Test for correct locale settings

Normal C++ programs like those which are built for tesseract automatically set the locale "C". There can be different locale settings if the tesseract library is used in other software. A wrong locale can cause wrong results from sscanf which is used at different places in the tesseract code, so make sure that we have the right locale settings and fail if that is not the case. Signed-off-by: Stefan Weil <sw@weilnetz.de>
tesseract-ocr · Jun 8, 2018 · 3292484f67af8bdda23aa5e510918d0115785291 · 3292484
1 parent a662306
commit 3292484f67af8bdda23aa5e510918d0115785291
Unified Split

Showing with 10 additions and 1 deletion.

+10 −1 src/api/baseapi.cpp
diff --git a/src/api/baseapi.cpp b/src/api/baseapi.cpp
@@ -43,6 +43,7 @@
 #endif  // _WIN32
 #include <algorithm>
+  
+#include <clocale>
 #include <fstream>
 #include <iostream>
 #include <iterator>
@@ -185,7 +186,15 @@ TessBaseAPI::TessBaseAPI()
      rect_width_(0),
      rect_height_(0),
      image_width_(0),
-  
-      image_height_(0) {}
+  
+      image_height_(0) {
+  
+  const char *locale;
+  
+  locale = std::setlocale(LC_ALL, nullptr);
+  
+  ASSERT_HOST(!strcmp(locale, "C"));
+  
+  locale = std::setlocale(LC_CTYPE, nullptr);
+  
+  ASSERT_HOST(!strcmp(locale, "C"));
+  
+  locale = std::setlocale(LC_NUMERIC, nullptr);
+  
+  ASSERT_HOST(!strcmp(locale, "C"));
+  
+}
 TessBaseAPI::~TessBaseAPI() {
  End();