1/*
2 * Copyright (C) 2014 The Android Open Source Project
3 *
4 * Licensed under the Apache License, Version 2.0 (the "License");
5 * you may not use this file except in compliance with the License.
6 * You may obtain a copy of the License at
7 *
8 *      http://www.apache.org/licenses/LICENSE-2.0
9 *
10 * Unless required by applicable law or agreed to in writing, software
11 * distributed under the License is distributed on an "AS IS" BASIS,
12 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13 * See the License for the specific language governing permissions and
14 * limitations under the License.
15 */
16
17#include "utils/utf8_utils.h"
18
19#include <gtest/gtest.h>
20
21#include <vector>
22
23#include "utils/int_array_view.h"
24
25namespace latinime {
26namespace dicttoolkit {
27namespace {
28
29TEST(Utf8UtilsTests, TestGetCodePoints) {
30    {
31        const std::vector<int> codePoints = Utf8Utils::getCodePoints("");
32        EXPECT_EQ(0u, codePoints.size());
33    }
34    {
35        const std::vector<int> codePoints = Utf8Utils::getCodePoints("test");
36        EXPECT_EQ(4u, codePoints.size());
37        EXPECT_EQ('t', codePoints[0]);
38        EXPECT_EQ('e', codePoints[1]);
39        EXPECT_EQ('s', codePoints[2]);
40        EXPECT_EQ('t', codePoints[3]);
41    }
42    {
43        const std::vector<int> codePoints = Utf8Utils::getCodePoints(u8"\u3042a\u03C2\u0410");
44        EXPECT_EQ(4u, codePoints.size());
45        EXPECT_EQ(0x3042, codePoints[0]); // HIRAGANA LETTER A
46        EXPECT_EQ('a', codePoints[1]);
47        EXPECT_EQ(0x03C2, codePoints[2]); // CYRILLIC CAPITAL LETTER A
48        EXPECT_EQ(0x0410, codePoints[3]); // GREEK SMALL LETTER FINAL SIGMA
49    }
50    {
51        const std::vector<int> codePoints = Utf8Utils::getCodePoints(u8"\U0001F36A?\U0001F752");
52        EXPECT_EQ(3u, codePoints.size());
53        EXPECT_EQ(0x1F36A, codePoints[0]); // COOKIE
54        EXPECT_EQ('?', codePoints[1]);
55        EXPECT_EQ(0x1F752, codePoints[2]); // ALCHEMICAL SYMBOL FOR STARRED TRIDENT
56    }
57
58    // Redundant UTF-8 sequences must be rejected.
59    EXPECT_TRUE(Utf8Utils::getCodePoints("\xC0\xAF").empty());
60    EXPECT_TRUE(Utf8Utils::getCodePoints("\xE0\x80\xAF").empty());
61    EXPECT_TRUE(Utf8Utils::getCodePoints("\xF0\x80\x80\xAF").empty());
62}
63
64TEST(Utf8UtilsTests, TestGetUtf8String) {
65    {
66        const std::vector<int> codePoints = {'t', 'e', 's', 't'};
67        EXPECT_EQ("test", Utf8Utils::getUtf8String(CodePointArrayView(codePoints)));
68    }
69    {
70        const std::vector<int> codePoints = {
71                0x00E0 /* LATIN SMALL LETTER A WITH GRAVE */,
72                0x03C2 /* GREEK SMALL LETTER FINAL SIGMA */,
73                0x0430 /* CYRILLIC SMALL LETTER A */,
74                0x3042 /* HIRAGANA LETTER A */,
75                0x1F36A /* COOKIE */,
76                0x1F752 /* ALCHEMICAL SYMBOL FOR STARRED TRIDENT */
77        };
78        EXPECT_EQ(u8"\u00E0\u03C2\u0430\u3042\U0001F36A\U0001F752",
79                Utf8Utils::getUtf8String(CodePointArrayView(codePoints)));
80    }
81}
82
83} // namespace
84} // namespace dicttoolkit
85} // namespace latinime
86