mirror of
https://github.com/DS4SD/docling.git
synced 2025-12-08 20:58:11 +00:00
fix(html): preserve code blocks in list items (#2131)
* chore(html): refactor parser to leverage context managers Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com> * fix(html): parse inline code snippets, also from list items Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com> * chore(html): remove hidden tags Remove tags that are not meant to be displayed. Add regression tests for code blocks, inline code, and hidden tags. Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com> --------- Signed-off-by: Cesar Berrospi Ramis <ceb@zurich.ibm.com>
This commit is contained in:
Cesar Berrospi Ramis
committed by
GitHub
GitHub
parent
c0268416cf
commit
fa3327e1a6
39
tests/data/groundtruth/docling_v2/html_code_snippets.html.itxt
vendored
Normal file
39
tests/data/groundtruth/docling_v2/html_code_snippets.html.itxt
vendored
Normal file
@@ -0,0 +1,39 @@
|
||||
item-0 at level 0: unspecified: group _root_
|
||||
item-1 at level 1: title: Code snippets
|
||||
item-2 at level 2: inline: group group
|
||||
item-3 at level 3: text: The Pythagorean theorem can be w ... tion relating the lengths of the sides
|
||||
item-4 at level 3: text: a
|
||||
item-5 at level 3: text: ,
|
||||
item-6 at level 3: text: b
|
||||
item-7 at level 3: text: and the hypotenuse
|
||||
item-8 at level 3: text: c
|
||||
item-9 at level 3: text: .
|
||||
item-10 at level 2: inline: group group
|
||||
item-11 at level 3: text: To use Docling, simply install
|
||||
item-12 at level 3: code: docling
|
||||
item-13 at level 3: text: from your package manager, e.g. pip:
|
||||
item-14 at level 3: code: pip install docling
|
||||
item-15 at level 2: inline: group group
|
||||
item-16 at level 3: text: To convert individual documents with python, use
|
||||
item-17 at level 3: code: convert()
|
||||
item-18 at level 3: text: , for example:
|
||||
item-19 at level 2: code: from docling.document_converter ... (result.document.export_to_markdown())
|
||||
item-20 at level 2: inline: group group
|
||||
item-21 at level 3: text: The program will output:
|
||||
item-22 at level 3: code: ## Docling Technical Report[...]
|
||||
item-23 at level 2: text: Prefetch the models:
|
||||
item-24 at level 2: list: group list
|
||||
item-25 at level 3: list_item:
|
||||
item-26 at level 4: inline: group group
|
||||
item-27 at level 5: text: Use the
|
||||
item-28 at level 5: code: docling-tools models download
|
||||
item-29 at level 5: text: utility:
|
||||
item-30 at level 3: list_item:
|
||||
item-31 at level 4: inline: group group
|
||||
item-32 at level 5: text: Alternatively, models can be programmatically downloaded using
|
||||
item-33 at level 5: code: docling.utils.model_downloader.download_models()
|
||||
item-34 at level 5: text: .
|
||||
item-35 at level 3: list_item:
|
||||
item-36 at level 4: inline: group group
|
||||
item-37 at level 5: text: Also, you can use download-hf-re ... rom HuggingFace by specifying repo id:
|
||||
item-38 at level 5: code: $ docling-tools models download- ... 256M-preview model from HuggingFace...
|
||||
674
tests/data/groundtruth/docling_v2/html_code_snippets.html.json
vendored
Normal file
674
tests/data/groundtruth/docling_v2/html_code_snippets.html.json
vendored
Normal file
@@ -0,0 +1,674 @@
|
||||
{
|
||||
"schema_name": "DoclingDocument",
|
||||
"version": "1.5.0",
|
||||
"name": "html_code_snippets",
|
||||
"origin": {
|
||||
"mimetype": "text/html",
|
||||
"binary_hash": 8468578485215893920,
|
||||
"filename": "html_code_snippets.html"
|
||||
},
|
||||
"furniture": {
|
||||
"self_ref": "#/furniture",
|
||||
"children": [],
|
||||
"content_layer": "furniture",
|
||||
"name": "_root_",
|
||||
"label": "unspecified"
|
||||
},
|
||||
"body": {
|
||||
"self_ref": "#/body",
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/0"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/1"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
"name": "_root_",
|
||||
"label": "unspecified"
|
||||
},
|
||||
"groups": [
|
||||
{
|
||||
"self_ref": "#/groups/0",
|
||||
"parent": {
|
||||
"$ref": "#/texts/1"
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/2"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/3"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/4"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/5"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/6"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/7"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/8"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
"name": "group",
|
||||
"label": "inline"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/groups/1",
|
||||
"parent": {
|
||||
"$ref": "#/texts/1"
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/9"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/10"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/11"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/12"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
"name": "group",
|
||||
"label": "inline"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/groups/2",
|
||||
"parent": {
|
||||
"$ref": "#/texts/1"
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/13"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/14"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/15"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
"name": "group",
|
||||
"label": "inline"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/groups/3",
|
||||
"parent": {
|
||||
"$ref": "#/texts/1"
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/17"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/18"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
"name": "group",
|
||||
"label": "inline"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/groups/4",
|
||||
"parent": {
|
||||
"$ref": "#/texts/1"
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/20"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/24"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/28"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
"name": "list",
|
||||
"label": "list"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/groups/5",
|
||||
"parent": {
|
||||
"$ref": "#/texts/20"
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/21"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/22"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/23"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
"name": "group",
|
||||
"label": "inline"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/groups/6",
|
||||
"parent": {
|
||||
"$ref": "#/texts/24"
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/25"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/26"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/27"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
"name": "group",
|
||||
"label": "inline"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/groups/7",
|
||||
"parent": {
|
||||
"$ref": "#/texts/28"
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/texts/29"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/30"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
"name": "group",
|
||||
"label": "inline"
|
||||
}
|
||||
],
|
||||
"texts": [
|
||||
{
|
||||
"self_ref": "#/texts/0",
|
||||
"parent": {
|
||||
"$ref": "#/body"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "furniture",
|
||||
"label": "title",
|
||||
"prov": [],
|
||||
"orig": "Code snippets in HTML",
|
||||
"text": "Code snippets in HTML"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/1",
|
||||
"parent": {
|
||||
"$ref": "#/body"
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/groups/0"
|
||||
},
|
||||
{
|
||||
"$ref": "#/groups/1"
|
||||
},
|
||||
{
|
||||
"$ref": "#/groups/2"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/16"
|
||||
},
|
||||
{
|
||||
"$ref": "#/groups/3"
|
||||
},
|
||||
{
|
||||
"$ref": "#/texts/19"
|
||||
},
|
||||
{
|
||||
"$ref": "#/groups/4"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
"label": "title",
|
||||
"prov": [],
|
||||
"orig": "Code snippets",
|
||||
"text": "Code snippets"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/2",
|
||||
"parent": {
|
||||
"$ref": "#/groups/0"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "text",
|
||||
"prov": [],
|
||||
"orig": "The Pythagorean theorem can be written as an equation relating the lengths of the sides",
|
||||
"text": "The Pythagorean theorem can be written as an equation relating the lengths of the sides"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/3",
|
||||
"parent": {
|
||||
"$ref": "#/groups/0"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "text",
|
||||
"prov": [],
|
||||
"orig": "a",
|
||||
"text": "a",
|
||||
"formatting": {
|
||||
"bold": false,
|
||||
"italic": true,
|
||||
"underline": false,
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/4",
|
||||
"parent": {
|
||||
"$ref": "#/groups/0"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "text",
|
||||
"prov": [],
|
||||
"orig": ",",
|
||||
"text": ","
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/5",
|
||||
"parent": {
|
||||
"$ref": "#/groups/0"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "text",
|
||||
"prov": [],
|
||||
"orig": "b",
|
||||
"text": "b",
|
||||
"formatting": {
|
||||
"bold": false,
|
||||
"italic": true,
|
||||
"underline": false,
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/6",
|
||||
"parent": {
|
||||
"$ref": "#/groups/0"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "text",
|
||||
"prov": [],
|
||||
"orig": "and the hypotenuse",
|
||||
"text": "and the hypotenuse"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/7",
|
||||
"parent": {
|
||||
"$ref": "#/groups/0"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "text",
|
||||
"prov": [],
|
||||
"orig": "c",
|
||||
"text": "c",
|
||||
"formatting": {
|
||||
"bold": false,
|
||||
"italic": true,
|
||||
"underline": false,
|
||||
"strikethrough": false,
|
||||
"script": "baseline"
|
||||
}
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/8",
|
||||
"parent": {
|
||||
"$ref": "#/groups/0"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "text",
|
||||
"prov": [],
|
||||
"orig": ".",
|
||||
"text": "."
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/9",
|
||||
"parent": {
|
||||
"$ref": "#/groups/1"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "text",
|
||||
"prov": [],
|
||||
"orig": "To use Docling, simply install",
|
||||
"text": "To use Docling, simply install"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/10",
|
||||
"parent": {
|
||||
"$ref": "#/groups/1"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "code",
|
||||
"prov": [],
|
||||
"orig": "docling",
|
||||
"text": "docling",
|
||||
"captions": [],
|
||||
"references": [],
|
||||
"footnotes": [],
|
||||
"code_language": "unknown"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/11",
|
||||
"parent": {
|
||||
"$ref": "#/groups/1"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "text",
|
||||
"prov": [],
|
||||
"orig": "from your package manager, e.g. pip:",
|
||||
"text": "from your package manager, e.g. pip:"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/12",
|
||||
"parent": {
|
||||
"$ref": "#/groups/1"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "code",
|
||||
"prov": [],
|
||||
"orig": "pip install docling",
|
||||
"text": "pip install docling",
|
||||
"captions": [],
|
||||
"references": [],
|
||||
"footnotes": [],
|
||||
"code_language": "unknown"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/13",
|
||||
"parent": {
|
||||
"$ref": "#/groups/2"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "text",
|
||||
"prov": [],
|
||||
"orig": "To convert individual documents with python, use",
|
||||
"text": "To convert individual documents with python, use"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/14",
|
||||
"parent": {
|
||||
"$ref": "#/groups/2"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "code",
|
||||
"prov": [],
|
||||
"orig": "convert()",
|
||||
"text": "convert()",
|
||||
"captions": [],
|
||||
"references": [],
|
||||
"footnotes": [],
|
||||
"code_language": "unknown"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/15",
|
||||
"parent": {
|
||||
"$ref": "#/groups/2"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "text",
|
||||
"prov": [],
|
||||
"orig": ", for example:",
|
||||
"text": ", for example:"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/16",
|
||||
"parent": {
|
||||
"$ref": "#/texts/1"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "code",
|
||||
"prov": [],
|
||||
"orig": "from docling.document_converter import DocumentConverter\n\nsource = \"https://arxiv.org/pdf/2408.09869\"\nconverter = DocumentConverter()\nresult = converter.convert(source)\nprint(result.document.export_to_markdown())",
|
||||
"text": "from docling.document_converter import DocumentConverter\n\nsource = \"https://arxiv.org/pdf/2408.09869\"\nconverter = DocumentConverter()\nresult = converter.convert(source)\nprint(result.document.export_to_markdown())",
|
||||
"captions": [],
|
||||
"references": [],
|
||||
"footnotes": [],
|
||||
"code_language": "unknown"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/17",
|
||||
"parent": {
|
||||
"$ref": "#/groups/3"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "text",
|
||||
"prov": [],
|
||||
"orig": "The program will output:",
|
||||
"text": "The program will output:"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/18",
|
||||
"parent": {
|
||||
"$ref": "#/groups/3"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "code",
|
||||
"prov": [],
|
||||
"orig": "## Docling Technical Report[...]",
|
||||
"text": "## Docling Technical Report[...]",
|
||||
"captions": [],
|
||||
"references": [],
|
||||
"footnotes": [],
|
||||
"code_language": "unknown"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/19",
|
||||
"parent": {
|
||||
"$ref": "#/texts/1"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "text",
|
||||
"prov": [],
|
||||
"orig": "Prefetch the models:",
|
||||
"text": "Prefetch the models:"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/20",
|
||||
"parent": {
|
||||
"$ref": "#/groups/4"
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/groups/5"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
"label": "list_item",
|
||||
"prov": [],
|
||||
"orig": "",
|
||||
"text": "",
|
||||
"enumerated": false,
|
||||
"marker": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/21",
|
||||
"parent": {
|
||||
"$ref": "#/groups/5"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "text",
|
||||
"prov": [],
|
||||
"orig": "Use the",
|
||||
"text": "Use the"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/22",
|
||||
"parent": {
|
||||
"$ref": "#/groups/5"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "code",
|
||||
"prov": [],
|
||||
"orig": "docling-tools models download",
|
||||
"text": "docling-tools models download",
|
||||
"captions": [],
|
||||
"references": [],
|
||||
"footnotes": [],
|
||||
"code_language": "unknown"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/23",
|
||||
"parent": {
|
||||
"$ref": "#/groups/5"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "text",
|
||||
"prov": [],
|
||||
"orig": "utility:",
|
||||
"text": "utility:"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/24",
|
||||
"parent": {
|
||||
"$ref": "#/groups/4"
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/groups/6"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
"label": "list_item",
|
||||
"prov": [],
|
||||
"orig": "",
|
||||
"text": "",
|
||||
"enumerated": false,
|
||||
"marker": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/25",
|
||||
"parent": {
|
||||
"$ref": "#/groups/6"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "text",
|
||||
"prov": [],
|
||||
"orig": "Alternatively, models can be programmatically downloaded using",
|
||||
"text": "Alternatively, models can be programmatically downloaded using"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/26",
|
||||
"parent": {
|
||||
"$ref": "#/groups/6"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "code",
|
||||
"prov": [],
|
||||
"orig": "docling.utils.model_downloader.download_models()",
|
||||
"text": "docling.utils.model_downloader.download_models()",
|
||||
"captions": [],
|
||||
"references": [],
|
||||
"footnotes": [],
|
||||
"code_language": "unknown"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/27",
|
||||
"parent": {
|
||||
"$ref": "#/groups/6"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "text",
|
||||
"prov": [],
|
||||
"orig": ".",
|
||||
"text": "."
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/28",
|
||||
"parent": {
|
||||
"$ref": "#/groups/4"
|
||||
},
|
||||
"children": [
|
||||
{
|
||||
"$ref": "#/groups/7"
|
||||
}
|
||||
],
|
||||
"content_layer": "body",
|
||||
"label": "list_item",
|
||||
"prov": [],
|
||||
"orig": "",
|
||||
"text": "",
|
||||
"enumerated": false,
|
||||
"marker": ""
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/29",
|
||||
"parent": {
|
||||
"$ref": "#/groups/7"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "text",
|
||||
"prov": [],
|
||||
"orig": "Also, you can use download-hf-repo parameter to download arbitrary models from HuggingFace by specifying repo id:",
|
||||
"text": "Also, you can use download-hf-repo parameter to download arbitrary models from HuggingFace by specifying repo id:"
|
||||
},
|
||||
{
|
||||
"self_ref": "#/texts/30",
|
||||
"parent": {
|
||||
"$ref": "#/groups/7"
|
||||
},
|
||||
"children": [],
|
||||
"content_layer": "body",
|
||||
"label": "code",
|
||||
"prov": [],
|
||||
"orig": "$ docling-tools models download-hf-repo ds4sd/SmolDocling-256M-preview Downloading ds4sd/SmolDocling-256M-preview model from HuggingFace...",
|
||||
"text": "$ docling-tools models download-hf-repo ds4sd/SmolDocling-256M-preview Downloading ds4sd/SmolDocling-256M-preview model from HuggingFace...",
|
||||
"captions": [],
|
||||
"references": [],
|
||||
"footnotes": [],
|
||||
"code_language": "unknown"
|
||||
}
|
||||
],
|
||||
"pictures": [],
|
||||
"tables": [],
|
||||
"key_value_items": [],
|
||||
"form_items": [],
|
||||
"pages": {}
|
||||
}
|
||||
24
tests/data/groundtruth/docling_v2/html_code_snippets.html.md
vendored
Normal file
24
tests/data/groundtruth/docling_v2/html_code_snippets.html.md
vendored
Normal file
@@ -0,0 +1,24 @@
|
||||
# Code snippets
|
||||
|
||||
The Pythagorean theorem can be written as an equation relating the lengths of the sides *a* , *b* and the hypotenuse *c* .
|
||||
|
||||
To use Docling, simply install `docling` from your package manager, e.g. pip: `pip install docling`
|
||||
|
||||
To convert individual documents with python, use `convert()` , for example:
|
||||
|
||||
```
|
||||
from docling.document_converter import DocumentConverter
|
||||
|
||||
source = "https://arxiv.org/pdf/2408.09869"
|
||||
converter = DocumentConverter()
|
||||
result = converter.convert(source)
|
||||
print(result.document.export_to_markdown())
|
||||
```
|
||||
|
||||
The program will output: `## Docling Technical Report[...]`
|
||||
|
||||
Prefetch the models:
|
||||
|
||||
- Use the `docling-tools models download` utility:
|
||||
- Alternatively, models can be programmatically downloaded using `docling.utils.model_downloader.download_models()` .
|
||||
- Also, you can use download-hf-repo parameter to download arbitrary models from HuggingFace by specifying repo id: `$ docling-tools models download-hf-repo ds4sd/SmolDocling-256M-preview Downloading ds4sd/SmolDocling-256M-preview model from HuggingFace...`
|
||||
41
tests/data/html/html_code_snippets.html
vendored
Normal file
41
tests/data/html/html_code_snippets.html
vendored
Normal file
@@ -0,0 +1,41 @@
|
||||
<!DOCTYPE html>
|
||||
<html>
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<title>Code snippets in HTML</title>
|
||||
</head>
|
||||
<body>
|
||||
|
||||
<h1>Code snippets</h1>
|
||||
|
||||
<p>The Pythagorean theorem can be written as an equation relating the lengths of the sides <var>a</var>, <var>b</var> and the hypotenuse <var>c</var>.</p>
|
||||
<p>To use Docling, simply install <code>docling</code>from your package manager, e.g. pip:
|
||||
<kbd>pip install docling</kbd>
|
||||
</p>
|
||||
<p>To convert individual documents with python, use <code>convert()</code>, for example:</p>
|
||||
<pre><code>
|
||||
from docling.document_converter import DocumentConverter
|
||||
|
||||
source = "https://arxiv.org/pdf/2408.09869"
|
||||
converter = DocumentConverter()
|
||||
result = converter.convert(source)
|
||||
print(result.document.export_to_markdown())
|
||||
</code></pre>
|
||||
<p>The program will output:
|
||||
<samp>## Docling Technical Report[...]</samp>
|
||||
</p>
|
||||
|
||||
<p>Prefetch the models:</p>
|
||||
<ul>
|
||||
<li>Use the <code>docling-tools models download</code> utility:</li>
|
||||
<li>Alternatively, models can be programmatically downloaded using <samp>docling.utils.model_downloader.download_models()</samp>.</li>
|
||||
<li>Also, you can use download-hf-repo parameter to download arbitrary models from HuggingFace by specifying repo id:
|
||||
<pre><code>
|
||||
$ docling-tools models download-hf-repo ds4sd/SmolDocling-256M-preview
|
||||
Downloading ds4sd/SmolDocling-256M-preview model from HuggingFace...
|
||||
</code></pre>
|
||||
<pre hidden><code>$ docling-tools</code></pre>
|
||||
</li>
|
||||
</ul>
|
||||
</body>
|
||||
</html>
|
||||
Reference in New Issue
Block a user