MDEV-27744 InnoDB: Failing assertion: !cursor->index->is_committed() in row0ins.cc (from row_ins_sec_index_entry_by_modify) | Assertion `0' failed in row_upd_sec_index_entry (debug) | Corruptionbb-10.3-bar-MDEV-27744

The crash happened with an indexed virtual column whose
value is evaluated using a function that has a different meaning
in sql_mode='' vs sql_mode=ORACLE:

- DECODE()
- LTRIM()
- RTRIM()
- LPAD()
- RPAD()
- REPLACE()
- SUBSTR()

For example:

CREATE TABLE t1 (
  b VARCHAR(1),
  g CHAR(1) GENERATED ALWAYS AS (SUBSTR(b,0,0)) VIRTUAL,
  KEY g(g)
);

So far we had replacement XXX_ORACLE() functions for all mentioned function,
e.g. SUBSTR_ORACLE() for SUBSTR(). So it was possible to correctly re-parse
SUBSTR_ORACLE() even in sql_mode=''.

But it was not possible to re-parse the MariaDB version of SUBSTR()
after switching to sql_mode=ORACLE. It was erroneously mis-interpreted
as SUBSTR_ORACLE().

As a result, this combination worked fine:

SET sql_mode=ORACLE;
CREATE TABLE t1 ... g CHAR(1) GENERATED ALWAYS AS (SUBSTR(b,0,0)) VIRTUAL, ...;
INSERT ...
FLUSH TABLES;
SET sql_mode='';
INSERT ...

But the other way around it crashed:

SET sql_mode='';
CREATE TABLE t1 ... g CHAR(1) GENERATED ALWAYS AS (SUBSTR(b,0,0)) VIRTUAL, ...;
INSERT ...
FLUSH TABLES;
SET sql_mode=ORACLE;
INSERT ...

At CREATE time, SUBSTR was instantiated as Item_func_substr and printed
in the FRM file as substr(). At re-open time with sql_mode=ORACLE, "substr()"
was erroneously instantiated as Item_func_substr_oracle.

Fix:

The fix proposes a symmetric solution. It provides a way to re-parse reliably
all sql_mode dependent functions to their original CREATE TABLE time meaning,
no matter what the open-time sql_mode is.

We take advantage of the same idea we previously used to resolve sql_mode
dependent data types.

Now all sql_mode dependent functions are printed by SHOW using a schema
qualifier when the current sql_mode differs from the function sql_mode:

SET sql_mode='';
CREATE TABLE t1 ... SUBSTR(a,b,c) ..;
SET sql_mode=ORACLE;
SHOW CREATE TABLE t1;   ->   mariadb_schema.substr(a,b,c)

SET sql_mode=ORACLE;
CREATE TABLE t2 ... SUBSTR(a,b,c) ..;
SET sql_mode='';
SHOW CREATE TABLE t1;   ->   oracle_schema.substr(a,b,c)

Old replacement names like substr_oracle() are still understood for
backward compatibility and used in FRM files (for downgrade compatibility),
but they are not printed by SHOW any more.

1 files changed, 29 insertions, 8 deletions

diff --git a/sql/sql_lex.h b/sql/sql_lex.h
index 064d0de8905..7729bd82b84 100644
--- a/sql/sql_lex.h
+++ b/sql/sql_lex.h
@@ -2230,6 +2230,15 @@ public:
   void reduce_digest_token(uint token_left, uint token_right);
 
 private:
+
+  enum Ident_mode
+  {
+    GENERAL_KEYWORD_OR_FUNC_LPAREN,
+    QUALIFIED_SPECIAL_FUNC_LPAREN
+  };
+
+  int scan_ident_common(THD *thd, Lex_ident_cli_st *str, Ident_mode mode);
+
   /**
     Set the echo mode.
 
@@ -2427,7 +2436,7 @@ public:
   }
 
   /** Get the raw query buffer. */
-  const char *get_buf()
+  const char *get_buf() const
   {
     return m_buf;
   }
@@ -2439,7 +2448,7 @@ public:
   }
 
   /** Get the end of the raw query buffer. */
-  const char *get_end_of_query()
+  const char *get_end_of_query() const
   {
     return m_end_of_query;
   }
@@ -2483,7 +2492,7 @@ public:
     Get the token end position in the pre-processed buffer,
     with trailing spaces removed.
   */
-  const char *get_cpp_tok_end_rtrim()
+  const char *get_cpp_tok_end_rtrim() const
   {
     const char *p;
     for (p= m_cpp_tok_end;
@@ -2555,9 +2564,9 @@ private:
 
   bool consume_comment(int remaining_recursions_permitted);
   int lex_one_token(union YYSTYPE *yylval, THD *thd);
-  int find_keyword(Lex_ident_cli_st *str, uint len, bool function);
+  int find_keyword(Lex_ident_cli_st *str, uint len, bool function) const;
+  int find_keyword_qualified_special_func(Lex_ident_cli_st *str, uint len) const;
   LEX_CSTRING get_token(uint skip, uint length);
-  int scan_ident_sysvar(THD *thd, Lex_ident_cli_st *str);
   int scan_ident_start(THD *thd, Lex_ident_cli_st *str);
   int scan_ident_middle(THD *thd, Lex_ident_cli_st *str,
                         CHARSET_INFO **cs, my_lex_states *);
@@ -3684,12 +3693,24 @@ public:
                           const Lex_ident_cli_st *var_name,
                           const Lex_ident_cli_st *field_name);
 
-  Item *make_item_func_replace(THD *thd, Item *org, Item *find, Item *replace);
-  Item *make_item_func_substr(THD *thd, Item *a, Item *b, Item *c);
-  Item *make_item_func_substr(THD *thd, Item *a, Item *b);
+  static const Schema *
+    find_func_schema_by_name_or_error(const Lex_ident_sys &schema_name,
+                                      const Lex_ident_sys &func_name);
+  Item *make_item_func_replace(THD *thd,
+                               const Lex_ident_cli_st &schema_name,
+                               const Lex_ident_cli_st &func_name,
+                               Item *org, Item *find, Item *replace);
+  Item *make_item_func_substr(THD *thd,
+                              const Lex_ident_cli_st &schema_name,
+                              const Lex_ident_cli_st &func_name,
+                              const Lex_substring_spec_st &spec);
   Item *make_item_func_call_generic(THD *thd, Lex_ident_cli_st *db,
                                     Lex_ident_cli_st *name, List<Item> *args);
   Item *make_item_func_call_generic(THD *thd,
+                                    const Lex_ident_sys &db,
+                                    const Lex_ident_sys &name,
+                                    List<Item> *args);
+  Item *make_item_func_call_generic(THD *thd,
                                     Lex_ident_cli_st *db,
                                     Lex_ident_cli_st *pkg,
                                     Lex_ident_cli_st *name,