arc-furnace 0.1.32 → 0.1.33
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/arc-furnace/csv_source.rb +34 -4
- data/lib/arc-furnace/excel_source.rb +4 -0
- data/lib/arc-furnace/version.rb +1 -1
- metadata +2 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 56c1cd7c32681828afee985402338a2774d6ebf2
|
4
|
+
data.tar.gz: d9d3aa812fa74ea4f49213d6aeb040a37b33ac75
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: b7b51fe6a3dc7f886e3e6e363fe73eb2e69bb70726e34aaf3d0f3aa88b54ad4ff611d24b5b599e982bc61fe72cadffdeaa5af4a07be6ad71ceb686be8c12d8f6
|
7
|
+
data.tar.gz: d7e7f3da2908a4ac93ba9febd6e4b02f32dabf8773b2b1bb42dbc4864ff515a2aa1dfe470cc4cfbb7f9ebafa1d3f119f585895f971c2f1aa94f53755a0126aac
|
@@ -6,27 +6,57 @@ module ArcFurnace
|
|
6
6
|
class CSVSource < EnumeratorSource
|
7
7
|
include CSVToHashWithDuplicateHeaders
|
8
8
|
|
9
|
-
attr_reader :value, :file, :csv, :delimiter
|
9
|
+
attr_reader :value, :file, :csv, :delimiter, :group_by,
|
10
|
+
:key_column, :preprocessed_csv
|
10
11
|
|
11
12
|
COMMA = ','.freeze
|
12
13
|
|
13
|
-
def initialize(
|
14
|
+
def initialize(
|
15
|
+
filename: nil,
|
16
|
+
csv: nil,
|
17
|
+
encoding: 'UTF-8',
|
18
|
+
delimiter: COMMA,
|
19
|
+
group_by: false,
|
20
|
+
key_column: nil
|
21
|
+
)
|
14
22
|
@file = File.open(filename, encoding: encoding) if filename
|
15
23
|
@csv = csv
|
16
24
|
@delimiter = delimiter
|
25
|
+
@preprocessed_csv = []
|
26
|
+
@group_by = group_by
|
27
|
+
@key_column = key_column
|
17
28
|
super()
|
18
29
|
end
|
19
30
|
|
31
|
+
alias_method :group_by?, :group_by
|
32
|
+
|
33
|
+
#
|
34
|
+
# note that group_by requires the entire file to be
|
35
|
+
# read into memory
|
36
|
+
#
|
37
|
+
def preprocess
|
38
|
+
if group_by?
|
39
|
+
parse_file { |row| @preprocessed_csv << csv_to_hash_with_duplicates(row) }
|
40
|
+
@preprocessed_csv = @preprocessed_csv.group_by { |row| row[key_column] }
|
41
|
+
end
|
42
|
+
end
|
43
|
+
|
20
44
|
def finalize
|
21
45
|
file.close if file
|
22
46
|
end
|
23
47
|
|
24
48
|
def build_enumerator
|
25
49
|
Enumerator.new do |yielder|
|
26
|
-
|
27
|
-
|
50
|
+
if group_by?
|
51
|
+
preprocessed_csv.each { |_, array| yielder.yield(array) }
|
52
|
+
else
|
53
|
+
parse_file { |row| yielder.yield(csv_to_hash_with_duplicates(row)) }
|
28
54
|
end
|
29
55
|
end
|
30
56
|
end
|
57
|
+
|
58
|
+
def parse_file
|
59
|
+
(csv ? csv : CSV.new(file, { headers: true, col_sep: delimiter })).each { |row| yield row }
|
60
|
+
end
|
31
61
|
end
|
32
62
|
end
|
data/lib/arc-furnace/version.rb
CHANGED
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: arc-furnace
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.33
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Daniel Spangenberger
|
@@ -9,7 +9,7 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: exe
|
11
11
|
cert_chain: []
|
12
|
-
date: 2018-04-
|
12
|
+
date: 2018-04-05 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: msgpack
|