Ensure all models work only on valid pages (#158)

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
This commit is contained in:
Christoph Auer
2024-10-18 08:54:06 +02:00
committed by GitHub
parent 034a411057
commit a00c937e19
10 changed files with 413 additions and 376 deletions

View File

@@ -134,13 +134,13 @@ class StandardPdfPipeline(PaginatedPipeline):
all_body = []
for p in conv_res.pages:
assert p.assembled is not None
for el in p.assembled.body:
all_body.append(el)
for el in p.assembled.headers:
all_headers.append(el)
for el in p.assembled.elements:
all_elements.append(el)
if p.assembled is not None:
for el in p.assembled.body:
all_body.append(el)
for el in p.assembled.headers:
all_headers.append(el)
for el in p.assembled.elements:
all_elements.append(el)
conv_res.assembled = AssembledUnit(
elements=all_elements, headers=all_headers, body=all_body