bindat (str, strz): Reject non-ASCII, non-`eight-bit' characters

* lisp/emacs-lisp/bindat.el (str) (strz): Signal an error if the user
attempts to pack a multibyte string containing characters other than
ASCII and `eight-bit' characters (bug#55897).
* doc/lispref/processes.texi (Bindat Types): Update documentation.
* test/lisp/emacs-lisp/bindat-tests.el (str) (strz): Add tests.

diff --git a/doc/lispref/processes.texi b/doc/lispref/processes.texi
index aa4d0e3ee4fcbc03e8be5cc4f1fecb5654fde34f..8c8f8fd6b2ad93d1a8e2f730e3d5f2738526fb73 100644 (file)
--- a/doc/lispref/processes.texi
+++ b/doc/lispref/processes.texi
@@ -3486,8 +3486,11 @@ When packing, the first @var{len} bytes of the input string are copied
 to the packed output.  If the input string is shorter than @var{len},
 the remaining bytes will be null (zero) unless a pre-allocated string
 was provided to @code{bindat-pack}, in which case the remaining bytes
-are left unmodified.  When unpacking, any null bytes in the packed
-input string will appear in the unpacked output.
+are left unmodified.  If the input string is multibyte with only ASCII
+and @code{eight-bit} characters, it is converted to unibyte before it
+is packed; other multibyte strings signal an error.  When unpacking,
+any null bytes in the packed input string will appear in the unpacked
+output.
 
 @item strz &optional @var{len}
 If @var{len} is not provided: Variable-length null-terminated unibyte
@@ -3497,8 +3500,11 @@ null (zero) unless a pre-allocated string was provided to
 @code{bindat-pack}, in which case that byte is left unmodified.  The
 length of the packed output is the length of the input string plus one
 (for the null terminator).  The input string must not contain any null
-bytes.  When unpacking, the resulting string contains all bytes up to
-(but excluding) the null byte.
+bytes.  If the input string is multibyte with only ASCII and
+@code{eight-bit} characters, it is converted to unibyte before it is
+packed; other multibyte strings signal an error.  When unpacking, the
+resulting string contains all bytes up to (but excluding) the null
+byte.
 
 @quotation Caution
 If a pre-allocated string is provided to @code{bindat-pack}, the

diff --git a/lisp/emacs-lisp/bindat.el b/lisp/emacs-lisp/bindat.el
index 84d5ea1e3b3cbe1029bd68085a787eb85b30aa94..2d6589b52def789e458745919587149ac6e335c4 100644 (file)
--- a/lisp/emacs-lisp/bindat.el
+++ b/lisp/emacs-lisp/bindat.el
@@ -435,12 +435,14 @@ e.g. corresponding to STRUCT.FIELD1[INDEX2].FIELD3..."
   (bindat--pack-u32r (ash v -32)))
 
 (defun bindat--pack-str (len v)
-  (dotimes (i (min len (length v)))
-    (aset bindat-raw (+ bindat-idx i) (aref v i)))
-  (setq bindat-idx (+ bindat-idx len)))
+  (let ((v (string-to-unibyte v)))
+    (dotimes (i (min len (length v)))
+      (aset bindat-raw (+ bindat-idx i) (aref v i)))
+    (setq bindat-idx (+ bindat-idx len))))
 
 (defun bindat--pack-strz (v)
-  (let ((len (length v)))
+  (let* ((v (string-to-unibyte v))
+         (len (length v)))
     (dotimes (i len)
       (aset bindat-raw (+ bindat-idx i) (aref v i)))
     (setq bindat-idx (+ bindat-idx len 1))))

diff --git a/test/lisp/emacs-lisp/bindat-tests.el b/test/lisp/emacs-lisp/bindat-tests.el
index 1ce402977f5361279bc2f916254e9405e93ecd77..8bb3baa485e3be6d658e88f1c63bc0c4d622662f 100644 (file)
--- a/test/lisp/emacs-lisp/bindat-tests.el
+++ b/test/lisp/emacs-lisp/bindat-tests.el
@@ -188,6 +188,22 @@
       (apply #'bindat-pack (append (car tc) (list prealloc)))
       (should (equal prealloc (cdr tc))))))
 
+(ert-deftest bindat-test--str-strz-multibyte ()
+  (dolist (spec (list (bindat-type str 2)
+                      (bindat-type strz 2)
+                      (bindat-type strz)))
+    (should (equal (bindat-pack spec (string-to-multibyte "x")) "x\0"))
+    (should (equal (bindat-pack spec (string-to-multibyte "\xff")) "\xff\0"))
+    (should-error (bindat-pack spec "💩"))
+    (should-error (bindat-pack spec "\N{U+ff}")))
+  (dolist (spec (list '((x str 2)) '((x strz 2))))
+    (should (equal (bindat-pack spec `((x . ,(string-to-multibyte "x"))))
+                   "x\0"))
+    (should (equal (bindat-pack spec `((x . ,(string-to-multibyte "\xff"))))
+                   "\xff\0"))
+    (should-error (bindat-pack spec '((x . "💩"))))
+    (should-error (bindat-pack spec '((x . "\N{U+ff}"))))))
+
 (let ((spec (bindat-type strz 2)))
   (ert-deftest bindat-test--strz-fixedlen-len ()
     (should (equal (bindat-length spec "") 2))