mirror/tesseract
1
0
Fork 0
mirror of https://github.com/tesseract-ocr/tesseract.git synced 2024-12-04 01:39:16 +08:00
Code Issues Actions 12 Packages Projects Releases Wiki Activity

A better fix to read unichars. Imbue C locale always since on different systems, default locale will give different results.

Browse Source
This commit is contained in:
Egor Pugin 2021-01-04 20:36:21 +03:00
parent 0364832ab8
commit 0c7139ce09
2 changed files with 4 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
src/classify/cutoffs.cpp
View File

@ -53,14 +53,10 @@ void Classify::ReadNewCutoffs(TFile* fp, uint16_t* Cutoffs) {
char line[kMaxLineSize];
while (fp->FGets(line, kMaxLineSize) != nullptr) {
std::string Class;
auto p = line;
while (*p != ' ' && p - line < kMaxLineSize)
Class.push_back(*p++);
CLASS_ID ClassId;
// do not use stream to extract Class as it may contain unicode spaces (0xA0)
// they are eaten by stream, but they are a part of Class
std::istringstream stream(p);
stream >> Cutoff;
std::istringstream stream(line);
stream.imbue(std::locale::classic());
stream >> Class >> Cutoff;
if (stream.fail()) {
break;
}

1
src/classify/normmatch.cpp
View File

@ -208,6 +208,7 @@ NORM_PROTOS *Classify::ReadNormProtos(TFile *fp) {
char line[kMaxLineSize];
while (fp->FGets(line, kMaxLineSize) != nullptr) {
std::istringstream stream(line);
stream.imbue(std::locale::classic());
stream >> unichar >> NumProtos;
if (stream.fail()) {
continue;