mirror/tesseract
1
0
Fork 0
mirror of https://github.com/tesseract-ocr/tesseract.git synced 2025-01-21 17:13:09 +08:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

Fix removal of duplicates in StructuredTable::FindLinedStructure

Browse Source 
Signed-off-by: Stefan Weil <sw@weilnetz.de>
This commit is contained in:
Stefan Weil 2021-03-16 17:47:49 +01:00
parent d604bf3c68
commit 8cfaf7bf64
1 changed files with 8 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
src/textord/tablerecog.cpp
View File

@ -158,9 +158,11 @@ bool StructuredTable::FindLinedStructure() {
// Sort and remove duplicates that may have occurred due to split lines.
std::sort(cell_x_.begin(), cell_x_.end());
std::unique(cell_x_.begin(), cell_x_.end());
auto last_x = std::unique(cell_x_.begin(), cell_x_.end());
cell_x_.erase(last_x, cell_x_.end());
std::sort(cell_y_.begin(), cell_y_.end());
std::unique(cell_y_.begin(), cell_y_.end());
auto last_y = std::unique(cell_y_.begin(), cell_y_.end());
cell_y_.erase(last_y, cell_y_.end());
// The border should be the extents of line boxes, not middle.
cell_x_[0] = bounding_box_.left();
@ -169,8 +171,10 @@ bool StructuredTable::FindLinedStructure() {
cell_y_[cell_y_.size() - 1] = bounding_box_.top();
// Remove duplicates that may have occurred due to moving the borders.
std::unique(cell_x_.begin(), cell_x_.end());
std::unique(cell_y_.begin(), cell_y_.end());
last_x = std::unique(cell_x_.begin(), cell_x_.end());
cell_x_.erase(last_x, cell_x_.end());
last_y = std::unique(cell_y_.begin(), cell_y_.end());
cell_y_.erase(last_y, cell_y_.end());
CalculateMargins();
CalculateStats();