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 typing

Browse Source 
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer 2025-06-13 16:16:12 +02:00
parent 5ec6de3ae4
commit bf1599b2c3
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
docling/utils/layout_postprocessor.py
View File

@ -8,7 +8,7 @@ from docling_core.types.doc import DocItemLabel, Size
from docling_core.types.doc.page import TextCell from docling_core.types.doc.page import TextCell
from rtree import index from rtree import index
from docling.datamodel.base_models import BoundingBox, Cluster from docling.datamodel.base_models import BoundingBox, Cluster, Page
_log = logging.getLogger(__name__) _log = logging.getLogger(__name__)
@ -194,7 +194,7 @@ class LayoutPostprocessor:
DocItemLabel.TITLE: DocItemLabel.SECTION_HEADER, DocItemLabel.TITLE: DocItemLabel.SECTION_HEADER,
} }
def __init__(self, page, clusters: List[Cluster]): def __init__(self, page: Page, clusters: List[Cluster]) -> None:
"""Initialize processor with page and clusters.""" """Initialize processor with page and clusters."""
self.cells = page.cells self.cells = page.cells
self.page = page self.page = page
@ -305,6 +305,7 @@ class LayoutPostprocessor:
special_clusters = self._handle_cross_type_overlaps(special_clusters) special_clusters = self._handle_cross_type_overlaps(special_clusters)
# Calculate page area from known page size # Calculate page area from known page size
assert self.page_size is not None
page_area = self.page_size.width * self.page_size.height page_area = self.page_size.width * self.page_size.height
if page_area > 0: if page_area > 0:
# Filter out full-page pictures # Filter out full-page pictures