[src/trunk]: src/share/locale/ctype Add characters in "Emoji & Pictographs" f...

[rin <rin%NetBSD.org@localhost>]

details:   https://anonhg.NetBSD.org/src/rev/98ad703fdbc9
branches:  trunk
changeset: 319559:98ad703fdbc9
user:      rin <rin%NetBSD.org@localhost>
date:      Sun Jun 03 07:54:51 2018 +0000

description:
Add characters in "Emoji & Pictographs" from Unicode 10.0.0:
  http://www.unicode.org/charts/

They are classified as PUNCT, which is historically used for characters other
than blank, alphabetic, or digit ones.

Glyph widths are taken from "East Asian Width":
  https://www.unicode.org/Public/10.0.0/ucd/EastAsianWidth.txt
Characters of "F" or "W" are classified to SWIDTH2, and others are classified
to SWIDTH1, as implicitly done in the previous revisions.

Should address problems like PR bin/53323.

Discussed with soda@. We thank Takuya SHIOZAKI (tshiozak@) for useful comments.

diffstat:

 share/locale/ctype/en_US.UTF-8.src |  90 ++++++++++++++++++++++++++++++++-----
 1 files changed, 77 insertions(+), 13 deletions(-)

diffs (112 lines):

diff -r 05ad12b10a2e -r 98ad703fdbc9 share/locale/ctype/en_US.UTF-8.src
--- a/share/locale/ctype/en_US.UTF-8.src        Sun Jun 03 07:24:18 2018 +0000
+++ b/share/locale/ctype/en_US.UTF-8.src        Sun Jun 03 07:54:51 2018 +0000
@@ -1,4 +1,4 @@
-/*     $NetBSD: en_US.UTF-8.src,v 1.5 2012/08/08 18:40:37 tnozaki Exp $        */
+/*     $NetBSD: en_US.UTF-8.src,v 1.6 2018/06/03 07:54:51 rin Exp $    */
 /*     $FreeBSD: /repoman/r/ncvs/src/share/mklocale/UTF-8.src,v 1.1 2004/03/27 08:14:14 tjr Exp $      */
 
 /*
@@ -1858,19 +1858,15 @@
  * U+2700 - U+27BF : Dingbats
  */
 
-GRAPH     0x2701 - 0x2704  0x2706 - 0x2709  0x270c - 0x2727  0x2729 - 0x274b
-GRAPH     0x274d  0x274f - 0x2752  0x2756  0x2758 - 0x275e  0x2761 - 0x2794
-GRAPH     0x2798 - 0x27af  0x27b1 - 0x27be
-PUNCT     0x2701 - 0x2704  0x2706 - 0x2709  0x270c - 0x2727  0x2729 - 0x274b
-PUNCT     0x274d  0x274f - 0x2752  0x2756  0x2758 - 0x275e  0x2761 - 0x2775
-PUNCT     0x2794  0x2798 - 0x27af  0x27b1 - 0x27be
-PRINT     0x2701 - 0x2704  0x2706 - 0x2709  0x270c - 0x2727  0x2729 - 0x274b
-PRINT     0x274d  0x274f - 0x2752  0x2756  0x2758 - 0x275e  0x2761 - 0x2794
-PRINT     0x2798 - 0x27af  0x27b1 - 0x27be
+GRAPH     0x2700 - 0x27bf
+PUNCT     0x2700 - 0x2775  0x2794 - 0x27bf
+PRINT     0x2700 - 0x27bf
 SPECIAL   0x2776 - 0x2793
-SWIDTH1   0x2701 - 0x2704  0x2706 - 0x2709  0x270c - 0x2727  0x2729 - 0x274b
-SWIDTH1   0x274d  0x274f - 0x2752  0x2756  0x2758 - 0x275e  0x2761 - 0x2794
-SWIDTH1   0x2798 - 0x27af  0x27b1 - 0x27be
+SWIDTH1   0x2700 - 0x2704  0x2706 - 0x2709  0x270c - 0x2727  0x2729 - 0x274b
+SWIDTH1   0x274d  0x274f - 0x2752  0x2756  0x2758 - 0x2794  0x2798 - 0x27af
+SWIDTH1   0x27b1 - 0x27be
+SWIDTH2   0x2705  0x270a - 0x270b  0x2728  0x274c  0x274e  0x2753 - 0x2755
+SWIDTH2   0x2757  0x2795 - 0x2797  0x27b0  0x27bf
 
 
 /*
@@ -2396,6 +2392,74 @@
 
 
 /*
+ * U+1F300 - U+1F5FF : Miscellaneous Symbols and Pictographs
+ */
+
+GRAPH     0x1f300 - 0x1f5ff
+PUNCT     0x1f300 - 0x1f5ff
+PRINT     0x1f300 - 0x1f5ff
+SWIDTH1   0x1f321 - 0x1f32c  0x1f336  0x1f37d  0x1f394 - 0x1f39f
+SWIDTH1   0x1f3cb - 0x1f3ce  0x1f3d4 - 0x1f3df  0x1f3f1 - 0x1f3f3
+SWIDTH1   0x1f3f5 - 0x1f3f7  0x1f43f  0x1f441  0x1f4fd - 0x1f4fe
+SWIDTH1   0x1f53e - 0x1f54a  0x1f54f  0x1f568 - 0x1f579  0x1f57b - 0x1f594
+SWIDTH1   0x1f597 - 0x1f5a3  0x1f5a5 - 0x1f5fa
+SWIDTH2   0x1f300 - 0x1f320  0x1f32d - 0x1f335  0x1f337 - 0x1f37c
+SWIDTH2   0x1f37e - 0x1f393  0x1f3a0 - 0x1f3ca  0x1f3cf - 0x1f3d3
+SWIDTH2   0x1f3e0 - 0x1f3f0  0x1f3f4  0x1f3f8 - 0x1f43e  0x1f440
+SWIDTH2   0x1f442 - 0x1f4fc  0x1f4ff - 0x1f53d  0x1f54b - 0x1f54e
+SWIDTH2   0x1f550 - 0x1f567  0x1f57a  0x1f595 - 0x1f596  0x1f5a4
+SWIDTH2   0x1f5fb - 0x1f5ff
+
+
+/*
+ * U+1F600 - U+1F64F : Emoticons
+ */
+
+GRAPH     0x1f600 - 0x1f64f
+PUNCT     0x1f600 - 0x1f64f
+PRINT     0x1f600 - 0x1f64f
+SWIDTH2   0x1f600 - 0x1f64f
+
+
+/*
+ * U+1F650 - U+1F67F : Ornamental Dingbats
+ */
+
+GRAPH     0x1f650 - 0x1f67f
+PUNCT     0x1f650 - 0x1f67f
+PRINT     0x1f650 - 0x1f67f
+SWIDTH1   0x1f650 - 0x1f67f
+
+
+/*
+ * U+1F680 - U+1F6FF : Transport and Map Symbols
+ */
+
+GRAPH     0x1f680 - 0x1f6d4  0x1f6e0 - 0x1f6ec  0x1f6f0 - 0x1f6f8
+PUNCT     0x1f680 - 0x1f6d4  0x1f6e0 - 0x1f6ec  0x1f6f0 - 0x1f6f8
+PRINT     0x1f680 - 0x1f6d4  0x1f6e0 - 0x1f6ec  0x1f6f0 - 0x1f6f8
+SWIDTH1   0x1f6c6 - 0x1f6cb  0x1f6cd - 0x1f6cf  0x1f6d3 - 0x1f6d4
+SWIDTH1   0x1f6e0 - 0x1f6ea  0x1f6f0 - 0x1f6f3
+SWIDTH2   0x1f680 - 0x1f6c5  0x1f6cc  0x1f6d0 - 0x1f6d2  0x1f6eb - 0x1f6ec
+SWIDTH2   0x1f6f4 - 0x1f6f8
+
+
+/*
+ * U+1F900 - U+1F9FF : Supplemental Symbols and Pictographs
+ */
+
+GRAPH     0x1f900 - 0x1f90b  0x1f910 - 0x1f93e  0x1f940 - 0x1f94c
+GRAPH     0x1f950 - 0x1f96b  0x1f980 - 0x1f997  0x1f9c0  0x1f9d0 - 0x1f9e6
+PUNCT     0x1f900 - 0x1f90b  0x1f910 - 0x1f93e  0x1f940 - 0x1f94c
+PUNCT     0x1f950 - 0x1f96b  0x1f980 - 0x1f997  0x1f9c0  0x1f9d0 - 0x1f9e6
+PRINT     0x1f900 - 0x1f90b  0x1f910 - 0x1f93e  0x1f940 - 0x1f94c
+PRINT     0x1f950 - 0x1f96b  0x1f980 - 0x1f997  0x1f9c0  0x1f9d0 - 0x1f9e6
+SWIDTH1   0x1f900 - 0x1f90b
+SWIDTH2   0x1f910 - 0x1f93e  0x1f940 - 0x1f94c  0x1f950 - 0x1f96b
+SWIDTH2   0x1f980 - 0x1f997  0x1f9c0  0x1f9d0 - 0x1f9e6
+
+
+/*
  * U+20000 - U+2A6DF : CJK Unified Ideographs Extension B
  */