opencc-sys 0.4.3+1.3.1

OpenCC bindings for Rust
Documentation 
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
89
90
91
92
93
94
95

/*
 * Open Chinese Convert
 *
 * Copyright 2015-2026 Carbo Kuo and contributors
 *
 * 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.
 */

#include "UTF8Util.hpp"
#include "TestUtils.hpp"

namespace opencc {

class UTF8UtilTest : public ::testing::Test {
protected:
  UTF8UtilTest() : text("東菄鶇䍶𠍀倲𩜍𢘐"), length(strlen(text)){};
  const char* text;
  const size_t length;
};

TEST_F(UTF8UtilTest, NextCharLength) {
  EXPECT_EQ(3, UTF8Util::NextCharLength(text));
  EXPECT_EQ(3, UTF8Util::NextCharLength(text + 3));
  EXPECT_EQ(3, UTF8Util::NextCharLength(text + 6));
  EXPECT_EQ(3, UTF8Util::NextCharLength(text + 9));
  EXPECT_EQ(4, UTF8Util::NextCharLength(text + 12));
  EXPECT_EQ(3, UTF8Util::NextCharLength(text + 16));
  EXPECT_EQ(4, UTF8Util::NextCharLength(text + 19));
  EXPECT_EQ(4, UTF8Util::NextCharLength(text + 23));
  EXPECT_THROW(EXPECT_EQ(3, UTF8Util::NextCharLength(text + 1)), InvalidUTF8);
  EXPECT_THROW(EXPECT_EQ(3, UTF8Util::NextCharLength(text + 2)), InvalidUTF8);
}

TEST_F(UTF8UtilTest, PrevCharLength) {
  EXPECT_EQ(4, UTF8Util::PrevCharLength(text + length));
  EXPECT_EQ(4, UTF8Util::PrevCharLength(text + length - 4));
  EXPECT_EQ(3, UTF8Util::PrevCharLength(text + length - 8));
  EXPECT_THROW(EXPECT_EQ(3, UTF8Util::PrevCharLength(text + 1)), InvalidUTF8);
}

TEST(UTF8UtilASCIITest, PrevCharLengthASCII) {
  // Heap-allocated ASCII string to catch issue #794 (OOB read with ASCII input)
  const std::string asciiStr = "abc";
  EXPECT_EQ(1,
            UTF8Util::PrevCharLength(asciiStr.c_str() + asciiStr.size()));
  EXPECT_EQ(1, UTF8Util::PrevCharLength(asciiStr.c_str() + 2));
  EXPECT_EQ(1, UTF8Util::PrevCharLength(asciiStr.c_str() + 1));
}

TEST(UTF8UtilTruncatedTest, LengthTruncatedSequence) {
  // Length() must throw InvalidUTF8 for truncated sequences instead of
  // reading past the null terminator (issue #799 fix).
  EXPECT_THROW(UTF8Util::Length("\xE0"), InvalidUTF8);   // incomplete 3-byte sequence
  EXPECT_THROW(UTF8Util::Length("\xF0"), InvalidUTF8);   // incomplete 4-byte sequence
  EXPECT_THROW(UTF8Util::Length("\xE0\xBF"), InvalidUTF8); // still incomplete 3-byte
}

TEST_F(UTF8UtilTest, Length) {
  EXPECT_EQ(0, UTF8Util::Length(""));
  EXPECT_EQ(8, UTF8Util::Length(text));
}

TEST_F(UTF8UtilTest, NotShorterThan) {
  EXPECT_TRUE(UTF8Util::NotShorterThan(text, 0));
  EXPECT_TRUE(UTF8Util::NotShorterThan(text, length));
  EXPECT_FALSE(UTF8Util::NotShorterThan(text, length + 1));
}

TEST_F(UTF8UtilTest, TruncateUTF8) {
  EXPECT_EQ("", UTF8Util::TruncateUTF8(text, 0));
  EXPECT_EQ("", UTF8Util::TruncateUTF8(text, 1));
  EXPECT_EQ("東", UTF8Util::TruncateUTF8(text, 3));
  EXPECT_EQ("東", UTF8Util::TruncateUTF8(text, 4));
  EXPECT_EQ("東菄鶇䍶𠍀", UTF8Util::TruncateUTF8(text, 16));
  EXPECT_EQ(text, UTF8Util::TruncateUTF8(text, length));
  EXPECT_EQ(text, UTF8Util::TruncateUTF8(text, length + 1));
}

TEST_F(UTF8UtilTest, GetByteMap) {
  std::vector<size_t> byteMap;
  UTF8Util::GetByteMap(text, 6, &byteMap);
  EXPECT_EQ(std::vector<size_t>({0, 3, 6, 9, 12, 16}), byteMap);
}

} // namespace opencc