mirror of
https://github.com/tesseract-ocr/tesseract.git
synced 2024-12-12 15:39:04 +08:00
42 lines
1.6 KiB
C++
42 lines
1.6 KiB
C++
|
#include "tesseract/training/normstrngs.h"
|
||
|
|
|
||
|
|
#include "tesseract/unittest/normstrngs_test.h"
|
||
|
|
|
||
|
|
namespace tesseract {
|
||
|
|
namespace {
|
||
|
|
|
||
|
|
// Test some random Khmer words.
|
||
|
|
TEST(ValidateKhmerTest, GoodKhmerWords) {
|
||
|
|
string str = "ព័ត៏មានប្លែកៗ";
|
||
|
|
ExpectGraphemeModeResults(str, UnicodeNormMode::kNFC, 13, 12, 7, str);
|
||
|
|
str = "ទំនុកច្រៀង";
|
||
|
|
ExpectGraphemeModeResults(str, UnicodeNormMode::kNFC, 10, 9, 5, str);
|
||
|
|
str = "កាលីហ្វូញ៉ា";
|
||
|
|
ExpectGraphemeModeResults(str, UnicodeNormMode::kNFC, 11, 10, 4, str);
|
||
|
|
str = "ចាប់ពីផ្លូវ";
|
||
|
|
ExpectGraphemeModeResults(str, UnicodeNormMode::kNFC, 11, 10, 5, str);
|
||
|
|
}
|
||
|
|
|
||
|
|
// Test some random Khmer words with dotted circles.
|
||
|
|
TEST(ValidateKhmerTest, BadKhmerWords) {
|
||
|
|
string result;
|
||
|
|
// Multiple dependent vowels not allowed
|
||
|
|
string str = "\u1796\u17b6\u17b7";
|
||
|
|
EXPECT_FALSE(NormalizeUTF8String(UnicodeNormMode::kNFC, OCRNorm::kNone,
|
||
|
|
GraphemeNorm::kNormalize, str.c_str(),
|
||
|
|
&result));
|
||
|
|
// Multiple shifters not allowed
|
||
|
|
str = "\u1798\u17c9\u17ca";
|
||
|
|
EXPECT_FALSE(NormalizeUTF8String(UnicodeNormMode::kNFC, OCRNorm::kNone,
|
||
|
|
GraphemeNorm::kNormalize, str.c_str(),
|
||
|
|
&result));
|
||
|
|
// Multiple signs not allowed
|
||
|
|
str = "\u1780\u17b6\u17cb\u17cd";
|
||
|
|
EXPECT_FALSE(NormalizeUTF8String(UnicodeNormMode::kNFC, OCRNorm::kNone,
|
||
|
|
GraphemeNorm::kNormalize, str.c_str(),
|
||
|
|
&result));
|
||
|
|
}
|
||
|
|
|
||
|
|
} // namespace
|
||
|
|
} // namespace tesseract
|