Detect scripts in non-BMP code blocks

Enabled local glyph rendering in some additional CJKV code blocks, as well as in Tangut, which is thrash-prone like CJKV. Disabled letter spacing for more cursive scripts.
maplibre · Aug 14, 2024 · 808f90c · 808f90c
1 parent 4c412e6
commit 808f90c
Show file tree

Hide file tree

Showing 4 changed files with 122 additions and 50 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -4,6 +4,7 @@
 
 - Add constants `MAX_TILE_ZOOM = 25` and `MIN_TILE_ZOOM = 0` as maximum and minimum world tile zoom (Z) values; replace hardcoded instances with those constants.
 - Add functions `isInBoundsForTileZoomXY` and `isInBoundsForZoomLngLat` to check whether a tile ZXY or a zoom+LngLat is in the world bounds; use `MAX_TILE_ZOOM` and `MIN_TILE_ZOOM` in those checks; replace existing hardcoded checks with those functions.
+- Render uncommon Chinese, Japanese, Korean, and Vietnamese characters. ([#4550](https://github.com/maplibre/maplibre-gl-js/pull/4550))
 - _...Add new stuff here..._
 
 ### 🐞 Bug fixes

diff --git a/src/render/glyph_manager.ts b/src/render/glyph_manager.ts
@@ -166,9 +166,16 @@ export class GlyphManager {
              unicodeBlockLookup['Hangul Syllables'](id) ||
              unicodeBlockLookup['Hiragana'](id) ||
              unicodeBlockLookup['Ideographic Description Characters'](id) ||
+             unicodeBlockLookup['Kana Extended-A'](id) ||
+             unicodeBlockLookup['Kana Extended-B'](id) ||
+             unicodeBlockLookup['Kana Supplement'](id) ||
              unicodeBlockLookup['Kangxi Radicals'](id) ||
              unicodeBlockLookup['Katakana'](id) ||
-             unicodeBlockLookup['Katakana Phonetic Extensions'](id));
+             unicodeBlockLookup['Katakana Phonetic Extensions'](id) ||
+             unicodeBlockLookup['Small Kana Extension'](id) ||
+             unicodeBlockLookup['Tangut'](id) ||
+             unicodeBlockLookup['Tangut Components'](id) ||
+             unicodeBlockLookup['Tangut Supplement'](id));
         /* eslint-enable new-cap */
     }
 

diff --git a/src/util/is_char_in_unicode_block.ts b/src/util/is_char_in_unicode_block.ts
@@ -17,13 +17,13 @@ export const unicodeBlockLookup: UnicodeBlockLookup = {
     // 'Armenian': (char) => char >= 0x0530 && char <= 0x058F,
     //'Hebrew': (char) => char >= 0x0590 && char <= 0x05FF,
     'Arabic': (char) => char >= 0x0600 && char <= 0x06FF,
-    //'Syriac': (char) => char >= 0x0700 && char <= 0x074F,
+    'Syriac': (char) => char >= 0x0700 && char <= 0x074F,
     'Arabic Supplement': (char) => char >= 0x0750 && char <= 0x077F,
     // 'Thaana': (char) => char >= 0x0780 && char <= 0x07BF,
     // 'NKo': (char) => char >= 0x07C0 && char <= 0x07FF,
     // 'Samaritan': (char) => char >= 0x0800 && char <= 0x083F,
     // 'Mandaic': (char) => char >= 0x0840 && char <= 0x085F,
-    // 'Syriac Supplement': (char) => char >= 0x0860 && char <= 0x086F,
+    'Syriac Supplement': (char) => char >= 0x0860 && char <= 0x086F,
     'Arabic Extended-B': (char) => char >= 0x0870 && char <= 0x089F,
     'Arabic Extended-A': (char) => char >= 0x08A0 && char <= 0x08FF,
     // 'Devanagari': (char) => char >= 0x0900 && char <= 0x097F,
@@ -53,7 +53,7 @@ export const unicodeBlockLookup: UnicodeBlockLookup = {
     // 'Buhid': (char) => char >= 0x1740 && char <= 0x175F,
     // 'Tagbanwa': (char) => char >= 0x1760 && char <= 0x177F,
     'Khmer': (char) => char >= 0x1780 && char <= 0x17FF,
-    // 'Mongolian': (char) => char >= 0x1800 && char <= 0x18AF,
+    'Mongolian': (char) => char >= 0x1800 && char <= 0x18AF,
     'Unified Canadian Aboriginal Syllabics Extended': (char) => char >= 0x18B0 && char <= 0x18FF,
     // 'Limbu': (char) => char >= 0x1900 && char <= 0x194F,
     // 'Tai Le': (char) => char >= 0x1950 && char <= 0x197F,
@@ -199,7 +199,7 @@ export const unicodeBlockLookup: UnicodeBlockLookup = {
     // 'Hatran': (char) => char >= 0x108E0 && char <= 0x108FF,
     // 'Phoenician': (char) => char >= 0x10900 && char <= 0x1091F,
     // 'Lydian': (char) => char >= 0x10920 && char <= 0x1093F,
-    // 'Meroitic Hieroglyphs': (char) => char >= 0x10980 && char <= 0x1099F,
+    'Meroitic Hieroglyphs': (char) => char >= 0x10980 && char <= 0x1099F,
     // 'Meroitic Cursive': (char) => char >= 0x109A0 && char <= 0x109FF,
     // 'Kharoshthi': (char) => char >= 0x10A00 && char <= 0x10A5F,
     // 'Old South Arabian': (char) => char >= 0x10A60 && char <= 0x10A7F,
@@ -218,7 +218,7 @@ export const unicodeBlockLookup: UnicodeBlockLookup = {
     // 'Arabic Extended-C': (char) => char >= 0x10EC0 && char <= 0x10EFF,
     // 'Old Sogdian': (char) => char >= 0x10F00 && char <= 0x10F2F,
     // 'Sogdian': (char) => char >= 0x10F30 && char <= 0x10F6F,
-    // 'Old Uyghur': (char) => char >= 0x10F70 && char <= 0x10FAF,
+    'Old Uyghur': (char) => char >= 0x10F70 && char <= 0x10FAF,
     // 'Chorasmian': (char) => char >= 0x10FB0 && char <= 0x10FDF,
     // 'Elymaic': (char) => char >= 0x10FE0 && char <= 0x10FFF,
     // 'Brahmi': (char) => char >= 0x11000 && char <= 0x1107F,
@@ -235,19 +235,19 @@ export const unicodeBlockLookup: UnicodeBlockLookup = {
     // 'Tulu-Tigalari': (char) => char >= 0x11380 && char <= 0x113FF,
     // 'Newa': (char) => char >= 0x11400 && char <= 0x1147F,
     // 'Tirhuta': (char) => char >= 0x11480 && char <= 0x114DF,
-    // 'Siddham': (char) => char >= 0x11580 && char <= 0x115FF,
+    'Siddham': (char) => char >= 0x11580 && char <= 0x115FF,
     // 'Modi': (char) => char >= 0x11600 && char <= 0x1165F,
-    // 'Mongolian Supplement': (char) => char >= 0x11660 && char <= 0x1167F,
+    'Mongolian Supplement': (char) => char >= 0x11660 && char <= 0x1167F,
     // 'Takri': (char) => char >= 0x11680 && char <= 0x116CF,
     // 'Myanmar Extended-C': (char) => char >= 0x116D0 && char <= 0x116FF,
     // 'Ahom': (char) => char >= 0x11700 && char <= 0x1174F,
     // 'Dogra': (char) => char >= 0x11800 && char <= 0x1184F,
     // 'Warang Citi': (char) => char >= 0x118A0 && char <= 0x118FF,
     // 'Dives Akuru': (char) => char >= 0x11900 && char <= 0x1195F,
     // 'Nandinagari': (char) => char >= 0x119A0 && char <= 0x119FF,
-    // 'Zanabazar Square': (char) => char >= 0x11A00 && char <= 0x11A4F,
-    // 'Soyombo': (char) => char >= 0x11A50 && char <= 0x11AAF,
-    // 'Unified Canadian Aboriginal Syllabics Extended-A': (char) => char >= 0x11AB0 && char <= 0x11ABF,
+    'Zanabazar Square': (char) => char >= 0x11A00 && char <= 0x11A4F,
+    'Soyombo': (char) => char >= 0x11A50 && char <= 0x11AAF,
+    'Unified Canadian Aboriginal Syllabics Extended-A': (char) => char >= 0x11AB0 && char <= 0x11ABF,
     // 'Pau Cin Hau': (char) => char >= 0x11AC0 && char <= 0x11AFF,
     // 'Devanagari Extended-A': (char) => char >= 0x11B00 && char <= 0x11B5F,
     // 'Sunuwar': (char) => char >= 0x11BC0 && char <= 0x11BFF,
@@ -263,10 +263,10 @@ export const unicodeBlockLookup: UnicodeBlockLookup = {
     // 'Cuneiform Numbers and Punctuation': (char) => char >= 0x12400 && char <= 0x1247F,
     // 'Early Dynastic Cuneiform': (char) => char >= 0x12480 && char <= 0x1254F,
     // 'Cypro-Minoan': (char) => char >= 0x12F90 && char <= 0x12FFF,
-    // 'Egyptian Hieroglyphs': (char) => char >= 0x13000 && char <= 0x1342F,
-    // 'Egyptian Hieroglyph Format Controls': (char) => char >= 0x13430 && char <= 0x1345F,
-    // 'Egyptian Hieroglyphs Extended-A': (char) => char >= 0x13460 && char <= 0x143FF,
-    // 'Anatolian Hieroglyphs': (char) => char >= 0x14400 && char <= 0x1467F,
+    'Egyptian Hieroglyphs': (char) => char >= 0x13000 && char <= 0x1342F,
+    'Egyptian Hieroglyph Format Controls': (char) => char >= 0x13430 && char <= 0x1345F,
+    'Egyptian Hieroglyphs Extended-A': (char) => char >= 0x13460 && char <= 0x143FF,
+    'Anatolian Hieroglyphs': (char) => char >= 0x14400 && char <= 0x1467F,
     // 'Gurung Khema': (char) => char >= 0x16100 && char <= 0x1613F,
     // 'Bamum Supplement': (char) => char >= 0x16800 && char <= 0x16A3F,
     // 'Mro': (char) => char >= 0x16A40 && char <= 0x16A6F,
@@ -276,29 +276,29 @@ export const unicodeBlockLookup: UnicodeBlockLookup = {
     // 'Kirat Rai': (char) => char >= 0x16D40 && char <= 0x16D7F,
     // 'Medefaidrin': (char) => char >= 0x16E40 && char <= 0x16E9F,
     // 'Miao': (char) => char >= 0x16F00 && char <= 0x16F9F,
-    // 'Ideographic Symbols and Punctuation': (char) => char >= 0x16FE0 && char <= 0x16FFF,
-    // 'Tangut': (char) => char >= 0x17000 && char <= 0x187FF,
-    // 'Tangut Components': (char) => char >= 0x18800 && char <= 0x18AFF,
-    // 'Khitan Small Script': (char) => char >= 0x18B00 && char <= 0x18CFF,
-    // 'Tangut Supplement': (char) => char >= 0x18D00 && char <= 0x18D7F,
-    // 'Kana Extended-B': (char) => char >= 0x1AFF0 && char <= 0x1AFFF,
-    // 'Kana Supplement': (char) => char >= 0x1B000 && char <= 0x1B0FF,
-    // 'Kana Extended-A': (char) => char >= 0x1B100 && char <= 0x1B12F,
-    // 'Small Kana Extension': (char) => char >= 0x1B130 && char <= 0x1B16F,
-    // 'Nushu': (char) => char >= 0x1B170 && char <= 0x1B2FF,
-    // 'Duployan': (char) => char >= 0x1BC00 && char <= 0x1BC9F,
+    'Ideographic Symbols and Punctuation': (char) => char >= 0x16FE0 && char <= 0x16FFF,
+    'Tangut': (char) => char >= 0x17000 && char <= 0x187FF,
+    'Tangut Components': (char) => char >= 0x18800 && char <= 0x18AFF,
+    'Khitan Small Script': (char) => char >= 0x18B00 && char <= 0x18CFF,
+    'Tangut Supplement': (char) => char >= 0x18D00 && char <= 0x18D7F,
+    'Kana Extended-B': (char) => char >= 0x1AFF0 && char <= 0x1AFFF,
+    'Kana Supplement': (char) => char >= 0x1B000 && char <= 0x1B0FF,
+    'Kana Extended-A': (char) => char >= 0x1B100 && char <= 0x1B12F,
+    'Small Kana Extension': (char) => char >= 0x1B130 && char <= 0x1B16F,
+    'Nushu': (char) => char >= 0x1B170 && char <= 0x1B2FF,
+    'Duployan': (char) => char >= 0x1BC00 && char <= 0x1BC9F,
     // 'Shorthand Format Controls': (char) => char >= 0x1BCA0 && char <= 0x1BCAF,
     // 'Symbols for Legacy Computing Supplement': (char) => char >= 0x1CC00 && char <= 0x1CEBF,
-    // 'Znamenny Musical Notation': (char) => char >= 0x1CF00 && char <= 0x1CFCF,
-    // 'Byzantine Musical Symbols': (char) => char >= 0x1D000 && char <= 0x1D0FF,
-    // 'Musical Symbols': (char) => char >= 0x1D100 && char <= 0x1D1FF,
+    'Znamenny Musical Notation': (char) => char >= 0x1CF00 && char <= 0x1CFCF,
+    'Byzantine Musical Symbols': (char) => char >= 0x1D000 && char <= 0x1D0FF,
+    'Musical Symbols': (char) => char >= 0x1D100 && char <= 0x1D1FF,
     // 'Ancient Greek Musical Notation': (char) => char >= 0x1D200 && char <= 0x1D24F,
     // 'Kaktovik Numerals': (char) => char >= 0x1D2C0 && char <= 0x1D2DF,
-    // 'Mayan Numerals': (char) => char >= 0x1D2E0 && char <= 0x1D2FF,
-    // 'Tai Xuan Jing Symbols': (char) => char >= 0x1D300 && char <= 0x1D35F,
-    // 'Counting Rod Numerals': (char) => char >= 0x1D360 && char <= 0x1D37F,
+    'Mayan Numerals': (char) => char >= 0x1D2E0 && char <= 0x1D2FF,
+    'Tai Xuan Jing Symbols': (char) => char >= 0x1D300 && char <= 0x1D35F,
+    'Counting Rod Numerals': (char) => char >= 0x1D360 && char <= 0x1D37F,
     // 'Mathematical Alphanumeric Symbols': (char) => char >= 0x1D400 && char <= 0x1D7FF,
-    // 'Sutton SignWriting': (char) => char >= 0x1D800 && char <= 0x1DAAF,
+    'Sutton SignWriting': (char) => char >= 0x1D800 && char <= 0x1DAAF,
     // 'Latin Extended-G': (char) => char >= 0x1DF00 && char <= 0x1DFFF,
     // 'Glagolitic Supplement': (char) => char >= 0x1E000 && char <= 0x1E02F,
     // 'Cyrillic Extended-D': (char) => char >= 0x1E030 && char <= 0x1E08F,
@@ -312,22 +312,22 @@ export const unicodeBlockLookup: UnicodeBlockLookup = {
     // 'Adlam': (char) => char >= 0x1E900 && char <= 0x1E95F,
     // 'Indic Siyaq Numbers': (char) => char >= 0x1EC70 && char <= 0x1ECBF,
     // 'Ottoman Siyaq Numbers': (char) => char >= 0x1ED00 && char <= 0x1ED4F,
-    // 'Arabic Mathematical Alphabetic Symbols': (char) => char >= 0x1EE00 && char <= 0x1EEFF,
-    // 'Mahjong Tiles': (char) => char >= 0x1F000 && char <= 0x1F02F,
-    // 'Domino Tiles': (char) => char >= 0x1F030 && char <= 0x1F09F,
-    // 'Playing Cards': (char) => char >= 0x1F0A0 && char <= 0x1F0FF,
-    // 'Enclosed Alphanumeric Supplement': (char) => char >= 0x1F100 && char <= 0x1F1FF,
+    'Arabic Mathematical Alphabetic Symbols': (char) => char >= 0x1EE00 && char <= 0x1EEFF,
+    'Mahjong Tiles': (char) => char >= 0x1F000 && char <= 0x1F02F,
+    'Domino Tiles': (char) => char >= 0x1F030 && char <= 0x1F09F,
+    'Playing Cards': (char) => char >= 0x1F0A0 && char <= 0x1F0FF,
+    'Enclosed Alphanumeric Supplement': (char) => char >= 0x1F100 && char <= 0x1F1FF,
     'Enclosed Ideographic Supplement': (char) => char >= 0x1F200 && char <= 0x1F2FF,
-    // 'Miscellaneous Symbols and Pictographs': (char) => char >= 0x1F300 && char <= 0x1F5FF,
-    // 'Emoticons': (char) => char >= 0x1F600 && char <= 0x1F64F,
-    // 'Ornamental Dingbats': (char) => char >= 0x1F650 && char <= 0x1F67F,
-    // 'Transport and Map Symbols': (char) => char >= 0x1F680 && char <= 0x1F6FF,
-    // 'Alchemical Symbols': (char) => char >= 0x1F700 && char <= 0x1F77F,
-    // 'Geometric Shapes Extended': (char) => char >= 0x1F780 && char <= 0x1F7FF,
+    'Miscellaneous Symbols and Pictographs': (char) => char >= 0x1F300 && char <= 0x1F5FF,
+    'Emoticons': (char) => char >= 0x1F600 && char <= 0x1F64F,
+    'Ornamental Dingbats': (char) => char >= 0x1F650 && char <= 0x1F67F,
+    'Transport and Map Symbols': (char) => char >= 0x1F680 && char <= 0x1F6FF,
+    'Alchemical Symbols': (char) => char >= 0x1F700 && char <= 0x1F77F,
+    'Geometric Shapes Extended': (char) => char >= 0x1F780 && char <= 0x1F7FF,
     // 'Supplemental Arrows-C': (char) => char >= 0x1F800 && char <= 0x1F8FF,
-    // 'Supplemental Symbols and Pictographs': (char) => char >= 0x1F900 && char <= 0x1F9FF,
-    // 'Chess Symbols': (char) => char >= 0x1FA00 && char <= 0x1FA6F,
-    // 'Symbols and Pictographs Extended-A': (char) => char >= 0x1FA70 && char <= 0x1FAFF,
+    'Supplemental Symbols and Pictographs': (char) => char >= 0x1F900 && char <= 0x1F9FF,
+    'Chess Symbols': (char) => char >= 0x1FA00 && char <= 0x1FA6F,
+    'Symbols and Pictographs Extended-A': (char) => char >= 0x1FA70 && char <= 0x1FAFF,
     // 'Symbols for Legacy Computing': (char) => char >= 0x1FB00 && char <= 0x1FBFF,
     'CJK Unified Ideographs Extension B': (char) => char >= 0x20000 && char <= 0x2A6DF,
     'CJK Unified Ideographs Extension C': (char) => char >= 0x2A700 && char <= 0x2B73F,
@@ -337,9 +337,9 @@ export const unicodeBlockLookup: UnicodeBlockLookup = {
     'CJK Unified Ideographs Extension I': (char) => char >= 0x2EBF0 && char <= 0x2EE5F,
     'CJK Unified Ideographs Extension G': (char) => char >= 0x30000 && char <= 0x3134F,
     'CJK Unified Ideographs Extension H': (char) => char >= 0x31350 && char <= 0x323AF,
-    'CJK Compatibility Ideographs Supplement': (char) => char >= 0x2F800 && char <= 0x2FA1F
+    'CJK Compatibility Ideographs Supplement': (char) => char >= 0x2F800 && char <= 0x2FA1F,
     // 'Tags': (char) => char >= 0xE0000 && char <= 0xE007F,
     // 'Variation Selectors Supplement': (char) => char >= 0xE0100 && char <= 0xE01EF,
-    // 'Supplementary Private Use Area-A': (char) => char >= 0xF0000 && char <= 0xFFFFF,
-    // 'Supplementary Private Use Area-B': (char) => char >= 0x100000 && char <= 0x10FFFF,
+    'Supplementary Private Use Area-A': (char) => char >= 0xF0000 && char <= 0xFFFFF,
+    'Supplementary Private Use Area-B': (char) => char >= 0x100000 && char <= 0x10FFFF
 };