mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-27 04:24:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

parametrize float serialization, propagate core updates

Browse Source 
Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>
This commit is contained in:
Panos Vagenas 2025-07-09 13:49:11 +02:00
parent b16b4ea069
commit 785c6b37f5
38 changed files with 316739 additions and 316709 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
docling/datamodel/base_models.py
View File

@ -12,6 +12,7 @@ from docling_core.types.doc import (
Size, Size,
TableCell, TableCell,
) )
from docling_core.types.doc.base import PydanticSerCtxKey, round_pydantic_float
from docling_core.types.doc.page import SegmentedPdfPage, TextCell from docling_core.types.doc.page import SegmentedPdfPage, TextCell
from docling_core.types.io import ( from docling_core.types.io import (
DocumentStream, DocumentStream,
@ -19,7 +20,14 @@ from docling_core.types.io import (
# DO NOT REMOVE; explicitly exposed from this location # DO NOT REMOVE; explicitly exposed from this location
from PIL.Image import Image from PIL.Image import Image
from pydantic import BaseModel, ConfigDict, Field, computed_field from pydantic import (
BaseModel,
ConfigDict,
Field,
FieldSerializationInfo,
computed_field,
field_serializer,
)
if TYPE_CHECKING: if TYPE_CHECKING:
from docling.backend.pdf_backend import PdfPageBackend from docling.backend.pdf_backend import PdfPageBackend
@ -142,6 +150,10 @@ class Cluster(BaseModel):
cells: List[TextCell] = [] cells: List[TextCell] = []
children: List["Cluster"] = [] # Add child cluster support children: List["Cluster"] = [] # Add child cluster support
@field_serializer("confidence")
def _serialize(self, value: float, info: FieldSerializationInfo) -> float:
return round_pydantic_float(value, info.context, PydanticSerCtxKey.CONFID_PREC)
class BasePageElement(BaseModel): class BasePageElement(BaseModel):
label: DocItemLabel label: DocItemLabel
@ -194,6 +206,16 @@ class FigureElement(BasePageElement):
predicted_class: Optional[str] = None predicted_class: Optional[str] = None
confidence: Optional[float] = None confidence: Optional[float] = None
@field_serializer("confidence")
def _serialize(
self, value: Optional[float], info: FieldSerializationInfo
) -> Optional[float]:
return (
round_pydantic_float(value, info.context, PydanticSerCtxKey.CONFID_PREC)
if value is not None
else None
)
class FigureClassificationPrediction(BaseModel): class FigureClassificationPrediction(BaseModel):
figure_count: int = 0 figure_count: int = 0

3
pyproject.toml
View File

@ -44,7 +44,8 @@ authors = [
requires-python = '>=3.9,<4.0' requires-python = '>=3.9,<4.0'
dependencies = [ dependencies = [
'pydantic (>=2.0.0,<3.0.0)', 'pydantic (>=2.0.0,<3.0.0)',
'docling-core[chunking] (>=2.40.0,<3.0.0)', # 'docling-core[chunking] (>=2.40.0,<3.0.0)',
"docling-core[chunking] @ git+https://github.com/docling-project/docling-core.git@0c648aafc28e94780b88bbd91870e2c74d9f9602",
'docling-parse (>=4.0.0,<5.0.0)', 'docling-parse (>=4.0.0,<5.0.0)',
'docling-ibm-models (>=3.6.0,<4)', 'docling-ibm-models (>=3.6.0,<4)',
'filetype (>=1.2.0,<2.0.0)', 'filetype (>=1.2.0,<2.0.0)',

7786
tests/data/groundtruth/docling_v2/2203.01017v2.json vendored
View File

File diff suppressed because it is too large Load Diff

179940
tests/data/groundtruth/docling_v2/2203.01017v2.pages.json vendored
View File

File diff suppressed because it is too large Load Diff

10006
tests/data/groundtruth/docling_v2/2206.01062.json vendored
View File

File diff suppressed because it is too large Load Diff

179876
tests/data/groundtruth/docling_v2/2206.01062.pages.json vendored
View File

File diff suppressed because it is too large Load Diff

700
tests/data/groundtruth/docling_v2/2305.03393v1-pg9.json vendored
View File

File diff suppressed because it is too large Load Diff

13028
tests/data/groundtruth/docling_v2/2305.03393v1-pg9.pages.json vendored
View File

File diff suppressed because it is too large Load Diff

4642
tests/data/groundtruth/docling_v2/2305.03393v1.json vendored
View File

File diff suppressed because it is too large Load Diff

105390
tests/data/groundtruth/docling_v2/2305.03393v1.pages.json vendored
View File

File diff suppressed because it is too large Load Diff

202
tests/data/groundtruth/docling_v2/amt_handbook_sample.json vendored
View File

@ -84,10 +84,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 71.99, "l": 72.0,
"t": 730.32, "t": 730.3,
"r": 314.11, "r": 314.1,
"b": 681.35, "b": 681.3,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -111,10 +111,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 71.99, "l": 72.0,
"t": 667.82, "t": 667.8,
"r": 313.15, "r": 313.2,
"b": 593.85, "b": 593.8,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -138,10 +138,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 71.99, "l": 72.0,
"t": 580.19, "t": 580.2,
"r": 167.27, "r": 167.3,
"b": 568.85, "b": 568.8,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -166,10 +166,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 71.99, "l": 72.0,
"t": 565.82, "t": 565.8,
"r": 318.49, "r": 318.5,
"b": 491.85, "b": 491.8,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -193,10 +193,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 71.99, "l": 72.0,
"t": 478.32, "t": 478.3,
"r": 316.66, "r": 316.7,
"b": 404.35, "b": 404.3,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -220,10 +220,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 71.99, "l": 72.0,
"t": 390.82, "t": 390.8,
"r": 318.81, "r": 318.8,
"b": 291.85, "b": 291.8,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -247,10 +247,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 71.99, "l": 72.0,
"t": 278.32, "t": 278.3,
"r": 313.91, "r": 313.9,
"b": 254.35, "b": 254.3,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -276,8 +276,8 @@
"bbox": { "bbox": {
"l": 72.0, "l": 72.0,
"t": 71.8, "t": 71.8,
"r": 184.15, "r": 184.1,
"b": 60.99, "b": 61.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -301,10 +301,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 102.42, "l": 102.4,
"t": 186.24, "t": 186.2,
"r": 161.32, "r": 161.3,
"b": 176.62, "b": 176.6,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -328,10 +328,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 91.69, "l": 91.7,
"t": 94.69, "t": 94.7,
"r": 129.77, "r": 129.8,
"b": 85.07, "b": 85.1,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -355,10 +355,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 162.48, "l": 162.5,
"t": 94.69, "t": 94.7,
"r": 207.86, "r": 207.9,
"b": 85.07, "b": 85.1,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -382,10 +382,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 237.31, "l": 237.3,
"t": 94.69, "t": 94.7,
"r": 289.56, "r": 289.6,
"b": 85.07, "b": 85.1,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -409,10 +409,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 216.93, "l": 216.9,
"t": 186.24, "t": 186.2,
"r": 277.8, "r": 277.8,
"b": 176.62, "b": 176.6,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -436,10 +436,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 320.99, "l": 321.0,
"t": 730.32, "t": 730.3,
"r": 561.81, "r": 561.8,
"b": 656.35, "b": 656.3,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -464,9 +464,9 @@
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 321.0, "l": 321.0,
"t": 655.32, "t": 655.3,
"r": 326.0, "r": 326.0,
"b": 643.85, "b": 643.8,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -491,9 +491,9 @@
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 321.0, "l": 321.0,
"t": 642.69, "t": 642.7,
"r": 451.0, "r": 451.0,
"b": 631.35, "b": 631.3,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -519,9 +519,9 @@
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 321.0, "l": 321.0,
"t": 628.32, "t": 628.3,
"r": 568.0, "r": 568.0,
"b": 416.85, "b": 416.8,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -546,9 +546,9 @@
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 321.0, "l": 321.0,
"t": 403.19, "t": 403.2,
"r": 388.51, "r": 388.5,
"b": 391.85, "b": 391.8,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -574,9 +574,9 @@
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 321.0, "l": 321.0,
"t": 388.82, "t": 388.8,
"r": 552.35, "r": 552.4,
"b": 364.85, "b": 364.8,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -601,9 +601,9 @@
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 321.0, "l": 321.0,
"t": 73.82, "t": 73.8,
"r": 481.65, "r": 481.6,
"b": 63.01, "b": 63.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -627,10 +627,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 479.14, "l": 479.1,
"t": 101.27, "t": 101.3,
"r": 531.17, "r": 531.2,
"b": 91.35, "b": 91.4,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -654,9 +654,9 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 474.37, "l": 474.4,
"t": 242.11, "t": 242.1,
"r": 535.23, "r": 535.2,
"b": 232.2, "b": 232.2,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
@ -681,10 +681,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 456.76, "l": 456.8,
"t": 342.0, "t": 342.0,
"r": 487.08, "r": 487.1,
"b": 332.39, "b": 332.4,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -708,10 +708,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 434.62, "l": 434.6,
"t": 196.18, "t": 196.2,
"r": 497.47, "r": 497.5,
"b": 186.56, "b": 186.6,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -735,10 +735,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 448.55, "l": 448.6,
"t": 220.68, "t": 220.7,
"r": 507.69, "r": 507.7,
"b": 211.06, "b": 211.1,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -762,10 +762,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 424.78, "l": 424.8,
"t": 109.89, "t": 109.9,
"r": 452.1, "r": 452.1,
"b": 100.27, "b": 100.3,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -789,10 +789,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 537.99, "l": 538.0,
"t": 46.02, "t": 46.0,
"r": 560.78, "r": 560.8,
"b": 33.71, "b": 33.7,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -837,10 +837,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 70.59, "l": 70.6,
"t": 242.78, "t": 242.8,
"r": 309.86, "r": 309.9,
"b": 79.61, "b": 79.6,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -892,10 +892,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 320.45, "l": 320.4,
"t": 352.36, "t": 352.4,
"r": 558.86, "r": 558.9,
"b": 81.69, "b": 81.7,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [

6708
tests/data/groundtruth/docling_v2/amt_handbook_sample.pages.json vendored
View File

File diff suppressed because it is too large Load Diff

126
tests/data/groundtruth/docling_v2/code_and_formula.json vendored
View File

@ -81,10 +81,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 133.77, "l": 133.8,
"t": 667.19, "t": 667.2,
"r": 315.92, "r": 315.9,
"b": 654.45, "b": 654.5,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -109,10 +109,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 133.77, "l": 133.8,
"t": 642.33, "t": 642.3,
"r": 477.48, "r": 477.5,
"b": 501.97, "b": 502.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -136,10 +136,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 133.77, "l": 133.8,
"t": 498.87, "t": 498.9,
"r": 477.48, "r": 477.5,
"b": 454.15, "b": 454.2,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -167,10 +167,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 134.24, "l": 134.2,
"t": 425.6, "t": 425.6,
"r": 263.22, "r": 263.2,
"b": 385.25, "b": 385.3,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -202,10 +202,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 223.16, "l": 223.2,
"t": 442.08, "t": 442.1,
"r": 388.09, "r": 388.1,
"b": 433.23, "b": 433.2,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -229,10 +229,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 133.77, "l": 133.8,
"t": 372.94, "t": 372.9,
"r": 477.48, "r": 477.5,
"b": 232.59, "b": 232.6,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -256,10 +256,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 133.77, "l": 133.8,
"t": 229.48, "t": 229.5,
"r": 477.48, "r": 477.5,
"b": 184.76, "b": 184.8,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -283,10 +283,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 303.13, "l": 303.1,
"t": 96.28, "t": 96.3,
"r": 308.11, "r": 308.1,
"b": 87.43, "b": 87.4,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -310,10 +310,10 @@
{ {
"page_no": 2, "page_no": 2,
"bbox": { "bbox": {
"l": 133.77, "l": 133.8,
"t": 717.08, "t": 717.1,
"r": 191.53, "r": 191.5,
"b": 704.34, "b": 704.3,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -338,10 +338,10 @@
{ {
"page_no": 2, "page_no": 2,
"bbox": { "bbox": {
"l": 133.77, "l": 133.8,
"t": 692.22, "t": 692.2,
"r": 477.48, "r": 477.5,
"b": 551.86, "b": 551.9,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -365,10 +365,10 @@
{ {
"page_no": 2, "page_no": 2,
"bbox": { "bbox": {
"l": 133.77, "l": 133.8,
"t": 548.76, "t": 548.8,
"r": 477.48, "r": 477.5,
"b": 492.09, "b": 492.1,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -392,10 +392,10 @@
{ {
"page_no": 2, "page_no": 2,
"bbox": { "bbox": {
"l": 280.55, "l": 280.6,
"t": 479.06, "t": 479.1,
"r": 330.7, "r": 330.7,
"b": 468.18, "b": 468.2,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -419,10 +419,10 @@
{ {
"page_no": 2, "page_no": 2,
"bbox": { "bbox": {
"l": 133.77, "l": 133.8,
"t": 459.09, "t": 459.1,
"r": 477.48, "r": 477.5,
"b": 318.74, "b": 318.7,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -446,10 +446,10 @@
{ {
"page_no": 2, "page_no": 2,
"bbox": { "bbox": {
"l": 133.77, "l": 133.8,
"t": 315.63, "t": 315.6,
"r": 477.48, "r": 477.5,
"b": 247.01, "b": 247.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -473,10 +473,10 @@
{ {
"page_no": 2, "page_no": 2,
"bbox": { "bbox": {
"l": 133.77, "l": 133.8,
"t": 243.9, "t": 243.9,
"r": 477.48, "r": 477.5,
"b": 175.28, "b": 175.3,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -500,10 +500,10 @@
{ {
"page_no": 2, "page_no": 2,
"bbox": { "bbox": {
"l": 303.13, "l": 303.1,
"t": 146.17, "t": 146.2,
"r": 308.11, "r": 308.1,
"b": 137.32, "b": 137.3,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -530,8 +530,8 @@
}, },
"2": { "2": {
"size": { "size": {
"width": 595.28, "width": 595.3,
"height": 841.89 "height": 841.9
}, },
"page_no": 2 "page_no": 2
} }

5720
tests/data/groundtruth/docling_v2/code_and_formula.pages.json vendored
View File

File diff suppressed because it is too large Load Diff

308
tests/data/groundtruth/docling_v2/multi_page.json vendored
View File

@ -309,9 +309,9 @@
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 72.0, "l": 72.0,
"t": 769.33, "t": 769.3,
"r": 262.99, "r": 263.0,
"b": 756.05, "b": 756.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -337,9 +337,9 @@
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 72.0, "l": 72.0,
"t": 741.73, "t": 741.7,
"r": 497.52, "r": 497.5,
"b": 714.53, "b": 714.5,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -364,9 +364,9 @@
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 72.0, "l": 72.0,
"t": 699.82, "t": 699.8,
"r": 325.82, "r": 325.8,
"b": 684.94, "b": 684.9,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -392,9 +392,9 @@
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 72.0, "l": 72.0,
"t": 670.69, "t": 670.7,
"r": 508.18, "r": 508.2,
"b": 615.65, "b": 615.6,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -419,9 +419,9 @@
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 72.0, "l": 72.0,
"t": 601.57, "t": 601.6,
"r": 504.5, "r": 504.5,
"b": 546.53, "b": 546.5,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -446,9 +446,9 @@
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 72.0, "l": 72.0,
"t": 504.22, "t": 504.2,
"r": 336.72, "r": 336.7,
"b": 489.34, "b": 489.3,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -474,9 +474,9 @@
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 72.0, "l": 72.0,
"t": 474.85, "t": 474.9,
"r": 523.19, "r": 523.2,
"b": 433.73, "b": 433.7,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -501,9 +501,9 @@
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 90.0, "l": 90.0,
"t": 419.65, "t": 419.7,
"r": 518.01, "r": 518.0,
"b": 364.85, "b": 364.8,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -530,9 +530,9 @@
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 90.0, "l": 90.0,
"t": 364.45, "t": 364.5,
"r": 497.52, "r": 497.5,
"b": 323.33, "b": 323.3,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -559,9 +559,9 @@
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 72.0, "l": 72.0,
"t": 309.01, "t": 309.0,
"r": 514.47, "r": 514.5,
"b": 281.57, "b": 281.6,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -586,9 +586,9 @@
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 72.0, "l": 72.0,
"t": 239.26, "t": 239.3,
"r": 306.71, "r": 306.7,
"b": 224.38, "b": 224.4,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -614,9 +614,9 @@
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 72.0, "l": 72.0,
"t": 210.13, "t": 210.1,
"r": 515.57, "r": 515.6,
"b": 182.69, "b": 182.7,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -641,9 +641,9 @@
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 90.0, "l": 90.0,
"t": 168.37, "t": 168.4,
"r": 522.53, "r": 522.5,
"b": 127.49, "b": 127.5,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -670,9 +670,9 @@
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 90.0, "l": 90.0,
"t": 127.09, "t": 127.1,
"r": 525.26, "r": 525.3,
"b": 85.97, "b": 86.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -699,9 +699,9 @@
"page_no": 2, "page_no": 2,
"bbox": { "bbox": {
"l": 72.0, "l": 72.0,
"t": 769.57, "t": 769.6,
"r": 516.5, "r": 516.5,
"b": 728.45, "b": 728.4,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -726,9 +726,9 @@
"page_no": 2, "page_no": 2,
"bbox": { "bbox": {
"l": 72.0, "l": 72.0,
"t": 686.14, "t": 686.1,
"r": 272.2, "r": 272.2,
"b": 671.26, "b": 671.3,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -754,9 +754,9 @@
"page_no": 2, "page_no": 2,
"bbox": { "bbox": {
"l": 72.0, "l": 72.0,
"t": 656.77, "t": 656.8,
"r": 510.87, "r": 510.9,
"b": 629.57, "b": 629.6,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -781,9 +781,9 @@
"page_no": 2, "page_no": 2,
"bbox": { "bbox": {
"l": 90.0, "l": 90.0,
"t": 615.25, "t": 615.3,
"r": 491.24, "r": 491.2,
"b": 588.29, "b": 588.3,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -810,9 +810,9 @@
"page_no": 2, "page_no": 2,
"bbox": { "bbox": {
"l": 90.0, "l": 90.0,
"t": 587.65, "t": 587.7,
"r": 517.54, "r": 517.5,
"b": 560.69, "b": 560.7,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -839,9 +839,9 @@
"page_no": 2, "page_no": 2,
"bbox": { "bbox": {
"l": 90.0, "l": 90.0,
"t": 560.05, "t": 560.1,
"r": 524.56, "r": 524.6,
"b": 518.93, "b": 518.9,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -868,9 +868,9 @@
"page_no": 2, "page_no": 2,
"bbox": { "bbox": {
"l": 72.0, "l": 72.0,
"t": 476.62, "t": 476.6,
"r": 231.71, "r": 231.7,
"b": 461.74, "b": 461.7,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -896,9 +896,9 @@
"page_no": 2, "page_no": 2,
"bbox": { "bbox": {
"l": 72.0, "l": 72.0,
"t": 447.25, "t": 447.3,
"r": 520.54, "r": 520.5,
"b": 378.53, "b": 378.5,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -923,9 +923,9 @@
"page_no": 2, "page_no": 2,
"bbox": { "bbox": {
"l": 72.0, "l": 72.0,
"t": 336.37, "t": 336.4,
"r": 515.56, "r": 515.6,
"b": 295.49, "b": 295.5,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -950,8 +950,8 @@
"page_no": 3, "page_no": 3,
"bbox": { "bbox": {
"l": 72.0, "l": 72.0,
"t": 769.18, "t": 769.2,
"r": 276.73, "r": 276.7,
"b": 754.3, "b": 754.3,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
@ -978,9 +978,9 @@
"page_no": 3, "page_no": 3,
"bbox": { "bbox": {
"l": 72.0, "l": 72.0,
"t": 740.05, "t": 740.1,
"r": 514.67, "r": 514.7,
"b": 698.93, "b": 698.9,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -1005,9 +1005,9 @@
"page_no": 3, "page_no": 3,
"bbox": { "bbox": {
"l": 90.0, "l": 90.0,
"t": 684.61, "t": 684.6,
"r": 519.51, "r": 519.5,
"b": 616.13, "b": 616.1,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -1034,9 +1034,9 @@
"page_no": 3, "page_no": 3,
"bbox": { "bbox": {
"l": 90.0, "l": 90.0,
"t": 615.73, "t": 615.7,
"r": 503.53, "r": 503.5,
"b": 560.93, "b": 560.9,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -1063,9 +1063,9 @@
"page_no": 3, "page_no": 3,
"bbox": { "bbox": {
"l": 90.0, "l": 90.0,
"t": 560.53, "t": 560.5,
"r": 524.48, "r": 524.5,
"b": 505.49, "b": 505.5,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -1092,8 +1092,8 @@
"page_no": 3, "page_no": 3,
"bbox": { "bbox": {
"l": 72.0, "l": 72.0,
"t": 463.18, "t": 463.2,
"r": 340.47, "r": 340.5,
"b": 448.3, "b": 448.3,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
@ -1120,9 +1120,9 @@
"page_no": 3, "page_no": 3,
"bbox": { "bbox": {
"l": 72.0, "l": 72.0,
"t": 434.05, "t": 434.1,
"r": 514.72, "r": 514.7,
"b": 392.93, "b": 392.9,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -1147,9 +1147,9 @@
"page_no": 3, "page_no": 3,
"bbox": { "bbox": {
"l": 90.0, "l": 90.0,
"t": 378.61, "t": 378.6,
"r": 509.27, "r": 509.3,
"b": 351.41, "b": 351.4,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -1176,9 +1176,9 @@
"page_no": 3, "page_no": 3,
"bbox": { "bbox": {
"l": 90.0, "l": 90.0,
"t": 351.01, "t": 351.0,
"r": 516.6, "r": 516.6,
"b": 323.81, "b": 323.8,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -1205,9 +1205,9 @@
"page_no": 3, "page_no": 3,
"bbox": { "bbox": {
"l": 90.0, "l": 90.0,
"t": 323.41, "t": 323.4,
"r": 486.9, "r": 486.9,
"b": 296.21, "b": 296.2,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -1234,9 +1234,9 @@
"page_no": 3, "page_no": 3,
"bbox": { "bbox": {
"l": 90.0, "l": 90.0,
"t": 295.81, "t": 295.8,
"r": 502.21, "r": 502.2,
"b": 268.61, "b": 268.6,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -1263,9 +1263,9 @@
"page_no": 3, "page_no": 3,
"bbox": { "bbox": {
"l": 90.0, "l": 90.0,
"t": 268.21, "t": 268.2,
"r": 521.88, "r": 521.9,
"b": 227.09, "b": 227.1,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -1292,9 +1292,9 @@
"page_no": 3, "page_no": 3,
"bbox": { "bbox": {
"l": 72.0, "l": 72.0,
"t": 184.54, "t": 184.5,
"r": 311.96, "r": 312.0,
"b": 169.66, "b": 169.7,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -1320,9 +1320,9 @@
"page_no": 3, "page_no": 3,
"bbox": { "bbox": {
"l": 72.0, "l": 72.0,
"t": 155.41, "t": 155.4,
"r": 518.9, "r": 518.9,
"b": 114.29, "b": 114.3,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -1347,9 +1347,9 @@
"page_no": 4, "page_no": 4,
"bbox": { "bbox": {
"l": 90.0, "l": 90.0,
"t": 769.57, "t": 769.6,
"r": 514.56, "r": 514.6,
"b": 728.69, "b": 728.7,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -1376,9 +1376,9 @@
"page_no": 4, "page_no": 4,
"bbox": { "bbox": {
"l": 90.0, "l": 90.0,
"t": 728.29, "t": 728.3,
"r": 521.9, "r": 521.9,
"b": 687.41, "b": 687.4,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -1405,9 +1405,9 @@
"page_no": 4, "page_no": 4,
"bbox": { "bbox": {
"l": 90.0, "l": 90.0,
"t": 686.77, "t": 686.8,
"r": 515.85, "r": 515.9,
"b": 645.65, "b": 645.6,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -1434,9 +1434,9 @@
"page_no": 4, "page_no": 4,
"bbox": { "bbox": {
"l": 72.0, "l": 72.0,
"t": 603.34, "t": 603.3,
"r": 295.45, "r": 295.5,
"b": 588.46, "b": 588.5,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -1462,9 +1462,9 @@
"page_no": 4, "page_no": 4,
"bbox": { "bbox": {
"l": 72.0, "l": 72.0,
"t": 573.73, "t": 573.7,
"r": 521.21, "r": 521.2,
"b": 560.45, "b": 560.4,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -1489,9 +1489,9 @@
"page_no": 4, "page_no": 4,
"bbox": { "bbox": {
"l": 90.0, "l": 90.0,
"t": 546.37, "t": 546.4,
"r": 523.84, "r": 523.8,
"b": 491.57, "b": 491.6,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -1518,9 +1518,9 @@
"page_no": 4, "page_no": 4,
"bbox": { "bbox": {
"l": 90.0, "l": 90.0,
"t": 491.17, "t": 491.2,
"r": 514.53, "r": 514.5,
"b": 436.37, "b": 436.4,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -1547,9 +1547,9 @@
"page_no": 4, "page_no": 4,
"bbox": { "bbox": {
"l": 90.0, "l": 90.0,
"t": 435.97, "t": 436.0,
"r": 502.92, "r": 502.9,
"b": 381.17, "b": 381.2,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -1576,9 +1576,9 @@
"page_no": 4, "page_no": 4,
"bbox": { "bbox": {
"l": 90.0, "l": 90.0,
"t": 380.77, "t": 380.8,
"r": 516.92, "r": 516.9,
"b": 339.89, "b": 339.9,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -1605,9 +1605,9 @@
"page_no": 4, "page_no": 4,
"bbox": { "bbox": {
"l": 90.0, "l": 90.0,
"t": 339.25, "t": 339.3,
"r": 510.91, "r": 510.9,
"b": 298.13, "b": 298.1,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -1634,9 +1634,9 @@
"page_no": 4, "page_no": 4,
"bbox": { "bbox": {
"l": 72.0, "l": 72.0,
"t": 255.82, "t": 255.8,
"r": 228.36, "r": 228.4,
"b": 240.94, "b": 240.9,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -1662,9 +1662,9 @@
"page_no": 4, "page_no": 4,
"bbox": { "bbox": {
"l": 72.0, "l": 72.0,
"t": 226.45, "t": 226.5,
"r": 515.05, "r": 515.0,
"b": 199.25, "b": 199.2,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -1689,9 +1689,9 @@
"page_no": 4, "page_no": 4,
"bbox": { "bbox": {
"l": 90.0, "l": 90.0,
"t": 184.93, "t": 184.9,
"r": 518.27, "r": 518.3,
"b": 157.97, "b": 158.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -1718,9 +1718,9 @@
"page_no": 4, "page_no": 4,
"bbox": { "bbox": {
"l": 90.0, "l": 90.0,
"t": 157.33, "t": 157.3,
"r": 525.52, "r": 525.5,
"b": 116.45, "b": 116.4,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -1747,9 +1747,9 @@
"page_no": 4, "page_no": 4,
"bbox": { "bbox": {
"l": 90.0, "l": 90.0,
"t": 116.05, "t": 116.1,
"r": 518.91, "r": 518.9,
"b": 88.61, "b": 88.6,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -1776,9 +1776,9 @@
"page_no": 5, "page_no": 5,
"bbox": { "bbox": {
"l": 72.0, "l": 72.0,
"t": 741.73, "t": 741.7,
"r": 510.5, "r": 510.5,
"b": 673.01, "b": 673.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -1799,35 +1799,35 @@
"1": { "1": {
"size": { "size": {
"width": 595.2, "width": 595.2,
"height": 841.92 "height": 841.9
}, },
"page_no": 1 "page_no": 1
}, },
"2": { "2": {
"size": { "size": {
"width": 595.2, "width": 595.2,
"height": 841.92 "height": 841.9
}, },
"page_no": 2 "page_no": 2
}, },
"3": { "3": {
"size": { "size": {
"width": 595.2, "width": 595.2,
"height": 841.92 "height": 841.9
}, },
"page_no": 3 "page_no": 3
}, },
"4": { "4": {
"size": { "size": {
"width": 595.2, "width": 595.2,
"height": 841.92 "height": 841.9
}, },
"page_no": 4 "page_no": 4
}, },
"5": { "5": {
"size": { "size": {
"width": 595.2, "width": 595.2,
"height": 841.92 "height": 841.9
}, },
"page_no": 5 "page_no": 5
} }

10128
tests/data/groundtruth/docling_v2/multi_page.pages.json vendored
View File

File diff suppressed because it is too large Load Diff

86
tests/data/groundtruth/docling_v2/picture_classification.json vendored
View File

@ -63,10 +63,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 133.77, "l": 133.8,
"t": 667.19, "t": 667.2,
"r": 252.36, "r": 252.4,
"b": 654.45, "b": 654.5,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -91,10 +91,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 133.77, "l": 133.8,
"t": 642.33, "t": 642.3,
"r": 477.48, "r": 477.5,
"b": 501.97, "b": 502.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -118,10 +118,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 226.89, "l": 226.9,
"t": 262.87, "t": 262.9,
"r": 384.35, "r": 384.4,
"b": 254.02, "b": 254.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -145,10 +145,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 133.77, "l": 133.8,
"t": 238.96, "t": 239.0,
"r": 477.48, "r": 477.5,
"b": 122.51, "b": 122.5,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -172,10 +172,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 303.13, "l": 303.1,
"t": 96.28, "t": 96.3,
"r": 308.11, "r": 308.1,
"b": 87.43, "b": 87.4,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -199,9 +199,9 @@
{ {
"page_no": 2, "page_no": 2,
"bbox": { "bbox": {
"l": 133.77, "l": 133.8,
"t": 664.15, "t": 664.1,
"r": 477.48, "r": 477.5,
"b": 523.8, "b": 523.8,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
@ -226,10 +226,10 @@
{ {
"page_no": 2, "page_no": 2,
"bbox": { "bbox": {
"l": 226.89, "l": 226.9,
"t": 268.79, "t": 268.8,
"r": 384.35, "r": 384.4,
"b": 259.94, "b": 259.9,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -253,10 +253,10 @@
{ {
"page_no": 2, "page_no": 2,
"bbox": { "bbox": {
"l": 133.77, "l": 133.8,
"t": 245.72, "t": 245.7,
"r": 477.48, "r": 477.5,
"b": 117.32, "b": 117.3,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -280,10 +280,10 @@
{ {
"page_no": 2, "page_no": 2,
"bbox": { "bbox": {
"l": 303.13, "l": 303.1,
"t": 96.28, "t": 96.3,
"r": 308.11, "r": 308.1,
"b": 87.43, "b": 87.4,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -313,10 +313,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 134.92, "l": 134.9,
"t": 487.11, "t": 487.1,
"r": 475.66, "r": 475.7,
"b": 281.78, "b": 281.8,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -350,10 +350,10 @@
{ {
"page_no": 2, "page_no": 2,
"bbox": { "bbox": {
"l": 218.82, "l": 218.8,
"t": 513.98, "t": 514.0,
"r": 391.96, "r": 392.0,
"b": 283.11, "b": 283.1,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [

3412
tests/data/groundtruth/docling_v2/picture_classification.pages.json vendored
View File

File diff suppressed because it is too large Load Diff

3994
tests/data/groundtruth/docling_v2/redp5110_sampled.json vendored
View File

File diff suppressed because it is too large Load Diff

82150
tests/data/groundtruth/docling_v2/redp5110_sampled.pages.json vendored
View File

File diff suppressed because it is too large Load Diff

50
tests/data/groundtruth/docling_v2/right_to_left_01.json vendored
View File

@ -57,10 +57,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 223.85, "l": 223.9,
"t": 719.46, "t": 719.5,
"r": 521.98, "r": 522.0,
"b": 704.45, "b": 704.5,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -85,10 +85,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 90.74, "l": 90.7,
"t": 689.99, "t": 690.0,
"r": 522.19, "r": 522.2,
"b": 635.31, "b": 635.3,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -113,9 +113,9 @@
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 208.1, "l": 208.1,
"t": 592.67, "t": 592.7,
"r": 208.1, "r": 208.1,
"b": 579.39, "b": 579.4,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -139,10 +139,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 509.35, "l": 509.3,
"t": 578.03, "t": 578.0,
"r": 509.35, "r": 509.3,
"b": 564.75, "b": 564.7,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -166,10 +166,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 99.86, "l": 99.9,
"t": 620.75, "t": 620.8,
"r": 522.24, "r": 522.2,
"b": 566.07, "b": 566.1,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -194,9 +194,9 @@
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 92.9, "l": 92.9,
"t": 551.63, "t": 551.6,
"r": 522.11, "r": 522.1,
"b": 496.92, "b": 496.9,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -220,10 +220,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 96.86, "l": 96.9,
"t": 482.36, "t": 482.4,
"r": 522.07, "r": 522.1,
"b": 441.48, "b": 441.5,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [

1700
tests/data/groundtruth/docling_v2/right_to_left_01.pages.json vendored
View File

File diff suppressed because it is too large Load Diff

42
tests/data/groundtruth/docling_v2/right_to_left_02.json vendored
View File

@ -54,10 +54,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 47.95, "l": 48.0,
"t": 37.83, "t": 37.8,
"r": 58.75, "r": 58.8,
"b": 23.79, "b": 23.8,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -81,10 +81,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 67.99, "l": 68.0,
"t": 632.26, "t": 632.3,
"r": 437.43, "r": 437.4,
"b": 422.59, "b": 422.6,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -108,10 +108,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 74.52, "l": 74.5,
"t": 408.0, "t": 408.0,
"r": 440.88, "r": 440.9,
"b": 376.32, "b": 376.3,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -136,8 +136,8 @@
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 69.1, "l": 69.1,
"t": 334.49, "t": 334.5,
"r": 437.31, "r": 437.3,
"b": 307.8, "b": 307.8,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
@ -162,10 +162,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 72.95, "l": 72.9,
"t": 263.09, "t": 263.1,
"r": 437.29, "r": 437.3,
"b": 193.95, "b": 194.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -191,10 +191,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 446.47, "l": 446.5,
"t": 641.21, "t": 641.2,
"r": 595.0, "r": 595.0,
"b": 191.28, "b": 191.3,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -216,7 +216,7 @@
"1": { "1": {
"size": { "size": {
"width": 595.2, "width": 595.2,
"height": 841.92 "height": 841.9
}, },
"page_no": 1 "page_no": 1
} }

9676
tests/data/groundtruth/docling_v2/right_to_left_02.pages.json vendored
View File

File diff suppressed because it is too large Load Diff

242
tests/data/groundtruth/docling_v2/right_to_left_03.json vendored
View File

@ -161,10 +161,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 68.78, "l": 68.8,
"t": 779.39, "t": 779.4,
"r": 267.66, "r": 267.7,
"b": 761.01, "b": 761.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -189,10 +189,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 388.99, "l": 389.0,
"t": 750.25, "t": 750.3,
"r": 481.6, "r": 481.6,
"b": 736.98, "b": 737.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -216,10 +216,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 373.99, "l": 374.0,
"t": 703.41, "t": 703.4,
"r": 479.53, "r": 479.5,
"b": 685.37, "b": 685.4,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -244,10 +244,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 458.74, "l": 458.7,
"t": 679.62, "t": 679.6,
"r": 519.24, "r": 519.2,
"b": 662.74, "b": 662.7,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -271,10 +271,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 66.26, "l": 66.3,
"t": 681.17, "t": 681.2,
"r": 264.82, "r": 264.8,
"b": 631.54, "b": 631.5,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -298,10 +298,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 420.91, "l": 420.9,
"t": 625.74, "t": 625.7,
"r": 519.16, "r": 519.2,
"b": 608.86, "b": 608.9,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -325,9 +325,9 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 236.81, "l": 236.8,
"t": 627.29, "t": 627.3,
"r": 265.01, "r": 265.0,
"b": 613.3, "b": 613.3,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
@ -352,10 +352,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 406.99, "l": 407.0,
"t": 603.03, "t": 603.0,
"r": 519.14, "r": 519.1,
"b": 586.15, "b": 586.2,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -379,10 +379,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 197.33, "l": 197.3,
"t": 604.58, "t": 604.6,
"r": 264.91, "r": 264.9,
"b": 590.59, "b": 590.6,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -406,10 +406,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 389.47, "l": 389.5,
"t": 580.35, "t": 580.3,
"r": 519.21, "r": 519.2,
"b": 563.47, "b": 563.5,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -433,10 +433,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 166.58, "l": 166.6,
"t": 581.9, "t": 581.9,
"r": 264.78, "r": 264.8,
"b": 567.91, "b": 567.9,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -460,10 +460,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 292.13, "l": 292.1,
"t": 557.67, "t": 557.7,
"r": 519.24, "r": 519.2,
"b": 518.59, "b": 518.6,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -487,10 +487,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 197.33, "l": 197.3,
"t": 559.22, "t": 559.2,
"r": 208.05, "r": 208.0,
"b": 545.23, "b": 545.2,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -514,10 +514,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 236.63, "l": 236.6,
"t": 559.22, "t": 559.2,
"r": 247.35, "r": 247.3,
"b": 545.23, "b": 545.2,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -541,10 +541,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 409.03, "l": 409.0,
"t": 490.59, "t": 490.6,
"r": 505.76, "r": 505.8,
"b": 473.71, "b": 473.7,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -569,10 +569,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 405.31, "l": 405.3,
"t": 467.89, "t": 467.9,
"r": 492.61, "r": 492.6,
"b": 451.01, "b": 451.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -597,9 +597,9 @@
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 137.9, "l": 137.9,
"t": 469.46, "t": 469.5,
"r": 187.82, "r": 187.8,
"b": 455.47, "b": 455.5,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -623,10 +623,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 426.31, "l": 426.3,
"t": 445.21, "t": 445.2,
"r": 492.59, "r": 492.6,
"b": 428.33, "b": 428.3,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -651,9 +651,9 @@
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 137.9, "l": 137.9,
"t": 446.76, "t": 446.8,
"r": 187.82, "r": 187.8,
"b": 432.77, "b": 432.8,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -677,10 +677,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 367.15, "l": 367.1,
"t": 422.53, "t": 422.5,
"r": 492.69, "r": 492.7,
"b": 405.65, "b": 405.7,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -705,9 +705,9 @@
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 154.7, "l": 154.7,
"t": 423.96, "t": 424.0,
"r": 171.2, "r": 171.2,
"b": 409.97, "b": 410.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -731,10 +731,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 399.43, "l": 399.4,
"t": 399.73, "t": 399.7,
"r": 492.63, "r": 492.6,
"b": 382.85, "b": 382.9,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -759,9 +759,9 @@
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 137.9, "l": 137.9,
"t": 401.28, "t": 401.3,
"r": 187.82, "r": 187.8,
"b": 387.29, "b": 387.3,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -785,10 +785,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 422.83, "l": 422.8,
"t": 377.05, "t": 377.0,
"r": 492.68, "r": 492.7,
"b": 360.17, "b": 360.2,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -812,10 +812,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 122.06, "l": 122.1,
"t": 378.6, "t": 378.6,
"r": 203.65, "r": 203.6,
"b": 364.61, "b": 364.6,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -839,10 +839,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 281.33, "l": 281.3,
"t": 352.69, "t": 352.7,
"r": 492.71, "r": 492.7,
"b": 313.73, "b": 313.7,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -866,10 +866,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 109.22, "l": 109.2,
"t": 354.24, "t": 354.2,
"r": 213.67, "r": 213.7,
"b": 340.25, "b": 340.2,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -893,10 +893,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 266.57, "l": 266.6,
"t": 307.78, "t": 307.8,
"r": 492.7, "r": 492.7,
"b": 268.82, "b": 268.8,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -920,10 +920,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 85.46, "l": 85.5,
"t": 309.33, "t": 309.3,
"r": 240.36, "r": 240.4,
"b": 295.34, "b": 295.3,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -947,10 +947,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 404.23, "l": 404.2,
"t": 262.9, "t": 262.9,
"r": 492.64, "r": 492.6,
"b": 246.02, "b": 246.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -974,10 +974,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 106.94, "l": 106.9,
"t": 264.45, "t": 264.5,
"r": 218.89, "r": 218.9,
"b": 250.46, "b": 250.5,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -1001,9 +1001,9 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 267.29, "l": 267.3,
"t": 62.55, "t": 62.5,
"r": 294.59, "r": 294.6,
"b": 52.0, "b": 52.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
@ -1034,10 +1034,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 388.58, "l": 388.6,
"t": 806.0, "t": 806.0,
"r": 482.48, "r": 482.5,
"b": 739.03, "b": 739.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -1058,8 +1058,8 @@
"pages": { "pages": {
"1": { "1": {
"size": { "size": {
"width": 595.32, "width": 595.3,
"height": 842.04 "height": 842.0
}, },
"page_no": 1 "page_no": 1
} }

6416
tests/data/groundtruth/docling_v2/right_to_left_03.pages.json vendored
View File

File diff suppressed because it is too large Load Diff

4
tests/data/webp/groundtruth/docling_v2/webp-test.json vendored
View File

@ -39,10 +39,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 234.09, "l": 234.1,
"t": 2570.1, "t": 2570.1,
"r": 1696.1, "r": 1696.1,
"b": 2319.12, "b": 2319.1,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [

162
tests/data/webp/groundtruth/docling_v2/webp-test.pages.json vendored
View File

@ -85,13 +85,13 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 246.41, "r_x0": 246.4,
"r_y0": 329.07, "r_y0": 329.1,
"r_x1": 1691.99, "r_x1": 1692.0,
"r_y1": 329.07, "r_y1": 329.1,
"r_x2": 1691.99, "r_x2": 1692.0,
"r_y2": 258.9, "r_y2": 258.9,
"r_x3": 246.41, "r_x3": 246.4,
"r_y3": 258.9, "r_y3": 258.9,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
@ -110,14 +110,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 234.09, "r_x0": 234.1,
"r_y0": 419.58, "r_y0": 419.6,
"r_x1": 1696.1, "r_x1": 1696.1,
"r_y1": 419.58, "r_y1": 419.6,
"r_x2": 1696.1, "r_x2": 1696.1,
"r_y2": 349.42, "r_y2": 349.4,
"r_x3": 234.09, "r_x3": 234.1,
"r_y3": 349.42, "r_y3": 349.4,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "JSON and Markdown in an easy self contained", "text": "JSON and Markdown in an easy self contained",
@ -136,13 +136,13 @@
}, },
"rect": { "rect": {
"r_x0": 242.3, "r_x0": 242.3,
"r_y0": 509.88, "r_y0": 509.9,
"r_x1": 513.35, "r_x1": 513.3,
"r_y1": 509.88, "r_y1": 509.9,
"r_x2": 513.35, "r_x2": 513.3,
"r_y2": 439.98, "r_y2": 440.0,
"r_x3": 242.3, "r_x3": 242.3,
"r_y3": 439.98, "r_y3": 440.0,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "package", "text": "package",
@ -165,13 +165,13 @@
"id": 0, "id": 0,
"label": "text", "label": "text",
"bbox": { "bbox": {
"l": 234.09, "l": 234.1,
"t": 258.9, "t": 258.9,
"r": 1696.1, "r": 1696.1,
"b": 509.88, "b": 509.9,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9721011519432068, "confidence": 0.97,
"cells": [ "cells": [
{ {
"index": 0, "index": 0,
@ -182,13 +182,13 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 246.41, "r_x0": 246.4,
"r_y0": 329.07, "r_y0": 329.1,
"r_x1": 1691.99, "r_x1": 1692.0,
"r_y1": 329.07, "r_y1": 329.1,
"r_x2": 1691.99, "r_x2": 1692.0,
"r_y2": 258.9, "r_y2": 258.9,
"r_x3": 246.41, "r_x3": 246.4,
"r_y3": 258.9, "r_y3": 258.9,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
@ -207,14 +207,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 234.09, "r_x0": 234.1,
"r_y0": 419.58, "r_y0": 419.6,
"r_x1": 1696.1, "r_x1": 1696.1,
"r_y1": 419.58, "r_y1": 419.6,
"r_x2": 1696.1, "r_x2": 1696.1,
"r_y2": 349.42, "r_y2": 349.4,
"r_x3": 234.09, "r_x3": 234.1,
"r_y3": 349.42, "r_y3": 349.4,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "JSON and Markdown in an easy self contained", "text": "JSON and Markdown in an easy self contained",
@ -233,13 +233,13 @@
}, },
"rect": { "rect": {
"r_x0": 242.3, "r_x0": 242.3,
"r_y0": 509.88, "r_y0": 509.9,
"r_x1": 513.35, "r_x1": 513.3,
"r_y1": 509.88, "r_y1": 509.9,
"r_x2": 513.35, "r_x2": 513.3,
"r_y2": 439.98, "r_y2": 440.0,
"r_x3": 242.3, "r_x3": 242.3,
"r_y3": 439.98, "r_y3": 440.0,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "package", "text": "package",
@ -270,13 +270,13 @@
"id": 0, "id": 0,
"label": "text", "label": "text",
"bbox": { "bbox": {
"l": 234.09, "l": 234.1,
"t": 258.9, "t": 258.9,
"r": 1696.1, "r": 1696.1,
"b": 509.88, "b": 509.9,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9721011519432068, "confidence": 0.97,
"cells": [ "cells": [
{ {
"index": 0, "index": 0,
@ -287,13 +287,13 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 246.41, "r_x0": 246.4,
"r_y0": 329.07, "r_y0": 329.1,
"r_x1": 1691.99, "r_x1": 1692.0,
"r_y1": 329.07, "r_y1": 329.1,
"r_x2": 1691.99, "r_x2": 1692.0,
"r_y2": 258.9, "r_y2": 258.9,
"r_x3": 246.41, "r_x3": 246.4,
"r_y3": 258.9, "r_y3": 258.9,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
@ -312,14 +312,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 234.09, "r_x0": 234.1,
"r_y0": 419.58, "r_y0": 419.6,
"r_x1": 1696.1, "r_x1": 1696.1,
"r_y1": 419.58, "r_y1": 419.6,
"r_x2": 1696.1, "r_x2": 1696.1,
"r_y2": 349.42, "r_y2": 349.4,
"r_x3": 234.09, "r_x3": 234.1,
"r_y3": 349.42, "r_y3": 349.4,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "JSON and Markdown in an easy self contained", "text": "JSON and Markdown in an easy self contained",
@ -338,13 +338,13 @@
}, },
"rect": { "rect": {
"r_x0": 242.3, "r_x0": 242.3,
"r_y0": 509.88, "r_y0": 509.9,
"r_x1": 513.35, "r_x1": 513.3,
"r_y1": 509.88, "r_y1": 509.9,
"r_x2": 513.35, "r_x2": 513.3,
"r_y2": 439.98, "r_y2": 440.0,
"r_x3": 242.3, "r_x3": 242.3,
"r_y3": 439.98, "r_y3": 440.0,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "package", "text": "package",
@ -368,13 +368,13 @@
"id": 0, "id": 0,
"label": "text", "label": "text",
"bbox": { "bbox": {
"l": 234.09, "l": 234.1,
"t": 258.9, "t": 258.9,
"r": 1696.1, "r": 1696.1,
"b": 509.88, "b": 509.9,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9721011519432068, "confidence": 0.97,
"cells": [ "cells": [
{ {
"index": 0, "index": 0,
@ -385,13 +385,13 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 246.41, "r_x0": 246.4,
"r_y0": 329.07, "r_y0": 329.1,
"r_x1": 1691.99, "r_x1": 1692.0,
"r_y1": 329.07, "r_y1": 329.1,
"r_x2": 1691.99, "r_x2": 1692.0,
"r_y2": 258.9, "r_y2": 258.9,
"r_x3": 246.41, "r_x3": 246.4,
"r_y3": 258.9, "r_y3": 258.9,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
@ -410,14 +410,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 234.09, "r_x0": 234.1,
"r_y0": 419.58, "r_y0": 419.6,
"r_x1": 1696.1, "r_x1": 1696.1,
"r_y1": 419.58, "r_y1": 419.6,
"r_x2": 1696.1, "r_x2": 1696.1,
"r_y2": 349.42, "r_y2": 349.4,
"r_x3": 234.09, "r_x3": 234.1,
"r_y3": 349.42, "r_y3": 349.4,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "JSON and Markdown in an easy self contained", "text": "JSON and Markdown in an easy self contained",
@ -436,13 +436,13 @@
}, },
"rect": { "rect": {
"r_x0": 242.3, "r_x0": 242.3,
"r_y0": 509.88, "r_y0": 509.9,
"r_x1": 513.35, "r_x1": 513.3,
"r_y1": 509.88, "r_y1": 509.9,
"r_x2": 513.35, "r_x2": 513.3,
"r_y2": 439.98, "r_y2": 440.0,
"r_x3": 242.3, "r_x3": 242.3,
"r_y3": 439.98, "r_y3": 440.0,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "package", "text": "package",

10
tests/data_scanned/groundtruth/docling_v2/ocr_test.json vendored
View File

@ -39,10 +39,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 69.68, "l": 69.7,
"t": 764.92, "t": 764.9,
"r": 504.87, "r": 504.9,
"b": 689.01, "b": 689.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -63,7 +63,7 @@
"1": { "1": {
"size": { "size": {
"width": 595.2, "width": 595.2,
"height": 841.92 "height": 841.9
}, },
"page_no": 1 "page_no": 1
} }

168
tests/data_scanned/groundtruth/docling_v2/ocr_test.pages.json vendored
View File

@ -3,7 +3,7 @@
"page_no": 0, "page_no": 0,
"size": { "size": {
"width": 595.2, "width": 595.2,
"height": 841.92 "height": 841.9
}, },
"parsed_page": { "parsed_page": {
"dimension": { "dimension": {
@ -14,43 +14,43 @@
"r_x1": 595.2, "r_x1": 595.2,
"r_y1": 0.0, "r_y1": 0.0,
"r_x2": 595.2, "r_x2": 595.2,
"r_y2": 841.92, "r_y2": 841.9,
"r_x3": 0.0, "r_x3": 0.0,
"r_y3": 841.92, "r_y3": 841.9,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"boundary_type": "crop_box", "boundary_type": "crop_box",
"art_bbox": { "art_bbox": {
"l": 0.0, "l": 0.0,
"t": 841.92, "t": 841.9,
"r": 595.2, "r": 595.2,
"b": 0.0, "b": 0.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"bleed_bbox": { "bleed_bbox": {
"l": 0.0, "l": 0.0,
"t": 841.92, "t": 841.9,
"r": 595.2, "r": 595.2,
"b": 0.0, "b": 0.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"crop_bbox": { "crop_bbox": {
"l": 0.0, "l": 0.0,
"t": 841.92, "t": 841.9,
"r": 595.2, "r": 595.2,
"b": 0.0, "b": 0.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"media_bbox": { "media_bbox": {
"l": 0.0, "l": 0.0,
"t": 841.92, "t": 841.9,
"r": 595.2, "r": 595.2,
"b": 0.0, "b": 0.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"trim_bbox": { "trim_bbox": {
"l": 0.0, "l": 0.0,
"t": 841.92, "t": 841.9,
"r": 595.2, "r": 595.2,
"b": 0.0, "b": 0.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
@ -69,13 +69,13 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 73.35, "r_x0": 73.3,
"r_y0": 98.0, "r_y0": 98.0,
"r_x1": 503.65, "r_x1": 503.6,
"r_y1": 98.0, "r_y1": 98.0,
"r_x2": 503.65, "r_x2": 503.6,
"r_y2": 77.0, "r_y2": 77.0,
"r_x3": 73.35, "r_x3": 73.3,
"r_y3": 77.0, "r_y3": 77.0,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
@ -94,13 +94,13 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 69.68, "r_x0": 69.7,
"r_y0": 124.83, "r_y0": 124.8,
"r_x1": 504.87, "r_x1": 504.9,
"r_y1": 124.83, "r_y1": 124.8,
"r_x2": 504.87, "r_x2": 504.9,
"r_y2": 104.0, "r_y2": 104.0,
"r_x3": 69.68, "r_x3": 69.7,
"r_y3": 104.0, "r_y3": 104.0,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
@ -119,13 +119,13 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 71.84, "r_x0": 71.8,
"r_y0": 152.91, "r_y0": 152.9,
"r_x1": 153.09, "r_x1": 153.1,
"r_y1": 152.91, "r_y1": 152.9,
"r_x2": 153.09, "r_x2": 153.1,
"r_y2": 129.8, "r_y2": 129.8,
"r_x3": 71.84, "r_x3": 71.8,
"r_y3": 129.8, "r_y3": 129.8,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
@ -149,13 +149,13 @@
"id": 0, "id": 0,
"label": "text", "label": "text",
"bbox": { "bbox": {
"l": 69.68, "l": 69.7,
"t": 77.0, "t": 77.0,
"r": 504.87, "r": 504.9,
"b": 152.91, "b": 152.9,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9715733528137207, "confidence": 0.97,
"cells": [ "cells": [
{ {
"index": 0, "index": 0,
@ -166,13 +166,13 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 73.35, "r_x0": 73.3,
"r_y0": 98.0, "r_y0": 98.0,
"r_x1": 503.65, "r_x1": 503.6,
"r_y1": 98.0, "r_y1": 98.0,
"r_x2": 503.65, "r_x2": 503.6,
"r_y2": 77.0, "r_y2": 77.0,
"r_x3": 73.35, "r_x3": 73.3,
"r_y3": 77.0, "r_y3": 77.0,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
@ -191,13 +191,13 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 69.68, "r_x0": 69.7,
"r_y0": 124.83, "r_y0": 124.8,
"r_x1": 504.87, "r_x1": 504.9,
"r_y1": 124.83, "r_y1": 124.8,
"r_x2": 504.87, "r_x2": 504.9,
"r_y2": 104.0, "r_y2": 104.0,
"r_x3": 69.68, "r_x3": 69.7,
"r_y3": 104.0, "r_y3": 104.0,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
@ -216,13 +216,13 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 71.84, "r_x0": 71.8,
"r_y0": 152.91, "r_y0": 152.9,
"r_x1": 153.09, "r_x1": 153.1,
"r_y1": 152.91, "r_y1": 152.9,
"r_x2": 153.09, "r_x2": 153.1,
"r_y2": 129.8, "r_y2": 129.8,
"r_x3": 71.84, "r_x3": 71.8,
"r_y3": 129.8, "r_y3": 129.8,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
@ -254,13 +254,13 @@
"id": 0, "id": 0,
"label": "text", "label": "text",
"bbox": { "bbox": {
"l": 69.68, "l": 69.7,
"t": 77.0, "t": 77.0,
"r": 504.87, "r": 504.9,
"b": 152.91, "b": 152.9,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9715733528137207, "confidence": 0.97,
"cells": [ "cells": [
{ {
"index": 0, "index": 0,
@ -271,13 +271,13 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 73.35, "r_x0": 73.3,
"r_y0": 98.0, "r_y0": 98.0,
"r_x1": 503.65, "r_x1": 503.6,
"r_y1": 98.0, "r_y1": 98.0,
"r_x2": 503.65, "r_x2": 503.6,
"r_y2": 77.0, "r_y2": 77.0,
"r_x3": 73.35, "r_x3": 73.3,
"r_y3": 77.0, "r_y3": 77.0,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
@ -296,13 +296,13 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 69.68, "r_x0": 69.7,
"r_y0": 124.83, "r_y0": 124.8,
"r_x1": 504.87, "r_x1": 504.9,
"r_y1": 124.83, "r_y1": 124.8,
"r_x2": 504.87, "r_x2": 504.9,
"r_y2": 104.0, "r_y2": 104.0,
"r_x3": 69.68, "r_x3": 69.7,
"r_y3": 104.0, "r_y3": 104.0,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
@ -321,13 +321,13 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 71.84, "r_x0": 71.8,
"r_y0": 152.91, "r_y0": 152.9,
"r_x1": 153.09, "r_x1": 153.1,
"r_y1": 152.91, "r_y1": 152.9,
"r_x2": 153.09, "r_x2": 153.1,
"r_y2": 129.8, "r_y2": 129.8,
"r_x3": 71.84, "r_x3": 71.8,
"r_y3": 129.8, "r_y3": 129.8,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
@ -352,13 +352,13 @@
"id": 0, "id": 0,
"label": "text", "label": "text",
"bbox": { "bbox": {
"l": 69.68, "l": 69.7,
"t": 77.0, "t": 77.0,
"r": 504.87, "r": 504.9,
"b": 152.91, "b": 152.9,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9715733528137207, "confidence": 0.97,
"cells": [ "cells": [
{ {
"index": 0, "index": 0,
@ -369,13 +369,13 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 73.35, "r_x0": 73.3,
"r_y0": 98.0, "r_y0": 98.0,
"r_x1": 503.65, "r_x1": 503.6,
"r_y1": 98.0, "r_y1": 98.0,
"r_x2": 503.65, "r_x2": 503.6,
"r_y2": 77.0, "r_y2": 77.0,
"r_x3": 73.35, "r_x3": 73.3,
"r_y3": 77.0, "r_y3": 77.0,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
@ -394,13 +394,13 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 69.68, "r_x0": 69.7,
"r_y0": 124.83, "r_y0": 124.8,
"r_x1": 504.87, "r_x1": 504.9,
"r_y1": 124.83, "r_y1": 124.8,
"r_x2": 504.87, "r_x2": 504.9,
"r_y2": 104.0, "r_y2": 104.0,
"r_x3": 69.68, "r_x3": 69.7,
"r_y3": 104.0, "r_y3": 104.0,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
@ -419,13 +419,13 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 71.84, "r_x0": 71.8,
"r_y0": 152.91, "r_y0": 152.9,
"r_x1": 153.09, "r_x1": 153.1,
"r_y1": 152.91, "r_y1": 152.9,
"r_x2": 153.09, "r_x2": 153.1,
"r_y2": 129.8, "r_y2": 129.8,
"r_x3": 71.84, "r_x3": 71.8,
"r_y3": 129.8, "r_y3": 129.8,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },

18
tests/data_scanned/groundtruth/docling_v2/ocr_test_rotated_180.json vendored
View File

@ -42,10 +42,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 441.26, "l": 441.3,
"t": 151.88, "t": 151.9,
"r": 522.03, "r": 522.0,
"b": 131.89, "b": 131.9,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -69,10 +69,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 89.24, "l": 89.2,
"t": 124.75, "t": 124.8,
"r": 523.21, "r": 523.2,
"b": 77.02, "b": 77.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -93,7 +93,7 @@
"1": { "1": {
"size": { "size": {
"width": 595.2, "width": 595.2,
"height": 841.92 "height": 841.9
}, },
"page_no": 1 "page_no": 1
} }

230
tests/data_scanned/groundtruth/docling_v2/ocr_test_rotated_180.pages.json vendored
View File

@ -3,7 +3,7 @@
"page_no": 0, "page_no": 0,
"size": { "size": {
"width": 595.2, "width": 595.2,
"height": 841.92 "height": 841.9
}, },
"parsed_page": { "parsed_page": {
"dimension": { "dimension": {
@ -14,43 +14,43 @@
"r_x1": 595.2, "r_x1": 595.2,
"r_y1": 0.0, "r_y1": 0.0,
"r_x2": 595.2, "r_x2": 595.2,
"r_y2": 841.92, "r_y2": 841.9,
"r_x3": 0.0, "r_x3": 0.0,
"r_y3": 841.92, "r_y3": 841.9,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"boundary_type": "crop_box", "boundary_type": "crop_box",
"art_bbox": { "art_bbox": {
"l": 0.0, "l": 0.0,
"t": 841.92, "t": 841.9,
"r": 595.2, "r": 595.2,
"b": 0.0, "b": 0.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"bleed_bbox": { "bleed_bbox": {
"l": 0.0, "l": 0.0,
"t": 841.92, "t": 841.9,
"r": 595.2, "r": 595.2,
"b": 0.0, "b": 0.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"crop_bbox": { "crop_bbox": {
"l": 0.0, "l": 0.0,
"t": 841.92, "t": 841.9,
"r": 595.2, "r": 595.2,
"b": 0.0, "b": 0.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"media_bbox": { "media_bbox": {
"l": 0.0, "l": 0.0,
"t": 841.92, "t": 841.9,
"r": 595.2, "r": 595.2,
"b": 0.0, "b": 0.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"trim_bbox": { "trim_bbox": {
"l": 0.0, "l": 0.0,
"t": 841.92, "t": 841.9,
"r": 595.2, "r": 595.2,
"b": 0.0, "b": 0.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
@ -69,14 +69,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 89.24, "r_x0": 89.2,
"r_y0": 764.9, "r_y0": 764.9,
"r_x1": 521.99, "r_x1": 522.0,
"r_y1": 764.9, "r_y1": 764.9,
"r_x2": 521.99, "r_x2": 522.0,
"r_y2": 744.09, "r_y2": 744.1,
"r_x3": 89.24, "r_x3": 89.2,
"r_y3": 744.09, "r_y3": 744.1,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "Docling bundles PDF document conversion to", "text": "Docling bundles PDF document conversion to",
@ -94,14 +94,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 89.24, "r_x0": 89.2,
"r_y0": 739.2, "r_y0": 739.2,
"r_x1": 523.21, "r_x1": 523.2,
"r_y1": 739.2, "r_y1": 739.2,
"r_x2": 523.21, "r_x2": 523.2,
"r_y2": 717.17, "r_y2": 717.2,
"r_x3": 89.24, "r_x3": 89.2,
"r_y3": 717.17, "r_y3": 717.2,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "JSON and Markdown in an easy self contained", "text": "JSON and Markdown in an easy self contained",
@ -119,14 +119,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 441.26, "r_x0": 441.3,
"r_y0": 710.03, "r_y0": 710.0,
"r_x1": 522.03, "r_x1": 522.0,
"r_y1": 710.03, "r_y1": 710.0,
"r_x2": 522.03, "r_x2": 522.0,
"r_y2": 690.04, "r_y2": 690.0,
"r_x3": 441.26, "r_x3": 441.3,
"r_y3": 690.04, "r_y3": 690.0,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "package", "text": "package",
@ -149,13 +149,13 @@
"id": 0, "id": 0,
"label": "text", "label": "text",
"bbox": { "bbox": {
"l": 89.24, "l": 89.2,
"t": 717.17, "t": 717.2,
"r": 523.21, "r": 523.2,
"b": 764.9, "b": 764.9,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.7318570613861084, "confidence": 0.73,
"cells": [ "cells": [
{ {
"index": 0, "index": 0,
@ -166,14 +166,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 89.24, "r_x0": 89.2,
"r_y0": 764.9, "r_y0": 764.9,
"r_x1": 521.99, "r_x1": 522.0,
"r_y1": 764.9, "r_y1": 764.9,
"r_x2": 521.99, "r_x2": 522.0,
"r_y2": 744.09, "r_y2": 744.1,
"r_x3": 89.24, "r_x3": 89.2,
"r_y3": 744.09, "r_y3": 744.1,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "Docling bundles PDF document conversion to", "text": "Docling bundles PDF document conversion to",
@ -191,14 +191,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 89.24, "r_x0": 89.2,
"r_y0": 739.2, "r_y0": 739.2,
"r_x1": 523.21, "r_x1": 523.2,
"r_y1": 739.2, "r_y1": 739.2,
"r_x2": 523.21, "r_x2": 523.2,
"r_y2": 717.17, "r_y2": 717.2,
"r_x3": 89.24, "r_x3": 89.2,
"r_y3": 717.17, "r_y3": 717.2,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "JSON and Markdown in an easy self contained", "text": "JSON and Markdown in an easy self contained",
@ -214,13 +214,13 @@
"id": 2, "id": 2,
"label": "text", "label": "text",
"bbox": { "bbox": {
"l": 441.26, "l": 441.3,
"t": 690.04, "t": 690.0,
"r": 522.03, "r": 522.0,
"b": 710.03, "b": 710.0,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.5982133150100708, "confidence": 0.6,
"cells": [ "cells": [
{ {
"index": 2, "index": 2,
@ -231,14 +231,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 441.26, "r_x0": 441.3,
"r_y0": 710.03, "r_y0": 710.0,
"r_x1": 522.03, "r_x1": 522.0,
"r_y1": 710.03, "r_y1": 710.0,
"r_x2": 522.03, "r_x2": 522.0,
"r_y2": 690.04, "r_y2": 690.0,
"r_x3": 441.26, "r_x3": 441.3,
"r_y3": 690.04, "r_y3": 690.0,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "package", "text": "package",
@ -269,13 +269,13 @@
"id": 0, "id": 0,
"label": "text", "label": "text",
"bbox": { "bbox": {
"l": 89.24, "l": 89.2,
"t": 717.17, "t": 717.2,
"r": 523.21, "r": 523.2,
"b": 764.9, "b": 764.9,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.7318570613861084, "confidence": 0.73,
"cells": [ "cells": [
{ {
"index": 0, "index": 0,
@ -286,14 +286,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 89.24, "r_x0": 89.2,
"r_y0": 764.9, "r_y0": 764.9,
"r_x1": 521.99, "r_x1": 522.0,
"r_y1": 764.9, "r_y1": 764.9,
"r_x2": 521.99, "r_x2": 522.0,
"r_y2": 744.09, "r_y2": 744.1,
"r_x3": 89.24, "r_x3": 89.2,
"r_y3": 744.09, "r_y3": 744.1,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "Docling bundles PDF document conversion to", "text": "Docling bundles PDF document conversion to",
@ -311,14 +311,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 89.24, "r_x0": 89.2,
"r_y0": 739.2, "r_y0": 739.2,
"r_x1": 523.21, "r_x1": 523.2,
"r_y1": 739.2, "r_y1": 739.2,
"r_x2": 523.21, "r_x2": 523.2,
"r_y2": 717.17, "r_y2": 717.2,
"r_x3": 89.24, "r_x3": 89.2,
"r_y3": 717.17, "r_y3": 717.2,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "JSON and Markdown in an easy self contained", "text": "JSON and Markdown in an easy self contained",
@ -340,13 +340,13 @@
"id": 2, "id": 2,
"label": "text", "label": "text",
"bbox": { "bbox": {
"l": 441.26, "l": 441.3,
"t": 690.04, "t": 690.0,
"r": 522.03, "r": 522.0,
"b": 710.03, "b": 710.0,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.5982133150100708, "confidence": 0.6,
"cells": [ "cells": [
{ {
"index": 2, "index": 2,
@ -357,14 +357,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 441.26, "r_x0": 441.3,
"r_y0": 710.03, "r_y0": 710.0,
"r_x1": 522.03, "r_x1": 522.0,
"r_y1": 710.03, "r_y1": 710.0,
"r_x2": 522.03, "r_x2": 522.0,
"r_y2": 690.04, "r_y2": 690.0,
"r_x3": 441.26, "r_x3": 441.3,
"r_y3": 690.04, "r_y3": 690.0,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "package", "text": "package",
@ -388,13 +388,13 @@
"id": 0, "id": 0,
"label": "text", "label": "text",
"bbox": { "bbox": {
"l": 89.24, "l": 89.2,
"t": 717.17, "t": 717.2,
"r": 523.21, "r": 523.2,
"b": 764.9, "b": 764.9,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.7318570613861084, "confidence": 0.73,
"cells": [ "cells": [
{ {
"index": 0, "index": 0,
@ -405,14 +405,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 89.24, "r_x0": 89.2,
"r_y0": 764.9, "r_y0": 764.9,
"r_x1": 521.99, "r_x1": 522.0,
"r_y1": 764.9, "r_y1": 764.9,
"r_x2": 521.99, "r_x2": 522.0,
"r_y2": 744.09, "r_y2": 744.1,
"r_x3": 89.24, "r_x3": 89.2,
"r_y3": 744.09, "r_y3": 744.1,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "Docling bundles PDF document conversion to", "text": "Docling bundles PDF document conversion to",
@ -430,14 +430,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 89.24, "r_x0": 89.2,
"r_y0": 739.2, "r_y0": 739.2,
"r_x1": 523.21, "r_x1": 523.2,
"r_y1": 739.2, "r_y1": 739.2,
"r_x2": 523.21, "r_x2": 523.2,
"r_y2": 717.17, "r_y2": 717.2,
"r_x3": 89.24, "r_x3": 89.2,
"r_y3": 717.17, "r_y3": 717.2,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "JSON and Markdown in an easy self contained", "text": "JSON and Markdown in an easy self contained",
@ -459,13 +459,13 @@
"id": 2, "id": 2,
"label": "text", "label": "text",
"bbox": { "bbox": {
"l": 441.26, "l": 441.3,
"t": 690.04, "t": 690.0,
"r": 522.03, "r": 522.0,
"b": 710.03, "b": 710.0,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.5982133150100708, "confidence": 0.6,
"cells": [ "cells": [
{ {
"index": 2, "index": 2,
@ -476,14 +476,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 441.26, "r_x0": 441.3,
"r_y0": 710.03, "r_y0": 710.0,
"r_x1": 522.03, "r_x1": 522.0,
"r_y1": 710.03, "r_y1": 710.0,
"r_x2": 522.03, "r_x2": 522.0,
"r_y2": 690.04, "r_y2": 690.0,
"r_x3": 441.26, "r_x3": 441.3,
"r_y3": 690.04, "r_y3": 690.0,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "package", "text": "package",

14
tests/data_scanned/groundtruth/docling_v2/ocr_test_rotated_270.json vendored
View File

@ -42,10 +42,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 717.17, "l": 717.2,
"t": 524.3, "t": 524.3,
"r": 764.9, "r": 764.9,
"b": 90.33, "b": 90.3,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -69,10 +69,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 690.24, "l": 690.2,
"t": 523.08, "t": 523.1,
"r": 709.83, "r": 709.8,
"b": 442.39, "b": 442.4,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -92,7 +92,7 @@
"pages": { "pages": {
"1": { "1": {
"size": { "size": {
"width": 841.92, "width": 841.9,
"height": 595.2 "height": 595.2
}, },
"page_no": 1 "page_no": 1

218
tests/data_scanned/groundtruth/docling_v2/ocr_test_rotated_270.pages.json vendored
View File

@ -2,7 +2,7 @@
{ {
"page_no": 0, "page_no": 0,
"size": { "size": {
"width": 841.92, "width": 841.9,
"height": 595.2 "height": 595.2
}, },
"parsed_page": { "parsed_page": {
@ -14,43 +14,43 @@
"r_x1": 595.2, "r_x1": 595.2,
"r_y1": 0.0, "r_y1": 0.0,
"r_x2": 595.2, "r_x2": 595.2,
"r_y2": 841.92, "r_y2": 841.9,
"r_x3": 0.0, "r_x3": 0.0,
"r_y3": 841.92, "r_y3": 841.9,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"boundary_type": "crop_box", "boundary_type": "crop_box",
"art_bbox": { "art_bbox": {
"l": 0.0, "l": 0.0,
"t": 841.92, "t": 841.9,
"r": 595.2, "r": 595.2,
"b": 0.0, "b": 0.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"bleed_bbox": { "bleed_bbox": {
"l": 0.0, "l": 0.0,
"t": 841.92, "t": 841.9,
"r": 595.2, "r": 595.2,
"b": 0.0, "b": 0.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"crop_bbox": { "crop_bbox": {
"l": 0.0, "l": 0.0,
"t": 841.92, "t": 841.9,
"r": 595.2, "r": 595.2,
"b": 0.0, "b": 0.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"media_bbox": { "media_bbox": {
"l": 0.0, "l": 0.0,
"t": 841.92, "t": 841.9,
"r": 595.2, "r": 595.2,
"b": 0.0, "b": 0.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"trim_bbox": { "trim_bbox": {
"l": 0.0, "l": 0.0,
"t": 841.92, "t": 841.9,
"r": 595.2, "r": 595.2,
"b": 0.0, "b": 0.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
@ -69,14 +69,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 744.09, "r_x0": 744.1,
"r_y0": 504.87, "r_y0": 504.9,
"r_x1": 764.9, "r_x1": 764.9,
"r_y1": 504.87, "r_y1": 504.9,
"r_x2": 764.9, "r_x2": 764.9,
"r_y2": 73.35, "r_y2": 73.3,
"r_x3": 744.09, "r_x3": 744.1,
"r_y3": 73.35, "r_y3": 73.3,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "Docling bundles PDF document conversion to", "text": "Docling bundles PDF document conversion to",
@ -94,13 +94,13 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 717.17, "r_x0": 717.2,
"r_y0": 504.87, "r_y0": 504.9,
"r_x1": 737.97, "r_x1": 738.0,
"r_y1": 504.87, "r_y1": 504.9,
"r_x2": 737.97, "r_x2": 738.0,
"r_y2": 70.9, "r_y2": 70.9,
"r_x3": 717.17, "r_x3": 717.2,
"r_y3": 70.9, "r_y3": 70.9,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
@ -119,14 +119,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 690.24, "r_x0": 690.2,
"r_y0": 152.81, "r_y0": 152.8,
"r_x1": 709.83, "r_x1": 709.8,
"r_y1": 152.81, "r_y1": 152.8,
"r_x2": 709.83, "r_x2": 709.8,
"r_y2": 72.12, "r_y2": 72.1,
"r_x3": 690.24, "r_x3": 690.2,
"r_y3": 72.12, "r_y3": 72.1,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "package", "text": "package",
@ -149,13 +149,13 @@
"id": 0, "id": 0,
"label": "page_header", "label": "page_header",
"bbox": { "bbox": {
"l": 717.17, "l": 717.2,
"t": 70.9, "t": 70.9,
"r": 764.9, "r": 764.9,
"b": 504.87, "b": 504.9,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.6915205121040344, "confidence": 0.69,
"cells": [ "cells": [
{ {
"index": 0, "index": 0,
@ -166,14 +166,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 744.09, "r_x0": 744.1,
"r_y0": 504.87, "r_y0": 504.9,
"r_x1": 764.9, "r_x1": 764.9,
"r_y1": 504.87, "r_y1": 504.9,
"r_x2": 764.9, "r_x2": 764.9,
"r_y2": 73.35, "r_y2": 73.3,
"r_x3": 744.09, "r_x3": 744.1,
"r_y3": 73.35, "r_y3": 73.3,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "Docling bundles PDF document conversion to", "text": "Docling bundles PDF document conversion to",
@ -191,13 +191,13 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 717.17, "r_x0": 717.2,
"r_y0": 504.87, "r_y0": 504.9,
"r_x1": 737.97, "r_x1": 738.0,
"r_y1": 504.87, "r_y1": 504.9,
"r_x2": 737.97, "r_x2": 738.0,
"r_y2": 70.9, "r_y2": 70.9,
"r_x3": 717.17, "r_x3": 717.2,
"r_y3": 70.9, "r_y3": 70.9,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
@ -214,10 +214,10 @@
"id": 8, "id": 8,
"label": "text", "label": "text",
"bbox": { "bbox": {
"l": 690.24, "l": 690.2,
"t": 72.12, "t": 72.1,
"r": 709.83, "r": 709.8,
"b": 152.81, "b": 152.8,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 1.0, "confidence": 1.0,
@ -231,14 +231,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 690.24, "r_x0": 690.2,
"r_y0": 152.81, "r_y0": 152.8,
"r_x1": 709.83, "r_x1": 709.8,
"r_y1": 152.81, "r_y1": 152.8,
"r_x2": 709.83, "r_x2": 709.8,
"r_y2": 72.12, "r_y2": 72.1,
"r_x3": 690.24, "r_x3": 690.2,
"r_y3": 72.12, "r_y3": 72.1,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "package", "text": "package",
@ -269,13 +269,13 @@
"id": 0, "id": 0,
"label": "page_header", "label": "page_header",
"bbox": { "bbox": {
"l": 717.17, "l": 717.2,
"t": 70.9, "t": 70.9,
"r": 764.9, "r": 764.9,
"b": 504.87, "b": 504.9,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.6915205121040344, "confidence": 0.69,
"cells": [ "cells": [
{ {
"index": 0, "index": 0,
@ -286,14 +286,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 744.09, "r_x0": 744.1,
"r_y0": 504.87, "r_y0": 504.9,
"r_x1": 764.9, "r_x1": 764.9,
"r_y1": 504.87, "r_y1": 504.9,
"r_x2": 764.9, "r_x2": 764.9,
"r_y2": 73.35, "r_y2": 73.3,
"r_x3": 744.09, "r_x3": 744.1,
"r_y3": 73.35, "r_y3": 73.3,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "Docling bundles PDF document conversion to", "text": "Docling bundles PDF document conversion to",
@ -311,13 +311,13 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 717.17, "r_x0": 717.2,
"r_y0": 504.87, "r_y0": 504.9,
"r_x1": 737.97, "r_x1": 738.0,
"r_y1": 504.87, "r_y1": 504.9,
"r_x2": 737.97, "r_x2": 738.0,
"r_y2": 70.9, "r_y2": 70.9,
"r_x3": 717.17, "r_x3": 717.2,
"r_y3": 70.9, "r_y3": 70.9,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
@ -340,10 +340,10 @@
"id": 8, "id": 8,
"label": "text", "label": "text",
"bbox": { "bbox": {
"l": 690.24, "l": 690.2,
"t": 72.12, "t": 72.1,
"r": 709.83, "r": 709.8,
"b": 152.81, "b": 152.8,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 1.0, "confidence": 1.0,
@ -357,14 +357,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 690.24, "r_x0": 690.2,
"r_y0": 152.81, "r_y0": 152.8,
"r_x1": 709.83, "r_x1": 709.8,
"r_y1": 152.81, "r_y1": 152.8,
"r_x2": 709.83, "r_x2": 709.8,
"r_y2": 72.12, "r_y2": 72.1,
"r_x3": 690.24, "r_x3": 690.2,
"r_y3": 72.12, "r_y3": 72.1,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "package", "text": "package",
@ -388,10 +388,10 @@
"id": 8, "id": 8,
"label": "text", "label": "text",
"bbox": { "bbox": {
"l": 690.24, "l": 690.2,
"t": 72.12, "t": 72.1,
"r": 709.83, "r": 709.8,
"b": 152.81, "b": 152.8,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 1.0, "confidence": 1.0,
@ -405,14 +405,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 690.24, "r_x0": 690.2,
"r_y0": 152.81, "r_y0": 152.8,
"r_x1": 709.83, "r_x1": 709.8,
"r_y1": 152.81, "r_y1": 152.8,
"r_x2": 709.83, "r_x2": 709.8,
"r_y2": 72.12, "r_y2": 72.1,
"r_x3": 690.24, "r_x3": 690.2,
"r_y3": 72.12, "r_y3": 72.1,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "package", "text": "package",
@ -436,13 +436,13 @@
"id": 0, "id": 0,
"label": "page_header", "label": "page_header",
"bbox": { "bbox": {
"l": 717.17, "l": 717.2,
"t": 70.9, "t": 70.9,
"r": 764.9, "r": 764.9,
"b": 504.87, "b": 504.9,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.6915205121040344, "confidence": 0.69,
"cells": [ "cells": [
{ {
"index": 0, "index": 0,
@ -453,14 +453,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 744.09, "r_x0": 744.1,
"r_y0": 504.87, "r_y0": 504.9,
"r_x1": 764.9, "r_x1": 764.9,
"r_y1": 504.87, "r_y1": 504.9,
"r_x2": 764.9, "r_x2": 764.9,
"r_y2": 73.35, "r_y2": 73.3,
"r_x3": 744.09, "r_x3": 744.1,
"r_y3": 73.35, "r_y3": 73.3,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "Docling bundles PDF document conversion to", "text": "Docling bundles PDF document conversion to",
@ -478,13 +478,13 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 717.17, "r_x0": 717.2,
"r_y0": 504.87, "r_y0": 504.9,
"r_x1": 737.97, "r_x1": 738.0,
"r_y1": 504.87, "r_y1": 504.9,
"r_x2": 737.97, "r_x2": 738.0,
"r_y2": 70.9, "r_y2": 70.9,
"r_x3": 717.17, "r_x3": 717.2,
"r_y3": 70.9, "r_y3": 70.9,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },

14
tests/data_scanned/groundtruth/docling_v2/ocr_test_rotated_90.json vendored
View File

@ -43,9 +43,9 @@
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 77.1, "l": 77.1,
"t": 506.07, "t": 506.1,
"r": 126.08, "r": 126.1,
"b": 71.88, "b": 71.9,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -69,10 +69,10 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 131.21, "l": 131.2,
"t": 154.19, "t": 154.2,
"r": 152.2, "r": 152.2,
"b": 74.12, "b": 74.1,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"charspan": [ "charspan": [
@ -92,7 +92,7 @@
"pages": { "pages": {
"1": { "1": {
"size": { "size": {
"width": 841.92, "width": 841.9,
"height": 595.2 "height": 595.2
}, },
"page_no": 1 "page_no": 1

224
tests/data_scanned/groundtruth/docling_v2/ocr_test_rotated_90.pages.json vendored
View File

@ -2,7 +2,7 @@
{ {
"page_no": 0, "page_no": 0,
"size": { "size": {
"width": 841.92, "width": 841.9,
"height": 595.2 "height": 595.2
}, },
"parsed_page": { "parsed_page": {
@ -14,43 +14,43 @@
"r_x1": 595.2, "r_x1": 595.2,
"r_y1": 0.0, "r_y1": 0.0,
"r_x2": 595.2, "r_x2": 595.2,
"r_y2": 841.92, "r_y2": 841.9,
"r_x3": 0.0, "r_x3": 0.0,
"r_y3": 841.92, "r_y3": 841.9,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"boundary_type": "crop_box", "boundary_type": "crop_box",
"art_bbox": { "art_bbox": {
"l": 0.0, "l": 0.0,
"t": 841.92, "t": 841.9,
"r": 595.2, "r": 595.2,
"b": 0.0, "b": 0.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"bleed_bbox": { "bleed_bbox": {
"l": 0.0, "l": 0.0,
"t": 841.92, "t": 841.9,
"r": 595.2, "r": 595.2,
"b": 0.0, "b": 0.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"crop_bbox": { "crop_bbox": {
"l": 0.0, "l": 0.0,
"t": 841.92, "t": 841.9,
"r": 595.2, "r": 595.2,
"b": 0.0, "b": 0.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"media_bbox": { "media_bbox": {
"l": 0.0, "l": 0.0,
"t": 841.92, "t": 841.9,
"r": 595.2, "r": 595.2,
"b": 0.0, "b": 0.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
}, },
"trim_bbox": { "trim_bbox": {
"l": 0.0, "l": 0.0,
"t": 841.92, "t": 841.9,
"r": 595.2, "r": 595.2,
"b": 0.0, "b": 0.0,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"
@ -70,13 +70,13 @@
}, },
"rect": { "rect": {
"r_x0": 77.1, "r_x0": 77.1,
"r_y0": 520.76, "r_y0": 520.8,
"r_x1": 96.68, "r_x1": 96.7,
"r_y1": 520.76, "r_y1": 520.8,
"r_x2": 96.68, "r_x2": 96.7,
"r_y2": 89.24, "r_y2": 89.2,
"r_x3": 77.1, "r_x3": 77.1,
"r_y3": 89.24, "r_y3": 89.2,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "Docling bundles PDF document conversion to", "text": "Docling bundles PDF document conversion to",
@ -94,14 +94,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 100.64, "r_x0": 100.6,
"r_y0": 523.32, "r_y0": 523.3,
"r_x1": 126.08, "r_x1": 126.1,
"r_y1": 523.32, "r_y1": 523.3,
"r_x2": 126.08, "r_x2": 126.1,
"r_y2": 89.13, "r_y2": 89.1,
"r_x3": 100.64, "r_x3": 100.6,
"r_y3": 89.13, "r_y3": 89.1,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "JSON and Markdown in an easy self contained", "text": "JSON and Markdown in an easy self contained",
@ -119,14 +119,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 131.21, "r_x0": 131.2,
"r_y0": 521.08, "r_y0": 521.1,
"r_x1": 152.2, "r_x1": 152.2,
"r_y1": 521.08, "r_y1": 521.1,
"r_x2": 152.2, "r_x2": 152.2,
"r_y2": 441.01, "r_y2": 441.0,
"r_x3": 131.21, "r_x3": 131.2,
"r_y3": 441.01, "r_y3": 441.0,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "package", "text": "package",
@ -150,12 +150,12 @@
"label": "page_header", "label": "page_header",
"bbox": { "bbox": {
"l": 77.1, "l": 77.1,
"t": 89.13, "t": 89.1,
"r": 126.08, "r": 126.1,
"b": 523.32, "b": 523.3,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.6016772389411926, "confidence": 0.6,
"cells": [ "cells": [
{ {
"index": 0, "index": 0,
@ -167,13 +167,13 @@
}, },
"rect": { "rect": {
"r_x0": 77.1, "r_x0": 77.1,
"r_y0": 520.76, "r_y0": 520.8,
"r_x1": 96.68, "r_x1": 96.7,
"r_y1": 520.76, "r_y1": 520.8,
"r_x2": 96.68, "r_x2": 96.7,
"r_y2": 89.24, "r_y2": 89.2,
"r_x3": 77.1, "r_x3": 77.1,
"r_y3": 89.24, "r_y3": 89.2,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "Docling bundles PDF document conversion to", "text": "Docling bundles PDF document conversion to",
@ -191,14 +191,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 100.64, "r_x0": 100.6,
"r_y0": 523.32, "r_y0": 523.3,
"r_x1": 126.08, "r_x1": 126.1,
"r_y1": 523.32, "r_y1": 523.3,
"r_x2": 126.08, "r_x2": 126.1,
"r_y2": 89.13, "r_y2": 89.1,
"r_x3": 100.64, "r_x3": 100.6,
"r_y3": 89.13, "r_y3": 89.1,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "JSON and Markdown in an easy self contained", "text": "JSON and Markdown in an easy self contained",
@ -214,13 +214,13 @@
"id": 1, "id": 1,
"label": "text", "label": "text",
"bbox": { "bbox": {
"l": 131.21, "l": 131.2,
"t": 441.01, "t": 441.0,
"r": 152.2, "r": 152.2,
"b": 521.08, "b": 521.1,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.5234212875366211, "confidence": 0.52,
"cells": [ "cells": [
{ {
"index": 2, "index": 2,
@ -231,14 +231,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 131.21, "r_x0": 131.2,
"r_y0": 521.08, "r_y0": 521.1,
"r_x1": 152.2, "r_x1": 152.2,
"r_y1": 521.08, "r_y1": 521.1,
"r_x2": 152.2, "r_x2": 152.2,
"r_y2": 441.01, "r_y2": 441.0,
"r_x3": 131.21, "r_x3": 131.2,
"r_y3": 441.01, "r_y3": 441.0,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "package", "text": "package",
@ -270,12 +270,12 @@
"label": "page_header", "label": "page_header",
"bbox": { "bbox": {
"l": 77.1, "l": 77.1,
"t": 89.13, "t": 89.1,
"r": 126.08, "r": 126.1,
"b": 523.32, "b": 523.3,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.6016772389411926, "confidence": 0.6,
"cells": [ "cells": [
{ {
"index": 0, "index": 0,
@ -287,13 +287,13 @@
}, },
"rect": { "rect": {
"r_x0": 77.1, "r_x0": 77.1,
"r_y0": 520.76, "r_y0": 520.8,
"r_x1": 96.68, "r_x1": 96.7,
"r_y1": 520.76, "r_y1": 520.8,
"r_x2": 96.68, "r_x2": 96.7,
"r_y2": 89.24, "r_y2": 89.2,
"r_x3": 77.1, "r_x3": 77.1,
"r_y3": 89.24, "r_y3": 89.2,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "Docling bundles PDF document conversion to", "text": "Docling bundles PDF document conversion to",
@ -311,14 +311,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 100.64, "r_x0": 100.6,
"r_y0": 523.32, "r_y0": 523.3,
"r_x1": 126.08, "r_x1": 126.1,
"r_y1": 523.32, "r_y1": 523.3,
"r_x2": 126.08, "r_x2": 126.1,
"r_y2": 89.13, "r_y2": 89.1,
"r_x3": 100.64, "r_x3": 100.6,
"r_y3": 89.13, "r_y3": 89.1,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "JSON and Markdown in an easy self contained", "text": "JSON and Markdown in an easy self contained",
@ -340,13 +340,13 @@
"id": 1, "id": 1,
"label": "text", "label": "text",
"bbox": { "bbox": {
"l": 131.21, "l": 131.2,
"t": 441.01, "t": 441.0,
"r": 152.2, "r": 152.2,
"b": 521.08, "b": 521.1,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.5234212875366211, "confidence": 0.52,
"cells": [ "cells": [
{ {
"index": 2, "index": 2,
@ -357,14 +357,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 131.21, "r_x0": 131.2,
"r_y0": 521.08, "r_y0": 521.1,
"r_x1": 152.2, "r_x1": 152.2,
"r_y1": 521.08, "r_y1": 521.1,
"r_x2": 152.2, "r_x2": 152.2,
"r_y2": 441.01, "r_y2": 441.0,
"r_x3": 131.21, "r_x3": 131.2,
"r_y3": 441.01, "r_y3": 441.0,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "package", "text": "package",
@ -388,13 +388,13 @@
"id": 1, "id": 1,
"label": "text", "label": "text",
"bbox": { "bbox": {
"l": 131.21, "l": 131.2,
"t": 441.01, "t": 441.0,
"r": 152.2, "r": 152.2,
"b": 521.08, "b": 521.1,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.5234212875366211, "confidence": 0.52,
"cells": [ "cells": [
{ {
"index": 2, "index": 2,
@ -405,14 +405,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 131.21, "r_x0": 131.2,
"r_y0": 521.08, "r_y0": 521.1,
"r_x1": 152.2, "r_x1": 152.2,
"r_y1": 521.08, "r_y1": 521.1,
"r_x2": 152.2, "r_x2": 152.2,
"r_y2": 441.01, "r_y2": 441.0,
"r_x3": 131.21, "r_x3": 131.2,
"r_y3": 441.01, "r_y3": 441.0,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "package", "text": "package",
@ -437,12 +437,12 @@
"label": "page_header", "label": "page_header",
"bbox": { "bbox": {
"l": 77.1, "l": 77.1,
"t": 89.13, "t": 89.1,
"r": 126.08, "r": 126.1,
"b": 523.32, "b": 523.3,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.6016772389411926, "confidence": 0.6,
"cells": [ "cells": [
{ {
"index": 0, "index": 0,
@ -454,13 +454,13 @@
}, },
"rect": { "rect": {
"r_x0": 77.1, "r_x0": 77.1,
"r_y0": 520.76, "r_y0": 520.8,
"r_x1": 96.68, "r_x1": 96.7,
"r_y1": 520.76, "r_y1": 520.8,
"r_x2": 96.68, "r_x2": 96.7,
"r_y2": 89.24, "r_y2": 89.2,
"r_x3": 77.1, "r_x3": 77.1,
"r_y3": 89.24, "r_y3": 89.2,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "Docling bundles PDF document conversion to", "text": "Docling bundles PDF document conversion to",
@ -478,14 +478,14 @@
"a": 255 "a": 255
}, },
"rect": { "rect": {
"r_x0": 100.64, "r_x0": 100.6,
"r_y0": 523.32, "r_y0": 523.3,
"r_x1": 126.08, "r_x1": 126.1,
"r_y1": 523.32, "r_y1": 523.3,
"r_x2": 126.08, "r_x2": 126.1,
"r_y2": 89.13, "r_y2": 89.1,
"r_x3": 100.64, "r_x3": 100.6,
"r_y3": 89.13, "r_y3": 89.1,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"text": "JSON and Markdown in an easy self contained", "text": "JSON and Markdown in an easy self contained",

23
tests/verify_utils.py
View File

@ -12,6 +12,10 @@ from docling_core.types.doc import (
TableItem, TableItem,
TextItem, TextItem,
) )
from docling_core.types.doc.base import (
BoundingBox,
PydanticSerCtxKey,
)
from docling_core.types.legacy_doc.document import ExportedCCSDocument as DsDocument from docling_core.types.legacy_doc.document import ExportedCCSDocument as DsDocument
from PIL import Image as PILImage from PIL import Image as PILImage
from pydantic import TypeAdapter from pydantic import TypeAdapter
@ -20,8 +24,8 @@ from pydantic.json import pydantic_encoder
from docling.datamodel.base_models import ConversionStatus, Page from docling.datamodel.base_models import ConversionStatus, Page
from docling.datamodel.document import ConversionResult from docling.datamodel.document import ConversionResult
COORD_PREC = 2 # decimal places for coordinates COORD_PREC = 1 # decimal places for coordinates
CONFID_PREC = 1 # decimal places for confidence CONFID_PREC = 2 # decimal places for confidence
def levenshtein(str1: str, str2: str) -> int: def levenshtein(str1: str, str2: str) -> int:
@ -79,9 +83,13 @@ def verify_cells(doc_pred_pages: List[Page], doc_true_pages: List[Page]):
assert true_text == pred_text, f"{true_text}!={pred_text}" assert true_text == pred_text, f"{true_text}!={pred_text}"
true_bbox = cell_true_item.rect.to_bounding_box().as_tuple() true_bbox = cell_true_item.rect.to_bounding_box().as_tuple()
pred_bbox = cell_pred_item.rect.to_bounding_box().as_tuple() norm_pred_bbox = BoundingBox.model_validate_json(
assert true_bbox == pred_bbox, ( cell_pred_item.rect.to_bounding_box().model_dump_json(
f"bbox is not the same: {true_bbox} != {pred_bbox}" context={PydanticSerCtxKey.COORD_PREC.value: COORD_PREC}
)
).as_tuple()
assert true_bbox == norm_pred_bbox, (
f"bbox is not the same: {true_bbox} != {norm_pred_bbox}"
) )
return True return True
@ -415,7 +423,10 @@ def verify_conversion_result_v2(
pages_data = [ pages_data = [
page.model_dump( page.model_dump(
mode="json", mode="json",
context={"coord_prec": COORD_PREC, "confid_prec": CONFID_PREC}, context={
PydanticSerCtxKey.COORD_PREC.value: COORD_PREC,
PydanticSerCtxKey.CONFID_PREC.value: CONFID_PREC,
},
) )
for page in doc_pred_pages for page in doc_pred_pages
] ]

8
uv.lock generated
View File

@ -904,7 +904,7 @@ requires-dist = [
{ name = "accelerate", marker = "extra == 'vlm'", specifier = ">=1.2.1,<2.0.0" }, { name = "accelerate", marker = "extra == 'vlm'", specifier = ">=1.2.1,<2.0.0" },
{ name = "beautifulsoup4", specifier = ">=4.12.3,<5.0.0" }, { name = "beautifulsoup4", specifier = ">=4.12.3,<5.0.0" },
{ name = "certifi", specifier = ">=2024.7.4" }, { name = "certifi", specifier = ">=2024.7.4" },
{ name = "docling-core", extras = ["chunking"], specifier = ">=2.40.0,<3.0.0" }, { name = "docling-core", extras = ["chunking"], git = "https://github.com/docling-project/docling-core.git?rev=0c648aafc28e94780b88bbd91870e2c74d9f9602" },
{ name = "docling-ibm-models", specifier = ">=3.6.0,<4" }, { name = "docling-ibm-models", specifier = ">=3.6.0,<4" },
{ name = "docling-parse", specifier = ">=4.0.0,<5.0.0" }, { name = "docling-parse", specifier = ">=4.0.0,<5.0.0" },
{ name = "easyocr", specifier = ">=1.7,<2.0" }, { name = "easyocr", specifier = ">=1.7,<2.0" },
@ -980,7 +980,7 @@ examples = [
[[package]] [[package]]
name = "docling-core" name = "docling-core"
version = "2.41.0" version = "2.41.0"
source = { registry = "https://pypi.org/simple" } source = { git = "https://github.com/docling-project/docling-core.git?rev=0c648aafc28e94780b88bbd91870e2c74d9f9602#0c648aafc28e94780b88bbd91870e2c74d9f9602" }
dependencies = [ dependencies = [
{ name = "jsonref" }, { name = "jsonref" },
{ name = "jsonschema" }, { name = "jsonschema" },
@ -993,10 +993,6 @@ dependencies = [
{ name = "typer" }, { name = "typer" },
{ name = "typing-extensions" }, { name = "typing-extensions" },
] ]
sdist = { url = "https://files.pythonhosted.org/packages/fc/d4/e2dd9212562888d251c41ac81571f206cd651eb73ca567ab99a073138311/docling_core-2.41.0.tar.gz", hash = "sha256:f0cc1da14a11de55b3d9fd8f560cf6feb5458eedde931c13db435be18fe655d8", size = 149075, upload-time = "2025-07-09T07:43:53.702Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/87/27/f33849493aa9b3925e766fcaf33f0254b808960b5c77aaab807c30343ea7/docling_core-2.41.0-py3-none-any.whl", hash = "sha256:2d719279e701f339ef30e8db7d00d35f4c2fef56a0a2f35a7bd4a39733ab39cd", size = 153553, upload-time = "2025-07-09T07:43:51.668Z" },
]
[package.optional-dependencies] [package.optional-dependencies]
chunking = [ chunking = [