fix(pypdfium): resolve overlapping text when merging bounding boxes (#1549)

get merged_text from boundingbox instead of merging it to prevent overlaps

Signed-off-by: Pedro Ribeiro <pedro_ribeiro_93@hotmail.com>
This commit is contained in:
Pedro Ribeiro
2025-05-19 14:26:00 +01:00
committed by GitHub
parent 12a0e64892
commit 98b5eeb844
52 changed files with 52225 additions and 4690 deletions

View File

@@ -1390,7 +1390,7 @@
"id": 2,
"label": "picture",
"bbox": {
"l": 134.9200439453125,
"l": 134.9199981689453,
"t": 304.890625,
"r": 475.6635437011719,
"b": 510.21826171875,
@@ -2174,7 +2174,7 @@
"id": 2,
"label": "picture",
"bbox": {
"l": 134.9200439453125,
"l": 134.9199981689453,
"t": 304.890625,
"r": 475.6635437011719,
"b": 510.21826171875,
@@ -2909,7 +2909,7 @@
"id": 2,
"label": "picture",
"bbox": {
"l": 134.9200439453125,
"l": 134.9199981689453,
"t": 304.890625,
"r": 475.6635437011719,
"b": 510.21826171875,
@@ -3623,7 +3623,7 @@
"b": 268.20489999999995,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9870928525924683,
"confidence": 0.987092912197113,
"cells": [
{
"index": 0,
@@ -3938,7 +3938,7 @@
"b": 532.05774,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9494236707687378,
"confidence": 0.9494234323501587,
"cells": [
{
"index": 12,
@@ -4302,7 +4302,7 @@
"id": 2,
"label": "picture",
"bbox": {
"l": 218.8155517578125,
"l": 218.81556701660156,
"t": 278.0153503417969,
"r": 391.96246337890625,
"b": 508.89410400390625,
@@ -4337,7 +4337,7 @@
"b": 268.20489999999995,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9870928525924683,
"confidence": 0.987092912197113,
"cells": [
{
"index": 0,
@@ -4658,7 +4658,7 @@
"b": 532.05774,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9494236707687378,
"confidence": 0.9494234323501587,
"cells": [
{
"index": 12,
@@ -5040,7 +5040,7 @@
"id": 2,
"label": "picture",
"bbox": {
"l": 218.8155517578125,
"l": 218.81556701660156,
"t": 278.0153503417969,
"r": 391.96246337890625,
"b": 508.89410400390625,
@@ -5072,7 +5072,7 @@
"b": 268.20489999999995,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9870928525924683,
"confidence": 0.987092912197113,
"cells": [
{
"index": 0,
@@ -5393,7 +5393,7 @@
"b": 532.05774,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9494236707687378,
"confidence": 0.9494234323501587,
"cells": [
{
"index": 12,
@@ -5729,7 +5729,7 @@
"id": 2,
"label": "picture",
"bbox": {
"l": 218.8155517578125,
"l": 218.81556701660156,
"t": 278.0153503417969,
"r": 391.96246337890625,
"b": 508.89410400390625,