1/*
2 * Copyright (C) 2013 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
17package com.android.inputmethod.latin.common;
18
19import com.android.inputmethod.annotations.UsedForTesting;
20
21import java.util.Random;
22
23import javax.annotation.Nonnull;
24
25// Utility methods related with code points used for tests.
26// TODO: Figure out where this class should be.
27@UsedForTesting
28public class CodePointUtils {
29    private CodePointUtils() {
30        // This utility class is not publicly instantiable.
31    }
32
33    public static final int[] LATIN_ALPHABETS_LOWER = {
34        'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm',
35        'n', 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z',
36        0x00E0 /* LATIN SMALL LETTER A WITH GRAVE */,
37        0x00E1 /* LATIN SMALL LETTER A WITH ACUTE */,
38        0x00E2 /* LATIN SMALL LETTER A WITH CIRCUMFLEX */,
39        0x00E3 /* LATIN SMALL LETTER A WITH TILDE */,
40        0x00E4 /* LATIN SMALL LETTER A WITH DIAERESIS */,
41        0x00E5 /* LATIN SMALL LETTER A WITH RING ABOVE */,
42        0x00E6 /* LATIN SMALL LETTER AE */,
43        0x00E7 /* LATIN SMALL LETTER C WITH CEDILLA */,
44        0x00E8 /* LATIN SMALL LETTER E WITH GRAVE */,
45        0x00E9 /* LATIN SMALL LETTER E WITH ACUTE */,
46        0x00EA /* LATIN SMALL LETTER E WITH CIRCUMFLEX */,
47        0x00EB /* LATIN SMALL LETTER E WITH DIAERESIS */,
48        0x00EC /* LATIN SMALL LETTER I WITH GRAVE */,
49        0x00ED /* LATIN SMALL LETTER I WITH ACUTE */,
50        0x00EE /* LATIN SMALL LETTER I WITH CIRCUMFLEX */,
51        0x00EF /* LATIN SMALL LETTER I WITH DIAERESIS */,
52        0x00F0 /* LATIN SMALL LETTER ETH */,
53        0x00F1 /* LATIN SMALL LETTER N WITH TILDE */,
54        0x00F2 /* LATIN SMALL LETTER O WITH GRAVE */,
55        0x00F3 /* LATIN SMALL LETTER O WITH ACUTE */,
56        0x00F4 /* LATIN SMALL LETTER O WITH CIRCUMFLEX */,
57        0x00F5 /* LATIN SMALL LETTER O WITH TILDE */,
58        0x00F6 /* LATIN SMALL LETTER O WITH DIAERESIS */,
59        0x00F7 /* LATIN SMALL LETTER O WITH STROKE */,
60        0x00F9 /* LATIN SMALL LETTER U WITH GRAVE */,
61        0x00FA /* LATIN SMALL LETTER U WITH ACUTE */,
62        0x00FB /* LATIN SMALL LETTER U WITH CIRCUMFLEX */,
63        0x00FC /* LATIN SMALL LETTER U WITH DIAERESIS */,
64        0x00FD /* LATIN SMALL LETTER Y WITH ACUTE */,
65        0x00FE /* LATIN SMALL LETTER THORN */,
66        0x00FF /* LATIN SMALL LETTER Y WITH DIAERESIS */
67    };
68
69    @UsedForTesting
70    @Nonnull
71    public static int[] generateCodePointSet(final int codePointSetSize,
72            @Nonnull final Random random) {
73        final int[] codePointSet = new int[codePointSetSize];
74        for (int i = codePointSet.length - 1; i >= 0; ) {
75            final int r = Math.abs(random.nextInt());
76            if (r < 0) {
77                continue;
78            }
79            // Don't insert 0~0x20, but insert any other code point.
80            // Code points are in the range 0~0x10FFFF.
81            final int candidateCodePoint = 0x20 + r % (Character.MAX_CODE_POINT - 0x20);
82            // Code points between MIN_ and MAX_SURROGATE are not valid on their own.
83            if (candidateCodePoint >= Character.MIN_SURROGATE
84                    && candidateCodePoint <= Character.MAX_SURROGATE) {
85                continue;
86            }
87            codePointSet[i] = candidateCodePoint;
88            --i;
89        }
90        return codePointSet;
91    }
92
93    /**
94     * Generates a random word.
95     */
96    @UsedForTesting
97    @Nonnull
98    public static String generateWord(@Nonnull final Random random,
99            @Nonnull final int[] codePointSet) {
100        final StringBuilder builder = new StringBuilder();
101        // 8 * 4 = 32 chars max, but we do it the following way so as to bias the random toward
102        // longer words. This should be closer to natural language, and more importantly, it will
103        // exercise the algorithms in dicttool much more.
104        final int count = 1 + (Math.abs(random.nextInt()) % 5)
105                + (Math.abs(random.nextInt()) % 5)
106                + (Math.abs(random.nextInt()) % 5)
107                + (Math.abs(random.nextInt()) % 5)
108                + (Math.abs(random.nextInt()) % 5)
109                + (Math.abs(random.nextInt()) % 5)
110                + (Math.abs(random.nextInt()) % 5)
111                + (Math.abs(random.nextInt()) % 5);
112        while (builder.length() < count) {
113            builder.appendCodePoint(codePointSet[Math.abs(random.nextInt()) % codePointSet.length]);
114        }
115        return builder.toString();
116    }
117}
118