MySQL 聚合函数初探

enum Sumfunctype {
    COUNT_FUNC,           // COUNT
    COUNT_DISTINCT_FUNC,  // COUNT (DISTINCT)
    SUM_FUNC,             // SUM
    SUM_DISTINCT_FUNC,    // SUM (DISTINCT)
    AVG_FUNC,             // AVG
    AVG_DISTINCT_FUNC,    // AVG (DISTINCT)
    MIN_FUNC,             // MIN
    MAX_FUNC,             // MAX
    STD_FUNC,             // STD/STDDEV/STDDEV_POP
    VARIANCE_FUNC,        // VARIANCE/VAR_POP and VAR_SAMP
    SUM_BIT_FUNC,         // BIT_AND, BIT_OR and BIT_XOR
    UDF_SUM_FUNC,         // user defined functions
    GROUP_CONCAT_FUNC,    // GROUP_CONCAT
    JSON_AGG_FUNC,        // JSON_ARRAYAGG and JSON_OBJECTAGG
    ROW_NUMBER_FUNC,      // Window functions
    RANK_FUNC,
    DENSE_RANK_FUNC,
    CUME_DIST_FUNC,
    PERCENT_RANK_FUNC,
    NTILE_FUNC,
    LEAD_LAG_FUNC,
    FIRST_LAST_VALUE_FUNC,
    NTH_VALUE_FUNC,
    ROLLUP_SUM_SWITCHER_FUNC,
    GEOMETRY_AGGREGATE_FUNC
  };

CREATE TABLE test_agg (c1 int NULL)

INSERT into test_agg values(1),(2),(3),(3),(4),(4),(5),(5),(5);

SELECT count(DISTINCT c1) from test_agg;

class Aggregator_simple : public Aggregator {
 public:
  Aggregator_simple(Item_sum *sum) : Aggregator(sum) {}
  Aggregator_type Aggrtype() override { return Aggregator::SIMPLE_AGGREGATOR; }
  bool setup(THD *thd) override { return item_sum->setup(thd); }
  void clear() override { item_sum->clear(); }
  bool add() override { return item_sum->add(); }
  void endup() override {}
};
class Aggregator_distinct : public Aggregator {
 public:
  ~Aggregator_distinct() override;
  Aggregator_type Aggrtype() override { return DISTINCT_AGGREGATOR; }

  bool setup(THD *) override;
  void clear() override;
  bool add() override;
  void endup() override;
};

if (!(table = create_tmp_table(thd, tmp_table_param, list, nullptr, true,
                                   false, query_block->active_options(),
                                   HA_POS_ERROR, "")))
if (all_binary) {
        cmp_arg = (void *)&tree_key_length;
        compare_key = simple_raw_key_cmp;
} else {
    if (table->s->fields == 1) {
        compare_key = simple_str_key_cmp;
        cmp_arg = (void *)table->field[0];
    } else {
        uint32 *length;
        compare_key = composite_key_cmp;
        ....
     }
  }
 tree = new (thd->mem_root) Unique(compare_key, cmp_arg, tree_key_length,
          item_sum->ram_limitation(thd));
 if (!tree) return true;

if (tree) {
      return tree->unique_add(table->record[0] + table->s->null_bytes);
    }
    if (!check_unique_constraint(table)) return false;
    if ((error = table->file->ha_write_row(table->record[0])) &&
        !table->file->is_ignorable_error(error))

inline bool unique_add(void *ptr) {
    DBUG_TRACE;
    DBUG_PRINT("info", ("tree %u - %lu", tree.elements_in_tree, max_elements));
    if (tree.elements_in_tree > max_elements && flush()) return true;
    return !tree_insert(&tree, ptr, 0, tree.custom_arg);
  }
bool Unique::flush() {
  Merge_chunk file_ptr;
  elements += tree.elements_in_tree;
  file_ptr.set_rowcount(tree.elements_in_tree);
  file_ptr.set_file_position(my_b_tell(&file));
  if (tree_walk(&tree, unique_write_to_file, this, left_root_right) ||
      file_ptrs.push_back(file_ptr))
    return true; /* purecov: inspected */
  delete_tree(&tree);
  return false;
}

if (tree && tree->is_in_memory()) {
      sum->count = (longlong)tree->elements_in_tree();
      endup_done = true;
    }
    if (!tree) {
      table->file->info(HA_STATUS_VARIABLE | HA_STATUS_NO_LOCK);
      if (table->file->ha_table_flags() & HA_STATS_RECORDS_IS_EXACT)
        sum->count = table->file->stats.records;
      else {
        if (table->file->inited) table->file->ha_index_or_rnd_end();
        ha_rows num_rows = 0;
        table->file->ha_records(&num_rows);
        if (table->hash_field) table->file->ha_index_init(0, false);
        sum->count = static_cast<longlong>(num_rows);
      }
      endup_done = true;
    }