mirror of
https://github.com/DS4SD/docling.git
synced 2025-12-09 13:18:24 +00:00
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:
@@ -16866,10 +16866,10 @@
|
||||
{
|
||||
"page_no": 1,
|
||||
"bbox": {
|
||||
"l": 323.408203125,
|
||||
"l": 323.4081115722656,
|
||||
"t": 541.6512603759766,
|
||||
"r": 553.2952270507812,
|
||||
"b": 266.1492919921875,
|
||||
"r": 553.295166015625,
|
||||
"b": 266.14935302734375,
|
||||
"coord_origin": "BOTTOMLEFT"
|
||||
},
|
||||
"charspan": [
|
||||
@@ -16941,9 +16941,9 @@
|
||||
"page_no": 3,
|
||||
"bbox": {
|
||||
"l": 88.33030700683594,
|
||||
"t": 699.1134796142578,
|
||||
"t": 699.1134490966797,
|
||||
"r": 263.7049560546875,
|
||||
"b": 571.4317321777344,
|
||||
"b": 571.4317626953125,
|
||||
"coord_origin": "BOTTOMLEFT"
|
||||
},
|
||||
"charspan": [
|
||||
@@ -16979,9 +16979,9 @@
|
||||
"page_no": 4,
|
||||
"bbox": {
|
||||
"l": 53.05912780761719,
|
||||
"t": 481.2087097167969,
|
||||
"t": 481.20867919921875,
|
||||
"r": 295.8506164550781,
|
||||
"b": 251.135986328125,
|
||||
"b": 251.1358642578125,
|
||||
"coord_origin": "BOTTOMLEFT"
|
||||
},
|
||||
"charspan": [
|
||||
@@ -17255,9 +17255,9 @@
|
||||
"page_no": 4,
|
||||
"bbox": {
|
||||
"l": 98.93103790283203,
|
||||
"t": 654.5245208740234,
|
||||
"t": 654.5244903564453,
|
||||
"r": 512.579833984375,
|
||||
"b": 497.91851806640625,
|
||||
"b": 497.91845703125,
|
||||
"coord_origin": "BOTTOMLEFT"
|
||||
},
|
||||
"charspan": [
|
||||
@@ -23506,7 +23506,7 @@
|
||||
"page_no": 6,
|
||||
"bbox": {
|
||||
"l": 62.02753829956055,
|
||||
"t": 596.3199310302734,
|
||||
"t": 596.3199462890625,
|
||||
"r": 285.78955078125,
|
||||
"b": 440.3381042480469,
|
||||
"coord_origin": "BOTTOMLEFT"
|
||||
@@ -26668,9 +26668,9 @@
|
||||
{
|
||||
"page_no": 7,
|
||||
"bbox": {
|
||||
"l": 80.35525512695312,
|
||||
"l": 80.35527038574219,
|
||||
"t": 641.0637054443359,
|
||||
"r": 267.0082092285156,
|
||||
"r": 267.00823974609375,
|
||||
"b": 496.5545349121094,
|
||||
"coord_origin": "BOTTOMLEFT"
|
||||
},
|
||||
@@ -31588,10 +31588,10 @@
|
||||
{
|
||||
"page_no": 8,
|
||||
"bbox": {
|
||||
"l": 72.6590347290039,
|
||||
"t": 619.5191955566406,
|
||||
"r": 274.83465576171875,
|
||||
"b": 452.1459655761719,
|
||||
"l": 72.65901947021484,
|
||||
"t": 619.5191650390625,
|
||||
"r": 274.8346862792969,
|
||||
"b": 452.14599609375,
|
||||
"coord_origin": "BOTTOMLEFT"
|
||||
},
|
||||
"charspan": [
|
||||
|
||||
Reference in New Issue
Block a user