glib: Update Unicode Character Database to version 13.0.0

Using commands:
```
glib/gen-unicode-tables.pl -both 13.0.0 path/to/UCD
tests/gen-casefold-txt.py 13.0.0 path/to/UCD/CaseFolding.txt \
   > tests/casefold.txt
tests/gen-casemap-txt.py 13.0.0 path/to/UCD/UnicodeData.txt \
   path/to/UCD/SpecialCasing.txt > tests/casemap.txt
```

Using UCD release https://www.unicode.org/Public/zipped/13.0.0/UCD.zip

With some manual additions to `GUnicodeScript` for the 4 new scripts
added in 13.0, using the first assigned character in each block in
`glib/tests/unicode.c`.

Signed-off-by: Philip Withnall <withnall@endlessm.com>
This commit is contained in:
Philip Withnall
2020-03-18 14:50:35 +00:00
parent bba5576fb2
commit a19e554517
10 changed files with 5675 additions and 4866 deletions

View File

@@ -424,6 +424,10 @@ typedef enum
* @G_UNICODE_SCRIPT_NANDINAGARI: Nand. Since: 2.62
* @G_UNICODE_SCRIPT_NYIAKENG_PUACHUE_HMONG: Rohg. Since: 2.62
* @G_UNICODE_SCRIPT_WANCHO: Wcho. Since: 2.62
* @G_UNICODE_SCRIPT_CHORASMIAN: Chorasmian. Since: 2.66
* @G_UNICODE_SCRIPT_DIVES_AKURU: Dives Akuru. Since: 2.66
* @G_UNICODE_SCRIPT_KHITAN_SMALL_SCRIPT: Khitan small script. Since: 2.66
* @G_UNICODE_SCRIPT_YEZIDI: Yezidi. Since: 2.66
*
* The #GUnicodeScript enumeration identifies different writing
* systems. The values correspond to the names as defined in the
@@ -615,7 +619,13 @@ typedef enum
G_UNICODE_SCRIPT_ELYMAIC, /* Elym */
G_UNICODE_SCRIPT_NANDINAGARI, /* Nand */
G_UNICODE_SCRIPT_NYIAKENG_PUACHUE_HMONG, /* Rohg */
G_UNICODE_SCRIPT_WANCHO /* Wcho */
G_UNICODE_SCRIPT_WANCHO, /* Wcho */
/* Unicode 13.0 additions */
G_UNICODE_SCRIPT_CHORASMIAN, /* Chrs */
G_UNICODE_SCRIPT_DIVES_AKURU, /* Diak */
G_UNICODE_SCRIPT_KHITAN_SMALL_SCRIPT, /* Kits */
G_UNICODE_SCRIPT_YEZIDI /* Yezi */
} GUnicodeScript;
GLIB_AVAILABLE_IN_ALL