fix: Proper handling of orphan IDs in layout postprocessing (#1118)

* Fix the handling of orphan IDs in layout postprocessing Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Update test cases Signed-off-by: Christoph Auer <cau@zurich.ibm.com> --------- Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
2025-12-09 05:08:14 +00:00 · 2025-03-05 14:30:59 +01:00
parent 357d41cc47
commit c56ab3a66b
33 changed files with 36 additions and 33 deletions
--- a/tests/data/groundtruth/docling_v1/2203.01017v2.pages.json
+++ b/tests/data/groundtruth/docling_v1/2203.01017v2.pages.json
--- a/tests/data/groundtruth/docling_v1/2206.01062.pages.json
+++ b/tests/data/groundtruth/docling_v1/2206.01062.pages.json
--- a/tests/data/groundtruth/docling_v1/2305.03393v1-pg9.json
+++ b/tests/data/groundtruth/docling_v1/2305.03393v1-pg9.json
--- a/tests/data/groundtruth/docling_v1/2305.03393v1-pg9.pages.json
+++ b/tests/data/groundtruth/docling_v1/2305.03393v1-pg9.pages.json
--- a/tests/data/groundtruth/docling_v1/2305.03393v1.pages.json
+++ b/tests/data/groundtruth/docling_v1/2305.03393v1.pages.json
--- a/tests/data/groundtruth/docling_v1/amt_handbook_sample.pages.json
+++ b/tests/data/groundtruth/docling_v1/amt_handbook_sample.pages.json
--- a/tests/data/groundtruth/docling_v1/code_and_formula.pages.json
+++ b/tests/data/groundtruth/docling_v1/code_and_formula.pages.json
--- a/tests/data/groundtruth/docling_v1/picture_classification.pages.json
+++ b/tests/data/groundtruth/docling_v1/picture_classification.pages.json
--- a/tests/data/groundtruth/docling_v1/redp5110_sampled.doctags.txt
+++ b/tests/data/groundtruth/docling_v1/redp5110_sampled.doctags.txt
@@ -7,7 +7,9 @@
 <figure>
 <location><page_1><loc_5><loc_11><loc_96><loc_63></location>
 </figure>
-<paragraph><location><page_1><loc_47><loc_94><loc_68><loc_96></location>Front cover</paragraph>
+<figure>
+<location><page_1><loc_52><loc_2><loc_95><loc_10></location>
+</figure>
 <subtitle-level-1><location><page_2><loc_11><loc_88><loc_28><loc_91></location>Contents</subtitle-level-1>
 <paragraph><location><page_3><loc_11><loc_89><loc_39><loc_91></location>DB2 for i Center of Excellence</paragraph>
 <paragraph><location><page_3><loc_15><loc_80><loc_38><loc_83></location>Solution Brief IBM Systems Lab Services and Training</paragraph>
--- a/tests/data/groundtruth/docling_v1/redp5110_sampled.json
+++ b/tests/data/groundtruth/docling_v1/redp5110_sampled.json
--- a/tests/data/groundtruth/docling_v1/redp5110_sampled.md
+++ b/tests/data/groundtruth/docling_v1/redp5110_sampled.md
@@ -6,7 +6,7 @@ Front cover

 <!-- image -->

-Front cover
+<!-- image -->

 ## Contents

--- a/tests/data/groundtruth/docling_v1/redp5110_sampled.pages.json
+++ b/tests/data/groundtruth/docling_v1/redp5110_sampled.pages.json
--- a/tests/data/groundtruth/docling_v1/right_to_left_01.pages.json
+++ b/tests/data/groundtruth/docling_v1/right_to_left_01.pages.json
--- a/tests/data/groundtruth/docling_v1/right_to_left_02.pages.json
+++ b/tests/data/groundtruth/docling_v1/right_to_left_02.pages.json
--- a/tests/data/groundtruth/docling_v1/right_to_left_03.pages.json
+++ b/tests/data/groundtruth/docling_v1/right_to_left_03.pages.json