master 8d5e8cd: Signal an error for the regexp "[:alnum:]"

[Mattias Engdegård]

branch: master
commit 8d5e8cddab732ac90e9ae930c63f7830f9dab24f
Author: Mattias Engdegård <address@hidden>
Commit: Mattias Engdegård <address@hidden>

    Signal an error for the regexp "[:alnum:]"
    
    Omitting the extra brackets is a common mistake; see discussion at
    https://lists.gnu.org/archive/html/emacs-devel/2020-02/msg00215.html
    
    * src/regex-emacs.c (reg_errcode_t, re_error_msgid): Add REG_ECLASSBR.
    (regex_compile): Check for the mistake.
    * test/src/regex-emacs-tests.el (regexp-invalid): Test.
    * etc/NEWS: Announce.
---
 etc/NEWS                      |  5 +++++
 src/regex-emacs.c             | 21 ++++++++++++++++++++-
 test/src/regex-emacs-tests.el |  5 +++++
 3 files changed, 30 insertions(+), 1 deletion(-)

diff --git a/etc/NEWS b/etc/NEWS
index ee3a3c1..96a612b 100644
--- a/etc/NEWS
+++ b/etc/NEWS
@@ -202,6 +202,11 @@ Emacs now supports bignums so this old glitch is no longer 
needed.
 'previous-system-time-locale' have been removed, as they were created
 by mistake and were not useful to Lisp code.
 
+** The regexp mistake '[:digit:]' is now an error.
+The correct syntax is '[[:digit:]]'.  Previously, forgetting the extra
+brackets silently resulted in a regexp that did not at all work as
+intended.
+
 
 * Lisp Changes in Emacs 28.1
 
diff --git a/src/regex-emacs.c b/src/regex-emacs.c
index 694431c..3882437 100644
--- a/src/regex-emacs.c
+++ b/src/regex-emacs.c
@@ -818,7 +818,8 @@ typedef enum
   REG_ESIZE,           /* Compiled pattern bigger than 2^16 bytes.  */
   REG_ERPAREN,         /* Unmatched ) or \); not returned from regcomp.  */
   REG_ERANGEX,         /* Range striding over charsets.  */
-  REG_ESIZEBR           /* n or m too big in \{n,m\} */
+  REG_ESIZEBR,          /* n or m too big in \{n,m\} */
+  REG_ECLASSBR,         /* Missing [] around [:class:].  */
 } reg_errcode_t;
 
 static const char *re_error_msgid[] =
@@ -842,6 +843,7 @@ static const char *re_error_msgid[] =
    [REG_ERPAREN] = "Unmatched ) or \\)",
    [REG_ERANGEX ] = "Range striding over charsets",
    [REG_ESIZEBR ] = "Invalid content of \\{\\}",
+   [REG_ECLASSBR] = "Class syntax is [[:digit:]]; missing brackets",
   };
 
 /* For 'regs_allocated'.  */
@@ -2000,6 +2002,23 @@ regex_compile (re_char *pattern, ptrdiff_t size,
 
            laststart = b;
 
+            /* Check for the mistake of forgetting the extra square brackets,
+               as in "[:alpha:]".  */
+            if (*p == ':')
+              {
+                re_char *q = p + 1;
+                while (q != pend && *q != ']')
+                  {
+                    if (*q == ':')
+                      {
+                        if (q + 1 != pend && q[1] == ']' && q > p + 1)
+                          FREE_STACK_RETURN (REG_ECLASSBR);
+                        break;
+                      }
+                    q++;
+                  }
+              }
+
            /* Test '*p == '^' twice, instead of using an if
               statement, so we need only one BUF_PUSH.  */
            BUF_PUSH (*p == '^' ? charset_not : charset);
diff --git a/test/src/regex-emacs-tests.el b/test/src/regex-emacs-tests.el
index f9372e3..661d416 100644
--- a/test/src/regex-emacs-tests.el
+++ b/test/src/regex-emacs-tests.el
@@ -803,4 +803,9 @@ This evaluates the TESTS test cases from glibc."
   (should-not (string-match "Ã¥" "\xe5"))
   (should-not (string-match "[Ã¥]" "\xe5")))
 
+(ert-deftest regexp-invalid ()
+  ;; relint suppression: Duplicated
+  (should-error (string-match "[:space:]" "")
+                :type 'invalid-regexp))
+
 ;;; regex-emacs-tests.el ends here