NeoAnd/Docling
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(markdown): fix single-formatted headings & list items (#1820)

Browse Source 
* fix(markdown): fix formatting & inline edge cases (show behavior before change)

Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>

* add change and updated test data

Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>

* update lock

Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>

* improve test case

Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>

---------

Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>
This commit is contained in:
Panos Vagenas
2025-06-25 13:05:06 +02:00
committed by GitHub
parent 41e8cae26b
commit 7c5614a37a
67 changed files with 2648 additions and 2351 deletions
Download Patch File Download Diff File Expand all files Collapse all files

248
tests/data/groundtruth/docling_v2/inline_and_formatting.md.yaml vendored
View File

@@ -5,8 +5,10 @@ body:
- $ref: '#/groups/0'
- $ref: '#/groups/1'
- $ref: '#/groups/2'
- $ref: '#/texts/27'
- $ref: '#/texts/32'
- $ref: '#/groups/8'
- $ref: '#/texts/35'
- $ref: '#/texts/39'
content_layer: body
label: unspecified
name: _root_
@@ -47,6 +49,8 @@ groups:
- $ref: '#/texts/18'
- $ref: '#/texts/22'
- $ref: '#/texts/26'
- $ref: '#/texts/27'
- $ref: '#/texts/28'
content_layer: body
label: ordered_list
name: list
@@ -94,47 +98,38 @@ groups:
$ref: '#/texts/22'
self_ref: '#/groups/6'
- children:
- $ref: '#/texts/28'
- $ref: '#/texts/29'
- $ref: '#/texts/30'
- $ref: '#/texts/31'
content_layer: body
label: inline
name: group
parent:
$ref: '#/texts/27'
$ref: '#/texts/28'
self_ref: '#/groups/7'
- children:
- $ref: '#/texts/30'
- $ref: '#/texts/33'
- $ref: '#/texts/34'
content_layer: body
label: list
name: list
label: inline
name: group
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'
- $ref: '#/texts/38'
content_layer: body
label: inline
name: group
parent:
$ref: '#/texts/33'
self_ref: '#/groups/10'
$ref: '#/texts/35'
self_ref: '#/groups/9'
key_value_items: []
name: inline_and_formatting
origin:
binary_hash: 9342273634728023910
binary_hash: 16409076955457599155
filename: inline_and_formatting.md
mimetype: text/markdown
pages: {}
@@ -174,6 +169,7 @@ texts:
formatting:
bold: false
italic: true
script: baseline
strikethrough: false
underline: false
label: text
@@ -188,6 +184,7 @@ texts:
formatting:
bold: true
italic: false
script: baseline
strikethrough: false
underline: false
label: text
@@ -202,6 +199,7 @@ texts:
formatting:
bold: true
italic: true
script: baseline
strikethrough: false
underline: false
label: text
@@ -277,6 +275,7 @@ texts:
formatting:
bold: true
italic: false
script: baseline
strikethrough: false
underline: false
hyperlink: https://github.com/docling-project/docling
@@ -436,130 +435,167 @@ texts:
prov: []
self_ref: '#/texts/26'
text: Open a Pull Request
- children: []
content_layer: body
enumerated: true
formatting:
bold: true
italic: false
script: baseline
strikethrough: false
underline: false
label: list_item
marker: '-'
orig: Whole list item has same formatting
parent:
$ref: '#/groups/2'
prov: []
self_ref: '#/texts/27'
text: Whole list item has same formatting
- children:
- $ref: '#/groups/7'
content_layer: body
enumerated: true
label: list_item
marker: '-'
orig: ''
parent:
$ref: '#/groups/2'
prov: []
self_ref: '#/texts/28'
text: ''
- children: []
content_layer: body
label: text
orig: List item has
parent:
$ref: '#/groups/7'
prov: []
self_ref: '#/texts/29'
text: List item has
- children: []
content_layer: body
formatting:
bold: false
italic: true
script: baseline
strikethrough: false
underline: false
label: text
orig: mixed or partial
parent:
$ref: '#/groups/7'
prov: []
self_ref: '#/texts/30'
text: mixed or partial
- children: []
content_layer: body
label: text
orig: formatting
parent:
$ref: '#/groups/7'
prov: []
self_ref: '#/texts/31'
text: formatting
- children: []
content_layer: body
formatting:
bold: false
italic: true
script: baseline
strikethrough: false
underline: false
label: title
orig: Whole heading is italic
parent:
$ref: '#/body'
prov: []
self_ref: '#/texts/32'
text: Whole heading is italic
- children: []
content_layer: body
label: text
orig: Some
parent:
$ref: '#/groups/8'
prov: []
self_ref: '#/texts/33'
text: Some
- captions: []
children: []
code_language: unknown
content_layer: body
footnotes: []
formatting:
bold: false
italic: true
script: baseline
strikethrough: false
underline: false
label: code
orig: formatted_code
parent:
$ref: '#/groups/8'
prov: []
references: []
self_ref: '#/texts/34'
text: formatted_code
- children:
- $ref: '#/groups/9'
content_layer: body
label: section_header
level: 1
orig: ''
parent:
$ref: '#/body'
prov: []
self_ref: '#/texts/27'
self_ref: '#/texts/35'
text: ''
- children: []
content_layer: body
formatting:
bold: false
italic: true
script: baseline
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
orig: Partially formatted
parent:
$ref: '#/groups/9'
prov: []
self_ref: '#/texts/31'
text: First
self_ref: '#/texts/36'
text: Partially formatted
- children: []
content_layer: body
label: text
orig: ': Lorem ipsum.'
orig: heading to_escape
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'
self_ref: '#/texts/37'
text: heading to_escape
- captions: []
children: []
code_language: unknown
content_layer: body
footnotes: []
label: code
orig: sit
orig: not_to_escape
parent:
$ref: '#/groups/10'
$ref: '#/groups/9'
prov: []
references: []
self_ref: '#/texts/36'
text: sit
self_ref: '#/texts/38'
text: not_to_escape
- children: []
content_layer: body
hyperlink: https://en.wikipedia.org/wiki/Albert_Einstein
label: text
orig: amet.
orig: $$E=mc^2$$
parent:
$ref: '#/groups/10'
$ref: '#/body'
prov: []
self_ref: '#/texts/37'
text: amet.
version: 1.3.0
self_ref: '#/texts/39'
text: $$E=mc^2$$
version: 1.4.0