From: Mattias Engdegård <mattiase@acm.org>
Date: Sat, 5 Jul 2025 11:20:18 +0000 (+0200)
Subject: Read non-ASCII chars from unibyte string sources as raw bytes
X-Git-Url: http://git.eshelyaron.com/gitweb/?a=commitdiff_plain;h=4452d51fd248918bcc49b99de9d90c758fa3c80f;p=emacs.git

Read non-ASCII chars from unibyte string sources as raw bytes

Previously, latin-1 was incorrectly assumed (bug#70988).

* src/lread.c (readchar): Convert to raw byte.
* test/src/lread-tests.el (lread-unibyte-string-source): New test.

(cherry picked from commit d13693ef4ec9428e2356b0de29913d533c5c4382)
---

diff --git a/src/lread.c b/src/lread.c
index 6cd6735a215..5d9bdb065e8 100644
--- a/src/lread.c
+++ b/src/lread.c
@@ -382,6 +382,8 @@ readchar (Lisp_Object readcharfun, bool *multibyte)
       else
 	{
 	  c = SREF (readcharfun, read_from_string_index_byte);
+	  if (!ASCII_CHAR_P (c))
+	    c = BYTE8_TO_CHAR (c);
 	  read_from_string_index++;
 	  read_from_string_index_byte++;
 	}
diff --git a/test/src/lread-tests.el b/test/src/lread-tests.el
index d832cc9aa4e..d9b31a6c438 100644
--- a/test/src/lread-tests.el
+++ b/test/src/lread-tests.el
@@ -392,4 +392,10 @@ literals (Bug#20852)."
          (val (read (lambda () (pop s)))))
     (should (equal (symbol-name val) "A∪ÿ"))))
 
+(ert-deftest lread-unibyte-string-source ()
+  (let* ((src "\"a\xff\"")
+         (val (read src)))
+    (should (equal val "a\xff"))        ; not "aÿ"
+    (should-not (multibyte-string-p val))))
+
 ;;; lread-tests.el ends here