mirror of
https://github.com/DS4SD/docling.git
synced 2025-07-26 03:55:00 +00:00
f542460af3
* add real e2e tests for html and docx Signed-off-by: Peter Staar <taa@zurich.ibm.com> * updated the output of itxt Signed-off-by: Peter Staar <taa@zurich.ibm.com> * reformatted the text Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fixed the tests Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fixed the tests (2) Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fixed the examples (1) Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fixed the output of the test Signed-off-by: Peter Staar <taa@zurich.ibm.com> * updated the tests, moved the ground-truth Signed-off-by: Peter Staar <taa@zurich.ibm.com> * moved the ground-truth data Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fixed the html tests Signed-off-by: Peter Staar <taa@zurich.ibm.com> * restructure title fix (#187) Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com> --------- Signed-off-by: Peter Staar <taa@zurich.ibm.com> Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com> Co-authored-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
749 lines
18 KiB
JSON
749 lines
18 KiB
JSON
{
|
|
"schema_name": "DoclingDocument",
|
|
"version": "1.0.0",
|
|
"name": "word_sample",
|
|
"origin": {
|
|
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
|
|
"binary_hash": 5964280909995938039,
|
|
"filename": "word_sample.docx"
|
|
},
|
|
"furniture": {
|
|
"self_ref": "#/furniture",
|
|
"children": [],
|
|
"name": "_root_",
|
|
"label": "unspecified"
|
|
},
|
|
"body": {
|
|
"self_ref": "#/body",
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/0"
|
|
},
|
|
{
|
|
"$ref": "#/texts/1"
|
|
}
|
|
],
|
|
"name": "_root_",
|
|
"label": "unspecified"
|
|
},
|
|
"groups": [
|
|
{
|
|
"self_ref": "#/groups/0",
|
|
"parent": {
|
|
"$ref": "#/texts/5"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/7"
|
|
},
|
|
{
|
|
"$ref": "#/texts/8"
|
|
},
|
|
{
|
|
"$ref": "#/texts/9"
|
|
}
|
|
],
|
|
"name": "list",
|
|
"label": "list"
|
|
},
|
|
{
|
|
"self_ref": "#/groups/1",
|
|
"parent": {
|
|
"$ref": "#/texts/5"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/11"
|
|
},
|
|
{
|
|
"$ref": "#/texts/12"
|
|
},
|
|
{
|
|
"$ref": "#/texts/13"
|
|
}
|
|
],
|
|
"name": "list",
|
|
"label": "list"
|
|
},
|
|
{
|
|
"self_ref": "#/groups/2",
|
|
"parent": {
|
|
"$ref": "#/texts/15"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/21"
|
|
},
|
|
{
|
|
"$ref": "#/texts/22"
|
|
},
|
|
{
|
|
"$ref": "#/texts/23"
|
|
}
|
|
],
|
|
"name": "list",
|
|
"label": "list"
|
|
}
|
|
],
|
|
"texts": [
|
|
{
|
|
"self_ref": "#/texts/0",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "Summer activities",
|
|
"text": "Summer activities"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/1",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/2"
|
|
},
|
|
{
|
|
"$ref": "#/texts/3"
|
|
},
|
|
{
|
|
"$ref": "#/texts/4"
|
|
},
|
|
{
|
|
"$ref": "#/texts/5"
|
|
}
|
|
],
|
|
"label": "title",
|
|
"prov": [],
|
|
"orig": "Swimming in the lake",
|
|
"text": "Swimming in the lake"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/2",
|
|
"parent": {
|
|
"$ref": "#/texts/1"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "Duck",
|
|
"text": "Duck"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/3",
|
|
"parent": {
|
|
"$ref": "#/texts/1"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/4",
|
|
"parent": {
|
|
"$ref": "#/texts/1"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "Figure 1: This is a cute duckling",
|
|
"text": "Figure 1: This is a cute duckling"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/5",
|
|
"parent": {
|
|
"$ref": "#/texts/1"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/6"
|
|
},
|
|
{
|
|
"$ref": "#/groups/0"
|
|
},
|
|
{
|
|
"$ref": "#/texts/10"
|
|
},
|
|
{
|
|
"$ref": "#/groups/1"
|
|
},
|
|
{
|
|
"$ref": "#/texts/14"
|
|
},
|
|
{
|
|
"$ref": "#/texts/15"
|
|
}
|
|
],
|
|
"label": "section_header",
|
|
"prov": [],
|
|
"orig": "Let\u2019s swim!",
|
|
"text": "Let\u2019s swim!",
|
|
"level": 1
|
|
},
|
|
{
|
|
"self_ref": "#/texts/6",
|
|
"parent": {
|
|
"$ref": "#/texts/5"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "To get started with swimming, first lay down in a water and try not to drown:",
|
|
"text": "To get started with swimming, first lay down in a water and try not to drown:"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/7",
|
|
"parent": {
|
|
"$ref": "#/groups/0"
|
|
},
|
|
"children": [],
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "You can relax and look around",
|
|
"text": "You can relax and look around",
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/8",
|
|
"parent": {
|
|
"$ref": "#/groups/0"
|
|
},
|
|
"children": [],
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "Paddle about",
|
|
"text": "Paddle about",
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/9",
|
|
"parent": {
|
|
"$ref": "#/groups/0"
|
|
},
|
|
"children": [],
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "Enjoy summer warmth",
|
|
"text": "Enjoy summer warmth",
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/10",
|
|
"parent": {
|
|
"$ref": "#/texts/5"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "Also, don\u2019t forget:",
|
|
"text": "Also, don\u2019t forget:"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/11",
|
|
"parent": {
|
|
"$ref": "#/groups/1"
|
|
},
|
|
"children": [],
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "Wear sunglasses",
|
|
"text": "Wear sunglasses",
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/12",
|
|
"parent": {
|
|
"$ref": "#/groups/1"
|
|
},
|
|
"children": [],
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "Don\u2019t forget to drink water",
|
|
"text": "Don\u2019t forget to drink water",
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/13",
|
|
"parent": {
|
|
"$ref": "#/groups/1"
|
|
},
|
|
"children": [],
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "Use sun cream",
|
|
"text": "Use sun cream",
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/14",
|
|
"parent": {
|
|
"$ref": "#/texts/5"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "Hmm, what else\u2026",
|
|
"text": "Hmm, what else\u2026"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/15",
|
|
"parent": {
|
|
"$ref": "#/texts/5"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/16"
|
|
},
|
|
{
|
|
"$ref": "#/texts/17"
|
|
},
|
|
{
|
|
"$ref": "#/texts/18"
|
|
},
|
|
{
|
|
"$ref": "#/tables/0"
|
|
},
|
|
{
|
|
"$ref": "#/texts/19"
|
|
},
|
|
{
|
|
"$ref": "#/texts/20"
|
|
},
|
|
{
|
|
"$ref": "#/groups/2"
|
|
}
|
|
],
|
|
"label": "section_header",
|
|
"prov": [],
|
|
"orig": "Let\u2019s eat",
|
|
"text": "Let\u2019s eat",
|
|
"level": 2
|
|
},
|
|
{
|
|
"self_ref": "#/texts/16",
|
|
"parent": {
|
|
"$ref": "#/texts/15"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "After we had a good day of swimming in the lake, it\u2019s important to eat something nice",
|
|
"text": "After we had a good day of swimming in the lake, it\u2019s important to eat something nice"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/17",
|
|
"parent": {
|
|
"$ref": "#/texts/15"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "I like to eat leaves",
|
|
"text": "I like to eat leaves"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/18",
|
|
"parent": {
|
|
"$ref": "#/texts/15"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "Here are some interesting things a respectful duck could eat:",
|
|
"text": "Here are some interesting things a respectful duck could eat:"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/19",
|
|
"parent": {
|
|
"$ref": "#/texts/15"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "",
|
|
"text": ""
|
|
},
|
|
{
|
|
"self_ref": "#/texts/20",
|
|
"parent": {
|
|
"$ref": "#/texts/15"
|
|
},
|
|
"children": [],
|
|
"label": "paragraph",
|
|
"prov": [],
|
|
"orig": "And let\u2019s add another list in the end:",
|
|
"text": "And let\u2019s add another list in the end:"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/21",
|
|
"parent": {
|
|
"$ref": "#/groups/2"
|
|
},
|
|
"children": [],
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "Leaves",
|
|
"text": "Leaves",
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/22",
|
|
"parent": {
|
|
"$ref": "#/groups/2"
|
|
},
|
|
"children": [],
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "Berries",
|
|
"text": "Berries",
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/23",
|
|
"parent": {
|
|
"$ref": "#/groups/2"
|
|
},
|
|
"children": [],
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "Grain",
|
|
"text": "Grain",
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
}
|
|
],
|
|
"pictures": [],
|
|
"tables": [
|
|
{
|
|
"self_ref": "#/tables/0",
|
|
"parent": {
|
|
"$ref": "#/texts/15"
|
|
},
|
|
"children": [],
|
|
"label": "table",
|
|
"prov": [],
|
|
"captions": [],
|
|
"references": [],
|
|
"footnotes": [],
|
|
"data": {
|
|
"table_cells": [
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 0,
|
|
"end_row_offset_idx": 1,
|
|
"start_col_offset_idx": 0,
|
|
"end_col_offset_idx": 1,
|
|
"text": "",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 0,
|
|
"end_row_offset_idx": 1,
|
|
"start_col_offset_idx": 1,
|
|
"end_col_offset_idx": 2,
|
|
"text": "Food",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 0,
|
|
"end_row_offset_idx": 1,
|
|
"start_col_offset_idx": 2,
|
|
"end_col_offset_idx": 3,
|
|
"text": "Calories per portion",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 1,
|
|
"end_row_offset_idx": 2,
|
|
"start_col_offset_idx": 0,
|
|
"end_col_offset_idx": 1,
|
|
"text": "Leaves",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 1,
|
|
"end_row_offset_idx": 2,
|
|
"start_col_offset_idx": 1,
|
|
"end_col_offset_idx": 2,
|
|
"text": "Ash, Elm, Maple",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 1,
|
|
"end_row_offset_idx": 2,
|
|
"start_col_offset_idx": 2,
|
|
"end_col_offset_idx": 3,
|
|
"text": "50",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 2,
|
|
"end_row_offset_idx": 3,
|
|
"start_col_offset_idx": 0,
|
|
"end_col_offset_idx": 1,
|
|
"text": "Berries",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 2,
|
|
"end_row_offset_idx": 3,
|
|
"start_col_offset_idx": 1,
|
|
"end_col_offset_idx": 2,
|
|
"text": "Blueberry, Strawberry, Cranberry",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 2,
|
|
"end_row_offset_idx": 3,
|
|
"start_col_offset_idx": 2,
|
|
"end_col_offset_idx": 3,
|
|
"text": "150",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 3,
|
|
"end_row_offset_idx": 4,
|
|
"start_col_offset_idx": 0,
|
|
"end_col_offset_idx": 1,
|
|
"text": "Grain",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 3,
|
|
"end_row_offset_idx": 4,
|
|
"start_col_offset_idx": 1,
|
|
"end_col_offset_idx": 2,
|
|
"text": "Corn, Buckwheat, Barley",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 3,
|
|
"end_row_offset_idx": 4,
|
|
"start_col_offset_idx": 2,
|
|
"end_col_offset_idx": 3,
|
|
"text": "200",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
}
|
|
],
|
|
"num_rows": 4,
|
|
"num_cols": 3,
|
|
"grid": [
|
|
[
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 0,
|
|
"end_row_offset_idx": 1,
|
|
"start_col_offset_idx": 0,
|
|
"end_col_offset_idx": 1,
|
|
"text": "",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 0,
|
|
"end_row_offset_idx": 1,
|
|
"start_col_offset_idx": 1,
|
|
"end_col_offset_idx": 2,
|
|
"text": "Food",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 0,
|
|
"end_row_offset_idx": 1,
|
|
"start_col_offset_idx": 2,
|
|
"end_col_offset_idx": 3,
|
|
"text": "Calories per portion",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
}
|
|
],
|
|
[
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 1,
|
|
"end_row_offset_idx": 2,
|
|
"start_col_offset_idx": 0,
|
|
"end_col_offset_idx": 1,
|
|
"text": "Leaves",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 1,
|
|
"end_row_offset_idx": 2,
|
|
"start_col_offset_idx": 1,
|
|
"end_col_offset_idx": 2,
|
|
"text": "Ash, Elm, Maple",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 1,
|
|
"end_row_offset_idx": 2,
|
|
"start_col_offset_idx": 2,
|
|
"end_col_offset_idx": 3,
|
|
"text": "50",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
}
|
|
],
|
|
[
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 2,
|
|
"end_row_offset_idx": 3,
|
|
"start_col_offset_idx": 0,
|
|
"end_col_offset_idx": 1,
|
|
"text": "Berries",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 2,
|
|
"end_row_offset_idx": 3,
|
|
"start_col_offset_idx": 1,
|
|
"end_col_offset_idx": 2,
|
|
"text": "Blueberry, Strawberry, Cranberry",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 2,
|
|
"end_row_offset_idx": 3,
|
|
"start_col_offset_idx": 2,
|
|
"end_col_offset_idx": 3,
|
|
"text": "150",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
}
|
|
],
|
|
[
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 3,
|
|
"end_row_offset_idx": 4,
|
|
"start_col_offset_idx": 0,
|
|
"end_col_offset_idx": 1,
|
|
"text": "Grain",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 3,
|
|
"end_row_offset_idx": 4,
|
|
"start_col_offset_idx": 1,
|
|
"end_col_offset_idx": 2,
|
|
"text": "Corn, Buckwheat, Barley",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
},
|
|
{
|
|
"row_span": 1,
|
|
"col_span": 1,
|
|
"start_row_offset_idx": 3,
|
|
"end_row_offset_idx": 4,
|
|
"start_col_offset_idx": 2,
|
|
"end_col_offset_idx": 3,
|
|
"text": "200",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
}
|
|
]
|
|
]
|
|
}
|
|
}
|
|
],
|
|
"key_value_items": [],
|
|
"pages": {}
|
|
} |