Update unicode data.

fabiocaccamo · Jan 3, 2023 · ea0dc3b · ea0dc3b
1 parent 374e149
commit ea0dc3b
Show file tree

Hide file tree

Showing 3 changed files with 66 additions and 28 deletions.
diff --git a/fontbro/data/unicode-blocks.json b/fontbro/data/unicode-blocks.json
@@ -835,6 +835,10 @@
         "characters_total": 64,
         "name": "Yezidi"
     },
+    {
+        "characters_total": 64,
+        "name": "Arabic Extended-C"
+    },
     {
         "characters_total": 48,
         "name": "Old Sogdian"
@@ -959,6 +963,10 @@
         "characters_total": 64,
         "name": "Pau Cin Hau"
     },
+    {
+        "characters_total": 96,
+        "name": "Devanagari Extended-A"
+    },
     {
         "characters_total": 112,
         "name": "Bhaiksuki"
@@ -979,6 +987,10 @@
         "characters_total": 32,
         "name": "Makasar"
     },
+    {
+        "characters_total": 96,
+        "name": "Kawi"
+    },
     {
         "characters_total": 16,
         "name": "Lisu Supplement"
@@ -1008,7 +1020,7 @@
         "name": "Egyptian Hieroglyphs"
     },
     {
-        "characters_total": 16,
+        "characters_total": 48,
         "name": "Egyptian Hieroglyph Format Controls"
     },
     {
@@ -1107,6 +1119,10 @@
         "characters_total": 80,
         "name": "Ancient Greek Musical Notation"
     },
+    {
+        "characters_total": 32,
+        "name": "Kaktovik Numerals"
+    },
     {
         "characters_total": 32,
         "name": "Mayan Numerals"
@@ -1135,6 +1151,10 @@
         "characters_total": 48,
         "name": "Glagolitic Supplement"
     },
+    {
+        "characters_total": 96,
+        "name": "Cyrillic Extended-D"
+    },
     {
         "characters_total": 80,
         "name": "Nyiakeng Puachue Hmong"
@@ -1147,6 +1167,10 @@
         "characters_total": 64,
         "name": "Wancho"
     },
+    {
+        "characters_total": 48,
+        "name": "Nag Mundari"
+    },
     {
         "characters_total": 32,
         "name": "Ethiopic Extended-B"
@@ -1263,6 +1287,10 @@
         "characters_total": 4944,
         "name": "CJK Unified Ideographs Extension G"
     },
+    {
+        "characters_total": 4192,
+        "name": "CJK Unified Ideographs Extension H"
+    },
     {
         "characters_total": 128,
         "name": "Tags"

diff --git a/fontbro/data/unicode-scripts.json b/fontbro/data/unicode-scripts.json
@@ -1,11 +1,11 @@
 [
     {
-        "characters_total": 8252,
+        "characters_total": 8301,
         "name": "Common",
         "tag": "Zyyy"
     },
     {
-        "characters_total": 1475,
+        "characters_total": 1481,
         "name": "Latin",
         "tag": "Latn"
     },
@@ -25,7 +25,7 @@
         "tag": "Grek"
     },
     {
-        "characters_total": 143750,
+        "characters_total": 143917,
         "name": "Unknown",
         "tag": "Zzzz"
     },
@@ -35,7 +35,7 @@
         "tag": "Copt"
     },
     {
-        "characters_total": 443,
+        "characters_total": 506,
         "name": "Cyrillic",
         "tag": "Cyrl"
     },
@@ -50,7 +50,7 @@
         "tag": "Hebr"
     },
     {
-        "characters_total": 1365,
+        "characters_total": 1368,
         "name": "Arabic",
         "tag": "Arab"
     },
@@ -80,7 +80,7 @@
         "tag": "Mand"
     },
     {
-        "characters_total": 154,
+        "characters_total": 164,
         "name": "Devanagari",
         "tag": "Deva"
     },
@@ -115,7 +115,7 @@
         "tag": "Telu"
     },
     {
-        "characters_total": 90,
+        "characters_total": 91,
         "name": "Kannada",
         "tag": "Knda"
     },
@@ -135,7 +135,7 @@
         "tag": "Thai"
     },
     {
-        "characters_total": 82,
+        "characters_total": 83,
         "name": "Lao",
         "tag": "Laoo"
     },
@@ -280,17 +280,17 @@
         "tag": "Tfng"
     },
     {
-        "characters_total": 94215,
+        "characters_total": 98408,
         "name": "Han",
         "tag": "Hani"
     },
     {
-        "characters_total": 380,
+        "characters_total": 381,
         "name": "Hiragana",
         "tag": "Hira"
     },
     {
-        "characters_total": 320,
+        "characters_total": 321,
         "name": "Katakana",
         "tag": "Kana"
     },
@@ -600,7 +600,7 @@
         "tag": "Shrd"
     },
     {
-        "characters_total": 62,
+        "characters_total": 65,
         "name": "Khojki",
         "tag": "Khoj"
     },
@@ -709,6 +709,11 @@
         "name": "Makasar",
         "tag": "Maka"
     },
+    {
+        "characters_total": 86,
+        "name": "Kawi",
+        "tag": "Kawi"
+    },
     {
         "characters_total": 1234,
         "name": "Cuneiform",
@@ -720,7 +725,7 @@
         "tag": "Cpmn"
     },
     {
-        "characters_total": 1080,
+        "characters_total": 1110,
         "name": "Egyptian Hieroglyphs",
         "tag": "Egyp"
     },
@@ -799,6 +804,11 @@
         "name": "Wancho",
         "tag": "Wcho"
     },
+    {
+        "characters_total": 42,
+        "name": "Nag Mundari",
+        "tag": "Nagm"
+    },
     {
         "characters_total": 213,
         "name": "Mende Kikakui",

diff --git a/tests/test_unicode_blocks_and_scripts.py b/tests/test_unicode_blocks_and_scripts.py
@@ -140,15 +140,15 @@ def test_get_unicode_scripts(self):
         expected_scripts = [
             {
                 "characters_count": 1505,
-                "characters_total": 8252,
-                "coverage": 0.18238002908385845,
+                "characters_total": 8301,
+                "coverage": 0.1813034574147693,
                 "name": "Common",
                 "tag": "Zyyy",
             },
             {
                 "characters_count": 345,
-                "characters_total": 1475,
-                "coverage": 0.23389830508474577,
+                "characters_total": 1481,
+                "coverage": 0.23295070898041864,
                 "name": "Latin",
                 "tag": "Latn",
             },
@@ -175,8 +175,8 @@ def test_get_unicode_scripts(self):
             },
             {
                 "characters_count": 66,
-                "characters_total": 443,
-                "coverage": 0.1489841986455982,
+                "characters_total": 506,
+                "coverage": 0.13043478260869565,
                 "name": "Cyrillic",
                 "tag": "Cyrl",
             },
@@ -189,22 +189,22 @@ def test_get_unicode_scripts(self):
             },
             {
                 "characters_count": 18100,
-                "characters_total": 94215,
-                "coverage": 0.19211378230642678,
+                "characters_total": 98408,
+                "coverage": 0.18392813592390864,
                 "name": "Han",
                 "tag": "Hani",
             },
             {
                 "characters_count": 90,
-                "characters_total": 380,
-                "coverage": 0.23684210526315788,
+                "characters_total": 381,
+                "coverage": 0.23622047244094488,
                 "name": "Hiragana",
                 "tag": "Hira",
             },
             {
                 "characters_count": 298,
-                "characters_total": 320,
-                "coverage": 0.93125,
+                "characters_total": 321,
+                "coverage": 0.9283489096573209,
                 "name": "Katakana",
                 "tag": "Kana",
             },
@@ -224,8 +224,8 @@ def test_get_unicode_scripts_with_coverage_threshold(self):
             },
             {
                 "characters_count": 298,
-                "characters_total": 320,
-                "coverage": 0.93125,
+                "characters_total": 321,
+                "coverage": 0.9283489096573209,
                 "name": "Katakana",
                 "tag": "Kana",
             },