Fix enforcement of restrictions inside regexp lookaround constraints.

Lookahead and lookbehind constraints aren't allowed to contain backrefs,
and parentheses within them are always considered non-capturing.  Or so
says the manual.  But the regexp parser forgot about these rules once
inside a parenthesized subexpression, so that constructs like (\w)(?=(\1))
were accepted (but then not correctly executed --- a case like this acted
like (\w)(?=\w), without any enforcement that the two \w's match the same
text).  And in (?=((foo))) the innermost parentheses would be counted as
capturing parentheses, though no text would ever be captured for them.

To fix, properly pass down the "type" argument to the recursive invocation
of parse().

Back-patch to all supported branches; it was agreed that silent
misexecution of such patterns is worse than throwing an error, even though
new errors in minor releases are generally not desirable.

diff --git a/src/backend/regex/regcomp.c b/src/backend/regex/regcomp.c
index 09ec8f3c89490c3ca5574c0342e1f956461e2ca1..487b5dabb8262add1430983e212280521d30f8ad 100644 (file)
--- a/src/backend/regex/regcomp.c
+++ b/src/backend/regex/regcomp.c
@@ -944,7 +944,7 @@ parseqatom(struct vars * v,
            EMPTYARC(lp, s);
            EMPTYARC(s2, rp);
            NOERR();
-           atom = parse(v, ')', PLAIN, s, s2);
+           atom = parse(v, ')', type, s, s2);
            assert(SEE(')') || ISERR());
            NEXT();
            NOERR();

diff --git a/src/test/regress/expected/regex.out b/src/test/regress/expected/regex.out
index be151858a3884a9c9f32d64608d80e959e8f912c..ba2923982f5ffa7f3bf59782915c73bda30cd333 100644 (file)
--- a/src/test/regress/expected/regex.out
+++ b/src/test/regress/expected/regex.out
@@ -321,3 +321,8 @@ select 'a' ~ '()+\1';
  t
 (1 row)
 
+-- Error conditions
+select 'xyz' ~ 'x(\w)(?=\1)';  -- no backrefs in LACONs
+ERROR:  invalid regular expression: invalid backreference number
+select 'xyz' ~ 'x(\w)(?=(\1))';
+ERROR:  invalid regular expression: invalid backreference number

diff --git a/src/test/regress/sql/regex.sql b/src/test/regress/sql/regex.sql
index c59fa35f24d81f5e2c4aceae0ada1ca3832f0ac4..7cf5e599822a6131e586520e9599f309506db94d 100644 (file)
--- a/src/test/regress/sql/regex.sql
+++ b/src/test/regress/sql/regex.sql
@@ -82,3 +82,7 @@ select 'a' ~ '$()|^\1';
 select 'a' ~ '.. ()|\1';
 select 'a' ~ '()*\1';
 select 'a' ~ '()+\1';
+
+-- Error conditions
+select 'xyz' ~ 'x(\w)(?=\1)';  -- no backrefs in LACONs
+select 'xyz' ~ 'x(\w)(?=(\1))';