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: set page number using 1-based indexing (#22)

Browse Source 
Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
This commit is contained in:
Panos Vagenas
2024-07-31 14:28:44 +02:00
committed by GitHub
parent e102827753
commit d2d9543415
4 changed files with 11 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
docling/datamodel/document.py
View File

@@ -125,7 +125,7 @@ class ConvertedDocument(BaseModel):
desc = DsDocumentDescription(logs=[])
page_hashes = [
PageReference(hash=p.page_hash, page=p.page_no, model="default")
PageReference(hash=p.page_hash, page=p.page_no + 1, model="default")
for p in self.pages
]
@@ -159,7 +159,7 @@ class ConvertedDocument(BaseModel):
prov=[
Prov(
bbox=target_bbox,
page=element.page_no,
page=element.page_no + 1,
span=[0, len(element.text)],
)
],
@@ -242,7 +242,7 @@ class ConvertedDocument(BaseModel):
prov=[
Prov(
bbox=target_bbox,
page=element.page_no,
page=element.page_no + 1,
span=[0, 0],
)
],
@@ -264,7 +264,7 @@ class ConvertedDocument(BaseModel):
prov=[
Prov(
bbox=target_bbox,
page=element.page_no,
page=element.page_no + 1,
span=[0, 0],
)
],
@@ -274,7 +274,7 @@ class ConvertedDocument(BaseModel):
)
page_dimensions = [
PageDimensions(page=p.page_no, height=p.size.height, width=p.size.width)
PageDimensions(page=p.page_no + 1, height=p.size.height, width=p.size.width)
for p in self.pages
]