feat(shannon): to support vector data type

client/mysql.cc

@@ -1162,6 +1162,11 @@ static COMMANDS commands[] = {
     {"TO_DAYS", 0, nullptr, false, ""},
     {"TOUCHES", 0, nullptr, false, ""},
     {"TRIM", 0, nullptr, false, ""},
+    {"TO_VECTOR", 0, nullptr, false, ""},
+    {"STRING_TO_VECTOR", 0, nullptr, false, ""},
+    {"FROM_VECTOR", 0, nullptr, false, ""},
+    {"VECTOR_TO_STRING", 0, nullptr, false, ""},
+    {"VECTOR_DIM", 0, nullptr, false, ""},
     {"UCASE", 0, nullptr, false, ""},
     {"UNCOMPRESS", 0, nullptr, false, ""},
     {"UNCOMPRESSED_LENGTH", 0, nullptr, false, ""},
@@ -3925,6 +3930,7 @@ static bool is_binary_field(MYSQL_FIELD *field) {
            field->type == MYSQL_TYPE_VAR_STRING ||
            field->type == MYSQL_TYPE_STRING ||
            field->type == MYSQL_TYPE_VARCHAR ||
+           field->type == MYSQL_TYPE_VECTOR ||
            field->type == MYSQL_TYPE_GEOMETRY));
 }
 

client/mysqldump.cc

@@ -4156,6 +4156,7 @@ static void dump_table(char *table, char *db) {
                                         field->type == MYSQL_TYPE_VAR_STRING ||
                                         field->type == MYSQL_TYPE_VARCHAR ||
                                         field->type == MYSQL_TYPE_BLOB ||
+                                        field->type == MYSQL_TYPE_VECTOR ||
                                         field->type == MYSQL_TYPE_LONG_BLOB ||
                                         field->type == MYSQL_TYPE_MEDIUM_BLOB ||
                                         field->type == MYSQL_TYPE_TINY_BLOB ||

client/mysqltest.cc

@@ -8302,6 +8302,30 @@ static void append_field(DYNAMIC_STRING *ds, uint col_idx, MYSQL_FIELD *field,
   }
 #endif
 
+  const size_t temp_val_max_width = (1 << 14);
+  char temp_val[temp_val_max_width];
+  DYNAMIC_STRING ds_temp = {.str = nullptr, .length = 0, .max_length = 0};
+  if (field->type == MYSQL_TYPE_VECTOR && !is_null) {
+    /* Do a binary to hex conversion for vector type */
+    size_t orig_len = len;
+    len = 2 + orig_len * 2;
+    char *destination = temp_val;
+    if (len > temp_val_max_width) {
+      init_dynamic_string(&ds_temp, "", len + 1);
+      destination = ds_temp.str;
+    }
+    const char *ptr = val;
+    const char *end = ptr + orig_len;
+    val = destination;
+    int written = sprintf(destination, "0x");
+    destination += written;
+    for (; ptr < end; ptr++, destination += written) {
+      written = sprintf(
+          destination, "%02X",
+          *(static_cast<const uchar *>(static_cast<const void *>(ptr))));
+    }
+  }
+
   if (!display_result_vertically) {
     if (col_idx) dynstr_append_mem(ds, "\t", 1);
     replace_dynstr_append_mem(ds, val, len);
@@ -8311,6 +8335,9 @@ static void append_field(DYNAMIC_STRING *ds, uint col_idx, MYSQL_FIELD *field,
     replace_dynstr_append_mem(ds, val, len);
     dynstr_append_mem(ds, "\n", 1);
   }
+  if (ds_temp.str != nullptr) {
+    dynstr_free(&ds_temp);
+  }
 }
 
 /*

cmake/mysql_version.cmake

@@ -26,7 +26,7 @@
 #
 
 SET(SHARED_LIB_MAJOR_VERSION "24")
-SET(SHARED_LIB_MINOR_VERSION "0")
+SET(SHARED_LIB_MINOR_VERSION "1")
 SET(PROTOCOL_VERSION "10")
 
 # Generate "something" to trigger cmake rerun when MYSQL_VERSION changes

include/field_types.h

@@ -74,6 +74,7 @@ enum enum_field_types {
   MYSQL_TYPE_DATETIME2,   /**< Internal to MySQL. Not used in protocol */
   MYSQL_TYPE_TIME2,       /**< Internal to MySQL. Not used in protocol */
   MYSQL_TYPE_TYPED_ARRAY, /**< Used for replication only */
+  MYSQL_TYPE_VECTOR = 242,
   MYSQL_TYPE_INVALID = 243,
   MYSQL_TYPE_BOOL = 244, /**< Currently just a placeholder */
   MYSQL_TYPE_JSON = 245,

include/mysql.h.pp

@@ -23,6 +23,7 @@
   MYSQL_TYPE_DATETIME2,
   MYSQL_TYPE_TIME2,
   MYSQL_TYPE_TYPED_ARRAY,
+  MYSQL_TYPE_VECTOR = 242,
   MYSQL_TYPE_INVALID = 243,
   MYSQL_TYPE_BOOL = 244,
   MYSQL_TYPE_JSON = 245,

include/mysql/components/services/bits/stored_program_bits.h

@@ -59,5 +59,6 @@
 #define MYSQL_SP_ARG_TYPE_VAR_STRING (1ULL << 31)
 #define MYSQL_SP_ARG_TYPE_STRING (1ULL << 32)
 #define MYSQL_SP_ARG_TYPE_GEOMETRY (1ULL << 33)
+#define MYSQL_SP_ARG_TYPE_VECTOR (1ULL << 34)
 
 #endif

libmysql/libmysql.cc

@@ -2915,6 +2915,7 @@ static void fetch_string_with_conversion(MYSQL_BIND *param, char *value,
     case MYSQL_TYPE_MEDIUM_BLOB:
     case MYSQL_TYPE_LONG_BLOB:
     case MYSQL_TYPE_BLOB:
+    case MYSQL_TYPE_VECTOR:
     case MYSQL_TYPE_DECIMAL:
     case MYSQL_TYPE_NEWDECIMAL:
     default: {
@@ -3526,6 +3527,7 @@ static bool is_binary_compatible(enum enum_field_types type1,
       range4[] = {
           MYSQL_TYPE_ENUM,        MYSQL_TYPE_SET,       MYSQL_TYPE_TINY_BLOB,
           MYSQL_TYPE_MEDIUM_BLOB, MYSQL_TYPE_LONG_BLOB, MYSQL_TYPE_BLOB,
+          MYSQL_TYPE_VECTOR,
           MYSQL_TYPE_VAR_STRING,  MYSQL_TYPE_STRING,    MYSQL_TYPE_GEOMETRY,
           MYSQL_TYPE_DECIMAL,     MYSQL_TYPE_NULL};
   static const enum enum_field_types *range_list[] = {range1, range2, range3,
@@ -3628,6 +3630,7 @@ static bool setup_one_fetch_function(MYSQL_BIND *param, MYSQL_FIELD *field) {
     case MYSQL_TYPE_MEDIUM_BLOB:
     case MYSQL_TYPE_LONG_BLOB:
     case MYSQL_TYPE_BLOB:
+    case MYSQL_TYPE_VECTOR:
     case MYSQL_TYPE_BIT:
       assert(param->buffer_length != 0);
       param->fetch_result = fetch_result_bin;

libs/mysql/binlog/event/binary_log_funcs.cpp

@@ -189,6 +189,7 @@ unsigned int max_display_length_for_field(enum_field_types sql_type,
        */
       return uint_max(metadata * 8);
 
+    case MYSQL_TYPE_VECTOR:
     case MYSQL_TYPE_LONG_BLOB:
     case MYSQL_TYPE_GEOMETRY:
     case MYSQL_TYPE_JSON:
@@ -347,6 +348,7 @@ uint32_t calc_field_size(unsigned char col, const unsigned char *master_data,
     case MYSQL_TYPE_MEDIUM_BLOB:
     case MYSQL_TYPE_LONG_BLOB:
     case MYSQL_TYPE_BLOB:
+    case MYSQL_TYPE_VECTOR:
     case MYSQL_TYPE_GEOMETRY:
     case MYSQL_TYPE_JSON: {
       /*

libs/mysql/binlog/event/rows_event.cpp

@@ -253,6 +253,24 @@ static void parse_geometry_type(std::vector<unsigned int> &vec,
   }
 }
 
+/**
+   Parses VECTOR_DIMENSIONALITY field.
+   @param[out] vec        stores vector columns's dimensionality extracted from
+   field.
+   @param[in]  reader_obj the Event_reader object containing the serialized
+                          field.
+   @param[in]  length     length of the field
+ */
+static void parse_vector_dimensionality(std::vector<unsigned int> &vec,
+                                        Event_reader &reader_obj,
+                                        unsigned int length) {
+  const char *field = reader_obj.ptr();
+  while (reader_obj.ptr() < field + length) {
+    vec.push_back(reader_obj.net_field_length_ll());
+    if (reader_obj.has_error()) return;
+  }
+}
+
 /**
    Parses SIMPLE_PRIMARY_KEY field.
 
@@ -373,6 +391,9 @@ Table_map_event::Optional_metadata_fields::Optional_metadata_fields(
       case COLUMN_VISIBILITY:
         parse_column_visibility(&m_column_visibility, reader_obj, len);
         break;
+      case VECTOR_DIMENSIONALITY:
+        parse_vector_dimensionality(m_vector_dimensionality, reader_obj, len);
+        break;
       default:
         BAPI_ASSERT(0);
     }

libs/mysql/binlog/event/rows_event.h

@@ -567,8 +567,9 @@ class Table_map_event : public Binary_log_event {
                                      columns, optimized to minimize
                                      space when many columns have the
                                      same charset. */
-    COLUMN_VISIBILITY             /* Flag to indicate column visibility
-                                     attribute. */
+    COLUMN_VISIBILITY,             /* Flag to indicate column visibility
+                                      attribute. */
+    VECTOR_DIMENSIONALITY         /* Vector column dimensionality */
   };
 
   /**
@@ -605,6 +606,7 @@ class Table_map_event : public Binary_log_event {
     std::vector<str_vector> m_enum_str_value;
     std::vector<str_vector> m_set_str_value;
     std::vector<unsigned int> m_geometry_type;
+    std::vector<unsigned int> m_vector_dimensionality;
     /*
       The uint_pair means <column index, prefix length>.  Prefix length is 0 if
       whole column value is used.