bug#52670: [PATCH] legacy base64 encoding of latin-1

[mattiase@acm.org]

[-- Attachment #1: Type: text/plain, Size: 150 bytes --]

It really looks like the erroneous behaviour was an unintended effect of commit 680d4b87f3d88a8b79f883cf3635036747588250. Anyway, here is a patch.


[-- Attachment #2: 0001-Fix-sloppy-base64-acceptance-of-some-multibyte-chara.patch --]
[-- Type: application/octet-stream, Size: 5100 bytes --]

From c979c063a96711b8dea018e7486b05a5a192bfd2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mattias=20Engdeg=C3=A5rd?= <mattiase@acm.org>
Date: Mon, 20 Dec 2021 18:17:23 +0100
Subject: [PATCH] Fix sloppy base64 acceptance of some multibyte characters

The base64 encoding functions incorrectly accepted some multibyte
characters; stop doing that (bug#52670).

* src/fns.c (base64_encode_1): Reject all multibyte characters.
* test/src/fns-tests.el (fns-tests-base64-encode-string)
(fns-test-base64url-encode-region)
(fns-test-base64url-encode-string): Add tests.
* doc/lispref/text.texi (Base 64): Rephrase outdated manual text.
---
 doc/lispref/text.texi |  5 ++---
 src/fns.c             |  6 +++---
 test/src/fns-tests.el | 16 +++++++++++++---
 3 files changed, 18 insertions(+), 9 deletions(-)

diff --git a/doc/lispref/text.texi b/doc/lispref/text.texi
index 5ab5e5715f..9771d8a7ed 100644
--- a/doc/lispref/text.texi
+++ b/doc/lispref/text.texi
@@ -4793,9 +4793,8 @@ Base 64
 This function converts the region from @var{beg} to @var{end} into base
 64 code.  It returns the length of the encoded text.  An error is
 signaled if a character in the region is multibyte, i.e., in a
-multibyte buffer the region must contain only characters from the
-charsets @code{ascii}, @code{eight-bit-control} and
-@code{eight-bit-graphic}.
+multibyte buffer the region must contain only ASCII characters or raw
+bytes.
 
 Normally, this function inserts newline characters into the encoded
 text, to avoid overlong lines.  However, if the optional argument
diff --git a/src/fns.c b/src/fns.c
index 76c76c92ba..23721334f7 100644
--- a/src/fns.c
+++ b/src/fns.c
@@ -3653,7 +3653,7 @@ base64_encode_1 (const char *from, char *to, ptrdiff_t length,
 	  c = string_char_and_length ((unsigned char *) from + i, &bytes);
 	  if (CHAR_BYTE8_P (c))
 	    c = CHAR_TO_BYTE8 (c);
-	  else if (c >= 256)
+	  else if (c >= 128)
 	    return -1;
 	  i += bytes;
 	}
@@ -3696,7 +3696,7 @@ base64_encode_1 (const char *from, char *to, ptrdiff_t length,
 	  c = string_char_and_length ((unsigned char *) from + i, &bytes);
 	  if (CHAR_BYTE8_P (c))
 	    c = CHAR_TO_BYTE8 (c);
-	  else if (c >= 256)
+	  else if (c >= 128)
 	    return -1;
 	  i += bytes;
 	}
@@ -3721,7 +3721,7 @@ base64_encode_1 (const char *from, char *to, ptrdiff_t length,
 	  c = string_char_and_length ((unsigned char *) from + i, &bytes);
 	  if (CHAR_BYTE8_P (c))
 	    c = CHAR_TO_BYTE8 (c);
-	  else if (c >= 256)
+	  else if (c >= 128)
 	    return -1;
 	  i += bytes;
 	}
diff --git a/test/src/fns-tests.el b/test/src/fns-tests.el
index bec5c03f9e..63423f622f 100644
--- a/test/src/fns-tests.el
+++ b/test/src/fns-tests.el
@@ -318,7 +318,10 @@ fns-tests-base64-encode-string
   (should (equal (base64-encode-string "fooba") "Zm9vYmE="))
   (should (equal (base64-encode-string "foobar") "Zm9vYmFy"))
   (should (equal (base64-encode-string "\x14\xfb\x9c\x03\xd9\x7e") "FPucA9l+"))
-  (should (equal (base64-encode-string "\x14\xfb\x9c\x03\xd9\x7f") "FPucA9l/")))
+  (should (equal (base64-encode-string "\x14\xfb\x9c\x03\xd9\x7f") "FPucA9l/"))
+
+  (should-error (base64-encode-string "ƒ"))
+  (should-error (base64-encode-string "ü")))
 
 (ert-deftest fns-test-base64url-encode-region ()
   ;; url variant with padding
@@ -360,7 +363,11 @@ fns-test-base64url-encode-region
   (should (equal (fns-tests--with-region base64url-encode-region (fns-tests--string-repeat "\x14\xfb\x9c\x03\xd9\x7e" 10) t)
                  (fns-tests--string-repeat "FPucA9l-" 10)))
   (should (equal (fns-tests--with-region base64url-encode-region (fns-tests--string-repeat "\x14\xfb\x9c\x03\xd9\x7f" 10) t)
-                 (fns-tests--string-repeat "FPucA9l_" 10))))
+                 (fns-tests--string-repeat "FPucA9l_" 10)))
+
+  (should-error (fns-tests--with-region base64url-encode-region "ƒ"))
+  (should-error (fns-tests--with-region base64url-encode-region "ü")))
+
 
 (ert-deftest fns-test-base64url-encode-string ()
   ;; url variant with padding
@@ -394,7 +401,10 @@ fns-test-base64url-encode-string
   (should (equal (base64url-encode-string (fns-tests--string-repeat "fooba" 15) t) (fns-tests--string-repeat "Zm9vYmFmb29iYWZvb2Jh" 5)))
   (should (equal (base64url-encode-string (fns-tests--string-repeat "foobar" 15) t) (concat (fns-tests--string-repeat "Zm9vYmFyZm9vYmFy" 7) "Zm9vYmFy")))
   (should (equal (base64url-encode-string (fns-tests--string-repeat "\x14\xfb\x9c\x03\xd9\x7e" 10) t) (fns-tests--string-repeat "FPucA9l-" 10)))
-  (should (equal (base64url-encode-string (fns-tests--string-repeat "\x14\xfb\x9c\x03\xd9\x7f" 10) t) (fns-tests--string-repeat "FPucA9l_" 10))))
+  (should (equal (base64url-encode-string (fns-tests--string-repeat "\x14\xfb\x9c\x03\xd9\x7f" 10) t) (fns-tests--string-repeat "FPucA9l_" 10)))
+
+  (should-error (base64url-encode-string "ƒ"))
+  (should-error (base64url-encode-string "ü")))
 
 (ert-deftest fns-tests-base64-decode-string ()
   ;; standard variant RFC2045
-- 
2.32.0 (Apple Git-132)