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

Update all test cases

Browse Source 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer 2025-06-20 13:31:28 +02:00
parent 926e32037d
commit c146c8f309
52 changed files with 923 additions and 618 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
tests/data/groundtruth/docling_v1/2305.03393v1-pg9.json vendored
View File

@ -213,10 +213,10 @@
"prov": [ "prov": [
{ {
"bbox": [ "bbox": [
139.6674041748047, 139.66741943359375,
322.5054626464844, 322.5054626464844,
475.00927734375, 475.00927734375,
454.4546203613281 454.45458984375
], ],
"page": 1, "page": 1,
"span": [ "span": [

58
tests/data/groundtruth/docling_v1/2305.03393v1-pg9.pages.json vendored
View File

@ -2705,7 +2705,7 @@
"b": 102.78223000000003, "b": 102.78223000000003,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9373533129692078, "confidence": 0.9373534917831421,
"cells": [ "cells": [
{ {
"index": 0, "index": 0,
@ -2745,7 +2745,7 @@
"b": 102.78223000000003, "b": 102.78223000000003,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.8858679533004761, "confidence": 0.8858680725097656,
"cells": [ "cells": [
{ {
"index": 1, "index": 1,
@ -2785,7 +2785,7 @@
"b": 152.90697999999998, "b": 152.90697999999998,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9806435108184814, "confidence": 0.9806433916091919,
"cells": [ "cells": [
{ {
"index": 2, "index": 2,
@ -2940,7 +2940,7 @@
"b": 255.42400999999995, "b": 255.42400999999995,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9850425124168396, "confidence": 0.98504239320755,
"cells": [ "cells": [
{ {
"index": 7, "index": 7,
@ -3155,7 +3155,7 @@
"b": 327.98218, "b": 327.98218,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9591907262802124, "confidence": 0.9591909050941467,
"cells": [ "cells": [
{ {
"index": 15, "index": 15,
@ -3339,8 +3339,8 @@
"id": 0, "id": 0,
"label": "table", "label": "table",
"bbox": { "bbox": {
"l": 139.6674041748047, "l": 139.66741943359375,
"t": 337.5453796386719, "t": 337.54541015625,
"r": 475.00927734375, "r": 475.00927734375,
"b": 469.4945373535156, "b": 469.4945373535156,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
@ -7846,7 +7846,7 @@
"b": 518.17419, "b": 518.17419,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9589295387268066, "confidence": 0.9589294195175171,
"cells": [ "cells": [
{ {
"index": 91, "index": 91,
@ -7911,7 +7911,7 @@
"b": 618.3, "b": 618.3,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9849976301193237, "confidence": 0.9849975109100342,
"cells": [ "cells": [
{ {
"index": 93, "index": 93,
@ -8243,8 +8243,8 @@
"id": 0, "id": 0,
"label": "table", "label": "table",
"bbox": { "bbox": {
"l": 139.6674041748047, "l": 139.66741943359375,
"t": 337.5453796386719, "t": 337.54541015625,
"r": 475.00927734375, "r": 475.00927734375,
"b": 469.4945373535156, "b": 469.4945373535156,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
@ -13641,7 +13641,7 @@
"b": 102.78223000000003, "b": 102.78223000000003,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9373533129692078, "confidence": 0.9373534917831421,
"cells": [ "cells": [
{ {
"index": 0, "index": 0,
@ -13687,7 +13687,7 @@
"b": 102.78223000000003, "b": 102.78223000000003,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.8858679533004761, "confidence": 0.8858680725097656,
"cells": [ "cells": [
{ {
"index": 1, "index": 1,
@ -13733,7 +13733,7 @@
"b": 152.90697999999998, "b": 152.90697999999998,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9806435108184814, "confidence": 0.9806433916091919,
"cells": [ "cells": [
{ {
"index": 2, "index": 2,
@ -13900,7 +13900,7 @@
"b": 255.42400999999995, "b": 255.42400999999995,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9850425124168396, "confidence": 0.98504239320755,
"cells": [ "cells": [
{ {
"index": 7, "index": 7,
@ -14121,7 +14121,7 @@
"b": 327.98218, "b": 327.98218,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9591907262802124, "confidence": 0.9591909050941467,
"cells": [ "cells": [
{ {
"index": 15, "index": 15,
@ -14311,8 +14311,8 @@
"id": 0, "id": 0,
"label": "table", "label": "table",
"bbox": { "bbox": {
"l": 139.6674041748047, "l": 139.66741943359375,
"t": 337.5453796386719, "t": 337.54541015625,
"r": 475.00927734375, "r": 475.00927734375,
"b": 469.4945373535156, "b": 469.4945373535156,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
@ -19701,7 +19701,7 @@
"b": 518.17419, "b": 518.17419,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9589295387268066, "confidence": 0.9589294195175171,
"cells": [ "cells": [
{ {
"index": 91, "index": 91,
@ -19772,7 +19772,7 @@
"b": 618.3, "b": 618.3,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9849976301193237, "confidence": 0.9849975109100342,
"cells": [ "cells": [
{ {
"index": 93, "index": 93,
@ -20116,7 +20116,7 @@
"b": 152.90697999999998, "b": 152.90697999999998,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9806435108184814, "confidence": 0.9806433916091919,
"cells": [ "cells": [
{ {
"index": 2, "index": 2,
@ -20283,7 +20283,7 @@
"b": 255.42400999999995, "b": 255.42400999999995,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9850425124168396, "confidence": 0.98504239320755,
"cells": [ "cells": [
{ {
"index": 7, "index": 7,
@ -20504,7 +20504,7 @@
"b": 327.98218, "b": 327.98218,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9591907262802124, "confidence": 0.9591909050941467,
"cells": [ "cells": [
{ {
"index": 15, "index": 15,
@ -20694,8 +20694,8 @@
"id": 0, "id": 0,
"label": "table", "label": "table",
"bbox": { "bbox": {
"l": 139.6674041748047, "l": 139.66741943359375,
"t": 337.5453796386719, "t": 337.54541015625,
"r": 475.00927734375, "r": 475.00927734375,
"b": 469.4945373535156, "b": 469.4945373535156,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
@ -26084,7 +26084,7 @@
"b": 518.17419, "b": 518.17419,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9589295387268066, "confidence": 0.9589294195175171,
"cells": [ "cells": [
{ {
"index": 91, "index": 91,
@ -26155,7 +26155,7 @@
"b": 618.3, "b": 618.3,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9849976301193237, "confidence": 0.9849975109100342,
"cells": [ "cells": [
{ {
"index": 93, "index": 93,
@ -26499,7 +26499,7 @@
"b": 102.78223000000003, "b": 102.78223000000003,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9373533129692078, "confidence": 0.9373534917831421,
"cells": [ "cells": [
{ {
"index": 0, "index": 0,
@ -26545,7 +26545,7 @@
"b": 102.78223000000003, "b": 102.78223000000003,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.8858679533004761, "confidence": 0.8858680725097656,
"cells": [ "cells": [
{ {
"index": 1, "index": 1,

4
tests/data/groundtruth/docling_v2/2305.03393v1-pg9.json vendored
View File

@ -336,8 +336,8 @@
{ {
"page_no": 1, "page_no": 1,
"bbox": { "bbox": {
"l": 139.6674041748047, "l": 139.66741943359375,
"t": 454.4546203613281, "t": 454.45458984375,
"r": 475.00927734375, "r": 475.00927734375,
"b": 322.5054626464844, "b": 322.5054626464844,
"coord_origin": "BOTTOMLEFT" "coord_origin": "BOTTOMLEFT"

58
tests/data/groundtruth/docling_v2/2305.03393v1-pg9.pages.json vendored
View File

@ -2705,7 +2705,7 @@
"b": 102.78223000000003, "b": 102.78223000000003,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9373533129692078, "confidence": 0.9373534917831421,
"cells": [ "cells": [
{ {
"index": 0, "index": 0,
@ -2745,7 +2745,7 @@
"b": 102.78223000000003, "b": 102.78223000000003,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.8858679533004761, "confidence": 0.8858680725097656,
"cells": [ "cells": [
{ {
"index": 1, "index": 1,
@ -2785,7 +2785,7 @@
"b": 152.90697999999998, "b": 152.90697999999998,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9806435108184814, "confidence": 0.9806433916091919,
"cells": [ "cells": [
{ {
"index": 2, "index": 2,
@ -2940,7 +2940,7 @@
"b": 255.42400999999995, "b": 255.42400999999995,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9850425124168396, "confidence": 0.98504239320755,
"cells": [ "cells": [
{ {
"index": 7, "index": 7,
@ -3155,7 +3155,7 @@
"b": 327.98218, "b": 327.98218,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9591907262802124, "confidence": 0.9591909050941467,
"cells": [ "cells": [
{ {
"index": 15, "index": 15,
@ -3339,8 +3339,8 @@
"id": 0, "id": 0,
"label": "table", "label": "table",
"bbox": { "bbox": {
"l": 139.6674041748047, "l": 139.66741943359375,
"t": 337.5453796386719, "t": 337.54541015625,
"r": 475.00927734375, "r": 475.00927734375,
"b": 469.4945373535156, "b": 469.4945373535156,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
@ -7846,7 +7846,7 @@
"b": 518.17419, "b": 518.17419,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9589295387268066, "confidence": 0.9589294195175171,
"cells": [ "cells": [
{ {
"index": 91, "index": 91,
@ -7911,7 +7911,7 @@
"b": 618.3, "b": 618.3,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9849976301193237, "confidence": 0.9849975109100342,
"cells": [ "cells": [
{ {
"index": 93, "index": 93,
@ -8243,8 +8243,8 @@
"id": 0, "id": 0,
"label": "table", "label": "table",
"bbox": { "bbox": {
"l": 139.6674041748047, "l": 139.66741943359375,
"t": 337.5453796386719, "t": 337.54541015625,
"r": 475.00927734375, "r": 475.00927734375,
"b": 469.4945373535156, "b": 469.4945373535156,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
@ -13641,7 +13641,7 @@
"b": 102.78223000000003, "b": 102.78223000000003,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9373533129692078, "confidence": 0.9373534917831421,
"cells": [ "cells": [
{ {
"index": 0, "index": 0,
@ -13687,7 +13687,7 @@
"b": 102.78223000000003, "b": 102.78223000000003,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.8858679533004761, "confidence": 0.8858680725097656,
"cells": [ "cells": [
{ {
"index": 1, "index": 1,
@ -13733,7 +13733,7 @@
"b": 152.90697999999998, "b": 152.90697999999998,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9806435108184814, "confidence": 0.9806433916091919,
"cells": [ "cells": [
{ {
"index": 2, "index": 2,
@ -13900,7 +13900,7 @@
"b": 255.42400999999995, "b": 255.42400999999995,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9850425124168396, "confidence": 0.98504239320755,
"cells": [ "cells": [
{ {
"index": 7, "index": 7,
@ -14121,7 +14121,7 @@
"b": 327.98218, "b": 327.98218,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9591907262802124, "confidence": 0.9591909050941467,
"cells": [ "cells": [
{ {
"index": 15, "index": 15,
@ -14311,8 +14311,8 @@
"id": 0, "id": 0,
"label": "table", "label": "table",
"bbox": { "bbox": {
"l": 139.6674041748047, "l": 139.66741943359375,
"t": 337.5453796386719, "t": 337.54541015625,
"r": 475.00927734375, "r": 475.00927734375,
"b": 469.4945373535156, "b": 469.4945373535156,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
@ -19701,7 +19701,7 @@
"b": 518.17419, "b": 518.17419,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9589295387268066, "confidence": 0.9589294195175171,
"cells": [ "cells": [
{ {
"index": 91, "index": 91,
@ -19772,7 +19772,7 @@
"b": 618.3, "b": 618.3,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9849976301193237, "confidence": 0.9849975109100342,
"cells": [ "cells": [
{ {
"index": 93, "index": 93,
@ -20116,7 +20116,7 @@
"b": 152.90697999999998, "b": 152.90697999999998,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9806435108184814, "confidence": 0.9806433916091919,
"cells": [ "cells": [
{ {
"index": 2, "index": 2,
@ -20283,7 +20283,7 @@
"b": 255.42400999999995, "b": 255.42400999999995,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9850425124168396, "confidence": 0.98504239320755,
"cells": [ "cells": [
{ {
"index": 7, "index": 7,
@ -20504,7 +20504,7 @@
"b": 327.98218, "b": 327.98218,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9591907262802124, "confidence": 0.9591909050941467,
"cells": [ "cells": [
{ {
"index": 15, "index": 15,
@ -20694,8 +20694,8 @@
"id": 0, "id": 0,
"label": "table", "label": "table",
"bbox": { "bbox": {
"l": 139.6674041748047, "l": 139.66741943359375,
"t": 337.5453796386719, "t": 337.54541015625,
"r": 475.00927734375, "r": 475.00927734375,
"b": 469.4945373535156, "b": 469.4945373535156,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
@ -26084,7 +26084,7 @@
"b": 518.17419, "b": 518.17419,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9589295387268066, "confidence": 0.9589294195175171,
"cells": [ "cells": [
{ {
"index": 91, "index": 91,
@ -26155,7 +26155,7 @@
"b": 618.3, "b": 618.3,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9849976301193237, "confidence": 0.9849975109100342,
"cells": [ "cells": [
{ {
"index": 93, "index": 93,
@ -26499,7 +26499,7 @@
"b": 102.78223000000003, "b": 102.78223000000003,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.9373533129692078, "confidence": 0.9373534917831421,
"cells": [ "cells": [
{ {
"index": 0, "index": 0,
@ -26545,7 +26545,7 @@
"b": 102.78223000000003, "b": 102.78223000000003,
"coord_origin": "TOPLEFT" "coord_origin": "TOPLEFT"
}, },
"confidence": 0.8858679533004761, "confidence": 0.8858680725097656,
"cells": [ "cells": [
{ {
"index": 1, "index": 1,

5
tests/data/groundtruth/docling_v2/csv-comma-in-cell.csv.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "csv-comma-in-cell", "name": "csv-comma-in-cell",
"origin": { "origin": {
"mimetype": "text/csv", "mimetype": "text/csv",
@ -538,7 +538,8 @@
} }
] ]
] ]
} },
"annotations": []
} }
], ],
"key_value_items": [], "key_value_items": [],

5
tests/data/groundtruth/docling_v2/csv-comma.csv.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "csv-comma", "name": "csv-comma",
"origin": { "origin": {
"mimetype": "text/csv", "mimetype": "text/csv",
@ -1788,7 +1788,8 @@
} }
] ]
] ]
} },
"annotations": []
} }
], ],
"key_value_items": [], "key_value_items": [],

5
tests/data/groundtruth/docling_v2/csv-inconsistent-header.csv.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "csv-inconsistent-header", "name": "csv-inconsistent-header",
"origin": { "origin": {
"mimetype": "text/csv", "mimetype": "text/csv",
@ -526,7 +526,8 @@
} }
] ]
] ]
} },
"annotations": []
} }
], ],
"key_value_items": [], "key_value_items": [],

5
tests/data/groundtruth/docling_v2/csv-pipe.csv.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "csv-pipe", "name": "csv-pipe",
"origin": { "origin": {
"mimetype": "text/csv", "mimetype": "text/csv",
@ -1788,7 +1788,8 @@
} }
] ]
] ]
} },
"annotations": []
} }
], ],
"key_value_items": [], "key_value_items": [],

5
tests/data/groundtruth/docling_v2/csv-semicolon.csv.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "csv-semicolon", "name": "csv-semicolon",
"origin": { "origin": {
"mimetype": "text/csv", "mimetype": "text/csv",
@ -1788,7 +1788,8 @@
} }
] ]
] ]
} },
"annotations": []
} }
], ],
"key_value_items": [], "key_value_items": [],

5
tests/data/groundtruth/docling_v2/csv-tab.csv.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "csv-tab", "name": "csv-tab",
"origin": { "origin": {
"mimetype": "text/csv", "mimetype": "text/csv",
@ -1788,7 +1788,8 @@
} }
] ]
] ]
} },
"annotations": []
} }
], ],
"key_value_items": [], "key_value_items": [],

5
tests/data/groundtruth/docling_v2/csv-too-few-columns.csv.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "csv-too-few-columns", "name": "csv-too-few-columns",
"origin": { "origin": {
"mimetype": "text/csv", "mimetype": "text/csv",
@ -526,7 +526,8 @@
} }
] ]
] ]
} },
"annotations": []
} }
], ],
"key_value_items": [], "key_value_items": [],

5
tests/data/groundtruth/docling_v2/csv-too-many-columns.csv.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "csv-too-many-columns", "name": "csv-too-many-columns",
"origin": { "origin": {
"mimetype": "text/csv", "mimetype": "text/csv",
@ -610,7 +610,8 @@
} }
] ]
] ]
} },
"annotations": []
} }
], ],
"key_value_items": [], "key_value_items": [],

23
tests/data/groundtruth/docling_v2/equations.docx.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "equations", "name": "equations",
"origin": { "origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document", "mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@ -250,7 +250,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -280,7 +281,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -322,7 +324,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -436,7 +439,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -466,7 +470,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -520,7 +525,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -634,7 +640,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {

2
tests/data/groundtruth/docling_v2/example_01.html.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "example_01", "name": "example_01",
"origin": { "origin": {
"mimetype": "text/html", "mimetype": "text/html",

2
tests/data/groundtruth/docling_v2/example_02.html.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "example_02", "name": "example_02",
"origin": { "origin": {
"mimetype": "text/html", "mimetype": "text/html",

5
tests/data/groundtruth/docling_v2/example_03.html.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "example_03", "name": "example_03",
"origin": { "origin": {
"mimetype": "text/html", "mimetype": "text/html",
@ -637,7 +637,8 @@
} }
] ]
] ]
} },
"annotations": []
} }
], ],
"key_value_items": [], "key_value_items": [],

5
tests/data/groundtruth/docling_v2/example_04.html.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "example_04", "name": "example_04",
"origin": { "origin": {
"mimetype": "text/html", "mimetype": "text/html",
@ -325,7 +325,8 @@
} }
] ]
] ]
} },
"annotations": []
} }
], ],
"key_value_items": [], "key_value_items": [],

5
tests/data/groundtruth/docling_v2/example_05.html.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "example_05", "name": "example_05",
"origin": { "origin": {
"mimetype": "text/html", "mimetype": "text/html",
@ -325,7 +325,8 @@
} }
] ]
] ]
} },
"annotations": []
} }
], ],
"key_value_items": [], "key_value_items": [],

2
tests/data/groundtruth/docling_v2/example_06.html.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "example_06", "name": "example_06",
"origin": { "origin": {
"mimetype": "text/html", "mimetype": "text/html",

2
tests/data/groundtruth/docling_v2/example_07.html.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "example_07", "name": "example_07",
"origin": { "origin": {
"mimetype": "text/html", "mimetype": "text/html",

11
tests/data/groundtruth/docling_v2/example_08.html.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "example_08", "name": "example_08",
"origin": { "origin": {
"mimetype": "text/html", "mimetype": "text/html",
@ -661,7 +661,8 @@
} }
] ]
] ]
} },
"annotations": []
}, },
{ {
"self_ref": "#/tables/1", "self_ref": "#/tables/1",
@ -1330,7 +1331,8 @@
} }
] ]
] ]
} },
"annotations": []
}, },
{ {
"self_ref": "#/tables/2", "self_ref": "#/tables/2",
@ -1999,7 +2001,8 @@
} }
] ]
] ]
} },
"annotations": []
} }
], ],
"key_value_items": [], "key_value_items": [],

9
tests/data/groundtruth/docling_v2/inline_and_formatting.md.yaml vendored
View File

@ -174,6 +174,7 @@ texts:
formatting: formatting:
bold: false bold: false
italic: true italic: true
script: baseline
strikethrough: false strikethrough: false
underline: false underline: false
label: text label: text
@ -188,6 +189,7 @@ texts:
formatting: formatting:
bold: true bold: true
italic: false italic: false
script: baseline
strikethrough: false strikethrough: false
underline: false underline: false
label: text label: text
@ -202,6 +204,7 @@ texts:
formatting: formatting:
bold: true bold: true
italic: true italic: true
script: baseline
strikethrough: false strikethrough: false
underline: false underline: false
label: text label: text
@ -277,6 +280,7 @@ texts:
formatting: formatting:
bold: true bold: true
italic: false italic: false
script: baseline
strikethrough: false strikethrough: false
underline: false underline: false
hyperlink: https://github.com/docling-project/docling hyperlink: https://github.com/docling-project/docling
@ -452,6 +456,7 @@ texts:
formatting: formatting:
bold: false bold: false
italic: true italic: true
script: baseline
strikethrough: false strikethrough: false
underline: false underline: false
label: text label: text
@ -487,6 +492,7 @@ texts:
formatting: formatting:
bold: true bold: true
italic: false italic: false
script: baseline
strikethrough: false strikethrough: false
underline: false underline: false
label: text label: text
@ -522,6 +528,7 @@ texts:
formatting: formatting:
bold: true bold: true
italic: false italic: false
script: baseline
strikethrough: false strikethrough: false
underline: false underline: false
label: text label: text
@ -562,4 +569,4 @@ texts:
prov: [] prov: []
self_ref: '#/texts/37' self_ref: '#/texts/37'
text: amet. text: amet.
version: 1.3.0 version: 1.4.0

5
tests/data/groundtruth/docling_v2/ipa20180000016.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "ipa20180000016.xml", "name": "ipa20180000016.xml",
"origin": { "origin": {
"mimetype": "application/xml", "mimetype": "application/xml",
@ -6005,7 +6005,8 @@
} }
] ]
] ]
} },
"annotations": []
} }
], ],
"key_value_items": [], "key_value_items": [],

2
tests/data/groundtruth/docling_v2/ipa20200022300.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "ipa20200022300.xml", "name": "ipa20200022300.xml",
"origin": { "origin": {
"mimetype": "application/xml", "mimetype": "application/xml",

17
tests/data/groundtruth/docling_v2/lorem_ipsum.docx.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "lorem_ipsum", "name": "lorem_ipsum",
"origin": { "origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document", "mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@ -66,7 +66,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -96,7 +97,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -126,7 +128,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -156,7 +159,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -186,7 +190,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
} }
], ],

5
tests/data/groundtruth/docling_v2/pa20010031492.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "pa20010031492.xml", "name": "pa20010031492.xml",
"origin": { "origin": {
"mimetype": "application/xml", "mimetype": "application/xml",
@ -2127,7 +2127,8 @@
} }
] ]
] ]
} },
"annotations": []
} }
], ],
"key_value_items": [], "key_value_items": [],

2
tests/data/groundtruth/docling_v2/pftaps057006474.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "pftaps057006474.txt", "name": "pftaps057006474.txt",
"origin": { "origin": {
"mimetype": "text/plain", "mimetype": "text/plain",

2
tests/data/groundtruth/docling_v2/pg06442728.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "pg06442728.xml", "name": "pg06442728.xml",
"origin": { "origin": {
"mimetype": "application/xml", "mimetype": "application/xml",

2
tests/data/groundtruth/docling_v2/powerpoint_bad_text.pptx.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "powerpoint_bad_text", "name": "powerpoint_bad_text",
"origin": { "origin": {
"mimetype": "application/vnd.ms-powerpoint", "mimetype": "application/vnd.ms-powerpoint",

5
tests/data/groundtruth/docling_v2/powerpoint_sample.pptx.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "powerpoint_sample", "name": "powerpoint_sample",
"origin": { "origin": {
"mimetype": "application/vnd.ms-powerpoint", "mimetype": "application/vnd.ms-powerpoint",
@ -2199,7 +2199,8 @@
} }
] ]
] ]
} },
"annotations": []
} }
], ],
"key_value_items": [], "key_value_items": [],

2
tests/data/groundtruth/docling_v2/powerpoint_with_image.pptx.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "powerpoint_with_image", "name": "powerpoint_with_image",
"origin": { "origin": {
"mimetype": "application/vnd.ms-powerpoint", "mimetype": "application/vnd.ms-powerpoint",

5
tests/data/groundtruth/docling_v2/sample_sales_data.xlsm.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "sample_sales_data", "name": "sample_sales_data",
"origin": { "origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", "mimetype": "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
@ -2136,7 +2136,8 @@
} }
] ]
] ]
} },
"annotations": []
} }
], ],
"key_value_items": [], "key_value_items": [],

17
tests/data/groundtruth/docling_v2/tablecell.docx.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "tablecell", "name": "tablecell",
"origin": { "origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document", "mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@ -78,7 +78,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -98,7 +99,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -130,7 +132,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -172,7 +175,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
} }
], ],
@ -419,7 +423,8 @@
} }
] ]
] ]
} },
"annotations": []
} }
], ],
"key_value_items": [], "key_value_items": [],

20
tests/data/groundtruth/docling_v2/test-01.xlsx.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "test-01", "name": "test-01",
"origin": { "origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", "mimetype": "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
@ -681,7 +681,8 @@
} }
] ]
] ]
} },
"annotations": []
}, },
{ {
"self_ref": "#/tables/1", "self_ref": "#/tables/1",
@ -1599,7 +1600,8 @@
} }
] ]
] ]
} },
"annotations": []
}, },
{ {
"self_ref": "#/tables/2", "self_ref": "#/tables/2",
@ -2005,7 +2007,8 @@
} }
] ]
] ]
} },
"annotations": []
}, },
{ {
"self_ref": "#/tables/3", "self_ref": "#/tables/3",
@ -2411,7 +2414,8 @@
} }
] ]
] ]
} },
"annotations": []
}, },
{ {
"self_ref": "#/tables/4", "self_ref": "#/tables/4",
@ -2893,7 +2897,8 @@
} }
] ]
] ]
} },
"annotations": []
}, },
{ {
"self_ref": "#/tables/5", "self_ref": "#/tables/5",
@ -3375,7 +3380,8 @@
} }
] ]
] ]
} },
"annotations": []
} }
], ],
"key_value_items": [], "key_value_items": [],

14
tests/data/groundtruth/docling_v2/test_emf_docx.docx.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "test_emf_docx", "name": "test_emf_docx",
"origin": { "origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document", "mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@ -60,7 +60,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -78,7 +79,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -96,7 +98,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -114,7 +117,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
} }
], ],

117
tests/data/groundtruth/docling_v2/textbox.docx.itxt vendored
View File

@ -11,83 +11,84 @@ item-0 at level 0: unspecified: group _root_
＊ Blisters ＊ Blisters
＊ Headache ＊ Headache
＊ Sore throat ＊ Sore throat
item-9 at level 1: list_item: item-9 at level 1: list: group group
item-10 at level 1: paragraph: item-10 at level 2: list_item:
item-11 at level 1: paragraph: item-11 at level 1: paragraph:
item-12 at level 1: section: group textbox item-12 at level 1: paragraph:
item-13 at level 2: paragraph: If a caregiver suspects that wit ... the same suggested reportable symptoms item-13 at level 1: section: group textbox
item-14 at level 1: paragraph: item-14 at level 2: paragraph: If a caregiver suspects that wit ... the same suggested reportable symptoms
item-15 at level 1: paragraph: item-15 at level 1: paragraph:
item-16 at level 1: paragraph: item-16 at level 1: paragraph:
item-17 at level 1: paragraph: item-17 at level 1: paragraph:
item-18 at level 1: section: group textbox item-18 at level 1: paragraph:
item-19 at level 2: paragraph: Yes item-19 at level 1: section: group textbox
item-20 at level 1: paragraph: item-20 at level 2: paragraph: Yes
item-21 at level 1: paragraph: item-21 at level 1: paragraph:
item-22 at level 1: section: group textbox item-22 at level 1: paragraph:
item-23 at level 2: list: group list item-23 at level 1: section: group textbox
item-24 at level 3: list_item: A report must be submitted withi ... saster Prevention Information Network. item-24 at level 2: list: group list
item-25 at level 3: list_item: A report must also be submitted ... d Infectious Disease Reporting System. item-25 at level 3: list_item: A report must be submitted withi ... saster Prevention Information Network.
item-26 at level 2: paragraph: item-26 at level 3: list_item: A report must also be submitted ... d Infectious Disease Reporting System.
item-27 at level 1: list: group list item-27 at level 2: paragraph:
item-28 at level 2: list_item: item-28 at level 1: list: group list
item-29 at level 1: paragraph: item-29 at level 2: list_item:
item-30 at level 1: paragraph: item-30 at level 1: paragraph:
item-31 at level 1: paragraph: item-31 at level 1: paragraph:
item-32 at level 1: paragraph: item-32 at level 1: paragraph:
item-33 at level 1: paragraph: item-33 at level 1: paragraph:
item-34 at level 1: section: group textbox item-34 at level 1: paragraph:
item-35 at level 2: paragraph: Health Bureau: item-35 at level 1: section: group textbox
item-36 at level 2: paragraph: Upon receiving a report from the ... rt to the Centers for Disease Control. item-36 at level 2: paragraph: Health Bureau:
item-37 at level 2: list: group list item-37 at level 2: paragraph: Upon receiving a report from the ... rt to the Centers for Disease Control.
item-38 at level 3: list_item: If necessary, provide health edu ... vidual to undergo specimen collection. item-38 at level 2: list: group list
item-39 at level 3: list_item: Implement appropriate epidemic p ... the Communicable Disease Control Act. item-39 at level 3: list_item: If necessary, provide health edu ... vidual to undergo specimen collection.
item-40 at level 2: paragraph: item-40 at level 3: list_item: Implement appropriate epidemic p ... the Communicable Disease Control Act.
item-41 at level 1: list: group list item-41 at level 2: paragraph:
item-42 at level 2: list_item: item-42 at level 1: list: group list
item-43 at level 1: paragraph: item-43 at level 2: list_item:
item-44 at level 1: section: group textbox item-44 at level 1: paragraph:
item-45 at level 2: paragraph: Department of Education: item-45 at level 1: section: group textbox
item-46 at level 2: paragraph: Department of Education:
Collabo ... vention measures at all school levels. Collabo ... vention measures at all school levels.
item-46 at level 1: paragraph:
item-47 at level 1: paragraph: item-47 at level 1: paragraph:
item-48 at level 1: paragraph: item-48 at level 1: paragraph:
item-49 at level 1: paragraph: item-49 at level 1: paragraph:
item-50 at level 1: paragraph: item-50 at level 1: paragraph:
item-51 at level 1: paragraph: item-51 at level 1: paragraph:
item-52 at level 1: paragraph: item-52 at level 1: paragraph:
item-53 at level 1: section: group textbox item-53 at level 1: paragraph:
item-54 at level 2: inline: group group item-54 at level 1: section: group textbox
item-55 at level 3: paragraph: The Health Bureau will handle item-55 at level 2: inline: group group
item-56 at level 3: paragraph: reporting and specimen collection item-56 at level 3: paragraph: The Health Bureau will handle
item-57 at level 3: paragraph: . item-57 at level 3: paragraph: reporting and specimen collection
item-58 at level 2: paragraph: item-58 at level 3: paragraph: .
item-59 at level 1: paragraph: item-59 at level 2: paragraph:
item-60 at level 1: paragraph: item-60 at level 1: paragraph:
item-61 at level 1: paragraph: item-61 at level 1: paragraph:
item-62 at level 1: section: group textbox item-62 at level 1: paragraph:
item-63 at level 2: paragraph: Whether the epidemic has eased. item-63 at level 1: section: group textbox
item-64 at level 2: paragraph: item-64 at level 2: paragraph: Whether the epidemic has eased.
item-65 at level 1: paragraph: item-65 at level 2: paragraph:
item-66 at level 1: section: group textbox item-66 at level 1: paragraph:
item-67 at level 2: paragraph: Whether the test results are pos ... legally designated infectious disease. item-67 at level 1: section: group textbox
item-68 at level 2: paragraph: No item-68 at level 2: paragraph: Whether the test results are pos ... legally designated infectious disease.
item-69 at level 1: paragraph: item-69 at level 2: paragraph: No
item-70 at level 1: paragraph: item-70 at level 1: paragraph:
item-71 at level 1: section: group textbox item-71 at level 1: paragraph:
item-72 at level 2: paragraph: Yes item-72 at level 1: section: group textbox
item-73 at level 1: paragraph: item-73 at level 2: paragraph: Yes
item-74 at level 1: section: group textbox item-74 at level 1: paragraph:
item-75 at level 2: paragraph: Yes item-75 at level 1: section: group textbox
item-76 at level 1: paragraph: item-76 at level 2: paragraph: Yes
item-77 at level 1: paragraph: item-77 at level 1: paragraph:
item-78 at level 1: section: group textbox item-78 at level 1: paragraph:
item-79 at level 2: paragraph: Case closed. item-79 at level 1: section: group textbox
item-80 at level 2: paragraph: item-80 at level 2: paragraph: Case closed.
item-81 at level 2: paragraph: The Health Bureau will carry out ... ters for Disease Control if necessary. item-81 at level 2: paragraph:
item-82 at level 1: paragraph: item-82 at level 2: paragraph: The Health Bureau will carry out ... ters for Disease Control if necessary.
item-83 at level 1: section: group textbox item-83 at level 1: paragraph:
item-84 at level 2: paragraph: No item-84 at level 1: section: group textbox
item-85 at level 1: paragraph: item-85 at level 2: paragraph: No
item-86 at level 1: paragraph: item-86 at level 1: paragraph:
item-87 at level 1: paragraph: item-87 at level 1: paragraph:
item-88 at level 1: paragraph:

446
tests/data/groundtruth/docling_v2/textbox.docx.json vendored
View File

File diff suppressed because it is too large Load Diff

2
tests/data/groundtruth/docling_v2/unit_test_01.html.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "unit_test_01", "name": "unit_test_01",
"origin": { "origin": {
"mimetype": "text/html", "mimetype": "text/html",

27
tests/data/groundtruth/docling_v2/unit_test_formatting.docx.itxt vendored
View File

@ -18,13 +18,20 @@ item-0 at level 0: unspecified: group _root_
item-17 at level 2: list_item: Bold bullet 2 item-17 at level 2: list_item: Bold bullet 2
item-18 at level 2: list_item: Underline bullet 3 item-18 at level 2: list_item: Underline bullet 3
item-19 at level 2: inline: group group item-19 at level 2: inline: group group
item-20 at level 3: list_item: Some item-20 at level 3: list: group group
item-21 at level 3: list_item: italic item-21 at level 4: list_item: Some
item-22 at level 3: list_item: bold item-22 at level 3: list: group group
item-23 at level 3: list_item: underline item-23 at level 4: list_item: italic
item-24 at level 2: list: group list item-24 at level 3: list: group group
item-25 at level 3: inline: group group item-25 at level 4: list_item: bold
item-26 at level 4: list_item: Nested item-26 at level 3: list: group group
item-27 at level 4: list_item: italic item-27 at level 4: list_item: underline
item-28 at level 4: list_item: bold item-28 at level 2: list: group list
item-29 at level 1: paragraph: item-29 at level 3: inline: group group
item-30 at level 4: list: group group
item-31 at level 5: list_item: Nested
item-32 at level 4: list: group group
item-33 at level 5: list_item: italic
item-34 at level 4: list: group group
item-35 at level 5: list_item: bold
item-36 at level 1: paragraph:

332
tests/data/groundtruth/docling_v2/unit_test_formatting.docx.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "unit_test_formatting", "name": "unit_test_formatting",
"origin": { "origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document", "mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@ -42,7 +42,7 @@
"$ref": "#/groups/1" "$ref": "#/groups/1"
}, },
{ {
"$ref": "#/texts/23" "$ref": "#/texts/16"
} }
], ],
"content_layer": "body", "content_layer": "body",
@ -115,16 +115,16 @@
}, },
"children": [ "children": [
{ {
"$ref": "#/texts/16" "$ref": "#/groups/11"
}, },
{ {
"$ref": "#/texts/17" "$ref": "#/groups/10"
}, },
{ {
"$ref": "#/texts/18" "$ref": "#/groups/9"
}, },
{ {
"$ref": "#/texts/19" "$ref": "#/groups/8"
} }
], ],
"content_layer": "body", "content_layer": "body",
@ -152,18 +152,116 @@
}, },
"children": [ "children": [
{ {
"$ref": "#/texts/20" "$ref": "#/groups/7"
}, },
{ {
"$ref": "#/texts/21" "$ref": "#/groups/6"
}, },
{
"$ref": "#/groups/5"
}
],
"content_layer": "body",
"name": "group",
"label": "inline"
},
{
"self_ref": "#/groups/5",
"parent": {
"$ref": "#/groups/4"
},
"children": [
{
"$ref": "#/texts/17"
}
],
"content_layer": "body",
"name": "group",
"label": "list"
},
{
"self_ref": "#/groups/6",
"parent": {
"$ref": "#/groups/4"
},
"children": [
{
"$ref": "#/texts/18"
}
],
"content_layer": "body",
"name": "group",
"label": "list"
},
{
"self_ref": "#/groups/7",
"parent": {
"$ref": "#/groups/4"
},
"children": [
{
"$ref": "#/texts/19"
}
],
"content_layer": "body",
"name": "group",
"label": "list"
},
{
"self_ref": "#/groups/8",
"parent": {
"$ref": "#/groups/2"
},
"children": [
{
"$ref": "#/texts/20"
}
],
"content_layer": "body",
"name": "group",
"label": "list"
},
{
"self_ref": "#/groups/9",
"parent": {
"$ref": "#/groups/2"
},
"children": [
{
"$ref": "#/texts/21"
}
],
"content_layer": "body",
"name": "group",
"label": "list"
},
{
"self_ref": "#/groups/10",
"parent": {
"$ref": "#/groups/2"
},
"children": [
{ {
"$ref": "#/texts/22" "$ref": "#/texts/22"
} }
], ],
"content_layer": "body", "content_layer": "body",
"name": "group", "name": "group",
"label": "inline" "label": "list"
},
{
"self_ref": "#/groups/11",
"parent": {
"$ref": "#/groups/2"
},
"children": [
{
"$ref": "#/texts/23"
}
],
"content_layer": "body",
"name": "group",
"label": "list"
} }
], ],
"texts": [ "texts": [
@ -182,7 +280,8 @@
"bold": false, "bold": false,
"italic": true, "italic": true,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -200,7 +299,8 @@
"bold": true, "bold": true,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -218,7 +318,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": true, "underline": true,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -236,7 +337,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"hyperlink": "https:/github.com/DS4SD/docling" "hyperlink": "https:/github.com/DS4SD/docling"
}, },
@ -255,7 +357,8 @@
"bold": true, "bold": true,
"italic": true, "italic": true,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"hyperlink": "https:/github.com/DS4SD/docling" "hyperlink": "https:/github.com/DS4SD/docling"
}, },
@ -274,7 +377,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -292,7 +396,8 @@
"bold": false, "bold": false,
"italic": true, "italic": true,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -310,7 +415,8 @@
"bold": true, "bold": true,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -328,7 +434,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": true, "underline": true,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -346,7 +453,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -364,7 +472,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"hyperlink": "https:/github.com/DS4SD/docling" "hyperlink": "https:/github.com/DS4SD/docling"
}, },
@ -383,7 +492,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -413,7 +523,8 @@
"bold": false, "bold": false,
"italic": true, "italic": true,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -433,7 +544,8 @@
"bold": true, "bold": true,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -453,7 +565,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": true, "underline": true,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -461,47 +574,19 @@
{ {
"self_ref": "#/texts/16", "self_ref": "#/texts/16",
"parent": { "parent": {
"$ref": "#/groups/2" "$ref": "#/body"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "body",
"label": "list_item", "label": "paragraph",
"prov": [], "prov": [],
"orig": "Some", "orig": "",
"text": "Some", "text": ""
"formatting": {
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false
},
"enumerated": false,
"marker": "-"
}, },
{ {
"self_ref": "#/texts/17", "self_ref": "#/texts/17",
"parent": { "parent": {
"$ref": "#/groups/2" "$ref": "#/groups/5"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "italic",
"text": "italic",
"formatting": {
"bold": false,
"italic": true,
"underline": false,
"strikethrough": false
},
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/18",
"parent": {
"$ref": "#/groups/2"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "body",
@ -513,7 +598,29 @@
"bold": true, "bold": true,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
},
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/18",
"parent": {
"$ref": "#/groups/6"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "italic",
"text": "italic",
"formatting": {
"bold": false,
"italic": true,
"underline": false,
"strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -521,27 +628,7 @@
{ {
"self_ref": "#/texts/19", "self_ref": "#/texts/19",
"parent": { "parent": {
"$ref": "#/groups/2" "$ref": "#/groups/7"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "underline",
"text": "underline",
"formatting": {
"bold": false,
"italic": false,
"underline": true,
"strikethrough": false
},
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/20",
"parent": {
"$ref": "#/groups/4"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "body",
@ -553,7 +640,29 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
},
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/20",
"parent": {
"$ref": "#/groups/8"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "underline",
"text": "underline",
"formatting": {
"bold": false,
"italic": false,
"underline": true,
"strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -561,27 +670,7 @@
{ {
"self_ref": "#/texts/21", "self_ref": "#/texts/21",
"parent": { "parent": {
"$ref": "#/groups/4" "$ref": "#/groups/9"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "italic",
"text": "italic",
"formatting": {
"bold": false,
"italic": true,
"underline": false,
"strikethrough": false
},
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/22",
"parent": {
"$ref": "#/groups/4"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "body",
@ -593,7 +682,29 @@
"bold": true, "bold": true,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
},
"enumerated": false,
"marker": "-"
},
{
"self_ref": "#/texts/22",
"parent": {
"$ref": "#/groups/10"
},
"children": [],
"content_layer": "body",
"label": "list_item",
"prov": [],
"orig": "italic",
"text": "italic",
"formatting": {
"bold": false,
"italic": true,
"underline": false,
"strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -601,14 +712,23 @@
{ {
"self_ref": "#/texts/23", "self_ref": "#/texts/23",
"parent": { "parent": {
"$ref": "#/body" "$ref": "#/groups/11"
}, },
"children": [], "children": [],
"content_layer": "body", "content_layer": "body",
"label": "paragraph", "label": "list_item",
"prov": [], "prov": [],
"orig": "", "orig": "Some",
"text": "" "text": "Some",
"formatting": {
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false,
"script": "baseline"
},
"enumerated": false,
"marker": "-"
} }
], ],
"pictures": [], "pictures": [],

4
tests/data/groundtruth/docling_v2/unit_test_formatting.docx.md vendored
View File

@ -13,5 +13,5 @@ Normal *italic* **bold** underline and [hyperlink](https:/github.com/DS4SD/docli
- *Italic bullet 1* - *Italic bullet 1*
- **Bold bullet 2** - **Bold bullet 2**
- Underline bullet 3 - Underline bullet 3
- Some *italic* **bold** underline - Some - *italic* - **bold** - underline
- Nested *italic* **bold** - Nested - *italic* - **bold**

44
tests/data/groundtruth/docling_v2/unit_test_headers.docx.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "unit_test_headers", "name": "unit_test_headers",
"origin": { "origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document", "mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@ -138,7 +138,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -168,7 +169,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -239,7 +241,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -269,7 +272,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -343,7 +347,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -373,7 +378,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -447,7 +453,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -477,7 +484,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -566,7 +574,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -596,7 +605,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -667,7 +677,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -697,7 +708,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -771,7 +783,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -801,7 +814,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {

44
tests/data/groundtruth/docling_v2/unit_test_headers_numbered.docx.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "unit_test_headers_numbered", "name": "unit_test_headers_numbered",
"origin": { "origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document", "mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@ -214,7 +214,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -244,7 +245,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -315,7 +317,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -345,7 +348,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -419,7 +423,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -449,7 +454,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -523,7 +529,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -553,7 +560,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -620,7 +628,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -650,7 +659,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -721,7 +731,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -751,7 +762,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -825,7 +837,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -855,7 +868,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {

83
tests/data/groundtruth/docling_v2/unit_test_lists.docx.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "unit_test_lists", "name": "unit_test_lists",
"origin": { "origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document", "mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@ -370,7 +370,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -400,7 +401,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -450,7 +452,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -470,7 +473,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -490,7 +494,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -542,7 +547,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -562,7 +568,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -582,7 +589,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -634,7 +642,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -654,7 +663,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -674,7 +684,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -694,7 +705,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -714,7 +726,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -734,7 +747,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -786,7 +800,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -806,7 +821,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -826,7 +842,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -878,7 +895,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -898,7 +916,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -918,7 +937,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -938,7 +958,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -996,7 +1017,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -1016,7 +1038,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -1036,7 +1059,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -1056,7 +1080,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -1076,7 +1101,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -1096,7 +1122,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"

8
tests/data/groundtruth/docling_v2/wiki_duck.html.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "wiki_duck", "name": "wiki_duck",
"origin": { "origin": {
"mimetype": "text/html", "mimetype": "text/html",
@ -8489,7 +8489,8 @@
} }
] ]
] ]
} },
"annotations": []
}, },
{ {
"self_ref": "#/tables/1", "self_ref": "#/tables/1",
@ -8648,7 +8649,8 @@
} }
] ]
] ]
} },
"annotations": []
} }
], ],
"key_value_items": [], "key_value_items": [],

62
tests/data/groundtruth/docling_v2/word_sample.docx.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "word_sample", "name": "word_sample",
"origin": { "origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document", "mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@ -106,7 +106,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -149,7 +150,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -167,7 +169,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -217,7 +220,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -235,7 +239,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -255,7 +260,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -275,7 +281,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -295,7 +302,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -313,7 +321,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -333,7 +342,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -353,7 +363,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -373,7 +384,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -426,7 +438,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -444,7 +457,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -462,7 +476,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -492,7 +507,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -510,7 +526,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -530,7 +547,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -550,7 +568,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
}, },
"enumerated": false, "enumerated": false,
"marker": "-" "marker": "-"
@ -897,7 +916,8 @@
} }
] ]
] ]
} },
"annotations": []
} }
], ],
"key_value_items": [], "key_value_items": [],

32
tests/data/groundtruth/docling_v2/word_tables.docx.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "word_tables", "name": "word_tables",
"origin": { "origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document", "mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@ -119,7 +119,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -149,7 +150,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -179,7 +181,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -209,7 +212,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -239,7 +243,8 @@
"bold": false, "bold": false,
"italic": false, "italic": false,
"underline": false, "underline": false,
"strikethrough": false "strikethrough": false,
"script": "baseline"
} }
}, },
{ {
@ -510,7 +515,8 @@
} }
] ]
] ]
} },
"annotations": []
}, },
{ {
"self_ref": "#/tables/1", "self_ref": "#/tables/1",
@ -729,7 +735,8 @@
} }
] ]
] ]
} },
"annotations": []
}, },
{ {
"self_ref": "#/tables/2", "self_ref": "#/tables/2",
@ -1020,7 +1027,8 @@
} }
] ]
] ]
} },
"annotations": []
}, },
{ {
"self_ref": "#/tables/3", "self_ref": "#/tables/3",
@ -1387,7 +1395,8 @@
} }
] ]
] ]
} },
"annotations": []
}, },
{ {
"self_ref": "#/tables/4", "self_ref": "#/tables/4",
@ -2398,7 +2407,8 @@
} }
] ]
] ]
} },
"annotations": []
} }
], ],
"key_value_items": [], "key_value_items": [],

2
tests/data/webp/groundtruth/docling_v2/webp-test.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "webp-test", "name": "webp-test",
"origin": { "origin": {
"mimetype": "application/pdf", "mimetype": "application/pdf",

2
tests/data_scanned/groundtruth/docling_v2/ocr_test.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "ocr_test", "name": "ocr_test",
"origin": { "origin": {
"mimetype": "application/pdf", "mimetype": "application/pdf",

2
tests/data_scanned/groundtruth/docling_v2/ocr_test_rotated_180.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "ocr_test_rotated_180", "name": "ocr_test_rotated_180",
"origin": { "origin": {
"mimetype": "application/pdf", "mimetype": "application/pdf",

2
tests/data_scanned/groundtruth/docling_v2/ocr_test_rotated_270.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "ocr_test_rotated_270", "name": "ocr_test_rotated_270",
"origin": { "origin": {
"mimetype": "application/pdf", "mimetype": "application/pdf",

2
tests/data_scanned/groundtruth/docling_v2/ocr_test_rotated_90.json vendored
View File

@ -1,6 +1,6 @@
{ {
"schema_name": "DoclingDocument", "schema_name": "DoclingDocument",
"version": "1.3.0", "version": "1.4.0",
"name": "ocr_test_rotated_90", "name": "ocr_test_rotated_90",
"origin": { "origin": {
"mimetype": "application/pdf", "mimetype": "application/pdf",