mirror of
https://github.com/DS4SD/docling.git
synced 2025-12-08 20:58:11 +00:00
feat(markdown): add formatting & improve inline support (#1804)
feat(markdown): support formatting & hyperlinks Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>
This commit is contained in:
Panos Vagenas
GitHub
20
tests/data/groundtruth/docling_v2/inline_and_formatting.md.md
vendored
Normal file
20
tests/data/groundtruth/docling_v2/inline_and_formatting.md.md
vendored
Normal file
@@ -0,0 +1,20 @@
|
||||
# Contribution guideline example
|
||||
|
||||
This is simple.
|
||||
|
||||
Foo *emphasis* **strong emphasis** ***both*** .
|
||||
|
||||
Create your feature branch: `git checkout -b feature/AmazingFeature` .
|
||||
|
||||
1. Pull the [**repository**](https://github.com/docling-project/docling) .
|
||||
2. Create your feature branch ( `git checkout -b feature/AmazingFeature` )
|
||||
3. Commit your changes ( `git commit -m 'Add some AmazingFeature'` )
|
||||
4. Push to the branch ( `git push origin feature/AmazingFeature` )
|
||||
5. Open a Pull Request
|
||||
|
||||
##
|
||||
|
||||
*Second* section
|
||||
|
||||
- **First** : Lorem ipsum.
|
||||
- **Second** : Dolor `sit` amet.
|
||||
565
tests/data/groundtruth/docling_v2/inline_and_formatting.md.yaml
vendored
Normal file
565
tests/data/groundtruth/docling_v2/inline_and_formatting.md.yaml
vendored
Normal file
@@ -0,0 +1,565 @@
|
||||
body:
|
||||
children:
|
||||
- $ref: '#/texts/0'
|
||||
- $ref: '#/texts/1'
|
||||
- $ref: '#/groups/0'
|
||||
- $ref: '#/groups/1'
|
||||
- $ref: '#/groups/2'
|
||||
- $ref: '#/texts/27'
|
||||
- $ref: '#/groups/8'
|
||||
content_layer: body
|
||||
label: unspecified
|
||||
name: _root_
|
||||
self_ref: '#/body'
|
||||
form_items: []
|
||||
furniture:
|
||||
children: []
|
||||
content_layer: furniture
|
||||
label: unspecified
|
||||
name: _root_
|
||||
self_ref: '#/furniture'
|
||||
groups:
|
||||
- children:
|
||||
- $ref: '#/texts/2'
|
||||
- $ref: '#/texts/3'
|
||||
- $ref: '#/texts/4'
|
||||
- $ref: '#/texts/5'
|
||||
- $ref: '#/texts/6'
|
||||
content_layer: body
|
||||
label: inline
|
||||
name: group
|
||||
parent:
|
||||
$ref: '#/body'
|
||||
self_ref: '#/groups/0'
|
||||
- children:
|
||||
- $ref: '#/texts/7'
|
||||
- $ref: '#/texts/8'
|
||||
- $ref: '#/texts/9'
|
||||
content_layer: body
|
||||
label: inline
|
||||
name: group
|
||||
parent:
|
||||
$ref: '#/body'
|
||||
self_ref: '#/groups/1'
|
||||
- children:
|
||||
- $ref: '#/texts/10'
|
||||
- $ref: '#/texts/14'
|
||||
- $ref: '#/texts/18'
|
||||
- $ref: '#/texts/22'
|
||||
- $ref: '#/texts/26'
|
||||
content_layer: body
|
||||
label: ordered_list
|
||||
name: list
|
||||
parent:
|
||||
$ref: '#/body'
|
||||
self_ref: '#/groups/2'
|
||||
- children:
|
||||
- $ref: '#/texts/11'
|
||||
- $ref: '#/texts/12'
|
||||
- $ref: '#/texts/13'
|
||||
content_layer: body
|
||||
label: inline
|
||||
name: group
|
||||
parent:
|
||||
$ref: '#/texts/10'
|
||||
self_ref: '#/groups/3'
|
||||
- children:
|
||||
- $ref: '#/texts/15'
|
||||
- $ref: '#/texts/16'
|
||||
- $ref: '#/texts/17'
|
||||
content_layer: body
|
||||
label: inline
|
||||
name: group
|
||||
parent:
|
||||
$ref: '#/texts/14'
|
||||
self_ref: '#/groups/4'
|
||||
- children:
|
||||
- $ref: '#/texts/19'
|
||||
- $ref: '#/texts/20'
|
||||
- $ref: '#/texts/21'
|
||||
content_layer: body
|
||||
label: inline
|
||||
name: group
|
||||
parent:
|
||||
$ref: '#/texts/18'
|
||||
self_ref: '#/groups/5'
|
||||
- children:
|
||||
- $ref: '#/texts/23'
|
||||
- $ref: '#/texts/24'
|
||||
- $ref: '#/texts/25'
|
||||
content_layer: body
|
||||
label: inline
|
||||
name: group
|
||||
parent:
|
||||
$ref: '#/texts/22'
|
||||
self_ref: '#/groups/6'
|
||||
- children:
|
||||
- $ref: '#/texts/28'
|
||||
- $ref: '#/texts/29'
|
||||
content_layer: body
|
||||
label: inline
|
||||
name: group
|
||||
parent:
|
||||
$ref: '#/texts/27'
|
||||
self_ref: '#/groups/7'
|
||||
- children:
|
||||
- $ref: '#/texts/30'
|
||||
- $ref: '#/texts/33'
|
||||
content_layer: body
|
||||
label: list
|
||||
name: list
|
||||
parent:
|
||||
$ref: '#/body'
|
||||
self_ref: '#/groups/8'
|
||||
- children:
|
||||
- $ref: '#/texts/31'
|
||||
- $ref: '#/texts/32'
|
||||
content_layer: body
|
||||
label: inline
|
||||
name: group
|
||||
parent:
|
||||
$ref: '#/texts/30'
|
||||
self_ref: '#/groups/9'
|
||||
- children:
|
||||
- $ref: '#/texts/34'
|
||||
- $ref: '#/texts/35'
|
||||
- $ref: '#/texts/36'
|
||||
- $ref: '#/texts/37'
|
||||
content_layer: body
|
||||
label: inline
|
||||
name: group
|
||||
parent:
|
||||
$ref: '#/texts/33'
|
||||
self_ref: '#/groups/10'
|
||||
key_value_items: []
|
||||
name: inline_and_formatting
|
||||
origin:
|
||||
binary_hash: 9342273634728023910
|
||||
filename: inline_and_formatting.md
|
||||
mimetype: text/markdown
|
||||
pages: {}
|
||||
pictures: []
|
||||
schema_name: DoclingDocument
|
||||
tables: []
|
||||
texts:
|
||||
- children: []
|
||||
content_layer: body
|
||||
label: title
|
||||
orig: Contribution guideline example
|
||||
parent:
|
||||
$ref: '#/body'
|
||||
prov: []
|
||||
self_ref: '#/texts/0'
|
||||
text: Contribution guideline example
|
||||
- children: []
|
||||
content_layer: body
|
||||
label: text
|
||||
orig: This is simple.
|
||||
parent:
|
||||
$ref: '#/body'
|
||||
prov: []
|
||||
self_ref: '#/texts/1'
|
||||
text: This is simple.
|
||||
- children: []
|
||||
content_layer: body
|
||||
label: text
|
||||
orig: Foo
|
||||
parent:
|
||||
$ref: '#/groups/0'
|
||||
prov: []
|
||||
self_ref: '#/texts/2'
|
||||
text: Foo
|
||||
- children: []
|
||||
content_layer: body
|
||||
formatting:
|
||||
bold: false
|
||||
italic: true
|
||||
strikethrough: false
|
||||
underline: false
|
||||
label: text
|
||||
orig: emphasis
|
||||
parent:
|
||||
$ref: '#/groups/0'
|
||||
prov: []
|
||||
self_ref: '#/texts/3'
|
||||
text: emphasis
|
||||
- children: []
|
||||
content_layer: body
|
||||
formatting:
|
||||
bold: true
|
||||
italic: false
|
||||
strikethrough: false
|
||||
underline: false
|
||||
label: text
|
||||
orig: strong emphasis
|
||||
parent:
|
||||
$ref: '#/groups/0'
|
||||
prov: []
|
||||
self_ref: '#/texts/4'
|
||||
text: strong emphasis
|
||||
- children: []
|
||||
content_layer: body
|
||||
formatting:
|
||||
bold: true
|
||||
italic: true
|
||||
strikethrough: false
|
||||
underline: false
|
||||
label: text
|
||||
orig: both
|
||||
parent:
|
||||
$ref: '#/groups/0'
|
||||
prov: []
|
||||
self_ref: '#/texts/5'
|
||||
text: both
|
||||
- children: []
|
||||
content_layer: body
|
||||
label: text
|
||||
orig: .
|
||||
parent:
|
||||
$ref: '#/groups/0'
|
||||
prov: []
|
||||
self_ref: '#/texts/6'
|
||||
text: .
|
||||
- children: []
|
||||
content_layer: body
|
||||
label: text
|
||||
orig: 'Create your feature branch:'
|
||||
parent:
|
||||
$ref: '#/groups/1'
|
||||
prov: []
|
||||
self_ref: '#/texts/7'
|
||||
text: 'Create your feature branch:'
|
||||
- captions: []
|
||||
children: []
|
||||
code_language: unknown
|
||||
content_layer: body
|
||||
footnotes: []
|
||||
label: code
|
||||
orig: git checkout -b feature/AmazingFeature
|
||||
parent:
|
||||
$ref: '#/groups/1'
|
||||
prov: []
|
||||
references: []
|
||||
self_ref: '#/texts/8'
|
||||
text: git checkout -b feature/AmazingFeature
|
||||
- children: []
|
||||
content_layer: body
|
||||
label: text
|
||||
orig: .
|
||||
parent:
|
||||
$ref: '#/groups/1'
|
||||
prov: []
|
||||
self_ref: '#/texts/9'
|
||||
text: .
|
||||
- children:
|
||||
- $ref: '#/groups/3'
|
||||
content_layer: body
|
||||
enumerated: true
|
||||
label: list_item
|
||||
marker: '-'
|
||||
orig: ''
|
||||
parent:
|
||||
$ref: '#/groups/2'
|
||||
prov: []
|
||||
self_ref: '#/texts/10'
|
||||
text: ''
|
||||
- children: []
|
||||
content_layer: body
|
||||
label: text
|
||||
orig: Pull the
|
||||
parent:
|
||||
$ref: '#/groups/3'
|
||||
prov: []
|
||||
self_ref: '#/texts/11'
|
||||
text: Pull the
|
||||
- children: []
|
||||
content_layer: body
|
||||
formatting:
|
||||
bold: true
|
||||
italic: false
|
||||
strikethrough: false
|
||||
underline: false
|
||||
hyperlink: https://github.com/docling-project/docling
|
||||
label: text
|
||||
orig: repository
|
||||
parent:
|
||||
$ref: '#/groups/3'
|
||||
prov: []
|
||||
self_ref: '#/texts/12'
|
||||
text: repository
|
||||
- children: []
|
||||
content_layer: body
|
||||
label: text
|
||||
orig: .
|
||||
parent:
|
||||
$ref: '#/groups/3'
|
||||
prov: []
|
||||
self_ref: '#/texts/13'
|
||||
text: .
|
||||
- children:
|
||||
- $ref: '#/groups/4'
|
||||
content_layer: body
|
||||
enumerated: true
|
||||
label: list_item
|
||||
marker: '-'
|
||||
orig: ''
|
||||
parent:
|
||||
$ref: '#/groups/2'
|
||||
prov: []
|
||||
self_ref: '#/texts/14'
|
||||
text: ''
|
||||
- children: []
|
||||
content_layer: body
|
||||
label: text
|
||||
orig: Create your feature branch (
|
||||
parent:
|
||||
$ref: '#/groups/4'
|
||||
prov: []
|
||||
self_ref: '#/texts/15'
|
||||
text: Create your feature branch (
|
||||
- captions: []
|
||||
children: []
|
||||
code_language: unknown
|
||||
content_layer: body
|
||||
footnotes: []
|
||||
label: code
|
||||
orig: git checkout -b feature/AmazingFeature
|
||||
parent:
|
||||
$ref: '#/groups/4'
|
||||
prov: []
|
||||
references: []
|
||||
self_ref: '#/texts/16'
|
||||
text: git checkout -b feature/AmazingFeature
|
||||
- children: []
|
||||
content_layer: body
|
||||
label: text
|
||||
orig: )
|
||||
parent:
|
||||
$ref: '#/groups/4'
|
||||
prov: []
|
||||
self_ref: '#/texts/17'
|
||||
text: )
|
||||
- children:
|
||||
- $ref: '#/groups/5'
|
||||
content_layer: body
|
||||
enumerated: true
|
||||
label: list_item
|
||||
marker: '-'
|
||||
orig: ''
|
||||
parent:
|
||||
$ref: '#/groups/2'
|
||||
prov: []
|
||||
self_ref: '#/texts/18'
|
||||
text: ''
|
||||
- children: []
|
||||
content_layer: body
|
||||
label: text
|
||||
orig: Commit your changes (
|
||||
parent:
|
||||
$ref: '#/groups/5'
|
||||
prov: []
|
||||
self_ref: '#/texts/19'
|
||||
text: Commit your changes (
|
||||
- captions: []
|
||||
children: []
|
||||
code_language: unknown
|
||||
content_layer: body
|
||||
footnotes: []
|
||||
label: code
|
||||
orig: git commit -m 'Add some AmazingFeature'
|
||||
parent:
|
||||
$ref: '#/groups/5'
|
||||
prov: []
|
||||
references: []
|
||||
self_ref: '#/texts/20'
|
||||
text: git commit -m 'Add some AmazingFeature'
|
||||
- children: []
|
||||
content_layer: body
|
||||
label: text
|
||||
orig: )
|
||||
parent:
|
||||
$ref: '#/groups/5'
|
||||
prov: []
|
||||
self_ref: '#/texts/21'
|
||||
text: )
|
||||
- children:
|
||||
- $ref: '#/groups/6'
|
||||
content_layer: body
|
||||
enumerated: true
|
||||
label: list_item
|
||||
marker: '-'
|
||||
orig: ''
|
||||
parent:
|
||||
$ref: '#/groups/2'
|
||||
prov: []
|
||||
self_ref: '#/texts/22'
|
||||
text: ''
|
||||
- children: []
|
||||
content_layer: body
|
||||
label: text
|
||||
orig: Push to the branch (
|
||||
parent:
|
||||
$ref: '#/groups/6'
|
||||
prov: []
|
||||
self_ref: '#/texts/23'
|
||||
text: Push to the branch (
|
||||
- captions: []
|
||||
children: []
|
||||
code_language: unknown
|
||||
content_layer: body
|
||||
footnotes: []
|
||||
label: code
|
||||
orig: git push origin feature/AmazingFeature
|
||||
parent:
|
||||
$ref: '#/groups/6'
|
||||
prov: []
|
||||
references: []
|
||||
self_ref: '#/texts/24'
|
||||
text: git push origin feature/AmazingFeature
|
||||
- children: []
|
||||
content_layer: body
|
||||
label: text
|
||||
orig: )
|
||||
parent:
|
||||
$ref: '#/groups/6'
|
||||
prov: []
|
||||
self_ref: '#/texts/25'
|
||||
text: )
|
||||
- children: []
|
||||
content_layer: body
|
||||
enumerated: true
|
||||
label: list_item
|
||||
marker: '-'
|
||||
orig: Open a Pull Request
|
||||
parent:
|
||||
$ref: '#/groups/2'
|
||||
prov: []
|
||||
self_ref: '#/texts/26'
|
||||
text: Open a Pull Request
|
||||
- children:
|
||||
- $ref: '#/groups/7'
|
||||
content_layer: body
|
||||
label: section_header
|
||||
level: 1
|
||||
orig: ''
|
||||
parent:
|
||||
$ref: '#/body'
|
||||
prov: []
|
||||
self_ref: '#/texts/27'
|
||||
text: ''
|
||||
- children: []
|
||||
content_layer: body
|
||||
formatting:
|
||||
bold: false
|
||||
italic: true
|
||||
strikethrough: false
|
||||
underline: false
|
||||
label: text
|
||||
orig: Second
|
||||
parent:
|
||||
$ref: '#/groups/7'
|
||||
prov: []
|
||||
self_ref: '#/texts/28'
|
||||
text: Second
|
||||
- children: []
|
||||
content_layer: body
|
||||
label: text
|
||||
orig: section
|
||||
parent:
|
||||
$ref: '#/groups/7'
|
||||
prov: []
|
||||
self_ref: '#/texts/29'
|
||||
text: section
|
||||
- children:
|
||||
- $ref: '#/groups/9'
|
||||
content_layer: body
|
||||
enumerated: false
|
||||
label: list_item
|
||||
marker: '-'
|
||||
orig: ''
|
||||
parent:
|
||||
$ref: '#/groups/8'
|
||||
prov: []
|
||||
self_ref: '#/texts/30'
|
||||
text: ''
|
||||
- children: []
|
||||
content_layer: body
|
||||
formatting:
|
||||
bold: true
|
||||
italic: false
|
||||
strikethrough: false
|
||||
underline: false
|
||||
label: text
|
||||
orig: First
|
||||
parent:
|
||||
$ref: '#/groups/9'
|
||||
prov: []
|
||||
self_ref: '#/texts/31'
|
||||
text: First
|
||||
- children: []
|
||||
content_layer: body
|
||||
label: text
|
||||
orig: ': Lorem ipsum.'
|
||||
parent:
|
||||
$ref: '#/groups/9'
|
||||
prov: []
|
||||
self_ref: '#/texts/32'
|
||||
text: ': Lorem ipsum.'
|
||||
- children:
|
||||
- $ref: '#/groups/10'
|
||||
content_layer: body
|
||||
enumerated: false
|
||||
label: list_item
|
||||
marker: '-'
|
||||
orig: ''
|
||||
parent:
|
||||
$ref: '#/groups/8'
|
||||
prov: []
|
||||
self_ref: '#/texts/33'
|
||||
text: ''
|
||||
- children: []
|
||||
content_layer: body
|
||||
formatting:
|
||||
bold: true
|
||||
italic: false
|
||||
strikethrough: false
|
||||
underline: false
|
||||
label: text
|
||||
orig: Second
|
||||
parent:
|
||||
$ref: '#/groups/10'
|
||||
prov: []
|
||||
self_ref: '#/texts/34'
|
||||
text: Second
|
||||
- children: []
|
||||
content_layer: body
|
||||
label: text
|
||||
orig: ': Dolor'
|
||||
parent:
|
||||
$ref: '#/groups/10'
|
||||
prov: []
|
||||
self_ref: '#/texts/35'
|
||||
text: ': Dolor'
|
||||
- captions: []
|
||||
children: []
|
||||
code_language: unknown
|
||||
content_layer: body
|
||||
footnotes: []
|
||||
label: code
|
||||
orig: sit
|
||||
parent:
|
||||
$ref: '#/groups/10'
|
||||
prov: []
|
||||
references: []
|
||||
self_ref: '#/texts/36'
|
||||
text: sit
|
||||
- children: []
|
||||
content_layer: body
|
||||
label: text
|
||||
orig: amet.
|
||||
parent:
|
||||
$ref: '#/groups/10'
|
||||
prov: []
|
||||
self_ref: '#/texts/37'
|
||||
text: amet.
|
||||
version: 1.3.0
|
||||
Reference in New Issue
Block a user