DenysMedvid/pdf2htmlEX
1
0
Fork 0
mirror of https://github.com/pdf2htmlEX/pdf2htmlEX.git synced 2024-07-05 01:28:39 +00:00
Code

Fix offset optimizing issue introduced by padding char (#398).

Browse Source
This commit is contained in:
Duan Yao 2014-08-03 19:47:58 +08:00
parent d02a8e5c01
commit c7053f392b
1 changed files with 10 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
src/HTMLTextLine.cc
View File

@ -52,12 +52,19 @@ void HTMLTextLine::append_offset(double width)
/*
* If the last offset is very thin, we can ignore it and directly use it
* But this should not happen often, and we will also filter near-zero offsets when outputting them
* So don't check it
* So don't check it.
*
* Offset must be appended immediately after the last real (non-padding) char, or the text optimizing
* algorithm may be confused: it may wrongly convert offsets at the beginning of a line to word-space.
*/
if((!offsets.empty()) && (offsets.back().start_idx == text.size()))
auto offset_idx = text.size();
while (offset_idx > 0 && text[offset_idx - 1] == 0)
--offset_idx;
if((!offsets.empty()) && (offsets.back().start_idx == offset_idx))
offsets.back().width += width;
else
offsets.emplace_back(text.size(), width);
offsets.emplace_back(offset_idx, width);
this->width += width;
}