[gnome-characters/wip/exalm/unistring: 2/3] Update to Unicode 14.0.0, CLDR 40

[Alexander Mikhaylenko <alexm src gnome org>]

commit 9a6141f7a4e645884b00c7154fe3f9ce8d92640d
Author: Alexander Mikhaylenko <alexm gnome org>
Date:   Fri Nov 26 13:25:49 2021 +0500

    Update to Unicode 14.0.0, CLDR 40
    
    Add a new emoji category and new CJK blocks. Handle Tangut ideograph names.
    
    We'll regenerate the actual data in the next commit because it's huge.

 data/sidebar.ui   | 10 +++++++++-
 lib/gc.c          | 30 +++++++++++++++++++++++++++---
 lib/gc.h          |  1 +
 lib/gen-emoji.py  |  7 ++++++-
 lib/regenerate.sh |  6 +++---
 src/sidebar.js    |  4 +++-
 6 files changed, 49 insertions(+), 9 deletions(-)
---
diff --git a/data/sidebar.ui b/data/sidebar.ui
index 16e74fa..65050cb 100644
--- a/data/sidebar.ui
+++ b/data/sidebar.ui
@@ -32,7 +32,15 @@
             <property name="category">GC_CATEGORY_EMOJI_SMILEYS</property>
             <property name="name">emoji-smileys</property>
             <property name="icon-name">emoji-people-symbolic</property>
-            <property name="title" translatable="yes">Smileys &amp; People</property>
+            <property name="title" translatable="yes">Smileys &amp; Emotion</property>
+          </object>
+        </child>
+        <child>
+          <object class="Gjs_SidebarRow" id="emojiPeopleRow">
+            <property name="category">GC_CATEGORY_EMOJI_PEOPLE</property>
+            <property name="name">emoji-people</property>
+            <property name="icon-name">emoji-body-symbolic</property>
+            <property name="title" translatable="yes">People &amp; Body</property>
           </object>
         </child>
         <child>
diff --git a/lib/gc.c b/lib/gc.c
index 749d39a..b630176 100644
--- a/lib/gc.c
+++ b/lib/gc.c
@@ -127,21 +127,30 @@ get_character_name (gunichar  uc,
 {
   struct CharacterName *res;
   const struct Block *block;
-  static struct Block *cjk_blocks[6];
+  static struct Block *cjk_blocks[8];
+  static struct Block *tangut_blocks[2];
   static struct Block *hangul_block;
   static gsize local_blocks_initialized = 0;
   gsize i;
 
   if (g_once_init_enter (&local_blocks_initialized))
     {
-      static const gunichar cjk_block_starters[6] =
+      static const gunichar cjk_block_starters[8] =
         {
-          0x4E00, 0x3400, 0x20000, 0x2A700, 0x2B740, 0x2B820
+          0x4E00, 0x3400, 0x20000, 0x2A700, 0x2B740, 0x2B820, 0x2CEB0, 0x30000
+        };
+
+      static const gunichar tangut_block_starters[2] =
+        {
+          0x17000, 0x18D00
         };
 
       for (i = 0; i < G_N_ELEMENTS (cjk_block_starters); i++)
         cjk_blocks[i] = (struct Block *)find_block (cjk_block_starters[i]);
 
+      for (i = 0; i < G_N_ELEMENTS (tangut_block_starters); i++)
+        tangut_blocks[i] = (struct Block *)find_block (tangut_block_starters[i]);
+
       hangul_block = (struct Block *)find_block (0xAC00);
 
       g_once_init_leave (&local_blocks_initialized, 1);
@@ -155,6 +164,13 @@ get_character_name (gunichar  uc,
         return buffer;
       }
 
+  for (i = 0; i < G_N_ELEMENTS (tangut_blocks); i++)
+    if (block == tangut_blocks[i])
+      {
+        snprintf (buffer, UNINAME_MAX, "TANGUT IDEOGRAPH-%X", uc);
+        return buffer;
+      }
+
   if (block == hangul_block)
     {
       gunichar decomposition[3] = { 0, 0, 0 };
@@ -526,6 +542,13 @@ gc_character_iter_init_for_category (GcCharacterIter *iter,
       iter->filter = filter_all;
       return;
 
+    case GC_CATEGORY_EMOJI_PEOPLE:
+      gc_character_iter_init (iter);
+      iter->characters = emoji_people_characters;
+      iter->character_count = EMOJI_PEOPLE_CHARACTER_COUNT;
+      iter->filter = filter_all;
+      return;
+
     case GC_CATEGORY_EMOJI_ANIMALS:
       gc_character_iter_init (iter);
       iter->characters = emoji_animals_characters;
@@ -1296,6 +1319,7 @@ gc_filter_characters (GcCategory           category,
     size_t length;
   } emoji_tables[] = {
     { emoji_smileys_characters, EMOJI_SMILEYS_CHARACTER_COUNT },
+    { emoji_people_characters, EMOJI_PEOPLE_CHARACTER_COUNT },
     { emoji_animals_characters, EMOJI_ANIMALS_CHARACTER_COUNT },
     { emoji_food_characters, EMOJI_FOOD_CHARACTER_COUNT },
     { emoji_travel_characters, EMOJI_TRAVEL_CHARACTER_COUNT },
diff --git a/lib/gc.h b/lib/gc.h
index 09935da..9feadca 100644
--- a/lib/gc.h
+++ b/lib/gc.h
@@ -25,6 +25,7 @@ typedef enum
   GC_CATEGORY_LETTER_LATIN,
   GC_CATEGORY_EMOJI,
   GC_CATEGORY_EMOJI_SMILEYS,
+  GC_CATEGORY_EMOJI_PEOPLE,
   GC_CATEGORY_EMOJI_ANIMALS,
   GC_CATEGORY_EMOJI_FOOD,
   GC_CATEGORY_EMOJI_ACTIVITIES,
diff --git a/lib/gen-emoji.py b/lib/gen-emoji.py
index d0bd5d4..f8fac8c 100755
--- a/lib/gen-emoji.py
+++ b/lib/gen-emoji.py
@@ -6,7 +6,9 @@ import io
 import re
 
 GROUPS = {
-    'Smileys & People': 'smileys',
+    'Smileys & Emotion': 'smileys',
+    'People & Body': 'people',
+    'Component': 'component',
     'Animals & Nature': 'animals',
     'Food & Drink': 'food',
     'Travel & Places': 'travel',
@@ -44,6 +46,9 @@ class Builder(object):
 
     def write(self, groups):
         for name, group in groups.items():
+            if len(group) == 0:
+                continue
+
             print('#define EMOJI_{}_CHARACTER_COUNT {}'.format(
                 GROUPS[name].upper(), len(group)))
             print('static const uint32_t emoji_{}_characters[{}] ='.format(
diff --git a/lib/regenerate.sh b/lib/regenerate.sh
index b80e9c1..72cc3c5 100755
--- a/lib/regenerate.sh
+++ b/lib/regenerate.sh
@@ -1,8 +1,8 @@
 #!/bin/bash
 
-CLDR_VERSION=27
-UCD_VERSION=9.0.0
-EMOJI_VERSION=5.0
+CLDR_VERSION=40
+UCD_VERSION=14.0.0
+EMOJI_VERSION=14.0
 
 wget -c "https://www.unicode.org/Public/$UCD_VERSION/ucd/Blocks.txt";
 wget -c "https://www.unicode.org/Public/$UCD_VERSION/ucd/Jamo.txt";
diff --git a/src/sidebar.js b/src/sidebar.js
index 5ed9c91..0d0d80c 100644
--- a/src/sidebar.js
+++ b/src/sidebar.js
@@ -25,7 +25,7 @@ var Sidebar = GObject.registerClass({
     Template: 'resource:///org/gnome/Characters/sidebar.ui',
     InternalChildren: [
         'list',
-        'recentRow', 'emojiSmileysRow', 'emojiAnimalsRow',
+        'recentRow', 'emojiSmileysRow', 'emojiPeopleRow', 'emojiAnimalsRow',
         'emojiFoodRow', 'emojiActivitiesRow', 'emojiTravelRow',
         'emojiObjectsRow', 'emojiSymbolsRow', 'emojiFlagsRow',
         'lettersPunctuationRow', 'lettersArrowsRow',
@@ -52,6 +52,8 @@ var Sidebar = GObject.registerClass({
         switch (name) {
         case 'smileys':
             return this._emojiSmileysRow;
+        case 'people':
+            return this._emojiPeopleRow;
         case 'animals':
             return this._emojiAnimalsRow;
         case 'food':