From d71cfc7fd9edd213c4705dbb99d7cc5f9165911b Mon Sep 17 00:00:00 2001
From: Paul Eggert <eggert@cs.ucla.edu>
Date: Fri, 29 Aug 2025 09:17:02 -0700
Subject: [PROPOSED 2/8] Update list of allowed chars in commentary
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

* Makefile (UNUSUAL_OK_CHARSET): Simplify by listing only chars
actually used in commentary or in the generated *.txt files.
Add –‘’“”•≤ as *.txt files can now contain these chars.
(character-set.ck): Relax limitations on *.txt and *.html files,
by limiting them only to OK lines; the lines no longer need be safe.
* NEWS: Mention this.
---
 Makefile | 18 ++++++------------
 NEWS     |  3 +++
 2 files changed, 9 insertions(+), 12 deletions(-)

diff --git a/Makefile b/Makefile
index 7d77da60..b716f0f2 100644
--- a/Makefile
+++ b/Makefile
@@ -534,13 +534,10 @@ SAFE_CHARSET3=	'abcdefghijklmnopqrstuvwxyz{|}~'
 SAFE_CHARSET=	$(SAFE_CHARSET1)$(SAFE_CHARSET2)$(SAFE_CHARSET3)
 SAFE_CHAR=	'[]'$(SAFE_CHARSET)'-]'
 
-# These non-alphabetic, non-ASCII printable characters are Latin-1,
-# and so are likely displayable even in editors like XEmacs 21
-# that have limited display capabilities.
-UNUSUAL_OK_LATIN_1 = ¡¢£¤¥¦§¨©«¬®¯°±²³´¶·¸¹»¼½¾¿×÷
-# Non-ASCII non-letters that OK_CHAR allows, as these characters are
-# useful in commentary.
-UNUSUAL_OK_CHARSET= $(UNUSUAL_OK_LATIN_1)
+# These non-alphabetic, non-ASCII printable characters are
+# used in commentary or in generated *.txt files
+# and are not likely to cause confusion.
+UNUSUAL_OK_CHARSET= §«°±»½¾×–‘’“”•≤
 
 # Put this in a bracket expression to match spaces.
 s = [:space:]
@@ -549,9 +546,6 @@ s = [:space:]
 # This is the same as SAFE_CHAR, except that UNUSUAL_OK_CHARSET and
 # multibyte letters are also allowed so that commentary can contain a
 # few safe symbols and people's names and can quote non-English sources.
-# Other non-letters are limited to ASCII renderings for the
-# convenience of maintainers using XEmacs 21.5.34, which by default
-# mishandles Unicode characters U+0100 and greater.
 OK_CHAR=	'[][:alpha:]$(UNUSUAL_OK_CHARSET)'$(SAFE_CHARSET)'-]'
 
 # SAFE_LINE matches a line of safe characters.
@@ -898,8 +892,8 @@ UTF8_LOCALE_MISSING = \
 character-set.ck: $(ENCHILADA)
 	$(UTF8_LOCALE_MISSING) || { \
 		sharp='#' && \
-		! grep -Env $(SAFE_LINE) $(MANS) date.1 $(MANTXTS) \
-			$(MISC) $(SOURCES) $(WEB_PAGES) \
+		! grep -Env $(SAFE_LINE) $(MANS) date.1 \
+			$(MISC) $(SOURCES) \
 			CONTRIBUTING LICENSE README SECURITY \
 			version tzdata.zi && \
 		! grep -Env $(SAFE_LINE)'|^UNUSUAL_OK_'$(OK_CHAR)'*$$' \
diff --git a/NEWS b/NEWS
index 9163c1fe..5f3e6650 100644
--- a/NEWS
+++ b/NEWS
@@ -28,6 +28,9 @@ Unreleased, experimental changes
     last-modified and expiration timestamps for leap second data.
     (Thanks to Judah Levine.)
 
+    Commentary now also uses characters from the set –‘’“”•≤ as this
+    can be useful and should work with current text editors.
+
 
 Release 2025b - 2025-03-22 13:40:46 -0700
 
-- 
2.48.1