NeoAnd/Docling
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: allow computing page images on-demand with scale and cache them (#36)

Browse Source 
* feat: allow computing page images on-demand and cache them

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* feat: expose scale for export of page images and document elements

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* fix comment

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
This commit is contained in:
Michele Dolfi
2024-08-20 13:27:19 +02:00
committed by GitHub
parent c253dd743a
commit 78347bf679
9 changed files with 104 additions and 77 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
docling/models/table_structure_model.py
View File

@@ -34,7 +34,9 @@ class TableStructureModel:
self.scale = 2.0 # Scale up table input images to 144 dpi
def draw_table_and_cells(self, page: Page, tbl_list: List[TableElement]):
image = page._backend.get_page_image()
image = (
page._backend.get_page_image()
) # make new image to avoid drawing on the saved ones
draw = ImageDraw.Draw(image)
for table_element in tbl_list:
@@ -94,13 +96,7 @@ class TableStructureModel:
"width": page.size.width * self.scale,
"height": page.size.height * self.scale,
}
# add image to page input.
if self.scale == 1.0:
page_input["image"] = numpy.asarray(page.image)
else: # render new page image on the fly at desired scale
page_input["image"] = numpy.asarray(
page._backend.get_page_image(scale=self.scale)
)
page_input["image"] = numpy.asarray(page.get_image(scale=self.scale))
table_clusters, table_bboxes = zip(*in_tables)