Files
docling/tests/data/groundtruth/docling_v2/webvtt_example_02.vtt.json
Cesar Berrospi Ramis 46efaaefee feat: add a backend parser for WebVTT files (#2288)
* feat: add a backend parser for WebVTT files

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>

* docs: update README with VTT support

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>

* docs: add description to supported formats

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>

* chore: upgrade docling-core to unescape WebVTT in markdown

Pin the new release of docling-core 2.48.2.
Do not escape HTML reserved characters when exporting WebVTT documents to markdown.

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>

* test: add missing copyright notice

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>

---------

Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
2025-09-22 15:24:34 +02:00

376 lines
7.5 KiB
JSON
Vendored
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
{
"schema_name": "DoclingDocument",
"version": "1.6.0",
"name": "webvtt_example_02",
"origin": {
"mimetype": "text/vtt",
"binary_hash": 12867774546881601731,
"filename": "webvtt_example_02.vtt"
},
"furniture": {
"self_ref": "#/furniture",
"children": [],
"content_layer": "furniture",
"name": "_root_",
"label": "unspecified"
},
"body": {
"self_ref": "#/body",
"children": [
{
"$ref": "#/groups/0"
},
{
"$ref": "#/groups/2"
},
{
"$ref": "#/groups/4"
},
{
"$ref": "#/groups/6"
}
],
"content_layer": "body",
"name": "_root_",
"label": "unspecified"
},
"groups": [
{
"self_ref": "#/groups/0",
"parent": {
"$ref": "#/body"
},
"children": [
{
"$ref": "#/texts/0"
},
{
"$ref": "#/groups/1"
}
],
"content_layer": "body",
"name": "WebVTT cue block",
"label": "section"
},
{
"self_ref": "#/groups/1",
"parent": {
"$ref": "#/groups/0"
},
"children": [
{
"$ref": "#/texts/1"
},
{
"$ref": "#/texts/2"
}
],
"content_layer": "body",
"name": "WebVTT cue voice span",
"label": "inline"
},
{
"self_ref": "#/groups/2",
"parent": {
"$ref": "#/body"
},
"children": [
{
"$ref": "#/texts/3"
},
{
"$ref": "#/groups/3"
}
],
"content_layer": "body",
"name": "WebVTT cue block",
"label": "section"
},
{
"self_ref": "#/groups/3",
"parent": {
"$ref": "#/groups/2"
},
"children": [
{
"$ref": "#/texts/4"
},
{
"$ref": "#/texts/5"
}
],
"content_layer": "body",
"name": "WebVTT cue voice span",
"label": "inline"
},
{
"self_ref": "#/groups/4",
"parent": {
"$ref": "#/body"
},
"children": [
{
"$ref": "#/texts/6"
},
{
"$ref": "#/groups/5"
},
{
"$ref": "#/texts/9"
}
],
"content_layer": "body",
"name": "WebVTT cue block",
"label": "section"
},
{
"self_ref": "#/groups/5",
"parent": {
"$ref": "#/groups/4"
},
"children": [
{
"$ref": "#/texts/7"
},
{
"$ref": "#/texts/8"
}
],
"content_layer": "body",
"name": "WebVTT cue voice span",
"label": "inline"
},
{
"self_ref": "#/groups/6",
"parent": {
"$ref": "#/body"
},
"children": [
{
"$ref": "#/texts/10"
},
{
"$ref": "#/groups/7"
}
],
"content_layer": "body",
"name": "WebVTT cue block",
"label": "section"
},
{
"self_ref": "#/groups/7",
"parent": {
"$ref": "#/groups/6"
},
"children": [
{
"$ref": "#/texts/11"
},
{
"$ref": "#/texts/12"
}
],
"content_layer": "body",
"name": "WebVTT cue voice span",
"label": "inline"
}
],
"texts": [
{
"self_ref": "#/texts/0",
"parent": {
"$ref": "#/groups/0"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "00:00.000 --> 00:02.000",
"text": "00:00.000 --> 00:02.000"
},
{
"self_ref": "#/texts/1",
"parent": {
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Esme (first, loud): ",
"text": "Esme (first, loud): "
},
{
"self_ref": "#/texts/2",
"parent": {
"$ref": "#/groups/1"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Its a blue apple tree!",
"text": "Its a blue apple tree!",
"formatting": {
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false,
"script": "baseline"
}
},
{
"self_ref": "#/texts/3",
"parent": {
"$ref": "#/groups/2"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "00:02.000 --> 00:04.000",
"text": "00:02.000 --> 00:04.000"
},
{
"self_ref": "#/texts/4",
"parent": {
"$ref": "#/groups/3"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Mary: ",
"text": "Mary: "
},
{
"self_ref": "#/texts/5",
"parent": {
"$ref": "#/groups/3"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "No way!",
"text": "No way!",
"formatting": {
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false,
"script": "baseline"
}
},
{
"self_ref": "#/texts/6",
"parent": {
"$ref": "#/groups/4"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "00:04.000 --> 00:06.000",
"text": "00:04.000 --> 00:06.000"
},
{
"self_ref": "#/texts/7",
"parent": {
"$ref": "#/groups/5"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Esme: ",
"text": "Esme: "
},
{
"self_ref": "#/texts/8",
"parent": {
"$ref": "#/groups/5"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Hee!",
"text": "Hee!",
"formatting": {
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false,
"script": "baseline"
}
},
{
"self_ref": "#/texts/9",
"parent": {
"$ref": "#/groups/4"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "laughter",
"text": "laughter",
"formatting": {
"bold": false,
"italic": true,
"underline": false,
"strikethrough": false,
"script": "baseline"
}
},
{
"self_ref": "#/texts/10",
"parent": {
"$ref": "#/groups/6"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "00:06.000 --> 00:08.000",
"text": "00:06.000 --> 00:08.000"
},
{
"self_ref": "#/texts/11",
"parent": {
"$ref": "#/groups/7"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Mary (loud): ",
"text": "Mary (loud): "
},
{
"self_ref": "#/texts/12",
"parent": {
"$ref": "#/groups/7"
},
"children": [],
"content_layer": "body",
"label": "text",
"prov": [],
"orig": "Thats awesome!",
"text": "Thats awesome!",
"formatting": {
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false,
"script": "baseline"
}
}
],
"pictures": [],
"tables": [],
"key_value_items": [],
"form_items": [],
"pages": {}
}