mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 12:48:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(docx): identifying numbered headers (#1231)

Browse Source 
* Modifications to identify numbered headers

Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>

* Add style check

Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>

---------

Signed-off-by: Rafael Teixeira de Lima <Rafael.td.lima@gmail.com>
This commit is contained in:
Rafael Teixeira de Lima
2025-03-25 11:41:02 +01:00
committed by GitHub
parent 0974ba4e1c
commit f739d0e4c5
4 changed files with 79 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
tests/data/groundtruth/docling_v2/unit_test_headers_numbered.docx.itxt
View File

@@ -1,7 +1,7 @@
item-0 at level 0: unspecified: group _root_
item-1 at level 1: title: Test Document
item-2 at level 2: paragraph:
item-3 at level 2: section_header: Section 1
item-3 at level 2: section_header: 1 Section 1
item-4 at level 1: paragraph:
item-5 at level 1: paragraph: Paragraph 1.1
item-6 at level 1: paragraph:
@@ -9,26 +9,26 @@ item-0 at level 0: unspecified: group _root_
item-8 at level 1: paragraph:
item-9 at level 1: section: group header-0
item-10 at level 2: section: group header-1
item-11 at level 3: section_header: Section 1.1
item-11 at level 3: section_header: 1.1 Section 1.1
item-12 at level 4: paragraph:
item-13 at level 4: paragraph: Paragraph 1.1.1
item-14 at level 4: paragraph:
item-15 at level 4: paragraph: Paragraph 1.1.2
item-16 at level 4: paragraph:
item-17 at level 3: section_header: Section 1.2
item-17 at level 3: section_header: 1.2 Section 1.2
item-18 at level 4: paragraph:
item-19 at level 4: paragraph: Paragraph 1.1.1
item-20 at level 4: paragraph:
item-21 at level 4: paragraph: Paragraph 1.1.2
item-22 at level 4: paragraph:
item-23 at level 4: section_header: Section 1.2.3
item-23 at level 4: section_header: 1.2.1 Section 1.2.3
item-24 at level 5: paragraph:
item-25 at level 5: paragraph: Paragraph 1.2.3.1
item-26 at level 5: paragraph:
item-27 at level 5: paragraph: Paragraph 1.2.3.1
item-28 at level 5: paragraph:
item-29 at level 5: paragraph:
item-30 at level 2: section_header: Section 2
item-30 at level 2: section_header: 2 Section 2
item-31 at level 1: paragraph:
item-32 at level 1: paragraph: Paragraph 2.1
item-33 at level 1: paragraph:
@@ -37,13 +37,13 @@ item-0 at level 0: unspecified: group _root_
item-36 at level 1: section: group header-0
item-37 at level 2: section: group header-1
item-38 at level 3: section: group header-2
item-39 at level 4: section_header: Section 2.1.1
item-39 at level 4: section_header: 2.1.1 Section 2.1.1
item-40 at level 5: paragraph:
item-41 at level 5: paragraph: Paragraph 2.1.1.1
item-42 at level 5: paragraph:
item-43 at level 5: paragraph: Paragraph 2.1.1.1
item-44 at level 5: paragraph:
item-45 at level 3: section_header: Section 2.1
item-45 at level 3: section_header: 2.2 Section 2.1
item-46 at level 4: paragraph:
item-47 at level 4: paragraph: Paragraph 2.1.1
item-48 at level 4: paragraph:

28
tests/data/groundtruth/docling_v2/unit_test_headers_numbered.docx.json
View File

@@ -183,8 +183,8 @@
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Section 1",
"text": "Section 1",
"orig": "1 Section 1",
"text": "1 Section 1",
"level": 1
},
{
@@ -272,8 +272,8 @@
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Section 1.1",
"text": "Section 1.1",
"orig": "1.1 Section 1.1",
"text": "1.1 Section 1.1",
"level": 2
},
{
@@ -364,8 +364,8 @@
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Section 1.2",
"text": "Section 1.2",
"orig": "1.2 Section 1.2",
"text": "1.2 Section 1.2",
"level": 2
},
{
@@ -456,8 +456,8 @@
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Section 1.2.3",
"text": "Section 1.2.3",
"orig": "1.2.1 Section 1.2.3",
"text": "1.2.1 Section 1.2.3",
"level": 3
},
{
@@ -541,8 +541,8 @@
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Section 2",
"text": "Section 2",
"orig": "2 Section 2",
"text": "2 Section 2",
"level": 1
},
{
@@ -630,8 +630,8 @@
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Section 2.1.1",
"text": "Section 2.1.1",
"orig": "2.1.1 Section 2.1.1",
"text": "2.1.1 Section 2.1.1",
"level": 3
},
{
@@ -722,8 +722,8 @@
"content_layer": "body",
"label": "section_header",
"prov": [],
"orig": "Section 2.1",
"text": "Section 2.1",
"orig": "2.2 Section 2.1",
"text": "2.2 Section 2.1",
"level": 2
},
{

14
tests/data/groundtruth/docling_v2/unit_test_headers_numbered.docx.md
View File

@@ -1,42 +1,42 @@
# Test Document
## Section 1
## 1 Section 1
Paragraph 1.1
Paragraph 1.2
### Section 1.1
### 1.1 Section 1.1
Paragraph 1.1.1
Paragraph 1.1.2
### Section 1.2
### 1.2 Section 1.2
Paragraph 1.1.1
Paragraph 1.1.2
#### Section 1.2.3
#### 1.2.1 Section 1.2.3
Paragraph 1.2.3.1
Paragraph 1.2.3.1
## Section 2
## 2 Section 2
Paragraph 2.1
Paragraph 2.2
#### Section 2.1.1
#### 2.1.1 Section 2.1.1
Paragraph 2.1.1.1
Paragraph 2.1.1.1
### Section 2.1
### 2.2 Section 2.1
Paragraph 2.1.1