mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-26 03:55:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

Detecting table orientation

Browse Source 
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
This commit is contained in:
Maksym Lysak 2025-04-03 11:10:57 +02:00
parent b3d111a3cd
commit 88a9756861
1 changed files with 20 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
docling/models/table_structure_model.py
View File

@ -219,6 +219,7 @@ class TableStructureModel(BasePageModel):
} }
table_clusters, table_bboxes = zip(*in_tables) table_clusters, table_bboxes = zip(*in_tables)
table_orientaton_angle_360 = 0
if len(table_bboxes): if len(table_bboxes):
for table_cluster, tbl_box in in_tables: for table_cluster, tbl_box in in_tables:
@ -229,6 +230,25 @@ class TableStructureModel(BasePageModel):
cell_unit=TextCellUnit.WORD, cell_unit=TextCellUnit.WORD,
bbox=table_cluster.bbox, bbox=table_cluster.bbox,
) )
# Table cluster orientation, derived from cells...
tcells_orientations = {}
for tcell in tcells:
if tcell.rect.angle_360 not in tcells_orientations:
tcells_orientations[tcell.rect.angle_360] = 1
else:
tcells_orientations[tcell.rect.angle_360] += 1
# Most of the cells in table bbox have this orientation:
if len(tcells_orientations.keys()) > 0:
table_orientaton_angle_360 = max(
tcells_orientations,
key=tcells_orientations.__getitem__,
)
print(
"TABLE ORIENTATION: {}".format(
table_orientaton_angle_360
)
)
if len(tcells) == 0: if len(tcells) == 0:
# In case word-level cells yield empty # In case word-level cells yield empty
tcells = table_cluster.cells tcells = table_cluster.cells