Merge remote-tracking branch 'la-vache/main' into sentence-terminal-d…

…andas
unicode-org · May 6, 2024 · e49961e · e49961e
2 parents a48c0d4 + a5c5716
commit e49961e
Show file tree

Hide file tree

Showing 143 changed files with 63,577 additions and 44,690 deletions.
diff --git a/c/uca/sifter/unidata.txt b/c/uca/sifter/unidata.txt
diff --git a/c/uca/sifter/unisift.c b/c/uca/sifter/unisift.c
@@ -53,6 +53,8 @@
  *               with multiple secondary decompositions in the input data.
  *   2024-Feb-20 Tweak end of block range for the Tangut Supplement block
  *               to match change in Unicode 14.0.
+ *   2024-Mar-29 Change main sift to treat non-Nd numerics as non-variables.
+ *   2024-Apr-05 Fixed botched edit in comment.
  */
 
 /*
@@ -177,15 +179,15 @@
 #define PATHNAMELEN (256)
 #define LONGESTARG  (256)
 
-static char versionString[] = "Sifter version 16.0.0d3, 2024-02-20\n";
+static char versionString[] = "Sifter version 16.0.0d4, 2024-04-05\n";
 
 static char unidatafilename[] = "unidata-16.0.0.txt";
 static char allkeysfilename[] = "allkeys-16.0.0.txt";
 static char decompsfilename[] = "decomps-16.0.0.txt";
 
 static char versionstring[] = "@version 16.0.0\n\n";
 
-#define COPYRIGHTYEAR (2023)
+#define COPYRIGHTYEAR (2024)
 
 #define defaultInfile "unidata.txt"
 
@@ -4454,17 +4456,22 @@ int doTrace;
             }
             else
 /*
- * Numerics with values outside the range 0..9 are treated just
- * like miscellaneous symbols.
+ * 2024-03-29 note: Prior to this date, numerics other than
+ * decimals and others with values 0..9 were treated as
+ * symbols and weighted as variables. Following agreement about
+ * converging DUCET with the CLDR default tailoring, they
+ * have been moved down in the input file and are treated as
+ * non-variables, weighted *after* the main set of 0..9
+ * primary weights for numbers.
  */
             {
                 SIFT_TRACE(p);
                 p->symbolBase = uvalue;
                 p->level1 = getNextPrimary( 0 );
                 p->level2 = FIRST_SECONDARY;
                 p->level3 = FIRST_TERTIARY;
-                p->variable = 1;
-                numIgnorables++;
+                // p->variable = 1;
+                // numIgnorables++;
             }
         }
 /*

diff --git a/docs/emoji/ordering.md b/docs/emoji/ordering.md
@@ -0,0 +1,17 @@
+# UTS #51
+
+## Ordering
+
+Occasionally the default emoji ordering needs to be changed. The process is mechanically
+straightforward:
+
+1.  Open [emojiOrdering.txt](https://github.com/unicode-org/unicodetools/blob/main/unicodetools/org/unicode/tools/emoji/emojiOrdering.txt),
+2.  Reorder the emoji in question, moving them between groups as necessary.
+3.  Follow the process to generate emoji described in generate-emoji.md.
+    1.  Check [emoji-test.txt](https://github.com/unicode-org/unicodetools/blob/main/unicodetools/data/emoji/dev/emoji-test.txt)
+        to make sure the changes are reflected there.
+    2.  Check the generated emoji-ordering.html to make sure the changes are reflected there as well.
+    3.  Note that there may also be minor changes to other pages, for example emoji-proposals.html
+        uses the order when listing multiple emoji for a single proposal.
+
+The final step is to provide the updated data to CLDR, instructions TBD.
diff --git a/unicodetools/data/emoji/dev/ReadMe.txt b/unicodetools/data/emoji/dev/ReadMe.txt
@@ -1,7 +1,7 @@
 # Unicode Emoji
 # © COPY_YEAR 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
+# For terms of use and license, see https://www.unicode.org/terms_of_use.html
 
 This directory contains PUB_STATUS data files for Unicode Emoji, Version EMOJI_VER
 

diff --git a/unicodetools/data/emoji/dev/emoji-sequences.txt b/unicodetools/data/emoji/dev/emoji-sequences.txt
@@ -1,8 +1,8 @@
 # emoji-sequences.txt
-# Date: 2024-01-16, 16:25:20 GMT
+# Date: 2024-05-01, 21:25:24 GMT
 # © 2024 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
+# For terms of use and license, see https://www.unicode.org/terms_of_use.html
 #
 # Emoji Sequence Data for UTS #51
 # Version: 16.0

diff --git a/unicodetools/data/emoji/dev/emoji-test.txt b/unicodetools/data/emoji/dev/emoji-test.txt
@@ -1,8 +1,8 @@
 # emoji-test.txt
-# Date: 2024-01-16, 16:25:20 GMT
+# Date: 2024-05-01, 21:25:24 GMT
 # © 2024 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
+# For terms of use and license, see https://www.unicode.org/terms_of_use.html
 #
 # Emoji Keyboard/Display Test Data for UTS #51
 # Version: 16.0

diff --git a/unicodetools/data/emoji/dev/emoji-zwj-sequences.txt b/unicodetools/data/emoji/dev/emoji-zwj-sequences.txt
@@ -1,8 +1,8 @@
 # emoji-zwj-sequences.txt
-# Date: 2024-01-11, 17:46:08 GMT
+# Date: 2024-05-01, 21:25:24 GMT
 # © 2024 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
+# For terms of use and license, see https://www.unicode.org/terms_of_use.html
 #
 # Emoji ZWJ Sequences for UTS #51
 # Version: 16.0

diff --git a/unicodetools/data/emoji/dev/internal/emoji-internal.txt b/unicodetools/data/emoji/dev/internal/emoji-internal.txt
@@ -1,8 +1,8 @@
 # emoji-internal.txt
-# Date: 2024-01-11, 17:46:06 GMT
+# Date: 2024-05-01, 21:25:22 GMT
 # © 2024 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
+# For terms of use and license, see https://www.unicode.org/terms_of_use.html
 #
 # Emoji Data Internal for UTS #51
 # Version: 16.0

diff --git a/unicodetools/data/emoji/dev/internal/emoji-sequences-nonrgi.txt b/unicodetools/data/emoji/dev/internal/emoji-sequences-nonrgi.txt
@@ -1,8 +1,8 @@
 # emoji-sequences-nonrgi.txt
-# Date: 2024-01-11, 17:46:08 GMT
+# Date: 2024-05-01, 21:25:24 GMT
 # © 2024 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
+# For terms of use and license, see https://www.unicode.org/terms_of_use.html
 #
 # Emoji Sequence Data — Non-RGI for UTS #51
 # Version: 16.0

diff --git a/unicodetools/data/emoji/dev/internal/emoji-zwj-sequences-nonrgi.txt b/unicodetools/data/emoji/dev/internal/emoji-zwj-sequences-nonrgi.txt
@@ -1,8 +1,8 @@
 # emoji-zwj-sequences-nonrgi.txt
-# Date: 2024-01-11, 17:46:08 GMT
+# Date: 2024-05-01, 21:25:24 GMT
 # © 2024 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
+# For terms of use and license, see https://www.unicode.org/terms_of_use.html
 #
 # Emoji ZWJ Sequences — Non-RGI for UTS #51
 # Version: 16.0