mirror of
https://github.com/DS4SD/docling.git
synced 2025-12-09 05:08:14 +00:00
refactor(HTML): handle text from styled html (#1960)
* A new HTML backend that handles styled html (ignors it) as well as images. Images are parsed as placeholders with a caption, if it exists. Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com> Co-authored-by: vaaale <2428222+vaaale@users.noreply.github.com> Signed-off-by: Alexander Vaagan <alexander.vaagan@gmail.com> Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com> Signed-off-by: vaaale <2428222+vaaale@users.noreply.github.com> * tests(HTML): re-enable test_ordered_lists Re-enable test_ordered_lists regression test for the HTML backend since docling-core now supports ordered lists with custom start value. Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com> --------- Signed-off-by: Alexander Vaagan <alexander.vaagan@gmail.com> Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com> Signed-off-by: vaaale <2428222+vaaale@users.noreply.github.com> Co-authored-by: Alexander Vaagan <2428222+vaaale@users.noreply.github.com>
This commit is contained in:
Cesar Berrospi Ramis
committed by
GitHub
GitHub
parent
5d98bcea1b
commit
a069b1175b
404
tests/data/groundtruth/docling_v2/example_09.html.json
vendored
Normal file
404
tests/data/groundtruth/docling_v2/example_09.html.json
vendored
Normal file
@@ -0,0 +1,404 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.5.0",
|
||||
"name": "example_09",
|
||||
"origin": {
|
||||
"mimetype": "text/html",
|
||||
"binary_hash": 6785336133244366107,
|
||||
"filename": "example_09.html"
|
||||
},
|
||||
"furniture": {
|
||||
"self_ref": "#/furniture",
|
||||
"children": [],
|
||||
"content_layer": "furniture",
|
||||
"name": "_root_",
|
||||
"label": "unspecified"
|
||||
},
|
||||
"body": {
|
||||
"self_ref": "#/body",
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/0"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/1"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/6"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/8"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/10"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
"name": "_root_",
|
||||
"label": "unspecified"
|
||||
},
|
||||
"groups": [
|
||||
{
|
||||
"self_ref": "#/groups/0",
|
||||
"parent": {
|
||||
"$ref": "#/texts/3"
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/5"
|
||||
},
|
||||
{
|
||||
"$ref": "#/pictures/1"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/7"
|
||||
},
|
||||
{
|
||||
"$ref": "#/pictures/2"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/9"
|
||||
},
|
||||
{
|
||||
"$ref": "#/pictures/3"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
"name": "list",
|
||||
"label": "list"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/groups/1",
|
||||
"parent": {
|
||||
"$ref": "#/texts/11"
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/13"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/14"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/15"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
"name": "ordered list",
|
||||
"label": "list"
|
||||
}
|
||||
],
|
||||
"texts": [
|
||||
{
|
||||
"self_ref": "#/texts/0",
|
||||
"parent": {
|
||||
"$ref": "#/body"
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/pictures/0"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/2"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/3"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
"label": "title",
|
||||
"prov": [],
|
||||
"orig": "Introduction to parsing HTML files with Docling",
|
||||
"text": "Introduction to parsing HTML files with Docling"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/1",
|
||||
"parent": {
|
||||
"$ref": "#/body"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "caption",
|
||||
"prov": [],
|
||||
"orig": "Docling",
|
||||
"text": "Docling"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/2",
|
||||
"parent": {
|
||||
"$ref": "#/texts/0"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "text",
|
||||
"prov": [],
|
||||
"orig": "Docling simplifies document processing, parsing diverse formats — including HTML — and providing seamless integrations with the gen AI ecosystem.",
|
||||
"text": "Docling simplifies document processing, parsing diverse formats — including HTML — and providing seamless integrations with the gen AI ecosystem."
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/3",
|
||||
"parent": {
|
||||
"$ref": "#/texts/0"
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/4"
|
||||
},
|
||||
{
|
||||
"$ref": "#/groups/0"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/11"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
"label": "section_header",
|
||||
"prov": [],
|
||||
"orig": "Supported file formats",
|
||||
"text": "Supported file formats",
|
||||
"level": 1
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/4",
|
||||
"parent": {
|
||||
"$ref": "#/texts/3"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "text",
|
||||
"prov": [],
|
||||
"orig": "Docling supports multiple file formats..",
|
||||
"text": "Docling supports multiple file formats.."
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/5",
|
||||
"parent": {
|
||||
"$ref": "#/groups/0"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "list_item",
|
||||
"prov": [],
|
||||
"orig": "Advanced PDF understanding",
|
||||
"text": "Advanced PDF understanding",
|
||||
"enumerated": false,
|
||||
"marker": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/6",
|
||||
"parent": {
|
||||
"$ref": "#/body"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "caption",
|
||||
"prov": [],
|
||||
"orig": "PDF",
|
||||
"text": "PDF"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/7",
|
||||
"parent": {
|
||||
"$ref": "#/groups/0"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "list_item",
|
||||
"prov": [],
|
||||
"orig": "Microsoft Office DOCX",
|
||||
"text": "Microsoft Office DOCX",
|
||||
"enumerated": false,
|
||||
"marker": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/8",
|
||||
"parent": {
|
||||
"$ref": "#/body"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "caption",
|
||||
"prov": [],
|
||||
"orig": "DOCX",
|
||||
"text": "DOCX"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/9",
|
||||
"parent": {
|
||||
"$ref": "#/groups/0"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "list_item",
|
||||
"prov": [],
|
||||
"orig": "HTML files (with optional support for images)",
|
||||
"text": "HTML files (with optional support for images)",
|
||||
"enumerated": false,
|
||||
"marker": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/10",
|
||||
"parent": {
|
||||
"$ref": "#/body"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "caption",
|
||||
"prov": [],
|
||||
"orig": "HTML",
|
||||
"text": "HTML"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/11",
|
||||
"parent": {
|
||||
"$ref": "#/texts/3"
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/12"
|
||||
},
|
||||
{
|
||||
"$ref": "#/groups/1"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
"label": "section_header",
|
||||
"prov": [],
|
||||
"orig": "Three backends for handling HTML files",
|
||||
"text": "Three backends for handling HTML files",
|
||||
"level": 2
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/12",
|
||||
"parent": {
|
||||
"$ref": "#/texts/11"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "text",
|
||||
"prov": [],
|
||||
"orig": "Docling has three backends for parsing HTML files:",
|
||||
"text": "Docling has three backends for parsing HTML files:"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/13",
|
||||
"parent": {
|
||||
"$ref": "#/groups/1"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "list_item",
|
||||
"prov": [],
|
||||
"orig": "HTMLDocumentBackend Ignores images",
|
||||
"text": "HTMLDocumentBackend Ignores images",
|
||||
"enumerated": true,
|
||||
"marker": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/14",
|
||||
"parent": {
|
||||
"$ref": "#/groups/1"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "list_item",
|
||||
"prov": [],
|
||||
"orig": "HTMLDocumentBackendImagesInline Extracts images inline",
|
||||
"text": "HTMLDocumentBackendImagesInline Extracts images inline",
|
||||
"enumerated": true,
|
||||
"marker": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/15",
|
||||
"parent": {
|
||||
"$ref": "#/groups/1"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "list_item",
|
||||
"prov": [],
|
||||
"orig": "HTMLDocumentBackendImagesReferenced Extracts images as references",
|
||||
"text": "HTMLDocumentBackendImagesReferenced Extracts images as references",
|
||||
"enumerated": true,
|
||||
"marker": ""
|
||||
}
|
||||
],
|
||||
"pictures": [
|
||||
{
|
||||
"self_ref": "#/pictures/0",
|
||||
"parent": {
|
||||
"$ref": "#/texts/0"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "picture",
|
||||
"prov": [],
|
||||
"captions": [
|
||||
{
|
||||
"$ref": "#/texts/1"
|
||||
}
|
||||
],
|
||||
"references": [],
|
||||
"footnotes": [],
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/pictures/1",
|
||||
"parent": {
|
||||
"$ref": "#/groups/0"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "picture",
|
||||
"prov": [],
|
||||
"captions": [
|
||||
{
|
||||
"$ref": "#/texts/6"
|
||||
}
|
||||
],
|
||||
"references": [],
|
||||
"footnotes": [],
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/pictures/2",
|
||||
"parent": {
|
||||
"$ref": "#/groups/0"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "picture",
|
||||
"prov": [],
|
||||
"captions": [
|
||||
{
|
||||
"$ref": "#/texts/8"
|
||||
}
|
||||
],
|
||||
"references": [],
|
||||
"footnotes": [],
|
||||
"annotations": []
|
||||
},
|
||||
{
|
||||
"self_ref": "#/pictures/3",
|
||||
"parent": {
|
||||
"$ref": "#/groups/0"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "picture",
|
||||
"prov": [],
|
||||
"captions": [
|
||||
{
|
||||
"$ref": "#/texts/10"
|
||||
}
|
||||
],
|
||||
"references": [],
|
||||
"footnotes": [],
|
||||
"annotations": []
|
||||
}
|
||||
],
|
||||
"tables": [],
|
||||
"key_value_items": [],
|
||||
"form_items": [],
|
||||
"pages": {}
|
||||
}
|
||||
Reference in New Issue
Block a user