mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-27 04:24:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

chore: Restore the orphan clusters

Browse Source 
Signed-off-by: Nikos Livathinos <nli@zurich.ibm.com>
This commit is contained in:
Nikos Livathinos 2025-02-14 11:13:54 +01:00
parent e824996406
commit b5b1ddca3b
1 changed files with 19 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

41
docling/utils/layout_postprocessor.py
View File

@ -264,29 +264,26 @@ class LayoutPostprocessor:
# Remove clusters with no cells
clusters = [cluster for cluster in clusters if cluster.cells]
###########################################################################################
# Debug
# # Handle orphaned cells
# unassigned = self._find_unassigned_cells(clusters)
# if unassigned:
# next_id = max((c.id for c in clusters), default=0) + 1
# orphan_clusters = []
# for i, cell in enumerate(unassigned):
# conf = 1.0
# if isinstance(cell, OcrCell):
# conf = cell.confidence
# Handle orphaned cells
unassigned = self._find_unassigned_cells(clusters)
if unassigned:
next_id = max((c.id for c in clusters), default=0) + 1
orphan_clusters = []
for i, cell in enumerate(unassigned):
conf = 1.0
if isinstance(cell, OcrCell):
conf = cell.confidence
# orphan_clusters.append(
# Cluster(
# id=next_id + i,
# label=DocItemLabel.TEXT,
# bbox=cell.bbox,
# confidence=conf,
# cells=[cell],
# )
# )
# clusters.extend(orphan_clusters)
###########################################################################################
orphan_clusters.append(
Cluster(
id=next_id + i,
label=DocItemLabel.TEXT,
bbox=cell.bbox,
confidence=conf,
cells=[cell],
)
)
clusters.extend(orphan_clusters)
# Iterative refinement
prev_count = len(clusters) + 1