Reduce an unnecessary O(N^3) loop in lexer.

The lexer's handling of operators contained an O(N^3) hazard when
dealing with long strings of + or - characters; it seems hard to
prevent this case from being O(N^2), but the additional N multiplier
was not needed.

Backpatch all the way since this has been there since 7.x, and it
presents at least a mild hazard in that trying to do Bind, PREPARE or
EXPLAIN on a hostile query could take excessive time (without
honouring cancels or timeouts) even if the query was never executed.

diff --git a/src/backend/parser/scan.l b/src/backend/parser/scan.l
index acd92698057928aeccfd68b4461c35981b31f0a0..967b2eaf9b99bb8a7be40cb703c4e307f9ad3585 100644 (file)
--- a/src/backend/parser/scan.l
+++ b/src/backend/parser/scan.l
@@ -881,20 +881,33 @@ other         .
                     * to forbid operator names like '?-' that could not be
                     * sequences of SQL operators.
                     */
-                   while (nchars > 1 &&
-                          (yytext[nchars - 1] == '+' ||
-                           yytext[nchars - 1] == '-'))
+                   if (nchars > 1 &&
+                       (yytext[nchars - 1] == '+' ||
+                        yytext[nchars - 1] == '-'))
                    {
                        int         ic;
 
                        for (ic = nchars - 2; ic >= 0; ic--)
                        {
-                           if (strchr("~!@#^&|`?%", yytext[ic]))
+                           char c = yytext[ic];
+                           if (c == '~' || c == '!' || c == '@' ||
+                               c == '#' || c == '^' || c == '&' ||
+                               c == '|' || c == '`' || c == '?' ||
+                               c == '%')
                                break;
                        }
-                       if (ic >= 0)
-                           break; /* found a char that makes it OK */
-                       nchars--; /* else remove the +/-, and check again */
+                       if (ic < 0)
+                       {
+                           /*
+                            * didn't find a qualifying character, so remove
+                            * all trailing [+-]
+                            */
+                           do {
+                               nchars--;
+                           } while (nchars > 1 &&
+                                (yytext[nchars - 1] == '+' ||
+                                 yytext[nchars - 1] == '-'));
+                       }
                    }
 
                    SET_YYLLOC();

diff --git a/src/fe_utils/psqlscan.l b/src/fe_utils/psqlscan.l
index 55067b450c2141a0b2b6c5f21366ba9dc8bbd09b..fe74abc1a6cb68a2ac9a7984078daca8efd1b778 100644 (file)
--- a/src/fe_utils/psqlscan.l
+++ b/src/fe_utils/psqlscan.l
@@ -798,20 +798,33 @@ other         .
                     * to forbid operator names like '?-' that could not be
                     * sequences of SQL operators.
                     */
-                   while (nchars > 1 &&
-                          (yytext[nchars - 1] == '+' ||
-                           yytext[nchars - 1] == '-'))
+                   if (nchars > 1 &&
+                       (yytext[nchars - 1] == '+' ||
+                        yytext[nchars - 1] == '-'))
                    {
                        int         ic;
 
                        for (ic = nchars - 2; ic >= 0; ic--)
                        {
-                           if (strchr("~!@#^&|`?%", yytext[ic]))
+                           char c = yytext[ic];
+                           if (c == '~' || c == '!' || c == '@' ||
+                               c == '#' || c == '^' || c == '&' ||
+                               c == '|' || c == '`' || c == '?' ||
+                               c == '%')
                                break;
                        }
-                       if (ic >= 0)
-                           break; /* found a char that makes it OK */
-                       nchars--; /* else remove the +/-, and check again */
+                       if (ic < 0)
+                       {
+                           /*
+                            * didn't find a qualifying character, so remove
+                            * all trailing [+-]
+                            */
+                           do {
+                               nchars--;
+                           } while (nchars > 1 &&
+                                (yytext[nchars - 1] == '+' ||
+                                 yytext[nchars - 1] == '-'));
+                       }
                    }
 
                    if (nchars < yyleng)

diff --git a/src/interfaces/ecpg/preproc/pgc.l b/src/interfaces/ecpg/preproc/pgc.l
index 07c722d1d7237c0ec3a0ee8987648f4cf17a65a4..bc47c23d03808ddaecfcec06c84129f68169f0b9 100644 (file)
--- a/src/interfaces/ecpg/preproc/pgc.l
+++ b/src/interfaces/ecpg/preproc/pgc.l
@@ -687,20 +687,33 @@ cppline           {space}*#([^i][A-Za-z]*|{if}|{ifdef}|{ifndef}|{import})((\/\*[^*/]*\*+
                         * to forbid operator names like '?-' that could not be
                         * sequences of SQL operators.
                         */
-                       while (nchars > 1 &&
-                              (yytext[nchars-1] == '+' ||
-                               yytext[nchars-1] == '-'))
+                       if (nchars > 1 &&
+                           (yytext[nchars - 1] == '+' ||
+                            yytext[nchars - 1] == '-'))
                        {
                            int     ic;
 
-                           for (ic = nchars-2; ic >= 0; ic--)
+                           for (ic = nchars - 2; ic >= 0; ic--)
                            {
-                               if (strchr("~!@#^&|`?%", yytext[ic]))
+                               char c = yytext[ic];
+                               if (c == '~' || c == '!' || c == '@' ||
+                                   c == '#' || c == '^' || c == '&' ||
+                                   c == '|' || c == '`' || c == '?' ||
+                                   c == '%')
                                    break;
                            }
-                           if (ic >= 0)
-                               break; /* found a char that makes it OK */
-                           nchars--; /* else remove the +/-, and check again */
+                           if (ic < 0)
+                           {
+                               /*
+                                * didn't find a qualifying character, so remove
+                                * all trailing [+-]
+                                */
+                               do {
+                                   nchars--;
+                               } while (nchars > 1 &&
+                                    (yytext[nchars - 1] == '+' ||
+                                     yytext[nchars - 1] == '-'));
+                           }
                        }
 
                        if (nchars < yyleng)