New upstream version 1.0upstream/1.0

1 files changed, 35 insertions, 24 deletions

diff --git a/lib/uniwbrk/u-wordbreaks.h b/lib/uniwbrk/u-wordbreaks.h
index 0d881c7b..e8eb01a7 100644
--- a/lib/uniwbrk/u-wordbreaks.h
+++ b/lib/uniwbrk/u-wordbreaks.h
@@ -1,28 +1,30 @@
 /* Word breaks in UTF-8/UTF-16/UTF-32 strings.  -*- coding: utf-8 -*-
-   Copyright (C) 2009-2018 Free Software Foundation, Inc.
+   Copyright (C) 2009-2022 Free Software Foundation, Inc.
    Written by Bruno Haible <bruno@clisp.org>, 2009.
 
-   This program is free software: you can redistribute it and/or
-   modify it under the terms of either:
-
-     * the GNU Lesser General Public License as published by the Free
-       Software Foundation; either version 3 of the License, or (at your
-       option) any later version.
-
-   or
-
-     * the GNU General Public License as published by the Free
-       Software Foundation; either version 2 of the License, or (at your
-       option) any later version.
-
-   or both in parallel, as here.
-   This program is distributed in the hope that it will be useful,
+   This file is free software.
+   It is dual-licensed under "the GNU LGPLv3+ or the GNU GPLv2+".
+   You can redistribute it and/or modify it under either
+     - the terms of the GNU Lesser General Public License as published
+       by the Free Software Foundation; either version 3, or (at your
+       option) any later version, or
+     - the terms of the GNU General Public License as published by the
+       Free Software Foundation; either version 2, or (at your option)
+       any later version, or
+     - the same dual license "the GNU LGPLv3+ or the GNU GPLv2+".
+
+   This file is distributed in the hope that it will be useful,
    but WITHOUT ANY WARRANTY; without even the implied warranty of
    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
-   Lesser General Public License for more details.
+   Lesser General Public License and the GNU General Public License
+   for more details.
 
-   You should have received a copy of the GNU Lesser General Public License
-   along with this program.  If not, see <https://www.gnu.org/licenses/>.  */
+   You should have received a copy of the GNU Lesser General Public
+   License and of the GNU General Public License along with this
+   program.  If not, see <https://www.gnu.org/licenses/>.  */
+
+/* This file implements section 4 "Word Boundaries"
+   of Unicode Standard Annex #29 <https://www.unicode.org/reports/tr29/>.  */
 
 void
 FUNC (const UNIT *s, size_t n, char *p)
@@ -48,6 +50,8 @@ FUNC (const UNIT *s, size_t n, char *p)
          -1 at the very beginning of the string.  */
       int secondlast_compchar_prop = -1;
 
+      /* Number of consecutive regional indicator (RI) characters seen
+         immediately before the current point.  */
       size_t ri_count = 0;
 
       /* Don't break inside multibyte characters.  */
@@ -74,11 +78,18 @@ FUNC (const UNIT *s, size_t n, char *p)
                            || prop == WBP_NEWLINE))
                 *p = 1;
               /* No break within emoji zwj sequence (WB3c).  */
-              else if (last_char_prop == WBP_ZWJ &&
-                       (prop == WBP_GAZ || prop == WBP_EBG))
+              else if (last_char_prop == WBP_ZWJ
+                       && uc_is_property_extended_pictographic (uc))
+                /* *p = 0 */;
+              /* Keep horizontal whitespace together (WB3d).  */
+              else if (last_char_prop == WBP_WSS && prop == WBP_WSS)
                 /* *p = 0 */;
-              /* Ignore Format and Extend characters.  */
-              else if (!(prop == WBP_EXTEND || prop == WBP_FORMAT || prop == WBP_ZWJ))
+              /* Ignore Format and Extend characters (WB4).  */
+              else if (prop == WBP_EXTEND
+                       || prop == WBP_FORMAT
+                       || prop == WBP_ZWJ)
+                /* *p = 0 */;
+              else
                 {
                   /* No break in these situations (see UAX #29):
 
@@ -147,7 +158,7 @@ FUNC (const UNIT *s, size_t n, char *p)
           last_char_prop = prop;
 
           /* Ignore Format and Extend characters, except at the
-             start of the line.  */
+             start of the line (WB4).  */
           if (last_compchar_prop < 0
               || last_compchar_prop == WBP_CR
               || last_compchar_prop == WBP_LF