factorylabs-activewarehouse-etl 0.9.1.2 → 0.9.1.3
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/Rakefile +4 -4
- data/lib/etl/engine.rb +2 -2
- data/lib/etl/parser/fixed_width_parser.rb +6 -5
- metadata +1 -2
- data/lib/etl/execution/record.rb +0 -18
data/Rakefile
CHANGED
@@ -72,11 +72,11 @@ module AWETL
|
|
72
72
|
ActiveWarehouse ETL is a pure Ruby Extract-Transform-Load application for loading data into a database.
|
73
73
|
EOF
|
74
74
|
|
75
|
-
s.add_dependency('rake', '>= 0.
|
76
|
-
s.add_dependency('activesupport', '>= 1.
|
77
|
-
s.add_dependency('activerecord', '>= 1.
|
75
|
+
s.add_dependency('rake', '>= 0.8.3')
|
76
|
+
s.add_dependency('activesupport', '>= 2.1.0')
|
77
|
+
s.add_dependency('activerecord', '>= 2.1.0')
|
78
78
|
s.add_dependency('fastercsv', '>= 1.2.0')
|
79
|
-
s.add_dependency('adapter_extensions', '>= 0.
|
79
|
+
s.add_dependency('adapter_extensions', '>= 0.5.0')
|
80
80
|
|
81
81
|
s.rdoc_options << '--exclude' << '.'
|
82
82
|
s.has_rdoc = false
|
data/lib/etl/engine.rb
CHANGED
@@ -470,8 +470,8 @@ module ETL #:nodoc:
|
|
470
470
|
say "Avg transforms: #{Engine.rows_read/benchmarks[:transforms]} rows/sec" if benchmarks[:transforms] > 0
|
471
471
|
say "Avg writes: #{Engine.rows_read/benchmarks[:writes]} rows/sec" if benchmarks[:writes] > 0
|
472
472
|
|
473
|
-
say "Avg time writing execution records: #{ETL::Execution::Record.average_time_spent}"
|
474
|
-
|
473
|
+
# say "Avg time writing execution records: #{ETL::Execution::Record.average_time_spent}"
|
474
|
+
#
|
475
475
|
# ETL::Transform::Transform.benchmarks.each do |klass, t|
|
476
476
|
# say "Avg #{klass}: #{Engine.rows_read/t} rows/sec"
|
477
477
|
# end
|
@@ -13,14 +13,15 @@ module ETL #:nodoc:
|
|
13
13
|
# Return each row
|
14
14
|
def each
|
15
15
|
Dir.glob(file).each do |file|
|
16
|
+
lines_skipped = 0
|
16
17
|
open(file).each do |line|
|
17
18
|
row = {}
|
18
|
-
lines_skipped
|
19
|
+
if lines_skipped < source.skip_lines
|
20
|
+
lines_skipped += 1
|
21
|
+
next
|
22
|
+
end
|
19
23
|
fields.each do |name, f|
|
20
|
-
|
21
|
-
lines_skipped += 1
|
22
|
-
next
|
23
|
-
end
|
24
|
+
|
24
25
|
# TODO make strip optional?
|
25
26
|
row[name] = line[f.field_start, f.field_length].strip
|
26
27
|
end
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: factorylabs-activewarehouse-etl
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.9.1.
|
4
|
+
version: 0.9.1.3
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Anthony Eden
|
@@ -124,7 +124,6 @@ files:
|
|
124
124
|
- lib/etl/execution/batch.rb
|
125
125
|
- lib/etl/execution/job.rb
|
126
126
|
- lib/etl/execution/migration.rb
|
127
|
-
- lib/etl/execution/record.rb
|
128
127
|
- lib/etl/generator/generator.rb
|
129
128
|
- lib/etl/generator/surrogate_key_generator.rb
|
130
129
|
- lib/etl/parser/apache_combined_log_parser.rb
|
data/lib/etl/execution/record.rb
DELETED
@@ -1,18 +0,0 @@
|
|
1
|
-
module ETL #:nodoc:
|
2
|
-
module Execution #:nodoc:
|
3
|
-
# Represents a single record
|
4
|
-
class Record < ETL::Execution::Base
|
5
|
-
belongs_to :table
|
6
|
-
class << self
|
7
|
-
attr_accessor :time_spent
|
8
|
-
def time_spent
|
9
|
-
@time_spent ||= 0
|
10
|
-
end
|
11
|
-
def average_time_spent
|
12
|
-
return 0 if time_spent == 0
|
13
|
-
ETL::Engine.rows_read / time_spent
|
14
|
-
end
|
15
|
-
end
|
16
|
-
end
|
17
|
-
end
|
18
|
-
end
|