updated to unicode 16.0.0 (bnoordhuis) - updated test262

Author: Fabrice Bellard

TODO

@@ -62,5 +62,6 @@ Optimization ideas:
 Test262o:   0/11262 errors, 463 excluded
 Test262o commit: 7da91bceb9ce7613f87db47ddd1292a2dda58b42 (es5-tests branch)
 
-Result: 8/76947 errors, 1497 excluded, 8117 skipped
-Test262 commit: 6cbb6da9473c56d95358d8e679c5a6d2b4574efb
+Result: 169/76838 errors, 3112 excluded, 7010 skipped
+Test262 commit: 56e77d6325067a545ea7e8ff5be5d9284334e33c
+

libunicode-table.h

@@ -61,7 +61,6 @@ Array.fromAsync=skip
 Array.prototype.at
 Array.prototype.flat
 Array.prototype.flatMap
-Array.prototype.flatten
 Array.prototype.includes
 Array.prototype.values
 ArrayBuffer
@@ -70,9 +69,11 @@ arrow-function
 async-functions
 async-iteration
 Atomics
+Atomics.pause=skip
 Atomics.waitAsync=skip
 BigInt
 caller
+canonical-tz=skip
 change-array-by-copy
 class
 class-fields-private
@@ -83,7 +84,6 @@ class-static-block
 class-static-fields-private
 class-static-fields-public
 class-static-methods-private
-cleanupSome=skip
 coalesce-expression
 computed-property-names
 const
@@ -103,11 +103,12 @@ destructuring-assignment
 destructuring-binding
 dynamic-import
 error-cause
+Error.isError=skip
+explicit-resource-management=skip
 exponentiation
 export-star-as-namespace-from-module
-FinalizationGroup=skip
-FinalizationRegistry.prototype.cleanupSome=skip
 FinalizationRegistry=skip
+Float16Array=skip
 Float32Array
 Float64Array
 for-in-order
@@ -118,19 +119,39 @@ hashbang
 host-gc-required=skip
 import-assertions=skip
 import-attributes=skip
+import-defer=skip
 import.meta
 Int16Array
 Int32Array
 Int8Array
+Intl-enumeration=skip
+intl-normative-optional=skip
+Intl.DateTimeFormat-datetimestyle=skip
+Intl.DateTimeFormat-dayPeriod=skip
+Intl.DateTimeFormat-extend-timezonename=skip
+Intl.DateTimeFormat-formatRange=skip
+Intl.DateTimeFormat-fractionalSecondDigits=skip
+Intl.DisplayNames-v2=skip
+Intl.DisplayNames=skip
+Intl.DurationFormat=skip
+Intl.ListFormat=skip
+Intl.Locale-info=skip
+Intl.Locale=skip
+Intl.NumberFormat-unified=skip
+Intl.NumberFormat-v3=skip
+Intl.RelativeTimeFormat=skip
+Intl.Segmenter=skip
 IsHTMLDDA
 iterator-helpers=skip
+iterator-sequencing=skip
 json-modules=skip
 json-parse-with-source=skip
 json-superset
 legacy-regexp=skip
 let
 logical-assignment-operators
 Map
+Math.sumPrecise=skip
 new.target
 numeric-separator-literal
 object-rest
@@ -141,6 +162,7 @@ Object.is
 optional-catch-binding
 optional-chaining
 Promise
+promise-try=skip
 promise-with-resolvers
 Promise.allSettled
 Promise.any
@@ -155,15 +177,19 @@ regexp-dotall
 regexp-duplicate-named-groups=skip
 regexp-lookbehind
 regexp-match-indices
+regexp-modifiers=skip
 regexp-named-groups
 regexp-unicode-property-escapes
 regexp-v-flag=skip
+RegExp.escape=skip
 resizable-arraybuffer=skip
 rest-parameters
 Set
 set-methods=skip
 ShadowRealm=skip
 SharedArrayBuffer
+source-phase-imports-module-source=skip
+source-phase-imports=skip
 string-trimming
 String.fromCodePoint
 String.prototype.at
@@ -202,6 +228,7 @@ u180e
 Uint16Array
 Uint32Array
 Uint8Array
+uint8array-base64=skip
 Uint8ClampedArray
 WeakMap
 WeakRef=skip
@@ -223,5 +250,8 @@ test262/test/built-ins/ThrowTypeError/unique-per-realm-function-proto.js
 #test262/test/built-ins/RegExp/CharacterClassEscapes/
 #test262/test/built-ins/RegExp/property-escapes/
 
+# frequently broken, sometimes contain engine-dependent tests
+test262/test/staging/
+
 [tests]
 # list test files or use config.testdir

test262.conf

@@ -22,7 +22,7 @@ index 9828b15..4a5919d 100644
 
  /**
 diff --git a/harness/regExpUtils.js b/harness/regExpUtils.js
-index b55f3c6..396bad4 100644
+index b397be0..c197ddc 100644
 --- a/harness/regExpUtils.js
 +++ b/harness/regExpUtils.js
 @@ -6,27 +6,30 @@ description: |
@@ -51,21 +51,20 @@ index b55f3c6..396bad4 100644
    const loneCodePoints = args.loneCodePoints;
    const ranges = args.ranges;
 -  const CHUNK_SIZE = 10000;
--  let result = Reflect.apply(String.fromCodePoint, null, loneCodePoints);
+   let result = String.fromCodePoint.apply(null, loneCodePoints);
 -  for (let i = 0; i < ranges.length; i++) {
--    const range = ranges[i];
--    const start = range[0];
--    const end = range[1];
--    const codePoints = [];
+-    let range = ranges[i];
+-    let start = range[0];
+-    let end = range[1];
+-    let codePoints = [];
 -    for (let length = 0, codePoint = start; codePoint <= end; codePoint++) {
 -      codePoints[length++] = codePoint;
 -      if (length === CHUNK_SIZE) {
--        result += Reflect.apply(String.fromCodePoint, null, codePoints);
+-        result += String.fromCodePoint.apply(null, codePoints);
 -        codePoints.length = length = 0;
 -      }
 -    }
--    result += Reflect.apply(String.fromCodePoint, null, codePoints);
-+  let result = String.fromCodePoint.apply(null, loneCodePoints);
+-    result += String.fromCodePoint.apply(null, codePoints);
 +  for (const [start, end] of ranges) {
 +    result += codePointRange(start, end + 1);
    }

tests/test262.patch

@@ -1,7 +1,7 @@
 #!/bin/sh
 set -e
 
-url="ftp://ftp.unicode.org/Public/15.0.0/ucd"
+url="ftp://ftp.unicode.org/Public/16.0.0/ucd"
 emoji_url="${url}/emoji/emoji-data.txt"
 
 files="CaseFolding.txt DerivedNormalizationProps.txt PropList.txt \

unicode_download.sh

@@ -625,7 +625,7 @@ void parse_derived_core_properties(const char *filename)
             p++;
             p += strspn(p, " \t");
             q = buf;
-            while (*p != '\0' && *p != ' ' && *p != '#' && *p != '\t') {
+            while (*p != '\0' && *p != ' ' && *p != '#' && *p != '\t' && *p != ';') {
                 if ((q - buf) < sizeof(buf) - 1)
                     *q++ = *p;
                 p++;
@@ -1117,6 +1117,24 @@ void find_run_type(TableEntry *te, CCInfo *tab, int code)
             te->ext_data[1] = ci->u_data[1];
             te->ext_data[2] = ci->u_data[2];
             te->ext_len = 3;
+        } else if (ci->u_len == 2 && ci->l_len == 0 && ci->f_len == 1) {
+            // U+FB05 LATIN SMALL LIGATURE LONG S T
+            assert(code == 0xFB05);
+            te->len = 1;
+            te->type = RUN_TYPE_UF_EXT2;
+            te->ext_data[0] = ci->u_data[0];
+            te->ext_data[1] = ci->u_data[1];
+            te->ext_len = 2;
+        } else if (ci->u_len == 3 && ci->l_len == 0 && ci->f_len == 1) {
+            // U+1FD3 GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA or
+            // U+1FE3 GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA
+            assert(code == 0x1FD3 || code == 0x1FE3);
+            te->len = 1;
+            te->type = RUN_TYPE_UF_EXT3;
+            te->ext_data[0] = ci->u_data[0];
+            te->ext_data[1] = ci->u_data[1];
+            te->ext_data[2] = ci->u_data[2];
+            te->ext_len = 3;
         } else {
             printf("unsupported encoding case:\n");
             dump_cc_info(ci, code);

unicode_gen.c

@@ -82,6 +82,7 @@ DEF(Egyptian_Hieroglyphs, "Egyp")
 DEF(Elbasan, "Elba")
 DEF(Elymaic, "Elym")
 DEF(Ethiopic, "Ethi")
+DEF(Garay, "Gara")
 DEF(Georgian, "Geor")
 DEF(Glagolitic, "Glag")
 DEF(Gothic, "Goth")
@@ -90,6 +91,7 @@ DEF(Greek, "Grek")
 DEF(Gujarati, "Gujr")
 DEF(Gunjala_Gondi, "Gong")
 DEF(Gurmukhi, "Guru")
+DEF(Gurung_Khema, "Gukh")
 DEF(Han, "Hani")
 DEF(Hangul, "Hang")
 DEF(Hanifi_Rohingya, "Rohg")
@@ -112,6 +114,7 @@ DEF(Khmer, "Khmr")
 DEF(Khojki, "Khoj")
 DEF(Khitan_Small_Script, "Kits")
 DEF(Khudawadi, "Sind")
+DEF(Kirat_Rai, "Krai")
 DEF(Lao, "Laoo")
 DEF(Latin, "Latn")
 DEF(Lepcha, "Lepc")
@@ -149,6 +152,7 @@ DEF(Nushu, "Nshu")
 DEF(Nyiakeng_Puachue_Hmong, "Hmnp")
 DEF(Ogham, "Ogam")
 DEF(Ol_Chiki, "Olck")
+DEF(Ol_Onal, "Onao")
 DEF(Old_Hungarian, "Hung")
 DEF(Old_Italic, "Ital")
 DEF(Old_North_Arabian, "Narb")
@@ -180,6 +184,7 @@ DEF(Sogdian, "Sogd")
 DEF(Sora_Sompeng, "Sora")
 DEF(Soyombo, "Soyo")
 DEF(Sundanese, "Sund")
+DEF(Sunuwar, "Sunu")
 DEF(Syloti_Nagri, "Sylo")
 DEF(Syriac, "Syrc")
 DEF(Tagalog, "Tglg")
@@ -197,7 +202,9 @@ DEF(Tibetan, "Tibt")
 DEF(Tifinagh, "Tfng")
 DEF(Tirhuta, "Tirh")
 DEF(Tangsa, "Tnsa")
+DEF(Todhri, "Todr")
 DEF(Toto, "Toto")
+DEF(Tulu_Tigalari, "Tutg")
 DEF(Ugaritic, "Ugar")
 DEF(Vai, "Vaii")
 DEF(Vithkuqi, "Vith")
@@ -236,11 +243,13 @@ DEF(Deprecated, "Dep")
 DEF(Diacritic, "Dia")
 DEF(Extender, "Ext")
 DEF(Hex_Digit, "Hex")
+DEF(IDS_Unary_Operator, "IDSU")
 DEF(IDS_Binary_Operator, "IDSB")
 DEF(IDS_Trinary_Operator, "IDST")
 DEF(Ideographic, "Ideo")
 DEF(Join_Control, "Join_C")
 DEF(Logical_Order_Exception, "LOE")
+DEF(Modifier_Combining_Mark, "MCM")
 DEF(Noncharacter_Code_Point, "NChar")
 DEF(Pattern_Syntax, "Pat_Syn")
 DEF(Pattern_White_Space, "Pat_WS")
@@ -279,6 +288,9 @@ DEF(Changes_When_Uppercased, "CWU")
 DEF(Grapheme_Base, "Gr_Base")
 DEF(Grapheme_Extend, "Gr_Ext")
 DEF(ID_Continue, "IDC")
+DEF(ID_Compat_Math_Start, "")
+DEF(ID_Compat_Math_Continue, "")
+DEF(InCB, "")
 DEF(Lowercase, "Lower")
 DEF(Math, "")
 DEF(Uppercase, "Upper")