csv_piper 0.1.3 → 0.1.4
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.
- checksums.yaml +4 -4
- data/.travis.yml +4 -0
- data/README.md +2 -0
- data/lib/csv_piper/piper.rb +1 -1
- data/lib/csv_piper/pre_processors/remove_extra_columns.rb +12 -2
- data/lib/csv_piper/version.rb +1 -1
- metadata +2 -1
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 8769722439ae9b640dedf199eb2a16a23d8b8be7
|
|
4
|
+
data.tar.gz: 1d4b35a6277fec01080e61831913dac7bce9b499
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 1a5c885a3513e441075c0de6e99b46f1be3eb63d9408a894566290ca262c3b6313a04527ce24cc89ac7cf231b72542418df232c785e7448cb3a7c567be07128f
|
|
7
|
+
data.tar.gz: 608d031277fb6b598d9da0b295b80e7347e4668ab7d1891d080cdaed870a55b58dbeb0917333bfaa6030bc4af0b1d5a8da9fcfe74787643e30e41fd8e87a9571
|
data/.travis.yml
ADDED
data/README.md
CHANGED
|
@@ -1,3 +1,5 @@
|
|
|
1
|
+
[](http://badge.fury.io/rb/csv_piper) [](https://travis-ci.org/jazzarati/csv_piper)
|
|
2
|
+
|
|
1
3
|
# CsvPiper
|
|
2
4
|
|
|
3
5
|
A simple wrapper to create a pipeline style csv processor that makes your transforms easily testable.
|
data/lib/csv_piper/piper.rb
CHANGED
|
@@ -5,7 +5,7 @@ module CsvPiper
|
|
|
5
5
|
CSV_HEADER_OPTIONS = { headers: true, return_headers: true, skip_blanks: true, skip_lines: /^(\s*,)*$/ }
|
|
6
6
|
|
|
7
7
|
def initialize(io_stream:, pre_processors: [], processors: [], csv_options: {}, required_headers: [])
|
|
8
|
-
@pre_processors =
|
|
8
|
+
@pre_processors = pre_processors
|
|
9
9
|
@processors = processors
|
|
10
10
|
@required_headers = required_headers
|
|
11
11
|
@csv_options = csv_options.merge(CSV_HEADER_OPTIONS)
|
|
@@ -1,10 +1,20 @@
|
|
|
1
1
|
module CsvPiper
|
|
2
2
|
module PreProcessors
|
|
3
|
-
class
|
|
3
|
+
class RemoveEmptyColumns
|
|
4
4
|
def process(origin, errors)
|
|
5
|
-
modified_origin = origin.reject { |key,
|
|
5
|
+
modified_origin = origin.reject { |key, _| key.nil? || key.strip.empty? }
|
|
6
6
|
[modified_origin, errors]
|
|
7
7
|
end
|
|
8
8
|
end
|
|
9
|
+
|
|
10
|
+
# Just removing nil is significanlty faster for large csvs (100M+ cells)
|
|
11
|
+
# (10M cells = ~20x faster on 10 col row [3.8s vs 0.19s], ~100x faster on 1000 col row [3.8s vs 0.035s]).
|
|
12
|
+
# Even better is your processors don't need this pre-processing.
|
|
13
|
+
class RemoveNilColumns
|
|
14
|
+
def process(origin, errors)
|
|
15
|
+
origin.delete(nil)
|
|
16
|
+
[origin, errors]
|
|
17
|
+
end
|
|
18
|
+
end
|
|
9
19
|
end
|
|
10
20
|
end
|
data/lib/csv_piper/version.rb
CHANGED
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: csv_piper
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.1.
|
|
4
|
+
version: 0.1.4
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Jarrod Sibbison
|
|
@@ -101,6 +101,7 @@ extra_rdoc_files: []
|
|
|
101
101
|
files:
|
|
102
102
|
- ".gitignore"
|
|
103
103
|
- ".rspec"
|
|
104
|
+
- ".travis.yml"
|
|
104
105
|
- Gemfile
|
|
105
106
|
- LICENSE.txt
|
|
106
107
|
- README.md
|