diff options
author | Mattias Engdegård <mattiase@acm.org> | 2021-12-20 18:17:23 +0100 |
---|---|---|
committer | Mattias Engdegård <mattiase@acm.org> | 2021-12-20 20:22:09 +0100 |
commit | a34650acff3740980ef23d900d35004bcfe2ef04 (patch) | |
tree | 5e34b2538df2849832e3971bc7d0cd9546b5adc9 | |
parent | 27be90154d1a4b19efe30c97f221b29e3becc920 (diff) | |
download | emacs-a34650acff3740980ef23d900d35004bcfe2ef04.tar.gz |
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* doc/lispref/text.texi (Base 64): Rephrase outdated manual text.
* etc/NEWS: Add a notice.
-rw-r--r-- | doc/lispref/text.texi | 5 | ||||
-rw-r--r-- | etc/NEWS | 8 | ||||
-rw-r--r-- | src/fns.c | 6 | ||||
-rw-r--r-- | test/src/fns-tests.el | 16 |
4 files changed, 26 insertions, 9 deletions
diff --git a/doc/lispref/text.texi b/doc/lispref/text.texi index 5ab5e5715f0..9771d8a7ed9 100644 --- a/doc/lispref/text.texi +++ b/doc/lispref/text.texi @@ -4793,9 +4793,8 @@ converting to and from this code. 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 @@ -848,6 +848,14 @@ This change is now applied in 'dired-insert-directory'. 'unify-8859-on-decoding-mode', 'unify-8859-on-encoding-mode', 'vc-arch-command'. ++++ +** Base64 encoding no longer tolerates latin-1 input. +The functions 'base64-encode-string', 'base64url-encode-string', +'base64-encode-region' and 'base64url-encode-region' no longer accept +characters in the range U+0080..U+00FF as substitutes for single bytes +in the range 128..255, but signal an error for all multibyte characters. +The input must be encoded text. + * Lisp Changes in Emacs 29.1 diff --git a/src/fns.c b/src/fns.c index 76c76c92ba9..23721334f76 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 bec5c03f9e7..63423f622f8 100644 --- a/test/src/fns-tests.el +++ b/test/src/fns-tests.el @@ -318,7 +318,10 @@ (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 @@ (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 @@ (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 |