Update to Unicode 8.0

Regenerate data tables from the Unicode Character Database, add
new scripts, and update tests to include some of the new data.
This commit is contained in:
Matthias Clasen
2015-10-04 10:21:43 -04:00
parent fc59c20e97
commit f9d9f9c056
8 changed files with 2592 additions and 1042 deletions

View File

@@ -276,11 +276,17 @@ test_unichar_script (void)
{ G_UNICODE_SCRIPT_SIDDHAM, 0x11580 },
{ G_UNICODE_SCRIPT_TIRHUTA, 0x11480 },
{ G_UNICODE_SCRIPT_WARANG_CITI, 0x118A0 },
{ G_UNICODE_SCRIPT_CHEROKEE, 0x0AB71 },
{ G_UNICODE_SCRIPT_HATRAN, 0x108E0 },
{ G_UNICODE_SCRIPT_OLD_HUNGARIAN, 0x10C80 },
{ G_UNICODE_SCRIPT_MULTANI, 0x11280 },
{ G_UNICODE_SCRIPT_AHOM, 0x11700 },
{ G_UNICODE_SCRIPT_CUNEIFORM, 0x12480 },
{ G_UNICODE_SCRIPT_ANATOLIAN_HIEROGLYPHS, 0x14400 },
{ G_UNICODE_SCRIPT_SIGNWRITING, 0x1D800 },
};
for (i = 0; i < G_N_ELEMENTS (examples); i++)
{
g_assert_cmpint (g_unichar_get_script (examples[i].c), ==, examples[i].script);
}
g_assert_cmpint (g_unichar_get_script (examples[i].c), ==, examples[i].script);
}
static void
@@ -852,6 +858,14 @@ test_iso15924 (void)
{ G_UNICODE_SCRIPT_SIDDHAM, "Sidd" },
{ G_UNICODE_SCRIPT_TIRHUTA, "Tirh" },
{ G_UNICODE_SCRIPT_WARANG_CITI, "Wara" },
/* Unicode 8.0 additions */
{ G_UNICODE_SCRIPT_AHOM, "Ahom" },
{ G_UNICODE_SCRIPT_ANATOLIAN_HIEROGLYPHS, "Hluw" },
{ G_UNICODE_SCRIPT_HATRAN, "Hatr" },
{ G_UNICODE_SCRIPT_MULTANI, "Mult" },
{ G_UNICODE_SCRIPT_OLD_HUNGARIAN, "Hung" },
{ G_UNICODE_SCRIPT_SIGNWRITING, "Sgnw" },
};
guint i;