Class: Statlysis::Javascript::MultiDimensionalCount

Inherits:
Object
  • Object
show all
Defined in:
lib/statlysis/javascript/count.rb

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(cron) ⇒ MultiDimensionalCount

Returns a new instance of MultiDimensionalCount.



9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
 
# File 'lib/statlysis/javascript/count.rb', line 9

def initialize cron
  @cron = cron

  # setup group_by_columns
  _group_by_columns = :_id if cron.group_by_columns.blank?
  _group_by_columns ||= cron.group_by_columns.map {|i| i[:column_name] }
  emit_key = _group_by_columns.map {|dc| "#{dc}: this.#{dc}" }.join(", ")
  emit_key = "{#{emit_key}}"

  # TODO setup sum_columns
  # default_emit_values_array += cron.sum_columns.map {|_sum_column| "#{_sum_column}: this.#{_sum_column}" }

  # setup group_concat_columns
  # NOTE if only one uniq emit value, then it'll never be appeared in reduce function
  emit_values_init_array = cron.group_concat_columns.map do |_group_concat_column|
    "emit_value.#{_group_concat_column}_values = [this.#{_group_concat_column}];\n"
  end
  emit_values_init_array += (_group_by_columns.map do |_group_by_column|
    "emit_value.#{_group_by_column} = this.#{_group_by_column};\n"
  end)

  @map_func = "function() {
    var emit_value = {count: 1};
    #{emit_values_init_array.join}

    emit (#{emit_key}, emit_value);
  }"

  # sum_init_values = cron.sum_columns.map {|_sum_column| "#{_sum_column} = 0.0" }
  # sum_init_values = "var #{sum_init_values};" if cron.sum_columns.any?

  # 如果使用Hash，将导致group_concat最终的数目和group_by数目不一致，因为多个任务并行时会导致覆盖(常见于个数多的分类，一个的则不会有这个问题），而可并行化的数组则不会。
  group_concat_values_init_array = cron.group_concat_columns.map {|_group_concat_column| "reducedObject.#{_group_concat_column}_values = [];" }
  group_concat_values_process_array = cron.group_concat_columns.map do |_group_concat_column|
    "reducedObject.#{_group_concat_column}_values = reducedObject.#{_group_concat_column}_values.concat(v['#{_group_concat_column}_values']);\n"
  end
  group_by_values_process_array = _group_by_columns.map do |_group_by_column|
    "reducedObject.#{_group_by_column} = v.#{_group_by_column};\n"
  end

  # emit value in map func should be the same structure as the
  # return value in reduce func, see more details in
  # http://rickosborne.org/download/SQL-to-MongoDB.pdf and
  # http://docs.mongodb.org/manual/tutorial/perform-incremental-map-reduce/
  @reduce_func = "function(key, values) {
    var reducedObject = key;
    reducedObject.count = 0;
    #{group_concat_values_init_array.join}

    values.forEach(function(v) {
      reducedObject.count += v['count'];
      #{group_by_values_process_array.join}
      #{group_concat_values_process_array.join}
    });

    return reducedObject;
  }"

  return self
end

Instance Attribute Details

#cron ⇒ Object (readonly)

Returns the value of attribute cron.



7
8
9
 
# File 'lib/statlysis/javascript/count.rb', line 7

def cron
  @cron
end

#map_func ⇒ Object (readonly)

Returns the value of attribute map_func.



6
7
8
 
# File 'lib/statlysis/javascript/count.rb', line 6

def map_func
  @map_func
end

#reduce_func ⇒ Object (readonly)

Returns the value of attribute reduce_func.



6
7
8
 
# File 'lib/statlysis/javascript/count.rb', line 6

def reduce_func
  @reduce_func
end