mirror of
https://github.com/DS4SD/docling.git
synced 2025-07-29 05:24:28 +00:00
e25d557c06
* added the contentlayer to html-backend
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* updated the handle_image function
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* reformatted code of html backend
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
* test(html): add more info if a test case fails
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* refactor(html): put parsed item in body if doc has no header
In case an HTML does not have any header tag, all parsed items are placed in
DoclingDocument's body content layer.
HTML paragraphs ('p' tags) are parsed as text items with paragraph label.
Update test ground truth accoring to the changes above.
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
* chore: set TextItem label to 'text' instead of 'paragraph'
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
---------
Signed-off-by: Peter Staar <taa@zurich.ibm.com>
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
646 lines
16 KiB
JSON
646 lines
16 KiB
JSON
{
|
|
"schema_name": "DoclingDocument",
|
|
"version": "1.1.0",
|
|
"name": "example_03",
|
|
"origin": {
|
|
"mimetype": "text/html",
|
|
"binary_hash": 17768514429310008971,
|
|
"filename": "example_03.html"
|
|
},
|
|
"furniture": {
|
|
"self_ref": "#/furniture",
|
|
"children": [],
|
|
"content_layer": "furniture",
|
|
"name": "_root_",
|
|
"label": "unspecified"
|
|
},
|
|
"body": {
|
|
"self_ref": "#/body",
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/0"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "_root_",
|
|
"label": "unspecified"
|
|
},
|
|
"groups": [
|
|
{
|
|
"self_ref": "#/groups/0",
|
|
"parent": {
|
|
"$ref": "#/texts/3"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/5"
|
|
},
|
|
{
|
|
"$ref": "#/texts/8"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "list",
|
|
"label": "list"
|
|
},
|
|
{
|
|
"self_ref": "#/groups/1",
|
|
"parent": {
|
|
"$ref": "#/texts/5"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/6"
|
|
},
|
|
{
|
|
"$ref": "#/texts/7"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "list",
|
|
"label": "list"
|
|
},
|
|
{
|
|
"self_ref": "#/groups/2",
|
|
"parent": {
|
|
"$ref": "#/texts/3"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/9"
|
|
},
|
|
{
|
|
"$ref": "#/texts/12"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "ordered list",
|
|
"label": "ordered_list"
|
|
},
|
|
{
|
|
"self_ref": "#/groups/3",
|
|
"parent": {
|
|
"$ref": "#/texts/9"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/10"
|
|
},
|
|
{
|
|
"$ref": "#/texts/11"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "ordered list",
|
|
"label": "ordered_list"
|
|
}
|
|
],
|
|
"texts": [
|
|
{
|
|
"self_ref": "#/texts/0",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/1"
|
|
},
|
|
{
|
|
"$ref": "#/texts/3"
|
|
},
|
|
{
|
|
"$ref": "#/texts/13"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"label": "title",
|
|
"prov": [],
|
|
"orig": "Example Document",
|
|
"text": "Example Document"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/1",
|
|
"parent": {
|
|
"$ref": "#/texts/0"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/2"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"label": "section_header",
|
|
"prov": [],
|
|
"orig": "Introduction",
|
|
"text": "Introduction",
|
|
"level": 2
|
|
},
|
|
{
|
|
"self_ref": "#/texts/2",
|
|
"parent": {
|
|
"$ref": "#/texts/1"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "This is the first paragraph of the introduction.",
|
|
"text": "This is the first paragraph of the introduction."
|
|
},
|
|
{
|
|
"self_ref": "#/texts/3",
|
|
"parent": {
|
|
"$ref": "#/texts/0"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/4"
|
|
},
|
|
{
|
|
"$ref": "#/groups/0"
|
|
},
|
|
{
|
|
"$ref": "#/groups/2"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"label": "section_header",
|
|
"prov": [],
|
|
"orig": "Background",
|
|
"text": "Background",
|
|
"level": 2
|
|
},
|
|
{
|
|
"self_ref": "#/texts/4",
|
|
"parent": {
|
|
"$ref": "#/texts/3"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "Some background information here.",
|
|
"text": "Some background information here."
|
|
},
|
|
{
|
|
"self_ref": "#/texts/5",
|
|
"parent": {
|
|
"$ref": "#/groups/0"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/groups/1"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "First item in unordered list",
|
|
"text": "First item in unordered list",
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/6",
|
|
"parent": {
|
|
"$ref": "#/groups/1"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "Nested item 1",
|
|
"text": "Nested item 1",
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/7",
|
|
"parent": {
|
|
"$ref": "#/groups/1"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "Nested item 2",
|
|
"text": "Nested item 2",
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/8",
|
|
"parent": {
|
|
"$ref": "#/groups/0"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "Second item in unordered list",
|
|
"text": "Second item in unordered list",
|
|
"enumerated": false,
|
|
"marker": "-"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/9",
|
|
"parent": {
|
|
"$ref": "#/groups/2"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/groups/3"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "First item in ordered list",
|
|
"text": "First item in ordered list",
|
|
"enumerated": true,
|
|
"marker": "1"
|
|
},
|
|
{
|
|
"self_ref": "#/texts/10",
|
|
"parent": {
|
|
"$ref": "#/groups/3"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "Nested ordered item 1",
|
|
"text": "Nested ordered item 1",
|
|
"enumerated": true,
|
|
"marker": "1."
|
|
},
|
|
{
|
|
"self_ref": "#/texts/11",
|
|
"parent": {
|
|
"$ref": "#/groups/3"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "Nested ordered item 2",
|
|
"text": "Nested ordered item 2",
|
|
"enumerated": true,
|
|
"marker": "2."
|
|
},
|
|
{
|
|
"self_ref": "#/texts/12",
|
|
"parent": {
|
|
"$ref": "#/groups/2"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "list_item",
|
|
"prov": [],
|
|
"orig": "Second item in ordered list",
|
|
"text": "Second item in ordered list",
|
|
"enumerated": true,
|
|
"marker": "2."
|
|
},
|
|
{
|
|
"self_ref": "#/texts/13",
|
|
"parent": {
|
|
"$ref": "#/texts/0"
|
|
},
|
|
"children": [
|
|
{
|
|
"$ref": "#/tables/0"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"label": "section_header",
|
|
"prov": [],
|
|
"orig": "Data Table",
|
|
"text": "Data Table",
|
|
"level": 2
|
|
}
|
|
],
|
|
"pictures": [],
|
|
"tables": [
|
|
{
|
|
"self_ref": "#/tables/0",
|
|
"parent": {
|
|
"$ref": "#/texts/13"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"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": "Header 1",
|
|
"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": "Header 2",
|
|
"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": "Header 3",
|
|
"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": "Row 1, Col 1",
|
|
"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": "Row 1, Col 2",
|
|
"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": "Row 1, Col 3",
|
|
"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": "Row 2, Col 1",
|
|
"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": "Row 2, Col 2",
|
|
"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": "Row 2, Col 3",
|
|
"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": "Row 3, Col 1",
|
|
"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": "Row 3, Col 2",
|
|
"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": "Row 3, Col 3",
|
|
"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": "Header 1",
|
|
"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": "Header 2",
|
|
"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": "Header 3",
|
|
"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": "Row 1, Col 1",
|
|
"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": "Row 1, Col 2",
|
|
"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": "Row 1, Col 3",
|
|
"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": "Row 2, Col 1",
|
|
"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": "Row 2, Col 2",
|
|
"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": "Row 2, Col 3",
|
|
"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": "Row 3, Col 1",
|
|
"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": "Row 3, Col 2",
|
|
"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": "Row 3, Col 3",
|
|
"column_header": false,
|
|
"row_header": false,
|
|
"row_section": false
|
|
}
|
|
]
|
|
]
|
|
}
|
|
}
|
|
],
|
|
"key_value_items": [],
|
|
"form_items": [],
|
|
"pages": {}
|
|
} |