mirror of
https://github.com/DS4SD/docling.git
synced 2025-07-26 03:55:00 +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>
108 lines
2.3 KiB
JSON
108 lines
2.3 KiB
JSON
{
|
|
"schema_name": "DoclingDocument",
|
|
"version": "1.1.0",
|
|
"name": "example_06",
|
|
"origin": {
|
|
"mimetype": "text/html",
|
|
"binary_hash": 14574683870626799530,
|
|
"filename": "example_06.html"
|
|
},
|
|
"furniture": {
|
|
"self_ref": "#/furniture",
|
|
"children": [],
|
|
"content_layer": "furniture",
|
|
"name": "_root_",
|
|
"label": "unspecified"
|
|
},
|
|
"body": {
|
|
"self_ref": "#/body",
|
|
"children": [
|
|
{
|
|
"$ref": "#/texts/0"
|
|
},
|
|
{
|
|
"$ref": "#/texts/1"
|
|
},
|
|
{
|
|
"$ref": "#/texts/2"
|
|
},
|
|
{
|
|
"$ref": "#/texts/3"
|
|
},
|
|
{
|
|
"$ref": "#/texts/4"
|
|
}
|
|
],
|
|
"content_layer": "body",
|
|
"name": "_root_",
|
|
"label": "unspecified"
|
|
},
|
|
"groups": [],
|
|
"texts": [
|
|
{
|
|
"self_ref": "#/texts/0",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "This is a div with text.",
|
|
"text": "This is a div with text."
|
|
},
|
|
{
|
|
"self_ref": "#/texts/1",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "This is another div with text.",
|
|
"text": "This is another div with text."
|
|
},
|
|
{
|
|
"self_ref": "#/texts/2",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "This is a regular paragraph.",
|
|
"text": "This is a regular paragraph."
|
|
},
|
|
{
|
|
"self_ref": "#/texts/3",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "This is a third div\nwith a new line.",
|
|
"text": "This is a third div\nwith a new line."
|
|
},
|
|
{
|
|
"self_ref": "#/texts/4",
|
|
"parent": {
|
|
"$ref": "#/body"
|
|
},
|
|
"children": [],
|
|
"content_layer": "body",
|
|
"label": "text",
|
|
"prov": [],
|
|
"orig": "This is a fourth div with a bold paragraph.",
|
|
"text": "This is a fourth div with a bold paragraph."
|
|
}
|
|
],
|
|
"pictures": [],
|
|
"tables": [],
|
|
"key_value_items": [],
|
|
"form_items": [],
|
|
"pages": {}
|
|
} |