mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-09 13:18:24 +00:00
Code Issues 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

62
tests/data/groundtruth/docling_v2/word_sample.docx.json vendored
View File

@@ -1,6 +1,6 @@
{
"schema_name": "DoclingDocument",
"version": "1.3.0",
"version": "1.4.0",
"name": "word_sample",
"origin": {
"mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
@@ -106,7 +106,8 @@
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false
"strikethrough": false,
"script": "baseline"
}
},
{
@@ -149,7 +150,8 @@
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false
"strikethrough": false,
"script": "baseline"
}
},
{
@@ -167,7 +169,8 @@
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false
"strikethrough": false,
"script": "baseline"
}
},
{
@@ -217,7 +220,8 @@
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false
"strikethrough": false,
"script": "baseline"
}
},
{
@@ -235,7 +239,8 @@
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false
"strikethrough": false,
"script": "baseline"
},
"enumerated": false,
"marker": "-"
@@ -255,7 +260,8 @@
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false
"strikethrough": false,
"script": "baseline"
},
"enumerated": false,
"marker": "-"
@@ -275,7 +281,8 @@
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false
"strikethrough": false,
"script": "baseline"
},
"enumerated": false,
"marker": "-"
@@ -295,7 +302,8 @@
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false
"strikethrough": false,
"script": "baseline"
}
},
{
@@ -313,7 +321,8 @@
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false
"strikethrough": false,
"script": "baseline"
},
"enumerated": false,
"marker": "-"
@@ -333,7 +342,8 @@
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false
"strikethrough": false,
"script": "baseline"
},
"enumerated": false,
"marker": "-"
@@ -353,7 +363,8 @@
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false
"strikethrough": false,
"script": "baseline"
},
"enumerated": false,
"marker": "-"
@@ -373,7 +384,8 @@
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false
"strikethrough": false,
"script": "baseline"
}
},
{
@@ -426,7 +438,8 @@
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false
"strikethrough": false,
"script": "baseline"
}
},
{
@@ -444,7 +457,8 @@
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false
"strikethrough": false,
"script": "baseline"
}
},
{
@@ -462,7 +476,8 @@
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false
"strikethrough": false,
"script": "baseline"
}
},
{
@@ -492,7 +507,8 @@
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false
"strikethrough": false,
"script": "baseline"
}
},
{
@@ -510,7 +526,8 @@
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false
"strikethrough": false,
"script": "baseline"
},
"enumerated": false,
"marker": "-"
@@ -530,7 +547,8 @@
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false
"strikethrough": false,
"script": "baseline"
},
"enumerated": false,
"marker": "-"
@@ -550,7 +568,8 @@
"bold": false,
"italic": false,
"underline": false,
"strikethrough": false
"strikethrough": false,
"script": "baseline"
},
"enumerated": false,
"marker": "-"
@@ -897,7 +916,8 @@
}
]
]
}
},
"annotations": []
}
],
"key_value_items": [],