Add functionality for bypassing MySQL whitespace/comments

This functionality is needed both in the query classifier, where
it was first created, and in the cache.

include/maxscale/modutil.h

@@ -53,9 +53,29 @@ GWBUF*          modutil_create_mysql_err_msg(int             packet_number,
                                              int             merrno,
                                              const char      *statemsg,
                                              const char      *msg);
+
 int modutil_count_signal_packets(GWBUF*, int, int, int*);
 mxs_pcre2_result_t modutil_mysql_wildcard_match(const char* pattern, const char* string);
 
+/**
+ * Given a buffer containing a MySQL statement, this function will return
+ * a pointer to the first character that is not whitespace. In this context,
+ * comments are also counted as whitespace. For instance:
+ *
+ *    "SELECT"                    => "SELECT"
+ *    "  SELECT                   => "SELECT"
+ *    " / * A comment * / SELECT" => "SELECT"
+ *    "-- comment\nSELECT"        => "SELECT"
+ *
+ *  @param sql  Pointer to buffer containing a MySQL statement
+ *  @param len  Length of sql.
+ *
+ *  @return The first non whitespace (including comments) character. If the
+ *          entire buffer is only whitespace, the returned pointer will point
+ *          to the character following the buffer (i.e. sql + len).
+ */
+char* modutil_MySQL_bypass_whitespace(char* sql, size_t len);
+
 /** Character and token searching functions */
 char* strnchr_esc(char* ptr, char c, int len);
 char* strnchr_esc_mysql(char* ptr, char c, int len);

server/core/modutil.c

@@ -1213,3 +1213,111 @@ char* modutil_get_canonical(GWBUF* querybuf)
 
     return querystr;
 }
+
+
+char* modutil_MySQL_bypass_whitespace(char* sql, size_t len)
+{
+    char *i = sql;
+    char *end = i + len;
+
+    while (i != end)
+    {
+        if (isspace(*i))
+        {
+            ++i;
+        }
+        else if (*i == '/') // Might be a comment
+        {
+            if ((i + 1 != end) && (*(i + 1) == '*')) // Indeed it was
+            {
+                i += 2;
+
+                while (i != end)
+                {
+                    if (*i == '*') // Might be the end of the comment
+                    {
+                        ++i;
+
+                        if (i != end)
+                        {
+                            if (*i == '/') // Indeed it was
+                            {
+                                ++i;
+                                break; // Out of this inner while.
+                            }
+                        }
+                    }
+                    else
+                    {
+                        // It was not the end of the comment.
+                        ++i;
+                    }
+                }
+            }
+            else
+            {
+                // Was not a comment, so we'll bail out.
+                break;
+            }
+        }
+        else if (*i == '-') // Might be the start of a comment to the end of line
+        {
+            bool is_comment = false;
+
+            if (i + 1 != end)
+            {
+                if (*(i + 1) == '-') // Might be, yes.
+                {
+                    if (i + 2 != end)
+                    {
+                        if (isspace(*(i + 2))) // Yes, it is.
+                        {
+                            is_comment = true;
+
+                            i += 3;
+
+                            while ((i != end) && (*i != '\n'))
+                            {
+                                ++i;
+                            }
+
+                            if (i != end)
+                            {
+                                ss_dassert(*i == '\n');
+                                ++i;
+                            }
+                        }
+                    }
+                }
+            }
+
+            if (!is_comment)
+            {
+                break;
+            }
+        }
+        else if (*i == '#')
+        {
+            ++i;
+
+            while ((i != end) && (*i != '\n'))
+            {
+                ++i;
+            }
+
+            if (i != end)
+            {
+                ss_dassert(*i == '\n');
+                ++i;
+            }
+            break;
+        }
+        else
+        {
+            // Neither whitespace not start of a comment, so we bail out.
+            break;
+        }
+    }
+
+    return i;
+}

server/core/test/testmodutil.c

@@ -578,6 +578,43 @@ void test_large_packets()
     }
 }
 
+char* bypass_whitespace(char* sql)
+{
+    return modutil_MySQL_bypass_whitespace(sql, strlen(sql));
+}
+
+void test_bypass_whitespace()
+{
+    char* sql;
+
+    sql = bypass_whitespace("SELECT");
+    ss_info_dassert(*sql == 'S', "1");
+
+    sql = bypass_whitespace(" SELECT");
+    ss_info_dassert(*sql == 'S', "2");
+
+    sql = bypass_whitespace("\tSELECT");
+    ss_info_dassert(*sql == 'S', "3");
+
+    sql = bypass_whitespace("\nSELECT");
+    ss_info_dassert(*sql == 'S', "4");
+
+    sql = bypass_whitespace("/* comment */SELECT");
+    ss_info_dassert(*sql == 'S', "5");
+
+    sql = bypass_whitespace(" /* comment */ SELECT");
+    ss_info_dassert(*sql == 'S', "6");
+
+    sql = bypass_whitespace("-- comment\nSELECT");
+    ss_info_dassert(*sql == 'S', "7");
+
+    sql = bypass_whitespace("-- comment\n /* comment */ SELECT");
+    ss_info_dassert(*sql == 'S', "8");
+
+    sql = bypass_whitespace("# comment\nSELECT");
+    ss_info_dassert(*sql == 'S', "9");
+}
+
 int main(int argc, char **argv)
 {
     int result = 0;
@@ -591,5 +628,6 @@ int main(int argc, char **argv)
     test_strnchr_esc();
     test_strnchr_esc_mysql();
     test_large_packets();
+    test_bypass_whitespace();
     exit(result);
 }