Unicode 15.1 (#795)

cisco · Jan 24, 2024 · 0fbd922 · 0fbd922
1 parent 2f51156
commit 0fbd922
Show file tree

Hide file tree

Showing 17 changed files with 1,804 additions and 1,291 deletions.
diff --git a/mats/5_4.ms b/mats/5_4.ms
@@ -1327,7 +1327,7 @@
       (if (not (= n (length chars)))
           (begin (display " but expected ")
                  (write n)
-                 (display " in Unicode 15.0")))
+                 (display " in Unicode 15.1")))
       (newline)
       0)
     (define-syntax test
@@ -1459,6 +1459,7 @@
   (test cat1 (char-general-category #\a) => 'Ll)
   (test cat2 (char-general-category #\space) => 'Zs)
   (test cat3 (char-general-category (integer->char #x10FFFF)) => 'Cn)
+  (test cat4 (char-general-category #\x31EF) => 'So) ; Unicode 15.1
 
   (test alpha1 (char-alphabetic? #\a) => #t)
   (test numer1 (char-numeric? #\1) => #t)

diff --git a/release_notes/release_notes.stex b/release_notes/release_notes.stex
@@ -113,6 +113,11 @@ Online versions of both books can be found at
 %-----------------------------------------------------------------------------
 \section{Functionality Changes}\label{section:functionality}
 
+\subsection{Unicode 15.1 support (9.9.9)}
+
+The character sets, character classes, and word-breaking algorithms for character, string,
+and Unicode-related bytevector operations have now been updated to Unicode 15.1.
+
 \subsection{New supported platforms and portable bytecode (9.9.9)}
 
 AArch64 (64-bit Arm), RV64G (64-bit RISC-V), and LoongArch64 architectures are

diff --git a/unicode/Makefile b/unicode/Makefile
@@ -1,6 +1,11 @@
-Scheme=../bin/scheme
+Scheme=../bin/zuo .. run
 
-doit: unicode-char-cases.ss unicode-charinfo.ss
+doit:
+	$(MAKE) update
+	$(MAKE) unicode-char-cases.ss unicode-charinfo.ss
+
+update:
+	./get-UNIDATA
 
 unicode-char-cases.ss: extract-char-cases.ss extract-common.ss unicode-data.ss
 	echo | $(Scheme) -q extract-char-cases.ss
@@ -12,10 +17,11 @@ unicode-char-cases.ss: \
  UNIDATA/CompositionExclusions.txt\
  UNIDATA/UnicodeData.txt\
  UNIDATA/CaseFolding.txt\
- UNIDATA/SpecialCasing.txt
+ UNIDATA/SpecialCasing.txt\
+ UNIDATA/GraphemeBreakProperty.txt
 
 unicode-charinfo.ss: \
  UNIDATA/UnicodeData.txt\
  UNIDATA/WordBreakProperty.txt\
- UNIDATA/PropList.txt
-
+ UNIDATA/PropList.txt\
+ UNIDATA/emoji-data.txt
diff --git a/unicode/ReadMe b/unicode/ReadMe
@@ -1,14 +1,2 @@
-To rebuild unicode-char-cases.ss and unicode-charinfo.ss, download into
-./UNIDATA the following files:
-
-http://www.unicode.org/Public/UCD/latest/ucd/CompositionExclusions.txt
-http://www.unicode.org/Public/UCD/latest/ucd/UnicodeData.txt
-http://www.unicode.org/Public/UCD/latest/ucd/CaseFolding.txt
-http://www.unicode.org/Public/UCD/latest/ucd/SpecialCasing.txt
-http://www.unicode.org/Public/UCD/latest/ucd/auxiliary/WordBreakProperty.txt
-http://www.unicode.org/Public/UCD/latest/ucd/PropList.txt
-http://www.unicode.org/Public/UCD/latest/ucd/NormalizationTest.txt
-http://www.unicode.org/Public/UCD/latest/ucd/auxiliary/GraphemeBreakProperty.txt
-http://www.unicode.org/Public/UCD/latest/ucd/emoji/emoji-data.txt
-
-Then run 'make'.
+To download the latest Unicode files and rebuild unicode-char-cases.ss and
+unicode-charinfo.ss, run 'make'.
diff --git a/unicode/UNIDATA/CaseFolding.txt b/unicode/UNIDATA/CaseFolding.txt
@@ -1,6 +1,6 @@
-# CaseFolding-15.0.0.txt
-# Date: 2022-02-02, 23:35:35 GMT
-# © 2022 Unicode®, Inc.
+# CaseFolding-15.1.0.txt
+# Date: 2023-05-12, 21:53:10 GMT
+# © 2023 Unicode®, Inc.
 # Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
 # For terms of use, see https://www.unicode.org/terms_of_use.html
 #
@@ -929,6 +929,7 @@
 1FCC; S; 1FC3; # GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI
 1FD2; F; 03B9 0308 0300; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND VARIA
 1FD3; F; 03B9 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
+1FD3; S; 0390; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
 1FD6; F; 03B9 0342; # GREEK SMALL LETTER IOTA WITH PERISPOMENI
 1FD7; F; 03B9 0308 0342; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND PERISPOMENI
 1FD8; C; 1FD0; # GREEK CAPITAL LETTER IOTA WITH VRACHY
@@ -937,6 +938,7 @@
 1FDB; C; 1F77; # GREEK CAPITAL LETTER IOTA WITH OXIA
 1FE2; F; 03C5 0308 0300; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND VARIA
 1FE3; F; 03C5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA
+1FE3; S; 03B0; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA
 1FE4; F; 03C1 0313; # GREEK SMALL LETTER RHO WITH PSILI
 1FE6; F; 03C5 0342; # GREEK SMALL LETTER UPSILON WITH PERISPOMENI
 1FE7; F; 03C5 0308 0342; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND PERISPOMENI
@@ -1328,6 +1330,7 @@ FB02; F; 0066 006C; # LATIN SMALL LIGATURE FL
 FB03; F; 0066 0066 0069; # LATIN SMALL LIGATURE FFI
 FB04; F; 0066 0066 006C; # LATIN SMALL LIGATURE FFL
 FB05; F; 0073 0074; # LATIN SMALL LIGATURE LONG S T
+FB05; S; FB06; # LATIN SMALL LIGATURE LONG S T
 FB06; F; 0073 0074; # LATIN SMALL LIGATURE ST
 FB13; F; 0574 0576; # ARMENIAN SMALL LIGATURE MEN NOW
 FB14; F; 0574 0565; # ARMENIAN SMALL LIGATURE MEN ECH

diff --git a/unicode/UNIDATA/CompositionExclusions.txt b/unicode/UNIDATA/CompositionExclusions.txt
@@ -1,6 +1,6 @@
-# CompositionExclusions-15.0.0.txt
-# Date: 2022-05-03, 18:50:00 GMT [KW, LI]
-# © 2022 Unicode®, Inc.
+# CompositionExclusions-15.1.0.txt
+# Date: 2023-01-05
+# © 2023 Unicode®, Inc.
 # For terms of use, see https://www.unicode.org/terms_of_use.html
 #
 # Unicode Character Database