summaryrefslogtreecommitdiff
path: root/glib/tests/unicode-normalize.c
blob: 191e5bb981de33a067df6ac14a3d34d6dc14dc6f (plain)
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
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
#undef G_DISABLE_ASSERT
#undef G_LOG_DOMAIN

#include <glib.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>

static char *
decode (const gchar *input)
{
  unsigned ch;
  int offset = 0;
  GString *result = g_string_new (NULL);

  do
    {
      g_assert_cmpint (sscanf (input + offset, "%x", &ch), ==, 1);
      g_string_append_unichar (result, ch);

      while (input[offset] && input[offset] != ' ')
	offset++;
      while (input[offset] && input[offset] == ' ')
	offset++;
    }
  while (input[offset]);

  return g_string_free (result, FALSE);
}

const char *names[4] = {
  "NFD",
  "NFC",
  "NFKD",
  "NFKC"
};

static void
test_form (int            line,
	   GNormalizeMode mode,
	   gboolean       do_compat,
	   int            expected,
	   char         **c,
	   char         **raw)
{
  int i;
  gboolean mode_is_compat = (mode == G_NORMALIZE_NFKC ||
			     mode == G_NORMALIZE_NFKD);

  if (mode_is_compat || !do_compat)
    {
      for (i = 0; i < 3; i++)
	{
	  char *result = g_utf8_normalize (c[i], -1, mode);
          g_assert_cmpstr (result, ==, c[expected]);
          g_free (result);
	}
    }
  if (mode_is_compat || do_compat)
    {
      for (i = 3; i < 5; i++)
	{
	  char *result = g_utf8_normalize (c[i], -1, mode);
          g_assert_cmpstr (result, ==, c[expected]);
          g_free (result);
	}
    }
}

static void
process_one (int line, gchar **columns)
{
  char *c[5];
  int i;

  for (i = 0; i < 5; i++)
    {
      c[i] = decode (columns[i]);
      g_assert_nonnull (c[i]);
    }

  test_form (line, G_NORMALIZE_NFD, FALSE, 2, c, columns);
  test_form (line, G_NORMALIZE_NFD, TRUE, 4, c, columns);
  test_form (line, G_NORMALIZE_NFC, FALSE, 1, c, columns);
  test_form (line, G_NORMALIZE_NFC, TRUE, 3, c, columns);
  test_form (line, G_NORMALIZE_NFKD, TRUE, 4, c, columns);
  test_form (line, G_NORMALIZE_NFKC, TRUE, 3, c, columns);

  for (i = 0; i < 5; i++)
    g_free (c[i]);
}

static void
test_unicode_normalize (void)
{
  GIOChannel *in;
  GError *error = NULL;
  gchar *filename = NULL;
  GString *buffer = g_string_new (NULL);
  int line = 1;

  filename = g_test_build_filename (G_TEST_DIST, "NormalizationTest.txt", NULL);
  g_assert_nonnull (filename);

  in = g_io_channel_new_file (filename, "r", &error);
  g_assert_no_error (error);
  g_assert_nonnull (in);
  g_free (filename);

  while (TRUE)
    {
      gsize term_pos;
      gchar **columns;

      if (g_io_channel_read_line_string (in, buffer, &term_pos, &error) != G_IO_STATUS_NORMAL)
	break;

      buffer->str[term_pos] = '\0';

      if (buffer->str[0] == '#') /* Comment */
	goto next;
      if (buffer->str[0] == '@') /* Part */
	{
	  g_test_message ("Processing %s", buffer->str + 1);
	  goto next;
	}

      columns = g_strsplit (buffer->str, ";", -1);
      if (!columns[0])
        {
          g_strfreev (columns);
          goto next;
        }

      process_one (line, columns);
      g_strfreev (columns);

    next:
      g_string_truncate (buffer, 0);
      line++;
    }

  g_assert_no_error (error);

  g_io_channel_unref (in);
  g_string_free (buffer, TRUE);
}

static void
test_unicode_normalize_invalid (void)
{
  /* g_utf8_normalize() should return NULL for all of these invalid inputs */
  const struct
  {
    gssize max_len;
    const gchar *str;
  } test_vectors[] = {
    /* input ending with truncated multibyte encoding */
    { -1, "\xC0" },
    { 1, "\xC0\x80" },
    { -1, "\xE0\x80" },
    { 2, "\xE0\x80\x80" },
    { -1, "\xF0\x80\x80" },
    { 3, "\xF0\x80\x80\x80" },
    { -1, "\xF8\x80\x80\x80" },
    { 4, "\xF8\x80\x80\x80\x80" },
    { 3, "\x20\xE2\x84\xAA" },
    { -1, "\x20\xE2\x00\xAA" },
    { -1, "\xC0\x80\xE0\x80" },
    { 4, "\xC0\x80\xE0\x80\x80" },
    /* input containing invalid multibyte encoding */
    { -1, "\xED\x85\x9C\xED\x15\x9C\xED\x85\x9C" },
  };
  gsize i;

  for (i = 0; i < G_N_ELEMENTS (test_vectors); i++)
    {
      g_test_message ("Invalid UTF-8 vector %" G_GSIZE_FORMAT, i);
      g_assert_null (g_utf8_normalize (test_vectors[i].str,
                                       test_vectors[i].max_len,
                                       G_NORMALIZE_ALL));
    }
}

int
main (int argc, char **argv)
{
  g_test_init (&argc, &argv, NULL);

  g_test_add_func ("/unicode/normalize", test_unicode_normalize);
  g_test_add_func ("/unicode/normalize-invalid",
                   test_unicode_normalize_invalid);

  return g_test_run ();
}