mirror of
https://github.com/tesseract-ocr/tesseract.git
synced 2025-01-18 22:43:45 +08:00
Avoids HTML escaping.
This commit is contained in:
parent
b1e4a82b0b
commit
858f4b75ce
@ -1732,13 +1732,13 @@ char* TessBaseAPI::GetHOCRTSVText(int page_number) {
|
||||
hocr_str += "\t";
|
||||
do {
|
||||
const char *grapheme = res_it->GetUTF8Text(RIL_SYMBOL);
|
||||
if (grapheme && grapheme[0] != 0) {
|
||||
if (grapheme[1] == 0) {
|
||||
hocr_str += HOcrEscape(grapheme);
|
||||
} else {
|
||||
// if (grapheme && grapheme[0] != 0) {
|
||||
// if (grapheme[1] == 0) {
|
||||
// hocr_str += HOcrEscape(grapheme);
|
||||
// } else {
|
||||
hocr_str += grapheme;
|
||||
}
|
||||
}
|
||||
// }
|
||||
// }
|
||||
delete []grapheme;
|
||||
res_it->Next(RIL_SYMBOL);
|
||||
} while (!res_it->Empty(RIL_BLOCK) && !res_it->IsAtBeginningOf(RIL_WORD));
|
||||
|
Loading…
Reference in New Issue
Block a user