mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-26 20:14:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix minor ground truth errors

Browse Source 
Signed-off-by: Michael Honaker <Michael.Honaker@ibm.com>
This commit is contained in:
Michael Honaker 2025-06-26 11:36:00 -04:00
parent bca8dd34b9
commit 6406defb1f
2 changed files with 2 additions and 54 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
tests/data/groundtruth/docling_v2/inline_and_formatting.md.md vendored
View File

@ -14,16 +14,14 @@ Create your feature branch: `git checkout -b feature/AmazingFeature` .
6. **Whole list item has same formatting** 6. **Whole list item has same formatting**
7. List item has *mixed or partial* formatting 7. List item has *mixed or partial* formatting
*# Whole heading is italic* # *Whole heading is italic*
- **First** : Lorem ipsum. - **First** : Lorem ipsum.
- **Second** : Dolor `sit` amet. - **Second** : Dolor `sit` amet.
Some *`formatted_code`* Some *`formatted_code`*
## ## *Partially formatted* heading to\_escape `not_to_escape`
*Partially formatted* heading to\_escape `not_to_escape`
[$$E=mc^2$$](https://en.wikipedia.org/wiki/Albert_Einstein) [$$E=mc^2$$](https://en.wikipedia.org/wiki/Albert_Einstein)

50
tests/data/groundtruth/docling_v2/inline_and_formatting.md.yaml vendored
View File

@ -312,7 +312,6 @@ tables:
prov: [] prov: []
references: [] references: []
self_ref: '#/tables/0' self_ref: '#/tables/0'
word_items_ids: []
texts: texts:
- children: [] - children: []
content_layer: body content_layer: body
@ -323,7 +322,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/0' self_ref: '#/texts/0'
text: Contribution guideline example text: Contribution guideline example
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
label: text label: text
@ -333,7 +331,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/1' self_ref: '#/texts/1'
text: This is simple. text: This is simple.
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
label: text label: text
@ -343,7 +340,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/2' self_ref: '#/texts/2'
text: Foo text: Foo
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
formatting: formatting:
@ -359,7 +355,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/3' self_ref: '#/texts/3'
text: emphasis text: emphasis
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
formatting: formatting:
@ -375,7 +370,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/4' self_ref: '#/texts/4'
text: strong emphasis text: strong emphasis
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
formatting: formatting:
@ -391,7 +385,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/5' self_ref: '#/texts/5'
text: both text: both
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
label: text label: text
@ -401,7 +394,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/6' self_ref: '#/texts/6'
text: . text: .
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
label: text label: text
@ -411,7 +403,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/7' self_ref: '#/texts/7'
text: 'Create your feature branch:' text: 'Create your feature branch:'
word_items_ids: []
- captions: [] - captions: []
children: [] children: []
code_language: unknown code_language: unknown
@ -425,7 +416,6 @@ texts:
references: [] references: []
self_ref: '#/texts/8' self_ref: '#/texts/8'
text: git checkout -b feature/AmazingFeature text: git checkout -b feature/AmazingFeature
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
label: text label: text
@ -435,7 +425,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/9' self_ref: '#/texts/9'
text: . text: .
word_items_ids: []
- children: - children:
- $ref: '#/groups/3' - $ref: '#/groups/3'
content_layer: body content_layer: body
@ -448,7 +437,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/10' self_ref: '#/texts/10'
text: '' text: ''
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
label: text label: text
@ -458,7 +446,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/11' self_ref: '#/texts/11'
text: Pull the text: Pull the
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
formatting: formatting:
@ -475,7 +462,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/12' self_ref: '#/texts/12'
text: repository text: repository
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
label: text label: text
@ -485,7 +471,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/13' self_ref: '#/texts/13'
text: . text: .
word_items_ids: []
- children: - children:
- $ref: '#/groups/4' - $ref: '#/groups/4'
content_layer: body content_layer: body
@ -498,7 +483,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/14' self_ref: '#/texts/14'
text: '' text: ''
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
label: text label: text
@ -508,7 +492,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/15' self_ref: '#/texts/15'
text: Create your feature branch ( text: Create your feature branch (
word_items_ids: []
- captions: [] - captions: []
children: [] children: []
code_language: unknown code_language: unknown
@ -522,7 +505,6 @@ texts:
references: [] references: []
self_ref: '#/texts/16' self_ref: '#/texts/16'
text: git checkout -b feature/AmazingFeature text: git checkout -b feature/AmazingFeature
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
label: text label: text
@ -532,7 +514,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/17' self_ref: '#/texts/17'
text: ) text: )
word_items_ids: []
- children: - children:
- $ref: '#/groups/5' - $ref: '#/groups/5'
content_layer: body content_layer: body
@ -545,7 +526,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/18' self_ref: '#/texts/18'
text: '' text: ''
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
label: text label: text
@ -555,7 +535,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/19' self_ref: '#/texts/19'
text: Commit your changes ( text: Commit your changes (
word_items_ids: []
- captions: [] - captions: []
children: [] children: []
code_language: unknown code_language: unknown
@ -569,7 +548,6 @@ texts:
references: [] references: []
self_ref: '#/texts/20' self_ref: '#/texts/20'
text: git commit -m 'Add some AmazingFeature' text: git commit -m 'Add some AmazingFeature'
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
label: text label: text
@ -579,7 +557,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/21' self_ref: '#/texts/21'
text: ) text: )
word_items_ids: []
- children: - children:
- $ref: '#/groups/6' - $ref: '#/groups/6'
content_layer: body content_layer: body
@ -592,7 +569,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/22' self_ref: '#/texts/22'
text: '' text: ''
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
label: text label: text
@ -602,7 +578,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/23' self_ref: '#/texts/23'
text: Push to the branch ( text: Push to the branch (
word_items_ids: []
- captions: [] - captions: []
children: [] children: []
code_language: unknown code_language: unknown
@ -616,7 +591,6 @@ texts:
references: [] references: []
self_ref: '#/texts/24' self_ref: '#/texts/24'
text: git push origin feature/AmazingFeature text: git push origin feature/AmazingFeature
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
label: text label: text
@ -626,7 +600,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/25' self_ref: '#/texts/25'
text: ) text: )
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
enumerated: true enumerated: true
@ -638,7 +611,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/26' self_ref: '#/texts/26'
text: Open a Pull Request text: Open a Pull Request
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
enumerated: true enumerated: true
@ -656,7 +628,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/27' self_ref: '#/texts/27'
text: Whole list item has same formatting text: Whole list item has same formatting
word_items_ids: []
- children: - children:
- $ref: '#/groups/7' - $ref: '#/groups/7'
content_layer: body content_layer: body
@ -669,7 +640,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/28' self_ref: '#/texts/28'
text: '' text: ''
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
label: text label: text
@ -679,7 +649,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/29' self_ref: '#/texts/29'
text: List item has text: List item has
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
formatting: formatting:
@ -695,7 +664,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/30' self_ref: '#/texts/30'
text: mixed or partial text: mixed or partial
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
label: text label: text
@ -705,7 +673,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/31' self_ref: '#/texts/31'
text: formatting text: formatting
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
formatting: formatting:
@ -721,7 +688,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/32' self_ref: '#/texts/32'
text: Whole heading is italic text: Whole heading is italic
word_items_ids: []
- children: - children:
- $ref: '#/groups/9' - $ref: '#/groups/9'
content_layer: body content_layer: body
@ -734,7 +700,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/33' self_ref: '#/texts/33'
text: '' text: ''
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
formatting: formatting:
@ -750,7 +715,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/34' self_ref: '#/texts/34'
text: First text: First
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
label: text label: text
@ -760,7 +724,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/35' self_ref: '#/texts/35'
text: ': Lorem ipsum.' text: ': Lorem ipsum.'
word_items_ids: []
- children: - children:
- $ref: '#/groups/10' - $ref: '#/groups/10'
content_layer: body content_layer: body
@ -773,7 +736,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/36' self_ref: '#/texts/36'
text: '' text: ''
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
formatting: formatting:
@ -789,7 +751,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/37' self_ref: '#/texts/37'
text: Second text: Second
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
label: text label: text
@ -799,7 +760,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/38' self_ref: '#/texts/38'
text: ': Dolor' text: ': Dolor'
word_items_ids: []
- captions: [] - captions: []
children: [] children: []
code_language: unknown code_language: unknown
@ -813,7 +773,6 @@ texts:
references: [] references: []
self_ref: '#/texts/39' self_ref: '#/texts/39'
text: sit text: sit
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
label: text label: text
@ -823,7 +782,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/40' self_ref: '#/texts/40'
text: amet. text: amet.
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
label: text label: text
@ -833,7 +791,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/41' self_ref: '#/texts/41'
text: Some text: Some
word_items_ids: []
- captions: [] - captions: []
children: [] children: []
code_language: unknown code_language: unknown
@ -853,7 +810,6 @@ texts:
references: [] references: []
self_ref: '#/texts/42' self_ref: '#/texts/42'
text: formatted_code text: formatted_code
word_items_ids: []
- children: - children:
- $ref: '#/groups/12' - $ref: '#/groups/12'
content_layer: body content_layer: body
@ -865,7 +821,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/43' self_ref: '#/texts/43'
text: '' text: ''
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
formatting: formatting:
@ -881,7 +836,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/44' self_ref: '#/texts/44'
text: Partially formatted text: Partially formatted
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
label: text label: text
@ -891,7 +845,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/45' self_ref: '#/texts/45'
text: heading to_escape text: heading to_escape
word_items_ids: []
- captions: [] - captions: []
children: [] children: []
code_language: unknown code_language: unknown
@ -905,7 +858,6 @@ texts:
references: [] references: []
self_ref: '#/texts/46' self_ref: '#/texts/46'
text: not_to_escape text: not_to_escape
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
hyperlink: https://en.wikipedia.org/wiki/Albert_Einstein hyperlink: https://en.wikipedia.org/wiki/Albert_Einstein
@ -916,7 +868,6 @@ texts:
prov: [] prov: []
self_ref: '#/texts/47' self_ref: '#/texts/47'
text: $$E=mc^2$$ text: $$E=mc^2$$
word_items_ids: []
- children: [] - children: []
content_layer: body content_layer: body
label: section_header label: section_header
@ -927,5 +878,4 @@ texts:
prov: [] prov: []
self_ref: '#/texts/48' self_ref: '#/texts/48'
text: Table Heading text: Table Heading
word_items_ids: []
version: 1.4.0 version: 1.4.0