MDEV-34376 Wrong data types when mixing an utf8 *TEXT column and a short binary

A mixture of a multi-byte *TEXT column and a short binary column
produced a too large column.
For example, COALESCE(tinytext_utf8mb4, short_varbinary)
produced a BLOB column instead of an expected TINYBLOB.

- Adding a virtual method Type_all_attributes::character_octet_length(),
  returning max_length by default.
- Overriding Item_field::character_octet_length() to extract
  the octet length from the underlying Field.
- Overriding Item_ref::character_octet_length() to extract
  the octet length from the references Item (e.g. as VIEW fields).
- Fixing Type_numeric_attributes::find_max_octet_length() to
  take the octet length using the new method character_octet_length()
  instead of accessing max_length directly.

mysql-test/main/ctype_utf8mb4.result

@@ -4165,5 +4165,126 @@ SELECT 1 COLLATE utf8mb4_bin;
 SELECT 1 COLLATE latin1_swedish_ci;
 ERROR 42000: COLLATION 'latin1_swedish_ci' is not valid for CHARACTER SET 'utf8mb4'
 #
+# MDEV-34376 Wrong data types when mixing an utf8 *TEXT column and a short binary
+#
+CREATE TABLE t1 (
+c_tinytext tinytext,
+c_text text,
+c_mediumtext mediumtext,
+c_longtext longtext
+) CHARACTER SET utf8mb4;
+CREATE VIEW v1 AS SELECT * FROM t1;
+CREATE VIEW v2 AS SELECT * FROM v1;
+# Using table fields
+CREATE TABLE t2 AS SELECT
+COALESCE(c_tinytext,   CAST('binary data' AS BINARY)) AS mix_tinytext_binary,
+COALESCE(c_text,       CAST('binary data' AS BINARY)) AS mix_text_binary,
+COALESCE(c_mediumtext, CAST('binary data' AS BINARY)) AS mix_mediumtext_binary,
+COALESCE(c_longtext, CAST('binary data' AS BINARY)) AS mix_longtext_binary
+FROM t1;
+SHOW CREATE TABLE t2;
+Table	Create Table
+t2	CREATE TABLE `t2` (
+  `mix_tinytext_binary` tinyblob DEFAULT NULL,
+  `mix_text_binary` blob DEFAULT NULL,
+  `mix_mediumtext_binary` mediumblob DEFAULT NULL,
+  `mix_longtext_binary` longblob DEFAULT NULL
+) ENGINE=MyISAM DEFAULT CHARSET=latin1 COLLATE=latin1_swedish_ci
+DROP TABLE t2;
+CREATE TABLE t2 AS SELECT
+c_tinytext   AS mix_tinytext_binary,
+c_text       AS mix_text_binary,
+c_mediumtext AS mix_mediumtext_binary,
+c_longtext   AS mix_longtext_binary
+FROM t1
+UNION SELECT
+CAST('binary data' AS BINARY),
+CAST('binary data' AS BINARY),
+CAST('binary data' AS BINARY),
+CAST('binary data' AS BINARY);
+SHOW CREATE TABLE t2;
+Table	Create Table
+t2	CREATE TABLE `t2` (
+  `mix_tinytext_binary` tinyblob DEFAULT NULL,
+  `mix_text_binary` blob DEFAULT NULL,
+  `mix_mediumtext_binary` mediumblob DEFAULT NULL,
+  `mix_longtext_binary` longblob DEFAULT NULL
+) ENGINE=MyISAM DEFAULT CHARSET=latin1 COLLATE=latin1_swedish_ci
+DROP TABLE t2;
+# Using view fields
+CREATE TABLE t2 AS SELECT
+COALESCE(c_tinytext,   CAST('binary data' AS BINARY)) AS mix_tinytext_binary,
+COALESCE(c_text,       CAST('binary data' AS BINARY)) AS mix_text_binary,
+COALESCE(c_mediumtext, CAST('binary data' AS BINARY)) AS mix_mediumtext_binary,
+COALESCE(c_longtext, CAST('binary data' AS BINARY)) AS mix_longtext_binary
+FROM v1;
+SHOW CREATE TABLE t2;
+Table	Create Table
+t2	CREATE TABLE `t2` (
+  `mix_tinytext_binary` tinyblob DEFAULT NULL,
+  `mix_text_binary` blob DEFAULT NULL,
+  `mix_mediumtext_binary` mediumblob DEFAULT NULL,
+  `mix_longtext_binary` longblob DEFAULT NULL
+) ENGINE=MyISAM DEFAULT CHARSET=latin1 COLLATE=latin1_swedish_ci
+DROP TABLE t2;
+CREATE TABLE t2 AS SELECT
+c_tinytext   AS mix_tinytext_binary,
+c_text       AS mix_text_binary,
+c_mediumtext AS mix_mediumtext_binary,
+c_longtext   AS mix_longtext_binary
+FROM v1
+UNION SELECT
+CAST('binary data' AS BINARY),
+CAST('binary data' AS BINARY),
+CAST('binary data' AS BINARY),
+CAST('binary data' AS BINARY);
+SHOW CREATE TABLE t2;
+Table	Create Table
+t2	CREATE TABLE `t2` (
+  `mix_tinytext_binary` tinyblob DEFAULT NULL,
+  `mix_text_binary` blob DEFAULT NULL,
+  `mix_mediumtext_binary` mediumblob DEFAULT NULL,
+  `mix_longtext_binary` longblob DEFAULT NULL
+) ENGINE=MyISAM DEFAULT CHARSET=latin1 COLLATE=latin1_swedish_ci
+DROP TABLE t2;
+# Using view on view fields
+CREATE TABLE t2 AS SELECT
+COALESCE(c_tinytext,   CAST('binary data' AS BINARY)) AS mix_tinytext_binary,
+COALESCE(c_text,       CAST('binary data' AS BINARY)) AS mix_text_binary,
+COALESCE(c_mediumtext, CAST('binary data' AS BINARY)) AS mix_mediumtext_binary,
+COALESCE(c_longtext, CAST('binary data' AS BINARY)) AS mix_longtext_binary
+FROM v2;
+SHOW CREATE TABLE t2;
+Table	Create Table
+t2	CREATE TABLE `t2` (
+  `mix_tinytext_binary` tinyblob DEFAULT NULL,
+  `mix_text_binary` blob DEFAULT NULL,
+  `mix_mediumtext_binary` mediumblob DEFAULT NULL,
+  `mix_longtext_binary` longblob DEFAULT NULL
+) ENGINE=MyISAM DEFAULT CHARSET=latin1 COLLATE=latin1_swedish_ci
+DROP TABLE t2;
+CREATE TABLE t2 AS SELECT
+c_tinytext   AS mix_tinytext_binary,
+c_text       AS mix_text_binary,
+c_mediumtext AS mix_mediumtext_binary,
+c_longtext   AS mix_longtext_binary
+FROM v2
+UNION SELECT
+CAST('binary data' AS BINARY),
+CAST('binary data' AS BINARY),
+CAST('binary data' AS BINARY),
+CAST('binary data' AS BINARY);
+SHOW CREATE TABLE t2;
+Table	Create Table
+t2	CREATE TABLE `t2` (
+  `mix_tinytext_binary` tinyblob DEFAULT NULL,
+  `mix_text_binary` blob DEFAULT NULL,
+  `mix_mediumtext_binary` mediumblob DEFAULT NULL,
+  `mix_longtext_binary` longblob DEFAULT NULL
+) ENGINE=MyISAM DEFAULT CHARSET=latin1 COLLATE=latin1_swedish_ci
+DROP TABLE t2;
+DROP VIEW v2, v1;
+DROP TABLE t1;
+#
 # End of 10.5 tests
 #

mysql-test/main/ctype_utf8mb4.test

@@ -2062,6 +2062,99 @@ SELECT 1 COLLATE utf8mb4_bin;
 --error ER_COLLATION_CHARSET_MISMATCH
 SELECT 1 COLLATE latin1_swedish_ci;
 
+--echo #
+--echo # MDEV-34376 Wrong data types when mixing an utf8 *TEXT column and a short binary
+--echo #
+
+CREATE TABLE t1 (
+  c_tinytext tinytext,
+  c_text text,
+  c_mediumtext mediumtext,
+  c_longtext longtext
+) CHARACTER SET utf8mb4;
+CREATE VIEW v1 AS SELECT * FROM t1;
+CREATE VIEW v2 AS SELECT * FROM v1;
+
+--echo # Using table fields
+
+CREATE TABLE t2 AS SELECT
+  COALESCE(c_tinytext,   CAST('binary data' AS BINARY)) AS mix_tinytext_binary,
+  COALESCE(c_text,       CAST('binary data' AS BINARY)) AS mix_text_binary,
+  COALESCE(c_mediumtext, CAST('binary data' AS BINARY)) AS mix_mediumtext_binary,
+  COALESCE(c_longtext, CAST('binary data' AS BINARY)) AS mix_longtext_binary
+FROM t1;
+SHOW CREATE TABLE t2;
+DROP TABLE t2;
+
+CREATE TABLE t2 AS SELECT
+  c_tinytext   AS mix_tinytext_binary,
+  c_text       AS mix_text_binary,
+  c_mediumtext AS mix_mediumtext_binary,
+  c_longtext   AS mix_longtext_binary
+FROM t1
+UNION SELECT
+  CAST('binary data' AS BINARY),
+  CAST('binary data' AS BINARY),
+  CAST('binary data' AS BINARY),
+  CAST('binary data' AS BINARY);
+SHOW CREATE TABLE t2;
+DROP TABLE t2;
+
+
+--echo # Using view fields
+
+CREATE TABLE t2 AS SELECT
+  COALESCE(c_tinytext,   CAST('binary data' AS BINARY)) AS mix_tinytext_binary,
+  COALESCE(c_text,       CAST('binary data' AS BINARY)) AS mix_text_binary,
+  COALESCE(c_mediumtext, CAST('binary data' AS BINARY)) AS mix_mediumtext_binary,
+  COALESCE(c_longtext, CAST('binary data' AS BINARY)) AS mix_longtext_binary
+FROM v1;
+SHOW CREATE TABLE t2;
+DROP TABLE t2;
+
+CREATE TABLE t2 AS SELECT
+  c_tinytext   AS mix_tinytext_binary,
+  c_text       AS mix_text_binary,
+  c_mediumtext AS mix_mediumtext_binary,
+  c_longtext   AS mix_longtext_binary
+FROM v1
+UNION SELECT
+  CAST('binary data' AS BINARY),
+  CAST('binary data' AS BINARY),
+  CAST('binary data' AS BINARY),
+  CAST('binary data' AS BINARY);
+SHOW CREATE TABLE t2;
+DROP TABLE t2;
+
+
+--echo # Using view on view fields
+
+CREATE TABLE t2 AS SELECT
+  COALESCE(c_tinytext,   CAST('binary data' AS BINARY)) AS mix_tinytext_binary,
+  COALESCE(c_text,       CAST('binary data' AS BINARY)) AS mix_text_binary,
+  COALESCE(c_mediumtext, CAST('binary data' AS BINARY)) AS mix_mediumtext_binary,
+  COALESCE(c_longtext, CAST('binary data' AS BINARY)) AS mix_longtext_binary
+FROM v2;
+SHOW CREATE TABLE t2;
+DROP TABLE t2;
+
+CREATE TABLE t2 AS SELECT
+  c_tinytext   AS mix_tinytext_binary,
+  c_text       AS mix_text_binary,
+  c_mediumtext AS mix_mediumtext_binary,
+  c_longtext   AS mix_longtext_binary
+FROM v2
+UNION SELECT
+  CAST('binary data' AS BINARY),
+  CAST('binary data' AS BINARY),
+  CAST('binary data' AS BINARY),
+  CAST('binary data' AS BINARY);
+SHOW CREATE TABLE t2;
+DROP TABLE t2;
+
+DROP VIEW v2, v1;
+DROP TABLE t1;
+
 --echo #
 --echo # End of 10.5 tests
 --echo #

sql/item.h

@@ -3576,6 +3576,10 @@ public:
       return &type_handler_null;
     return field->type_handler();
   }
+  uint32 character_octet_length() const override
+  {
+    return field->character_octet_length();
+  }
   Field *create_tmp_field_from_item_field(MEM_ROOT *root, TABLE *new_table,
                                           Item_ref *orig_item,
                                           const Tmp_field_param *param);
@@ -5578,6 +5582,10 @@ public:
   { return (*ref)->type_handler(); }
   const Type_handler *real_type_handler() const override
   { return (*ref)->real_type_handler(); }
+  uint32 character_octet_length() const override
+  {
+    return Item_ref::real_item()->character_octet_length();
+  }
   Field *get_tmp_table_field() override
   { return result_field ? result_field : (*ref)->get_tmp_table_field(); }
   Item *get_tmp_table_item(THD *thd) override;
@@ -5616,6 +5624,10 @@ public:
     (*ref)->save_in_field(result_field, no_conversions);
   }
   Item *real_item() override { return ref ? (*ref)->real_item() : this; }
+  const Item *real_item() const
+  {
+    return const_cast<Item_ref*>(this)->Item_ref::real_item();
+  }
   const TYPELIB *get_typelib() const override
   {
     return ref ? (*ref)->get_typelib() : NULL;

sql/sql_type.cc

@@ -1221,7 +1221,7 @@ uint32 Type_numeric_attributes::find_max_octet_length(Item **item, uint nitems)
 {
   uint32 octet_length= 0;
   for (uint i= 0; i < nitems ; i++)
-    set_if_bigger(octet_length, item[i]->max_length);
+    set_if_bigger(octet_length, item[i]->character_octet_length());
   return octet_length;
 }
 

sql/sql_type.h

@@ -3345,6 +3345,7 @@ public:
   { }
   virtual ~Type_all_attributes() = default;
   virtual void set_maybe_null(bool maybe_null_arg)= 0;
+  virtual uint32 character_octet_length() const { return max_length; }
   // Returns total number of decimal digits
   virtual uint decimal_precision() const= 0;
   virtual const TYPELIB *get_typelib() const= 0;