[ruby-core:109950] [Ruby master Bug#19007] Unicode tables differences from Unicode.org 14.0 data and removed properties since 13.0

Issue #19007 has been updated by nobu (Nobuyoshi Nakada).


https://github.com/nobu/ruby/tree/emoji

----------------------------------------
Bug #19007: Unicode tables differences from Unicode.org 14.0 data and removed properties since 13.0
https://bugs.ruby-lang.org/issues/19007#change-99198

* Author: nobu (Nobuyoshi Nakada)
* Status: Open
* Priority: Normal
* Assignee: duerst (Martin D端rst)
* Target version: 3.2
* ruby -v: 3.2.0 6898984f1cd
* Backport: 2.7: DONTNEED, 3.0: DONTNEED, 3.1: DONTNEED
----------------------------------------
I found the header in Unicode Emoji 14.0 data files had changed slightly (and again at 15.0), but `enc/unicode/case-folding.rb` didn't follow it.
Then I fixed it and rebuilt the headers under `enc/unicode/14.0.0`, `name2ctype.h` had diffences from the master, as bellow.

`CR_Lower`, `CR_Cased` and `CR_Other_Lowercase` just seem misses in the previous operation, and no problems.

But U+11720..U+11721 in `CR_Grapheme_Cluster_Break_SpacingMark` is absent in the original data of the Unicode.org.
According to @naruse's investigation, it was removed at the commit [Update to Unicode 14.0.0], while U+11720 is still SpacingMark in the latest https://www.unicode.org/reports/tr29/.

[Update to Unicode 14.0.0]: https://github.com/latex3/unicode-data/commit/5570040ac8a30e2c2ca4912d415ecaa0498fa23a#diff-1e957b94de10ea96d32a338c005b1f05788af458cf335fc92683bc297e53ed94L582

```diff
diff --git a/enc/unicode/14.0.0/name2ctype.h b/enc/unicode/14.0.0/name2ctype.h
index 99a3eeca190..f49e5cd7273 100644
--- a/enc/unicode/14.0.0/name2ctype.h
+++ b/enc/unicode/14.0.0/name2ctype.h
@@ -1565,7 +1565,7 @@ static const OnigCodePoint CR_Graph[] = {
 
 /* 'Lower': [[:Lower:]] */
 static const OnigCodePoint CR_Lower[] = {
-	664,
+	668,
 	0x0061, 0x007a,
 	0x00aa, 0x00aa,
 	0x00b5, 0x00b5,
@@ -2196,6 +2196,10 @@ static const OnigCodePoint CR_Lower[] = {
 	0x105a3, 0x105b1,
 	0x105b3, 0x105b9,
 	0x105bb, 0x105bc,
+	0x10780, 0x10780,
+	0x10783, 0x10785,
+	0x10787, 0x107b0,
+	0x107b2, 0x107ba,
 	0x10cc0, 0x10cf2,
 	0x118c0, 0x118df,
 	0x16e60, 0x16e7f,
@@ -12651,7 +12655,7 @@ static const OnigCodePoint CR_Math[] = {
 
 /* 'Cased': Derived Property */
 static const OnigCodePoint CR_Cased[] = {
-	151,
+	155,
 	0x0041, 0x005a,
 	0x0061, 0x007a,
 	0x00aa, 0x00aa,
@@ -12763,6 +12767,10 @@ static const OnigCodePoint CR_Cased[] = {
 	0x105a3, 0x105b1,
 	0x105b3, 0x105b9,
 	0x105bb, 0x105bc,
+	0x10780, 0x10780,
+	0x10783, 0x10785,
+	0x10787, 0x107b0,
+	0x107b2, 0x107ba,
 	0x10c80, 0x10cb2,
 	0x10cc0, 0x10cf2,
 	0x118a0, 0x118df,
@@ -22615,7 +22623,7 @@ static const OnigCodePoint CR_Extender[] = {
 
 /* 'Other_Lowercase': Binary Property */
 static const OnigCodePoint CR_Other_Lowercase[] = {
-	20,
+	24,
 	0x00aa, 0x00aa,
 	0x00ba, 0x00ba,
 	0x02b0, 0x02b8,
@@ -22636,6 +22644,10 @@ static const OnigCodePoint CR_Other_Lowercase[] = {
 	0xa770, 0xa770,
 	0xa7f8, 0xa7f9,
 	0xab5c, 0xab5f,
+	0x10780, 0x10780,
+	0x10783, 0x10785,
+	0x10787, 0x107b0,
+	0x107b2, 0x107ba,
 }; /* CR_Other_Lowercase */
 
 /* 'Other_Uppercase': Binary Property */
@@ -37049,7 +37061,7 @@ static const OnigCodePoint CR_Grapheme_Cluster_Break_Extend[] = {
 
 /* 'Grapheme_Cluster_Break_SpacingMark': Grapheme_Cluster_Break=SpacingMark */
 static const OnigCodePoint CR_Grapheme_Cluster_Break_SpacingMark[] = {
-	161,
+	160,
 	0x0903, 0x0903,
 	0x093b, 0x093b,
 	0x093e, 0x0940,
@@ -37183,7 +37195,6 @@ static const OnigCodePoint CR_Grapheme_Cluster_Break_SpacingMark[] = {
 	0x116ac, 0x116ac,
 	0x116ae, 0x116af,
 	0x116b6, 0x116b6,
-	0x11720, 0x11721,
 	0x11726, 0x11726,
 	0x1182c, 0x1182e,
 	0x11838, 0x11838,
```



-- 
https://bugs.ruby-lang.org/

Unsubscribe: <mailto:[e-mail]?subject=unsubscribe>
<http://lists.ruby-lang.org/cgi-bin/mailman/options/ruby-core>