LCOV - GNU Libidn - tests/tst_nfkc.c

 Line data Source code

 1  : /* tst_nfkc.c --- Self tests for stringprep_utf8_nfkc_normalize().
 2  : * Copyright (C) 2002-2020 Simon Josefsson
 3  : *
 4  : * This file is part of GNU Libidn.
 5  : *
 6  : * This program is free software: you can redistribute it and/or modify
 7  : * it under the terms of the GNU General Public License as published by
 8  : * the Free Software Foundation, either version 3 of the License, or
 9  : * (at your option) any later version.
 10  : *
 11  : * This program is distributed in the hope that it will be useful,
 12  : * but WITHOUT ANY WARRANTY; without even the implied warranty of
 13  : * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
 14  : * GNU General Public License for more details.
 15  : *
 16  : * You should have received a copy of the GNU General Public License
 17  : * along with this program. If not, see <http://www.gnu.org/licenses/>.
 18  : *
 19  : */
 20  : 
 21  : #ifdef HAVE_CONFIG_H
 22  : # include "config.h"
 23  : #endif
 24  : 
 25  : #include <stdio.h>
 26  : #include <stdlib.h>
 27  : #include <stdarg.h>
 28  : #include <string.h>
 29  : 
 30  : #include <stringprep.h>
 31  : 
 32  : #include "utils.h"
 33  : 
 34  : struct nfkc
 35  : {
 36  : const char *in;
 37  : const char *out;
 38  : };
 39  : 
 40  : static struct nfkc nfkc[] = {
 41  : {"\xC2\xB5", "\xCE\xBC"},
 42  : {"\xC2\xAA", "\x61"},
 43  : /* From <http://www.unicode.org/review/pr-29.html>. Note that we
 44  : * compute the output according to Unicode 3.2 without the proposed
 45  : * update.
 46  : *
 47  : * 1.
 48  : *
 49  : * U+1100 (ᄀ) HANGUL CHOSEONG KIYEOK +
 50  : * U+0300 (◌̀) COMBINING GRAVE ACCENT +
 51  : * U+1161 (ᅡ) HANGUL JUNGSEONG A
 52  : *
 53  : * According to the old language, the NFC form of this would be B:
 54  : *
 55  : * 2.
 56  : *
 57  : * U+AC00 (가) HANGUL SYLLABLE GA +
 58  : * U+0300 (◌̀) COMBINING GRAVE ACCENT
 59  : */
 60  : {"\xE1\x84\x80\xCC\x80\xE1\x85\xA1", "\xEA\xB0\x80\xCC\x80"},
 61  : /* Second test case from page. Again, we do not implement the
 62  : * updated proposal. <U+0B47; U+0300; U+0B3E> -> U+0B4B U+0300
 63  : */
 64  : {"\xE0\xAD\x87\xCC\x80\xE0\xAC\xBE", "\xE0\xAD\x8b\xCC\x80"}
 65  : };
 66  : 
 67  : void
 68  1 : doit (void)
 69  : {
 70  : char *out;
 71  : unsigned i;
 72  : 
 73  5 : for (i = 0; i < sizeof (nfkc) / sizeof (nfkc[0]); i++)
 74  : {
 75  4 : if (debug)
 76  0 : printf ("NFKC entry %u\n", i);
 77  : 
 78  4 : out = stringprep_utf8_nfkc_normalize (nfkc[i].in,
 79  4 : (ssize_t) strlen (nfkc[i].in));
 80  4 : if (out == NULL)
 81  : {
 82  0 : fail ("NFKC entry %u failed fatally\n", i);
 83  0 : continue;
 84  : }
 85  : 
 86  4 : if (debug)
 87  : {
 88  : uint32_t *t;
 89  : size_t len;
 90  : 
 91  0 : printf ("in:\n");
 92  0 : escapeprint (nfkc[i].in, strlen (nfkc[i].in));
 93  0 : hexprint (nfkc[i].in, strlen (nfkc[i].in));
 94  0 : binprint (nfkc[i].in, strlen (nfkc[i].in));
 95  : 
 96  : 
 97  0 : printf ("out:\n");
 98  0 : escapeprint (out, strlen (out));
 99  0 : hexprint (out, strlen (out));
 100  0 : binprint (out, strlen (out));
 101  0 : t = stringprep_utf8_to_ucs4 (out, -1, &len);
 102  0 : if (t)
 103  : {
 104  0 : ucs4print (t, len);
 105  0 : free (t);
 106  : }
 107  : 
 108  0 : printf ("expected out:\n");
 109  0 : escapeprint (nfkc[i].out, strlen (nfkc[i].out));
 110  0 : hexprint (nfkc[i].out, strlen (nfkc[i].out));
 111  0 : binprint (nfkc[i].out, strlen (nfkc[i].out));
 112  : }
 113  : 
 114  4 : if (strlen (nfkc[i].out) != strlen (out) ||
 115  4 : memcmp (nfkc[i].out, out, strlen (out)) != 0)
 116  : {
 117  0 : fail ("NFKC entry %u failed\n", i);
 118  0 : if (debug)
 119  0 : printf ("ERROR\n");
 120  : }
 121  4 : else if (debug)
 122  0 : printf ("OK\n");
 123  : 
 124  4 : free (out);
 125  : }
 126  1 : }