9688720703125,
148.73028564453125,
520.942138671875,
251.71649169921875
251.7164306640625
],
"page": 7,
"span": [
@@ -10152,9 +10152,9 @@
{
"bbox": [
53.62853240966797,
499.6000061035156,
499.60003662109375,
298.5574951171875,
573.0514526367188
573.0514221191406
],
"page": 8,
"span": [
@@ -12941,7 +12941,7 @@
"prov": [
{
"bbox": [
83.31759643554688,
83.31756591796875,
304.7430114746094,
248.873046875,
395.9864501953125
@@ -12968,9 +12968,9 @@
{
"bbox": [
310.3294372558594,
655.8524932861328,
655.8524780273438,
555.8338623046875,
690.8223342895508
690.8223266601562
],
"page": 13,
"span": [
@@ -12994,9 +12994,9 @@
{
"bbox": [
309.9566345214844,
607.2774353027344,
607.2774658203125,
555.7466430664062,
637.3854827880859
637.3855133056641
],
"page": 13,
"span": [
@@ -13019,10 +13019,10 @@
"prov": [
{
"bbox": [
309.96356201171875,
558.4485168457031,
555.7053833007812,
596.2945098876953
309.9635314941406,
558.4485473632812,
555.7054443359375,
596.2945861816406
],
"page": 13,
"span": [
@@ -13175,10 +13175,10 @@
"prov": [
{
"bbox": [
51.726383209228516,
447.7555236816406,
283.1140441894531,
518.3907470703125
51.72642135620117,
447.7554931640625,
283.114013671875,
518.3907165527344
],
"page": 14,
"span": [
@@ -13201,7 +13201,7 @@
"prov": [
{
"bbox": [
51.43488693237305,
51.434879302978516,
300.17974853515625,
310.7267150878906,
338.51251220703125
@@ -13253,7 +13253,7 @@
"prov": [
{
"bbox": [
51.2728271484375,
51.27280807495117,
200.086669921875,
311.0897216796875,
238.271484375
@@ -13435,10 +13435,10 @@
"prov": [
{
"bbox": [
319.0649719238281,
319.06494140625,
122.80792236328125,
533.7738647460938,
182.1590576171875
533.77392578125,
182.1591796875
],
"page": 14,
"span": [
@@ -13461,8 +13461,8 @@
"prov": [
{
"bbox": [
55.11635208129883,
542.6654968261719,
55.116363525390625,
542.6654510498047,
279.370849609375,
655.7449951171875
],
@@ -13513,10 +13513,10 @@
"prov": [
{
"bbox": [
323.0059814453125,
569.0885772705078,
525.9517211914062,
670.4528656005859
323.0059509277344,
569.0885925292969,
525.95166015625,
670.4528503417969
],
"page": 15,
"span": [
@@ -13540,9 +13540,9 @@
{
"bbox": [
323.384765625,
447.9078674316406,
447.90789794921875,
526.1268920898438,
550.0270690917969
550.0270538330078
],
"page": 15,
"span": [
@@ -13566,9 +13566,9 @@
{
"bbox": [
323.46868896484375,
327.73956298828125,
327.739501953125,
525.9569091796875,
429.5492248535156
429.5491638183594
],
"page": 15,
"span": [
tests/data/groundtruth/docling_v1/2203.01017v2.pages.json
+830 -830
View File
File diff suppressed because it is too large Load Diff
tests/data/groundtruth/docling_v1/2206.01062.json
+16 -16
View File
@@ -3099,9 +3099,9 @@
"prov": [
{
"bbox": [
323.4081115722656,
266.14935302734375,
553.295166015625,
323.408203125,
266.1492919921875,
553.2952270507812,
541.6512603759766
],
"page": 1,
@@ -3122,9 +3122,9 @@
{
"bbox": [
88.33030700683594,
571.4317626953125,
571.4317321777344,
263.7049560546875,
699.1134490966797
699.1134796142578
],
"page": 3,
"span": [
@@ -3144,9 +3144,9 @@
{
"bbox": [
53.05912780761719,
251.1358642578125,
251.135986328125,
295.8506164550781,
481.20867919921875
481.2087097167969
],
"page": 4,
"span": [
@@ -3234,9 +3234,9 @@
{
"bbox": [
98.93103790283203,
497.91845703125,
497.91851806640625,
512.579833984375,
654.5244903564453
654.5245208740234
],
"page": 4,
"span": [
@@ -8153,7 +8153,7 @@
62.02753829956055,
440.3381042480469,
285.78955078125,
596.3199462890625
596.3199310302734
],
"page": 6,
"span": [
@@ -10514,9 +10514,9 @@
"prov": [
{
"bbox": [
80.35527038574219,
80.35525512695312,
496.5545349121094,
267.00823974609375,
267.0082092285156,
641.0637054443359
],
"page": 7,
@@ -14214,10 +14214,10 @@
"prov": [
{
"bbox": [
72.65901947021484,
452.14599609375,
274.8346862792969,
619.5191650390625
72.6590347290039,
452.1459655761719,
274.83465576171875,
619.5191955566406
],
"page": 8,
"span": [
tests/data/groundtruth/docling_v1/2206.01062.pages.json
+325 -325
View File
File diff suppressed because it is too large Load Diff
tests/data/groundtruth/docling_v1/2305.03393v1-pg9.json
+2 -2
View File
@@ -213,9 +213,9 @@
"prov": [
{
"bbox": [
139.6674041748047,
139.66746520996094,
322.5054626464844,
475.00927734375,
475.0093078613281,
454.4546203613281
],
"page": 1,
tests/data/groundtruth/docling_v1/2305.03393v1-pg9.pages.json
+26 -26
View File
@@ -2646,7 +2646,7 @@
"b": 102.78223000000003,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9373533129692078,
"confidence": 0.9373531937599182,
"cells": [
{
"index": 0,
@@ -2686,7 +2686,7 @@
"b": 102.78223000000003,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8858681321144104,
"confidence": 0.8858677744865417,
"cells": [
{
"index": 1,
@@ -2816,7 +2816,7 @@
"b": 179.20818999999995,
"coord_origin": "TOPLEFT"
},
"confidence": 0.957740306854248,
"confidence": 0.9577404260635376,
"cells": [
{
"index": 5,
@@ -2881,7 +2881,7 @@
"b": 255.42400999999995,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9850425124168396,
"confidence": 0.98504239320755,
"cells": [
{
"index": 7,
@@ -3096,7 +3096,7 @@
"b": 327.98218,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9591907262802124,
"confidence": 0.9591910243034363,
"cells": [
{
"index": 15,
@@ -3280,9 +3280,9 @@
"id": 0,
"label": "table",
"bbox": {
"l": 139.6674041748047,
"l": 139.66746520996094,
"t": 337.5453796386719,
"r": 475.00927734375,
"r": 475.0093078613281,
"b": 469.4945373535156,
"coord_origin": "TOPLEFT"
},
@@ -7852,7 +7852,7 @@
"b": 618.3,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9849976301193237,
"confidence": 0.9849975109100342,
"cells": [
{
"index": 93,
@@ -8184,9 +8184,9 @@
"id": 0,
"label": "table",
"bbox": {
"l": 139.6674041748047,
"l": 139.66746520996094,
"t": 337.5453796386719,
"r": 475.00927734375,
"r": 475.0093078613281,
"b": 469.4945373535156,
"coord_origin": "TOPLEFT"
},
@@ -13582,7 +13582,7 @@
"b": 102.78223000000003,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9373533129692078,
"confidence": 0.9373531937599182,
"cells": [
{
"index": 0,
@@ -13628,7 +13628,7 @@
"b": 102.78223000000003,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8858681321144104,
"confidence": 0.8858677744865417,
"cells": [
{
"index": 1,
@@ -13770,7 +13770,7 @@
"b": 179.20818999999995,
"coord_origin": "TOPLEFT"
},
"confidence": 0.957740306854248,
"confidence": 0.9577404260635376,
"cells": [
{
"index": 5,
@@ -13841,7 +13841,7 @@
"b": 255.42400999999995,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9850425124168396,
"confidence": 0.98504239320755,
"cells": [
{
"index": 7,
@@ -14062,7 +14062,7 @@
"b": 327.98218,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9591907262802124,
"confidence": 0.9591910243034363,
"cells": [
{
"index": 15,
@@ -14252,9 +14252,9 @@
"id": 0,
"label": "table",
"bbox": {
"l": 139.6674041748047,
"l": 139.66746520996094,
"t": 337.5453796386719,
"r": 475.00927734375,
"r": 475.0093078613281,
"b": 469.4945373535156,
"coord_origin": "TOPLEFT"
},
@@ -19713,7 +19713,7 @@
"b": 618.3,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9849976301193237,
"confidence": 0.9849975109100342,
"cells": [
{
"index": 93,
@@ -20153,7 +20153,7 @@
"b": 179.20818999999995,
"coord_origin": "TOPLEFT"
},
"confidence": 0.957740306854248,
"confidence": 0.9577404260635376,
"cells": [
{
"index": 5,
@@ -20224,7 +20224,7 @@
"b": 255.42400999999995,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9850425124168396,
"confidence": 0.98504239320755,
"cells": [
{
"index": 7,
@@ -20445,7 +20445,7 @@
"b": 327.98218,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9591907262802124,
"confidence": 0.9591910243034363,
"cells": [
{
"index": 15,
@@ -20635,9 +20635,9 @@
"id": 0,
"label": "table",
"bbox": {
"l": 139.6674041748047,
"l": 139.66746520996094,
"t": 337.5453796386719,
"r": 475.00927734375,
"r": 475.0093078613281,
"b": 469.4945373535156,
"coord_origin": "TOPLEFT"
},
@@ -26096,7 +26096,7 @@
"b": 618.3,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9849976301193237,
"confidence": 0.9849975109100342,
"cells": [
{
"index": 93,
@@ -26440,7 +26440,7 @@
"b": 102.78223000000003,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9373533129692078,
"confidence": 0.9373531937599182,
"cells": [
{
"index": 0,
@@ -26486,7 +26486,7 @@
"b": 102.78223000000003,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8858681321144104,
"confidence": 0.8858677744865417,
"cells": [
{
"index": 1,
tests/data/groundtruth/docling_v1/2305.03393v1.json
+12 -12
View File
@@ -2498,9 +2498,9 @@
{
"bbox": [
148.45364379882812,
366.1538391113281,
366.1537780761719,
464.3608093261719,
583.6257476806641
583.6257629394531
],
"page": 2,
"span": [
@@ -2541,9 +2541,9 @@
"prov": [
{
"bbox": [
164.6503143310547,
164.65028381347656,
511.6590576171875,
449.550537109375,
449.5505676269531,
628.2029113769531
],
"page": 7,
@@ -2563,7 +2563,7 @@
"prov": [
{
"bbox": [
140.70960998535156,
140.70968627929688,
198.32281494140625,
472.73382568359375,
283.9361572265625
@@ -2585,10 +2585,10 @@
"prov": [
{
"bbox": [
162.67434692382812,
128.786376953125,
451.70068359375,
347.3774719238281
162.67430114746094,
128.78643798828125,
451.70062255859375,
347.37744140625
],
"page": 10,
"span": [
@@ -2607,9 +2607,9 @@
"prov": [
{
"bbox": [
168.3928985595703,
168.39285278320312,
157.99432373046875,
447.3513488769531,
447.35137939453125,
610.0334930419922
],
"page": 11,
@@ -4065,7 +4065,7 @@
143.6376495361328,
528.7375183105469,
470.8485412597656,
635.6522827148438
635.6522979736328
],
"page": 10,
"span": [
tests/data/groundtruth/docling_v1/2305.03393v1.pages.json
+286 -286
View File
File diff suppressed because it is too large Load Diff
tests/data/groundtruth/docling_v1/amt_handbook_sample.json
+1 -1
View File
@@ -426,7 +426,7 @@
320.4467468261719,
81.689208984375,
558.8576049804688,
352.3592834472656
352.359375
],
"page": 1,
"span": [
tests/data/groundtruth/docling_v1/amt_handbook_sample.pages.json
+27 -27
View File
@@ -3411,7 +3411,7 @@
"b": 519.65363,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9695364832878113,
"confidence": 0.9695363640785217,
"cells": [
{
"index": 34,
@@ -4081,7 +4081,7 @@
"b": 142.65363000000002,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9263732433319092,
"confidence": 0.9263731241226196,
"cells": [
{
"index": 59,
@@ -4611,7 +4611,7 @@
"b": 382.15362999999996,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9253151416778564,
"confidence": 0.9253152012825012,
"cells": [
{
"index": 79,
@@ -4651,7 +4651,7 @@
"b": 409.15362999999996,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9676452875137329,
"confidence": 0.9676451683044434,
"cells": [
{
"index": 80,
@@ -4711,12 +4711,12 @@
"label": "picture",
"bbox": {
"l": 320.4467468261719,
"t": 421.6407165527344,
"t": 421.640625,
"r": 558.8576049804688,
"b": 692.310791015625,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9881085753440857,
"confidence": 0.9881086945533752,
"cells": [
{
"index": 82,
@@ -5463,7 +5463,7 @@
"b": 713.009598,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9449449777603149,
"confidence": 0.9449448585510254,
"cells": [
{
"index": 93,
@@ -5528,7 +5528,7 @@
"b": 710.989597,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9497623443603516,
"confidence": 0.9497622847557068,
"cells": [
{
"index": 95,
@@ -5593,7 +5593,7 @@
"b": 740.290298,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9368569850921631,
"confidence": 0.9368568658828735,
"cells": [
{
"index": 97,
@@ -6624,7 +6624,7 @@
"b": 519.65363,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9695364832878113,
"confidence": 0.9695363640785217,
"cells": [
{
"index": 34,
@@ -7312,7 +7312,7 @@
"b": 142.65363000000002,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9263732433319092,
"confidence": 0.9263731241226196,
"cells": [
{
"index": 59,
@@ -7854,7 +7854,7 @@
"b": 382.15362999999996,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9253151416778564,
"confidence": 0.9253152012825012,
"cells": [
{
"index": 79,
@@ -7900,7 +7900,7 @@
"b": 409.15362999999996,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9676452875137329,
"confidence": 0.9676451683044434,
"cells": [
{
"index": 80,
@@ -7966,12 +7966,12 @@
"label": "picture",
"bbox": {
"l": 320.4467468261719,
"t": 421.6407165527344,
"t": 421.640625,
"r": 558.8576049804688,
"b": 692.310791015625,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9881085753440857,
"confidence": 0.9881086945533752,
"cells": [
{
"index": 82,
@@ -8738,7 +8738,7 @@
"b": 713.009598,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9449449777603149,
"confidence": 0.9449448585510254,
"cells": [
{
"index": 93,
@@ -8809,7 +8809,7 @@
"b": 710.989597,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9497623443603516,
"confidence": 0.9497622847557068,
"cells": [
{
"index": 95,
@@ -8880,7 +8880,7 @@
"b": 740.290298,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9368569850921631,
"confidence": 0.9368568658828735,
"cells": [
{
"index": 97,
@@ -9904,7 +9904,7 @@
"b": 519.65363,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9695364832878113,
"confidence": 0.9695363640785217,
"cells": [
{
"index": 34,
@@ -10592,7 +10592,7 @@
"b": 142.65363000000002,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9263732433319092,
"confidence": 0.9263731241226196,
"cells": [
{
"index": 59,
@@ -11134,7 +11134,7 @@
"b": 382.15362999999996,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9253151416778564,
"confidence": 0.9253152012825012,
"cells": [
{
"index": 79,
@@ -11180,7 +11180,7 @@
"b": 409.15362999999996,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9676452875137329,
"confidence": 0.9676451683044434,
"cells": [
{
"index": 80,
@@ -11246,12 +11246,12 @@
"label": "picture",
"bbox": {
"l": 320.4467468261719,
"t": 421.6407165527344,
"t": 421.640625,
"r": 558.8576049804688,
"b": 692.310791015625,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9881085753440857,
"confidence": 0.9881086945533752,
"cells": [
{
"index": 82,
@@ -12018,7 +12018,7 @@
"b": 713.009598,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9449449777603149,
"confidence": 0.9449448585510254,
"cells": [
{
"index": 93,
@@ -12089,7 +12089,7 @@
"b": 710.989597,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9497623443603516,
"confidence": 0.9497622847557068,
"cells": [
{
"index": 95,
@@ -12162,7 +12162,7 @@
"b": 740.290298,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9368569850921631,
"confidence": 0.9368568658828735,
"cells": [
{
"index": 97,
tests/data/groundtruth/docling_v1/code_and_formula.pages.json
+18 -18
View File
@@ -1541,7 +1541,7 @@
"b": 358.76782,
"coord_origin": "TOPLEFT"
},
"confidence": 0.5588339567184448,
"confidence": 0.5588350296020508,
"cells": [
{
"index": 18,
@@ -1581,7 +1581,7 @@
"b": 406.74554,
"coord_origin": "TOPLEFT"
},
"confidence": 0.6312211155891418,
"confidence": 0.6312209963798523,
"cells": [
{
"index": 19,
@@ -2036,7 +2036,7 @@
"b": 607.23564,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9843752980232239,
"confidence": 0.9843751788139343,
"cells": [
{
"index": 36,
@@ -2719,7 +2719,7 @@
"b": 358.76782,
"coord_origin": "TOPLEFT"
},
"confidence": 0.5588339567184448,
"confidence": 0.5588350296020508,
"cells": [
{
"index": 18,
@@ -2765,7 +2765,7 @@
"b": 406.74554,
"coord_origin": "TOPLEFT"
},
"confidence": 0.6312211155891418,
"confidence": 0.6312209963798523,
"cells": [
{
"index": 19,
@@ -3232,7 +3232,7 @@
"b": 607.23564,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9843752980232239,
"confidence": 0.9843751788139343,
"cells": [
{
"index": 36,
@@ -3914,7 +3914,7 @@
"b": 358.76782,
"coord_origin": "TOPLEFT"
},
"confidence": 0.5588339567184448,
"confidence": 0.5588350296020508,
"cells": [
{
"index": 18,
@@ -3960,7 +3960,7 @@
"b": 406.74554,
"coord_origin": "TOPLEFT"
},
"confidence": 0.6312211155891418,
"confidence": 0.6312209963798523,
"cells": [
{
"index": 19,
@@ -4427,7 +4427,7 @@
"b": 607.23564,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9843752980232239,
"confidence": 0.9843751788139343,
"cells": [
{
"index": 36,
@@ -5782,7 +5782,7 @@
"b": 137.5481507594625,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9505067467689514,
"confidence": 0.950506865978241,
"cells": [
{
"index": 0,
@@ -6302,7 +6302,7 @@
"b": 373.7119120634245,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8727476000785828,
"confidence": 0.8727474808692932,
"cells": [
{
"index": 19,
@@ -7037,7 +7037,7 @@
"b": 704.5687238902275,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8504503965377808,
"confidence": 0.8504500389099121,
"cells": [
{
"index": 46,
@@ -7092,7 +7092,7 @@
"b": 137.5481507594625,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9505067467689514,
"confidence": 0.950506865978241,
"cells": [
{
"index": 0,
@@ -7630,7 +7630,7 @@
"b": 373.7119120634245,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8727476000785828,
"confidence": 0.8727474808692932,
"cells": [
{
"index": 19,
@@ -8389,7 +8389,7 @@
"b": 704.5687238902275,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8504503965377808,
"confidence": 0.8504500389099121,
"cells": [
{
"index": 46,
@@ -8437,7 +8437,7 @@
"b": 137.5481507594625,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9505067467689514,
"confidence": 0.950506865978241,
"cells": [
{
"index": 0,
@@ -8975,7 +8975,7 @@
"b": 373.7119120634245,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8727476000785828,
"confidence": 0.8727474808692932,
"cells": [
{
"index": 19,
@@ -9736,7 +9736,7 @@
"b": 704.5687238902275,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8504503965377808,
"confidence": 0.8504500389099121,
"cells": [
{
"index": 46,
tests/data/groundtruth/docling_v1/multi_page.pages.json
+72 -72
View File
@@ -1071,7 +1071,7 @@
"b": 85.87195029682243,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9216852784156799,
"confidence": 0.9216853976249695,
"cells": [
{
"index": 0,
@@ -1111,7 +1111,7 @@
"b": 127.39196044033929,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9795150756835938,
"confidence": 0.9795149564743042,
"cells": [
{
"index": 1,
@@ -1176,7 +1176,7 @@
"b": 156.98303054262306,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9472767114639282,
"confidence": 0.9472769498825073,
"cells": [
{
"index": 3,
@@ -1576,7 +1576,7 @@
"b": 477.07196164903314,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9806972742080688,
"confidence": 0.9806973934173584,
"cells": [
{
"index": 16,
@@ -1946,7 +1946,7 @@
"b": 617.5429721345812,
"coord_origin": "TOPLEFT"
},
"confidence": 0.950114905834198,
"confidence": 0.9501149654388428,
"cells": [
{
"index": 29,
@@ -1986,7 +1986,7 @@
"b": 659.2319622786822,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9778240919113159,
"confidence": 0.9778239727020264,
"cells": [
{
"index": 30,
@@ -2051,7 +2051,7 @@
"b": 714.4319424694847,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9782076478004456,
"confidence": 0.978207528591156,
"cells": [
{
"index": 32,
@@ -2346,7 +2346,7 @@
"b": 85.87195029682243,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9216852784156799,
"confidence": 0.9216853976249695,
"cells": [
{
"index": 0,
@@ -2392,7 +2392,7 @@
"b": 127.39196044033929,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9795150756835938,
"confidence": 0.9795149564743042,
"cells": [
{
"index": 1,
@@ -2463,7 +2463,7 @@
"b": 156.98303054262306,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9472767114639282,
"confidence": 0.9472769498825073,
"cells": [
{
"index": 3,
@@ -2893,7 +2893,7 @@
"b": 477.07196164903314,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9806972742080688,
"confidence": 0.9806973934173584,
"cells": [
{
"index": 16,
@@ -3281,7 +3281,7 @@
"b": 617.5429721345812,
"coord_origin": "TOPLEFT"
},
"confidence": 0.950114905834198,
"confidence": 0.9501149654388428,
"cells": [
{
"index": 29,
@@ -3327,7 +3327,7 @@
"b": 659.2319622786822,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9778240919113159,
"confidence": 0.9778239727020264,
"cells": [
{
"index": 30,
@@ -3398,7 +3398,7 @@
"b": 714.4319424694847,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9782076478004456,
"confidence": 0.978207528591156,
"cells": [
{
"index": 32,
@@ -3692,7 +3692,7 @@
"b": 85.87195029682243,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9216852784156799,
"confidence": 0.9216853976249695,
"cells": [
{
"index": 0,
@@ -3738,7 +3738,7 @@
"b": 127.39196044033929,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9795150756835938,
"confidence": 0.9795149564743042,
"cells": [
{
"index": 1,
@@ -3809,7 +3809,7 @@
"b": 156.98303054262306,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9472767114639282,
"confidence": 0.9472769498825073,
"cells": [
{
"index": 3,
@@ -4239,7 +4239,7 @@
"b": 477.07196164903314,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9806972742080688,
"confidence": 0.9806973934173584,
"cells": [
{
"index": 16,
@@ -4627,7 +4627,7 @@
"b": 617.5429721345812,
"coord_origin": "TOPLEFT"
},
"confidence": 0.950114905834198,
"confidence": 0.9501149654388428,
"cells": [
{
"index": 29,
@@ -4673,7 +4673,7 @@
"b": 659.2319622786822,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9778240919113159,
"confidence": 0.9778239727020264,
"cells": [
{
"index": 30,
@@ -4744,7 +4744,7 @@
"b": 714.4319424694847,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9782076478004456,
"confidence": 0.978207528591156,
"cells": [
{
"index": 32,
@@ -5748,7 +5748,7 @@
"b": 113.47198039222405,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9813448190689087,
"confidence": 0.9813449382781982,
"cells": [
{
"index": 0,
@@ -5878,7 +5878,7 @@
"b": 212.35199073400975,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9798638820648193,
"confidence": 0.9798637628555298,
"cells": [
{
"index": 4,
@@ -6173,7 +6173,7 @@
"b": 322.99194111644454,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9762884378433228,
"confidence": 0.9762883186340332,
"cells": [
{
"index": 14,
@@ -6313,7 +6313,7 @@
"b": 380.18298131412945,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9581918120384216,
"confidence": 0.9581919312477112,
"cells": [
{
"index": 19,
@@ -6598,7 +6598,7 @@
"b": 113.47198039222405,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9813448190689087,
"confidence": 0.9813449382781982,
"cells": [
{
"index": 0,
@@ -6740,7 +6740,7 @@
"b": 212.35199073400975,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9798638820648193,
"confidence": 0.9798637628555298,
"cells": [
{
"index": 4,
@@ -7053,7 +7053,7 @@
"b": 322.99194111644454,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9762884378433228,
"confidence": 0.9762883186340332,
"cells": [
{
"index": 14,
@@ -7199,7 +7199,7 @@
"b": 380.18298131412945,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9581918120384216,
"confidence": 0.9581919312477112,
"cells": [
{
"index": 19,
@@ -7489,7 +7489,7 @@
"b": 113.47198039222405,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9813448190689087,
"confidence": 0.9813449382781982,
"cells": [
{
"index": 0,
@@ -7631,7 +7631,7 @@
"b": 212.35199073400975,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9798638820648193,
"confidence": 0.9798637628555298,
"cells": [
{
"index": 4,
@@ -7944,7 +7944,7 @@
"b": 322.99194111644454,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9762884378433228,
"confidence": 0.9762883186340332,
"cells": [
{
"index": 14,
@@ -8090,7 +8090,7 @@
"b": 380.18298131412945,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9581918120384216,
"confidence": 0.9581919312477112,
"cells": [
{
"index": 19,
@@ -10010,7 +10010,7 @@
"b": 280.9919409712686,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9800205230712891,
"confidence": 0.9800204038619995,
"cells": [
{
"index": 11,
@@ -10380,7 +10380,7 @@
"b": 448.9919715519727,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9789240956306458,
"confidence": 0.9789239764213562,
"cells": [
{
"index": 24,
@@ -10470,7 +10470,7 @@
"b": 490.51196169548945,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9704653024673462,
"confidence": 0.9704654216766357,
"cells": [
{
"index": 27,
@@ -10585,7 +10585,7 @@
"b": 518.1119717908908,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9631043672561646,
"confidence": 0.963104248046875,
"cells": [
{
"index": 31,
@@ -10815,7 +10815,7 @@
"b": 573.3119819816936,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9727876782417297,
"confidence": 0.9727875590324402,
"cells": [
{
"index": 39,
@@ -10930,7 +10930,7 @@
"b": 614.8319721252104,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9798402190208435,
"confidence": 0.9798403382301331,
"cells": [
{
"index": 43,
@@ -11070,7 +11070,7 @@
"b": 672.2629723237247,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9490435123443604,
"confidence": 0.9490436315536499,
"cells": [
{
"index": 48,
@@ -11553,7 +11553,7 @@
"b": 280.9919409712686,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9800205230712891,
"confidence": 0.9800204038619995,
"cells": [
{
"index": 11,
@@ -11941,7 +11941,7 @@
"b": 448.9919715519727,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9789240956306458,
"confidence": 0.9789239764213562,
"cells": [
{
"index": 24,
@@ -12037,7 +12037,7 @@
"b": 490.51196169548945,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9704653024673462,
"confidence": 0.9704654216766357,
"cells": [
{
"index": 27,
@@ -12158,7 +12158,7 @@
"b": 518.1119717908908,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9631043672561646,
"confidence": 0.963104248046875,
"cells": [
{
"index": 31,
@@ -12400,7 +12400,7 @@
"b": 573.3119819816936,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9727876782417297,
"confidence": 0.9727875590324402,
"cells": [
{
"index": 39,
@@ -12521,7 +12521,7 @@
"b": 614.8319721252104,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9798402190208435,
"confidence": 0.9798403382301331,
"cells": [
{
"index": 43,
@@ -12667,7 +12667,7 @@
"b": 672.2629723237247,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9490435123443604,
"confidence": 0.9490436315536499,
"cells": [
{
"index": 48,
@@ -13149,7 +13149,7 @@
"b": 280.9919409712686,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9800205230712891,
"confidence": 0.9800204038619995,
"cells": [
{
"index": 11,
@@ -13537,7 +13537,7 @@
"b": 448.9919715519727,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9789240956306458,
"confidence": 0.9789239764213562,
"cells": [
{
"index": 24,
@@ -13633,7 +13633,7 @@
"b": 490.51196169548945,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9704653024673462,
"confidence": 0.9704654216766357,
"cells": [
{
"index": 27,
@@ -13754,7 +13754,7 @@
"b": 518.1119717908908,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9631043672561646,
"confidence": 0.963104248046875,
"cells": [
{
"index": 31,
@@ -13996,7 +13996,7 @@
"b": 573.3119819816936,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9727876782417297,
"confidence": 0.9727875590324402,
"cells": [
{
"index": 39,
@@ -14117,7 +14117,7 @@
"b": 614.8319721252104,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9798402190208435,
"confidence": 0.9798403382301331,
"cells": [
{
"index": 43,
@@ -14263,7 +14263,7 @@
"b": 672.2629723237247,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9490435123443604,
"confidence": 0.9490436315536499,
"cells": [
{
"index": 48,
@@ -15942,7 +15942,7 @@
"b": 113.23199039139433,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9798315167427063,
"confidence": 0.9798316359519958,
"cells": [
{
"index": 0,
@@ -16222,7 +16222,7 @@
"b": 196.27197067842803,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9792094230651855,
"confidence": 0.9792095422744751,
"cells": [
{
"index": 10,
@@ -16362,7 +16362,7 @@
"b": 253.463010876113,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9634494781494141,
"confidence": 0.9634493589401245,
"cells": [
{
"index": 15,
@@ -16772,7 +16772,7 @@
"b": 460.751981592622,
"coord_origin": "TOPLEFT"
},
"confidence": 0.979421854019165,
"confidence": 0.9794219732284546,
"cells": [
{
"index": 29,
@@ -17077,7 +17077,7 @@
"b": 543.7919618796556,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9810317158699036,
"confidence": 0.9810318350791931,
"cells": [
{
"index": 40,
@@ -17257,7 +17257,7 @@
"b": 642.6719622214413,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9675389528274536,
"confidence": 0.9675387144088745,
"cells": [
{
"index": 46,
@@ -17707,7 +17707,7 @@
"b": 113.23199039139433,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9798315167427063,
"confidence": 0.9798316359519958,
"cells": [
{
"index": 0,
@@ -17999,7 +17999,7 @@
"b": 196.27197067842803,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9792094230651855,
"confidence": 0.9792095422744751,
"cells": [
{
"index": 10,
@@ -18145,7 +18145,7 @@
"b": 253.463010876113,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9634494781494141,
"confidence": 0.9634493589401245,
"cells": [
{
"index": 15,
@@ -18579,7 +18579,7 @@
"b": 460.751981592622,
"coord_origin": "TOPLEFT"
},
"confidence": 0.979421854019165,
"confidence": 0.9794219732284546,
"cells": [
{
"index": 29,
@@ -18896,7 +18896,7 @@
"b": 543.7919618796556,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9810317158699036,
"confidence": 0.9810318350791931,
"cells": [
{
"index": 40,
@@ -19088,7 +19088,7 @@
"b": 642.6719622214413,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9675389528274536,
"confidence": 0.9675387144088745,
"cells": [
{
"index": 46,
@@ -19549,7 +19549,7 @@
"b": 113.23199039139433,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9798315167427063,
"confidence": 0.9798316359519958,
"cells": [
{
"index": 0,
@@ -19841,7 +19841,7 @@
"b": 196.27197067842803,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9792094230651855,
"confidence": 0.9792095422744751,
"cells": [
{
"index": 10,
@@ -19987,7 +19987,7 @@
"b": 253.463010876113,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9634494781494141,
"confidence": 0.9634493589401245,
"cells": [
{
"index": 15,
@@ -20421,7 +20421,7 @@
"b": 460.751981592622,
"coord_origin": "TOPLEFT"
},
"confidence": 0.979421854019165,
"confidence": 0.9794219732284546,
"cells": [
{
"index": 29,
@@ -20738,7 +20738,7 @@
"b": 543.7919618796556,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9810317158699036,
"confidence": 0.9810318350791931,
"cells": [
{
"index": 40,
@@ -20930,7 +20930,7 @@
"b": 642.6719622214413,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9675389528274536,
"confidence": 0.9675387144088745,
"cells": [
{
"index": 46,
tests/data/groundtruth/docling_v1/picture_classification.json
+2 -2
View File
@@ -222,7 +222,7 @@
"prov": [
{
"bbox": [
134.9199981689453,
134.9200439453125,
281.78173828125,
475.6635437011719,
487.109375
@@ -244,7 +244,7 @@
"prov": [
{
"bbox": [
218.81556701660156,
218.8155517578125,
283.10589599609375,
391.96246337890625,
513.9846496582031
tests/data/groundtruth/docling_v1/picture_classification.pages.json
+12 -12
View File
@@ -1390,7 +1390,7 @@
"id": 2,
"label": "picture",
"bbox": {
"l": 134.9199981689453,
"l": 134.9200439453125,
"t": 304.890625,
"r": 475.6635437011719,
"b": 510.21826171875,
@@ -2174,7 +2174,7 @@
"id": 2,
"label": "picture",
"bbox": {
"l": 134.9199981689453,
"l": 134.9200439453125,
"t": 304.890625,
"r": 475.6635437011719,
"b": 510.21826171875,
@@ -2909,7 +2909,7 @@
"id": 2,
"label": "picture",
"bbox": {
"l": 134.9199981689453,
"l": 134.9200439453125,
"t": 304.890625,
"r": 475.6635437011719,
"b": 510.21826171875,
@@ -3623,7 +3623,7 @@
"b": 268.20489999999995,
"coord_origin": "TOPLEFT"
},
"confidence": 0.987092912197113,
"confidence": 0.9870928525924683,
"cells": [
{
"index": 0,
@@ -3938,7 +3938,7 @@
"b": 532.05774,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9494234323501587,
"confidence": 0.9494236707687378,
"cells": [
{
"index": 12,
@@ -4302,7 +4302,7 @@
"id": 2,
"label": "picture",
"bbox": {
"l": 218.81556701660156,
"l": 218.8155517578125,
"t": 278.0153503417969,
"r": 391.96246337890625,
"b": 508.89410400390625,
@@ -4337,7 +4337,7 @@
"b": 268.20489999999995,
"coord_origin": "TOPLEFT"
},
"confidence": 0.987092912197113,
"confidence": 0.9870928525924683,
"cells": [
{
"index": 0,
@@ -4658,7 +4658,7 @@
"b": 532.05774,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9494234323501587,
"confidence": 0.9494236707687378,
"cells": [
{
"index": 12,
@@ -5040,7 +5040,7 @@
"id": 2,
"label": "picture",
"bbox": {
"l": 218.81556701660156,
"l": 218.8155517578125,
"t": 278.0153503417969,
"r": 391.96246337890625,
"b": 508.89410400390625,
@@ -5072,7 +5072,7 @@
"b": 268.20489999999995,
"coord_origin": "TOPLEFT"
},
"confidence": 0.987092912197113,
"confidence": 0.9870928525924683,
"cells": [
{
"index": 0,
@@ -5393,7 +5393,7 @@
"b": 532.05774,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9494234323501587,
"confidence": 0.9494236707687378,
"cells": [
{
"index": 12,
@@ -5729,7 +5729,7 @@
"id": 2,
"label": "picture",
"bbox": {
"l": 218.81556701660156,
"l": 218.8155517578125,
"t": 278.0153503417969,
"r": 391.96246337890625,
"b": 508.89410400390625,
tests/data/groundtruth/docling_v1/redp5110_sampled.json
+26 -26
View File
@@ -3989,7 +3989,7 @@
"prov": [
{
"bbox": [
33.09052658081055,
33.09040069580078,
89.5469970703125,
585.1502075195312,
498.9671630859375
@@ -4055,9 +4055,9 @@
"prov": [
{
"bbox": [
64.16704559326172,
64.1669921875,
103.87176513671875,
258.77435302734375,
258.7742919921875,
188.49365234375
],
"page": 3,
@@ -4099,7 +4099,7 @@
"prov": [
{
"bbox": [
145.41448974609375,
145.4144744873047,
156.616943359375,
252.08840942382812,
264.7552490234375
@@ -4121,10 +4121,10 @@
"prov": [
{
"bbox": [
32.075260162353516,
554.0421142578125,
32.075252532958984,
554.0420684814453,
239.620361328125,
721.4226608276367
721.4226226806641
],
"page": 5,
"span": [
@@ -4168,7 +4168,7 @@
135.97177124023438,
381.39068603515625,
545.4180908203125,
684.5892562866211
684.5892486572266
],
"page": 10,
"span": [
@@ -4187,10 +4187,10 @@
"prov": [
{
"bbox": [
135.64834594726562,
135.64837646484375,
197.24334716796875,
301.23675537109375,
407.8263244628906
301.2367248535156,
407.8262939453125
],
"page": 11,
"span": [
@@ -4209,10 +4209,10 @@
"prov": [
{
"bbox": [
63.80195617675781,
621.9679107666016,
547.1146850585938,
696.6176071166992
63.801902770996094,
621.9678497314453,
547.11474609375,
696.6175842285156
],
"page": 14,
"span": [
@@ -4231,7 +4231,7 @@
"prov": [
{
"bbox": [
63.9850959777832,
63.985130310058594,
145.8603515625,
530.0478515625,
364.09503173828125
@@ -4254,9 +4254,9 @@
{
"bbox": [
136.5016632080078,
314.45880126953125,
314.4587707519531,
545.4508666992188,
672.7509078979492
672.7508773803711
],
"page": 15,
"span": [
@@ -4343,10 +4343,10 @@
"prov": [
{
"bbox": [
136.1495819091797,
76.3485107421875,
547.52685546875,
659.9669189453125
136.1496124267578,
76.34844970703125,
547.5267944335938,
659.9669647216797
],
"page": 2,
"span": [
@@ -6705,9 +6705,9 @@
{
"bbox": [
135.52462768554688,
349.94940185546875,
349.949462890625,
545.8714599609375,
502.2746887207031
502.2747802734375
],
"page": 8,
"span": [
@@ -7164,7 +7164,7 @@
64.41139221191406,
70.39208984375,
547.3950805664062,
398.3863525390625
398.3863830566406
],
"page": 9,
"span": [
@@ -9130,7 +9130,7 @@
"prov": [
{
"bbox": [
63.55635070800781,
63.55636978149414,
495.77532958984375,
548.5687255859375,
687.7661285400391
tests/data/groundtruth/docling_v1/redp5110_sampled.pages.json
+507 -507
View File
File diff suppressed because it is too large Load Diff
tests/data/groundtruth/docling_v1/right_to_left_01.pages.json
+6 -6
View File
@@ -1171,7 +1171,7 @@
"b": 295.08200000000005,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9547481536865234,
"confidence": 0.9547483325004578,
"cells": [
{
"index": 17,
@@ -1311,7 +1311,7 @@
"b": 350.522,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9672118425369263,
"confidence": 0.9672117233276367,
"cells": [
{
"index": 22,
@@ -1971,7 +1971,7 @@
"b": 295.08200000000005,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9547481536865234,
"confidence": 0.9547483325004578,
"cells": [
{
"index": 17,
@@ -2117,7 +2117,7 @@
"b": 350.522,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9672118425369263,
"confidence": 0.9672117233276367,
"cells": [
{
"index": 22,
@@ -2770,7 +2770,7 @@
"b": 295.08200000000005,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9547481536865234,
"confidence": 0.9547483325004578,
"cells": [
{
"index": 17,
@@ -2916,7 +2916,7 @@
"b": 350.522,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9672118425369263,
"confidence": 0.9672117233276367,
"cells": [
{
"index": 22,
tests/data/groundtruth/docling_v1/right_to_left_02.pages.json
+9 -9
View File
@@ -5951,7 +5951,7 @@
"b": 465.596681609368,
"coord_origin": "TOPLEFT"
},
"confidence": 0.93938809633255,
"confidence": 0.9393879771232605,
"cells": [
{
"index": 77,
@@ -7406,7 +7406,7 @@
"b": 534.1167018462124,
"coord_origin": "TOPLEFT"
},
"confidence": 0.5769621729850769,
"confidence": 0.5769620537757874,
"cells": [
{
"index": 134,
@@ -8046,7 +8046,7 @@
"b": 650.6431884765625,
"coord_origin": "TOPLEFT"
},
"confidence": 0.6444893479347229,
"confidence": 0.6444889903068542,
"cells": [],
"children": []
}
@@ -10042,7 +10042,7 @@
"b": 465.596681609368,
"coord_origin": "TOPLEFT"
},
"confidence": 0.93938809633255,
"confidence": 0.9393879771232605,
"cells": [
{
"index": 77,
@@ -11509,7 +11509,7 @@
"b": 534.1167018462124,
"coord_origin": "TOPLEFT"
},
"confidence": 0.5769621729850769,
"confidence": 0.5769620537757874,
"cells": [
{
"index": 134,
@@ -12155,7 +12155,7 @@
"b": 650.6431884765625,
"coord_origin": "TOPLEFT"
},
"confidence": 0.6444893479347229,
"confidence": 0.6444889903068542,
"cells": [],
"children": []
},
@@ -14148,7 +14148,7 @@
"b": 465.596681609368,
"coord_origin": "TOPLEFT"
},
"confidence": 0.93938809633255,
"confidence": 0.9393879771232605,
"cells": [
{
"index": 77,
@@ -15615,7 +15615,7 @@
"b": 534.1167018462124,
"coord_origin": "TOPLEFT"
},
"confidence": 0.5769621729850769,
"confidence": 0.5769620537757874,
"cells": [
{
"index": 134,
@@ -16261,7 +16261,7 @@
"b": 650.6431884765625,
"coord_origin": "TOPLEFT"
},
"confidence": 0.6444893479347229,
"confidence": 0.6444889903068542,
"cells": [],
"children": []
},
tests/data/groundtruth/docling_v1/right_to_left_03.json
+1 -1
View File
@@ -744,7 +744,7 @@
388.5767822265625,
739.034423828125,
482.4759216308594,
806.0040969848633
806.0041046142578
],
"page": 1,
"span": [
tests/data/groundtruth/docling_v1/right_to_left_03.pages.json
+78 -78
View File
@@ -1391,7 +1391,7 @@
"label": "picture",
"bbox": {
"l": 388.5767822265625,
"t": 36.03588104248047,
"t": 36.03587341308594,
"r": 482.4759216308594,
"b": 103.00555419921875,
"coord_origin": "TOPLEFT"
@@ -1477,7 +1477,7 @@
"b": 81.03008981017001,
"coord_origin": "TOPLEFT"
},
"confidence": 0.6917959451675415,
"confidence": 0.6917961239814758,
"cells": [
{
"index": 2,
@@ -1517,7 +1517,7 @@
"b": 790.0379791491694,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8992282152175903,
"confidence": 0.899228036403656,
"cells": [
{
"index": 3,
@@ -1597,7 +1597,7 @@
"b": 323.44982924225053,
"coord_origin": "TOPLEFT"
},
"confidence": 0.6362582445144653,
"confidence": 0.6362584233283997,
"cells": [
{
"index": 5,
@@ -2361,7 +2361,7 @@
"b": 179.2998695799522,
"coord_origin": "TOPLEFT"
},
"confidence": 0.7258322834968567,
"confidence": 0.7258325815200806,
"cells": [
{
"index": 5,
@@ -2891,7 +2891,7 @@
"b": 233.17986945372706,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8121819496154785,
"confidence": 0.8121814727783203,
"cells": [
{
"index": 25,
@@ -2931,7 +2931,7 @@
"b": 228.73998946412837,
"coord_origin": "TOPLEFT"
},
"confidence": 0.7672221660614014,
"confidence": 0.7672220468521118,
"cells": [
{
"index": 26,
@@ -2971,7 +2971,7 @@
"b": 255.88982940052404,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8320454955101013,
"confidence": 0.8320456743240356,
"cells": [
{
"index": 27,
@@ -3011,7 +3011,7 @@
"b": 251.44994941092557,
"coord_origin": "TOPLEFT"
},
"confidence": 0.5538817644119263,
"confidence": 0.5538824796676636,
"cells": [
{
"index": 28,
@@ -3051,7 +3051,7 @@
"b": 278.5698293473914,
"coord_origin": "TOPLEFT"
},
"confidence": 0.7908995151519775,
"confidence": 0.7909000515937805,
"cells": [
{
"index": 29,
@@ -3131,7 +3131,7 @@
"b": 323.44982924225053,
"coord_origin": "TOPLEFT"
},
"confidence": 0.6534579396247864,
"confidence": 0.6534578204154968,
"cells": [
{
"index": 31,
@@ -3236,7 +3236,7 @@
"b": 296.80999930466,
"coord_origin": "TOPLEFT"
},
"confidence": 0.5417138934135437,
"confidence": 0.5417144298553467,
"cells": [
{
"index": 35,
@@ -3318,7 +3318,7 @@
"b": 596.0198686036978,
"coord_origin": "TOPLEFT"
},
"confidence": 0.7191378474235535,
"confidence": 0.719137966632843,
"cells": [
{
"index": 37,
@@ -3822,7 +3822,7 @@
"b": 386.56997909437825,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8262876868247986,
"confidence": 0.8262879252433777,
"cells": [
{
"index": 38,
@@ -3862,7 +3862,7 @@
"b": 413.70983903079747,
"coord_origin": "TOPLEFT"
},
"confidence": 0.7766715884208679,
"confidence": 0.7766718864440918,
"cells": [
{
"index": 39,
@@ -3902,7 +3902,7 @@
"b": 409.26995904119883,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8204739093780518,
"confidence": 0.8204737901687622,
"cells": [
{
"index": 40,
@@ -3942,7 +3942,7 @@
"b": 436.3898589776647,
"coord_origin": "TOPLEFT"
},
"confidence": 0.7670676708221436,
"confidence": 0.7670677900314331,
"cells": [
{
"index": 41,
@@ -3982,7 +3982,7 @@
"b": 432.0699789877849,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8048339486122131,
"confidence": 0.8048340082168579,
"cells": [
{
"index": 42,
@@ -4062,7 +4062,7 @@
"b": 454.7499689346523,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8273372054100037,
"confidence": 0.827337384223938,
"cells": [
{
"index": 44,
@@ -4102,7 +4102,7 @@
"b": 481.8698388711183,
"coord_origin": "TOPLEFT"
},
"confidence": 0.7342240214347839,
"confidence": 0.7342236638069153,
"cells": [
{
"index": 45,
@@ -4142,7 +4142,7 @@
"b": 477.42995888151955,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8411223888397217,
"confidence": 0.8411222696304321,
"cells": [
{
"index": 46,
@@ -4182,7 +4182,7 @@
"b": 528.3098487623228,
"coord_origin": "TOPLEFT"
},
"confidence": 0.7251590490341187,
"confidence": 0.7251589894294739,
"cells": [
{
"index": 47,
@@ -4247,7 +4247,7 @@
"b": 501.78997882445117,
"coord_origin": "TOPLEFT"
},
"confidence": 0.7848676443099976,
"confidence": 0.7848678827285767,
"cells": [
{
"index": 49,
@@ -4287,7 +4287,7 @@
"b": 573.2198486571116,
"coord_origin": "TOPLEFT"
},
"confidence": 0.758643627166748,
"confidence": 0.7586438059806824,
"cells": [
{
"index": 50,
@@ -4352,7 +4352,7 @@
"b": 546.69997871924,
"coord_origin": "TOPLEFT"
},
"confidence": 0.7897858619689941,
"confidence": 0.7897851467132568,
"cells": [
{
"index": 52,
@@ -4432,7 +4432,7 @@
"b": 591.5799886140991,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8144806027412415,
"confidence": 0.8144810795783997,
"cells": [
{
"index": 54,
@@ -4484,7 +4484,7 @@
"label": "picture",
"bbox": {
"l": 388.5767822265625,
"t": 36.03588104248047,
"t": 36.03587341308594,
"r": 482.4759216308594,
"b": 103.00555419921875,
"coord_origin": "TOPLEFT"
@@ -4580,7 +4580,7 @@
"b": 81.03008981017001,
"coord_origin": "TOPLEFT"
},
"confidence": 0.6917959451675415,
"confidence": 0.6917961239814758,
"cells": [
{
"index": 2,
@@ -4626,7 +4626,7 @@
"b": 790.0379791491694,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8992282152175903,
"confidence": 0.899228036403656,
"cells": [
{
"index": 3,
@@ -4718,7 +4718,7 @@
"b": 323.44982924225053,
"coord_origin": "TOPLEFT"
},
"confidence": 0.6362582445144653,
"confidence": 0.6362584233283997,
"cells": [
{
"index": 5,
@@ -5482,7 +5482,7 @@
"b": 179.2998695799522,
"coord_origin": "TOPLEFT"
},
"confidence": 0.7258322834968567,
"confidence": 0.7258325815200806,
"cells": [
{
"index": 5,
@@ -6012,7 +6012,7 @@
"b": 233.17986945372706,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8121819496154785,
"confidence": 0.8121814727783203,
"cells": [
{
"index": 25,
@@ -6052,7 +6052,7 @@
"b": 228.73998946412837,
"coord_origin": "TOPLEFT"
},
"confidence": 0.7672221660614014,
"confidence": 0.7672220468521118,
"cells": [
{
"index": 26,
@@ -6092,7 +6092,7 @@
"b": 255.88982940052404,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8320454955101013,
"confidence": 0.8320456743240356,
"cells": [
{
"index": 27,
@@ -6132,7 +6132,7 @@
"b": 251.44994941092557,
"coord_origin": "TOPLEFT"
},
"confidence": 0.5538817644119263,
"confidence": 0.5538824796676636,
"cells": [
{
"index": 28,
@@ -6172,7 +6172,7 @@
"b": 278.5698293473914,
"coord_origin": "TOPLEFT"
},
"confidence": 0.7908995151519775,
"confidence": 0.7909000515937805,
"cells": [
{
"index": 29,
@@ -6252,7 +6252,7 @@
"b": 323.44982924225053,
"coord_origin": "TOPLEFT"
},
"confidence": 0.6534579396247864,
"confidence": 0.6534578204154968,
"cells": [
{
"index": 31,
@@ -6357,7 +6357,7 @@
"b": 296.80999930466,
"coord_origin": "TOPLEFT"
},
"confidence": 0.5417138934135437,
"confidence": 0.5417144298553467,
"cells": [
{
"index": 35,
@@ -6451,7 +6451,7 @@
"b": 596.0198686036978,
"coord_origin": "TOPLEFT"
},
"confidence": 0.7191378474235535,
"confidence": 0.719137966632843,
"cells": [
{
"index": 37,
@@ -6955,7 +6955,7 @@
"b": 386.56997909437825,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8262876868247986,
"confidence": 0.8262879252433777,
"cells": [
{
"index": 38,
@@ -6995,7 +6995,7 @@
"b": 413.70983903079747,
"coord_origin": "TOPLEFT"
},
"confidence": 0.7766715884208679,
"confidence": 0.7766718864440918,
"cells": [
{
"index": 39,
@@ -7035,7 +7035,7 @@
"b": 409.26995904119883,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8204739093780518,
"confidence": 0.8204737901687622,
"cells": [
{
"index": 40,
@@ -7075,7 +7075,7 @@
"b": 436.3898589776647,
"coord_origin": "TOPLEFT"
},
"confidence": 0.7670676708221436,
"confidence": 0.7670677900314331,
"cells": [
{
"index": 41,
@@ -7115,7 +7115,7 @@
"b": 432.0699789877849,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8048339486122131,
"confidence": 0.8048340082168579,
"cells": [
{
"index": 42,
@@ -7195,7 +7195,7 @@
"b": 454.7499689346523,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8273372054100037,
"confidence": 0.827337384223938,
"cells": [
{
"index": 44,
@@ -7235,7 +7235,7 @@
"b": 481.8698388711183,
"coord_origin": "TOPLEFT"
},
"confidence": 0.7342240214347839,
"confidence": 0.7342236638069153,
"cells": [
{
"index": 45,
@@ -7275,7 +7275,7 @@
"b": 477.42995888151955,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8411223888397217,
"confidence": 0.8411222696304321,
"cells": [
{
"index": 46,
@@ -7315,7 +7315,7 @@
"b": 528.3098487623228,
"coord_origin": "TOPLEFT"
},
"confidence": 0.7251590490341187,
"confidence": 0.7251589894294739,
"cells": [
{
"index": 47,
@@ -7380,7 +7380,7 @@
"b": 501.78997882445117,
"coord_origin": "TOPLEFT"
},
"confidence": 0.7848676443099976,
"confidence": 0.7848678827285767,
"cells": [
{
"index": 49,
@@ -7420,7 +7420,7 @@
"b": 573.2198486571116,
"coord_origin": "TOPLEFT"
},
"confidence": 0.758643627166748,
"confidence": 0.7586438059806824,
"cells": [
{
"index": 50,
@@ -7485,7 +7485,7 @@
"b": 546.69997871924,
"coord_origin": "TOPLEFT"
},
"confidence": 0.7897858619689941,
"confidence": 0.7897851467132568,
"cells": [
{
"index": 52,
@@ -7565,7 +7565,7 @@
"b": 591.5799886140991,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8144806027412415,
"confidence": 0.8144810795783997,
"cells": [
{
"index": 54,
@@ -7610,7 +7610,7 @@
"label": "picture",
"bbox": {
"l": 388.5767822265625,
"t": 36.03588104248047,
"t": 36.03587341308594,
"r": 482.4759216308594,
"b": 103.00555419921875,
"coord_origin": "TOPLEFT"
@@ -7706,7 +7706,7 @@
"b": 81.03008981017001,
"coord_origin": "TOPLEFT"
},
"confidence": 0.6917959451675415,
"confidence": 0.6917961239814758,
"cells": [
{
"index": 2,
@@ -7798,7 +7798,7 @@
"b": 323.44982924225053,
"coord_origin": "TOPLEFT"
},
"confidence": 0.6362582445144653,
"confidence": 0.6362584233283997,
"cells": [
{
"index": 5,
@@ -8562,7 +8562,7 @@
"b": 179.2998695799522,
"coord_origin": "TOPLEFT"
},
"confidence": 0.7258322834968567,
"confidence": 0.7258325815200806,
"cells": [
{
"index": 5,
@@ -9092,7 +9092,7 @@
"b": 233.17986945372706,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8121819496154785,
"confidence": 0.8121814727783203,
"cells": [
{
"index": 25,
@@ -9132,7 +9132,7 @@
"b": 228.73998946412837,
"coord_origin": "TOPLEFT"
},
"confidence": 0.7672221660614014,
"confidence": 0.7672220468521118,
"cells": [
{
"index": 26,
@@ -9172,7 +9172,7 @@
"b": 255.88982940052404,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8320454955101013,
"confidence": 0.8320456743240356,
"cells": [
{
"index": 27,
@@ -9212,7 +9212,7 @@
"b": 251.44994941092557,
"coord_origin": "TOPLEFT"
},
"confidence": 0.5538817644119263,
"confidence": 0.5538824796676636,
"cells": [
{
"index": 28,
@@ -9252,7 +9252,7 @@
"b": 278.5698293473914,
"coord_origin": "TOPLEFT"
},
"confidence": 0.7908995151519775,
"confidence": 0.7909000515937805,
"cells": [
{
"index": 29,
@@ -9332,7 +9332,7 @@
"b": 323.44982924225053,
"coord_origin": "TOPLEFT"
},
"confidence": 0.6534579396247864,
"confidence": 0.6534578204154968,
"cells": [
{
"index": 31,
@@ -9437,7 +9437,7 @@
"b": 296.80999930466,
"coord_origin": "TOPLEFT"
},
"confidence": 0.5417138934135437,
"confidence": 0.5417144298553467,
"cells": [
{
"index": 35,
@@ -9531,7 +9531,7 @@
"b": 596.0198686036978,
"coord_origin": "TOPLEFT"
},
"confidence": 0.7191378474235535,
"confidence": 0.719137966632843,
"cells": [
{
"index": 37,
@@ -10035,7 +10035,7 @@
"b": 386.56997909437825,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8262876868247986,
"confidence": 0.8262879252433777,
"cells": [
{
"index": 38,
@@ -10075,7 +10075,7 @@
"b": 413.70983903079747,
"coord_origin": "TOPLEFT"
},
"confidence": 0.7766715884208679,
"confidence": 0.7766718864440918,
"cells": [
{
"index": 39,
@@ -10115,7 +10115,7 @@
"b": 409.26995904119883,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8204739093780518,
"confidence": 0.8204737901687622,
"cells": [
{
"index": 40,
@@ -10155,7 +10155,7 @@
"b": 436.3898589776647,
"coord_origin": "TOPLEFT"
},
"confidence": 0.7670676708221436,
"confidence": 0.7670677900314331,
"cells": [
{
"index": 41,
@@ -10195,7 +10195,7 @@
"b": 432.0699789877849,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8048339486122131,
"confidence": 0.8048340082168579,
"cells": [
{
"index": 42,
@@ -10275,7 +10275,7 @@
"b": 454.7499689346523,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8273372054100037,
"confidence": 0.827337384223938,
"cells": [
{
"index": 44,
@@ -10315,7 +10315,7 @@
"b": 481.8698388711183,
"coord_origin": "TOPLEFT"
},
"confidence": 0.7342240214347839,
"confidence": 0.7342236638069153,
"cells": [
{
"index": 45,
@@ -10355,7 +10355,7 @@
"b": 477.42995888151955,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8411223888397217,
"confidence": 0.8411222696304321,
"cells": [
{
"index": 46,
@@ -10395,7 +10395,7 @@
"b": 528.3098487623228,
"coord_origin": "TOPLEFT"
},
"confidence": 0.7251590490341187,
"confidence": 0.7251589894294739,
"cells": [
{
"index": 47,
@@ -10460,7 +10460,7 @@
"b": 501.78997882445117,
"coord_origin": "TOPLEFT"
},
"confidence": 0.7848676443099976,
"confidence": 0.7848678827285767,
"cells": [
{
"index": 49,
@@ -10500,7 +10500,7 @@
"b": 573.2198486571116,
"coord_origin": "TOPLEFT"
},
"confidence": 0.758643627166748,
"confidence": 0.7586438059806824,
"cells": [
{
"index": 50,
@@ -10565,7 +10565,7 @@
"b": 546.69997871924,
"coord_origin": "TOPLEFT"
},
"confidence": 0.7897858619689941,
"confidence": 0.7897851467132568,
"cells": [
{
"index": 52,
@@ -10645,7 +10645,7 @@
"b": 591.5799886140991,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8144806027412415,
"confidence": 0.8144810795783997,
"cells": [
{
"index": 54,
@@ -10695,7 +10695,7 @@
"b": 790.0379791491694,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8992282152175903,
"confidence": 0.899228036403656,
"cells": [
{
"index": 3,