From 8802474a219ad3be01825466a8837d3775f8b31b Mon Sep 17 00:00:00 2001
From: Eli Zaretskii <eliz@gnu.org>
Date: Tue, 14 Apr 2015 18:37:07 +0300
Subject: [PATCH] Assign correct general-category and names to surrogates

* admin/unidata/unidata-gen.el (unidata-setup-list): Don't ignore
surrogates.  This avoids assigning them the default
general-category of 'Cn', i.e. unassigned codepoints.
(unidata-get-name): Give surrogates synthetic names.
---
 admin/unidata/unidata-gen.el | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/admin/unidata/unidata-gen.el b/admin/unidata/unidata-gen.el
index 8af6fa0dd72..583d492495c 100644
--- a/admin/unidata/unidata-gen.el
+++ b/admin/unidata/unidata-gen.el
@@ -102,7 +102,8 @@
 	 (tail table)
 	 (block-names '(("^<CJK Ideograph" . CJK\ IDEOGRAPH)
 			("^<Hangul Syllable" . HANGUL\ SYLLABLE)
-			("^<.*Surrogate" . nil)
+			("^<.*High Surrogate" . HIGH\ SURROGATE)
+			("^<.*Low Surrogate" . LOW\ SURROGATE)
 			("^<.*Private Use" . PRIVATE\ USE)))
 	 val char name)
     (setq unidata-text-file (expand-file-name unidata-text-file unidata-dir))
@@ -137,11 +138,8 @@
 		    (if (string-match (caar l) block-name)
 			(setq name (cdar l) l nil)
 		      (setq l (cdr l))))
-		  (if (not name)
-		      ;; As this is a surrogate pair range, ignore it.
-		      (setq val nil)
-		    (setcar val (cons first char))
-		    (setcar (cdr val) name))))
+		  (setcar val (cons first char))
+		  (setcar (cdr val) name)))
 
 	    (when val
 	      (setcdr tail (list val))
@@ -783,6 +781,10 @@ Property value is a symbol `o' (Open), `c' (Close), or `n' (None)."
 	     (format "%s-%04X" sym char))
 	    ((eq sym 'CJK\ COMPATIBILITY\ IDEOGRAPH)
 	     (format "%s-%04X" sym char))
+	    ((eq sym 'HIGH\ SURROGATE)
+	     (format "%s-%04X" sym char))
+	    ((eq sym 'LOW\ SURROGATE)
+	     (format "%s-%04X" sym char))
 	    ((eq sym 'VARIATION\ SELECTOR)
 	     (format "%s-%d" sym (+ (- char #xe0100) 17))))))))
 
-- 
2.39.5