forked from tesseract-ocr/tesseract
-
Notifications
You must be signed in to change notification settings - Fork 1
/
normstrngs_test.h
88 lines (79 loc) · 3.28 KB
/
normstrngs_test.h
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
// (C) Copyright 2017, Google Inc.
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
// http://www.apache.org/licenses/LICENSE-2.0
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
#ifndef TESSERACT_UNITTEST_NORMSTRNGS_TEST_H_
#define TESSERACT_UNITTEST_NORMSTRNGS_TEST_H_
#include <tesseract/unichar.h>
#include <sstream> // for std::stringstream
#include <string>
#include <vector>
namespace tesseract {
inline std::string CodepointList(const std::vector<char32> &str32) {
std::stringstream result;
int total_chars = str32.size();
result << std::hex;
for (int i = 0; i < total_chars; ++i) {
result << "[" << str32[i] << "]";
}
return result.str();
}
inline std::string PrintString32WithUnicodes(const std::string &str) {
std::vector<char32> str32 = UNICHAR::UTF8ToUTF32(str.c_str());
std::string s = "\"";
s += "\" " + CodepointList(str32);
return s;
}
inline std::string PrintStringVectorWithUnicodes(const std::vector<std::string> &glyphs) {
std::string result;
for (const auto &s : glyphs) {
result += "Glyph:";
result += PrintString32WithUnicodes(s) + "\n";
}
return result;
}
inline void ExpectGraphemeModeResults(const std::string &str, UnicodeNormMode u_mode,
int unicode_count, int glyph_count, int grapheme_count,
const std::string &target_str) {
std::vector<std::string> glyphs;
std::string s;
EXPECT_TRUE(NormalizeCleanAndSegmentUTF8(
u_mode, OCRNorm::kNone, GraphemeNormMode::kIndividualUnicodes, true, str.c_str(), &glyphs));
EXPECT_EQ(glyphs.size(), unicode_count) << PrintStringVectorWithUnicodes(glyphs);
for (auto &glyph : glyphs) {
s += glyph;
}
EXPECT_EQ(target_str, s);
EXPECT_TRUE(NormalizeCleanAndSegmentUTF8(u_mode, OCRNorm::kNone, GraphemeNormMode::kGlyphSplit,
true, str.c_str(), &glyphs));
EXPECT_EQ(glyphs.size(), glyph_count) << PrintStringVectorWithUnicodes(glyphs);
s.clear();
for (auto &glyph : glyphs) {
s += glyph;
}
EXPECT_EQ(target_str, s);
EXPECT_TRUE(NormalizeCleanAndSegmentUTF8(u_mode, OCRNorm::kNone, GraphemeNormMode::kCombined,
true, str.c_str(), &glyphs));
EXPECT_EQ(glyphs.size(), grapheme_count) << PrintStringVectorWithUnicodes(glyphs);
s.clear();
for (auto &glyph : glyphs) {
s += glyph;
}
EXPECT_EQ(target_str, s);
EXPECT_TRUE(NormalizeCleanAndSegmentUTF8(u_mode, OCRNorm::kNone, GraphemeNormMode::kSingleString,
true, str.c_str(), &glyphs));
EXPECT_EQ(glyphs.size(), 1) << PrintStringVectorWithUnicodes(glyphs);
EXPECT_EQ(target_str, glyphs[0]);
std::string result;
EXPECT_TRUE(
NormalizeUTF8String(u_mode, OCRNorm::kNone, GraphemeNorm::kNormalize, str.c_str(), &result));
EXPECT_EQ(target_str, result);
}
} // namespace tesseract
#endif // TESSERACT_UNITTEST_NORMSTRNGS_TEST_H_