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
@@ -1541,7 +1541,7 @@
"b": 358.76782,
"coord_origin": "TOPLEFT"
},
"confidence": 0.5588350296020508,
"confidence": 0.5588339567184448,
"cells": [
{
"index": 18,
@@ -1581,7 +1581,7 @@
"b": 406.74554,
"coord_origin": "TOPLEFT"
},
"confidence": 0.6312209963798523,
"confidence": 0.6312211155891418,
"cells": [
{
"index": 19,
@@ -2036,7 +2036,7 @@
"b": 607.23564,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9843751788139343,
"confidence": 0.9843752980232239,
"cells": [
{
"index": 36,
@@ -2719,7 +2719,7 @@
"b": 358.76782,
"coord_origin": "TOPLEFT"
},
"confidence": 0.5588350296020508,
"confidence": 0.5588339567184448,
"cells": [
{
"index": 18,
@@ -2765,7 +2765,7 @@
"b": 406.74554,
"coord_origin": "TOPLEFT"
},
"confidence": 0.6312209963798523,
"confidence": 0.6312211155891418,
"cells": [
{
"index": 19,
@@ -3232,7 +3232,7 @@
"b": 607.23564,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9843751788139343,
"confidence": 0.9843752980232239,
"cells": [
{
"index": 36,
@@ -3914,7 +3914,7 @@
"b": 358.76782,
"coord_origin": "TOPLEFT"
},
"confidence": 0.5588350296020508,
"confidence": 0.5588339567184448,
"cells": [
{
"index": 18,
@@ -3960,7 +3960,7 @@
"b": 406.74554,
"coord_origin": "TOPLEFT"
},
"confidence": 0.6312209963798523,
"confidence": 0.6312211155891418,
"cells": [
{
"index": 19,
@@ -4427,7 +4427,7 @@
"b": 607.23564,
"coord_origin": "TOPLEFT"
},
"confidence": 0.9843751788139343,
"confidence": 0.9843752980232239,
"cells": [
{
"index": 36,
@@ -5782,7 +5782,7 @@
"b": 137.5481507594625,
"coord_origin": "TOPLEFT"
},
"confidence": 0.950506865978241,
"confidence": 0.9505067467689514,
"cells": [
{
"index": 0,
@@ -6302,7 +6302,7 @@
"b": 373.7119120634245,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8727474808692932,
"confidence": 0.8727476000785828,
"cells": [
{
"index": 19,
@@ -7037,7 +7037,7 @@
"b": 704.5687238902275,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8504500389099121,
"confidence": 0.8504503965377808,
"cells": [
{
"index": 46,
@@ -7092,7 +7092,7 @@
"b": 137.5481507594625,
"coord_origin": "TOPLEFT"
},
"confidence": 0.950506865978241,
"confidence": 0.9505067467689514,
"cells": [
{
"index": 0,
@@ -7630,7 +7630,7 @@
"b": 373.7119120634245,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8727474808692932,
"confidence": 0.8727476000785828,
"cells": [
{
"index": 19,
@@ -8389,7 +8389,7 @@
"b": 704.5687238902275,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8504500389099121,
"confidence": 0.8504503965377808,
"cells": [
{
"index": 46,
@@ -8437,7 +8437,7 @@
"b": 137.5481507594625,
"coord_origin": "TOPLEFT"
},
"confidence": 0.950506865978241,
"confidence": 0.9505067467689514,
"cells": [
{
"index": 0,
@@ -8975,7 +8975,7 @@
"b": 373.7119120634245,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8727474808692932,
"confidence": 0.8727476000785828,
"cells": [
{
"index": 19,
@@ -9736,7 +9736,7 @@
"b": 704.5687238902275,
"coord_origin": "TOPLEFT"
},
"confidence": 0.8504500389099121,
"confidence": 0.8504503965377808,
"cells": [
{
"index": 46,