hasherize_csv 0.0.7 → 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- data/.travis.yml +1 -0
- data/README.md +31 -0
- data/lib/hasherize_csv.rb +15 -17
- data/lib/hasherize_csv/version.rb +1 -1
- data/test/test_hasherize_csv.rb +7 -0
- metadata +2 -2
data/.travis.yml
CHANGED
data/README.md
CHANGED
@@ -3,6 +3,7 @@
|
|
3
3
|
|
4
4
|
Dead simple CSV parsing, with configurable regex selectors if required.
|
5
5
|
Reads line-by-line, so you can parse big CSV files without running out of memory.
|
6
|
+
The first line is always assumed to be column headers, and thus keys in the corresponding hash.
|
6
7
|
|
7
8
|
### Simple case
|
8
9
|
Given sample_csv.csv
|
@@ -28,3 +29,33 @@ The output will be
|
|
28
29
|
{'Col1' => 'Val1', 'Col2' => 'Val2', 'Col3' => 'Val3'}
|
29
30
|
{'Col1' => 'Val4', 'Col2' => 'Val5', 'Col3' => 'Val6'}
|
30
31
|
```
|
32
|
+
|
33
|
+
### Complex case: parse strange line endings and elegantly select quoted fields
|
34
|
+
Given complex_sample.csv
|
35
|
+
```csv
|
36
|
+
"Col1";"Col2";"Col3"\r
|
37
|
+
"Val1";"Val2";"Val3"\r
|
38
|
+
"Val4";"Val5
|
39
|
+
|
40
|
+
Oh my, newlines in the record!";"Val6"\r
|
41
|
+
```
|
42
|
+
|
43
|
+
and
|
44
|
+
```ruby
|
45
|
+
require 'hasherize_csv'
|
46
|
+
@f = File.new("complex_sample.csv")
|
47
|
+
|
48
|
+
#HasherizeCsv yields the value of the first match group in the :value_pattern regex
|
49
|
+
@csv = HasherizeCsv::Csv.new(@f, :separator => "\r", :value_pattern => /\"(.*?)\"/m)
|
50
|
+
|
51
|
+
@csv.each do |hash|
|
52
|
+
puts hash.inspect
|
53
|
+
end
|
54
|
+
```
|
55
|
+
|
56
|
+
The output will be
|
57
|
+
```
|
58
|
+
{'Col1' => 'Val1', 'Col2' => 'Val2', 'Col3' => 'Val3'}
|
59
|
+
{'Col1' => 'Val4', 'Col2' => 'Val5\n\nOh my, newlines in the record!', 'Col3' => 'Val6'}
|
60
|
+
```
|
61
|
+
|
data/lib/hasherize_csv.rb
CHANGED
@@ -7,37 +7,35 @@ module HasherizeCsv
|
|
7
7
|
end
|
8
8
|
|
9
9
|
class Csv
|
10
|
+
include Enumerable
|
10
11
|
attr_accessor :keys, :file, :separator
|
11
12
|
def initialize file, opts = {}
|
12
13
|
@file = file
|
13
14
|
@separator = opts[:separator] || DefaultOpts::DEFAULT[:separator]
|
14
15
|
@value_pattern = opts[:value_pattern] || DefaultOpts::DEFAULT[:value_pattern]
|
15
16
|
@keys = []
|
16
|
-
|
17
|
-
end
|
18
|
-
|
19
|
-
def next_item
|
20
|
-
next_line { |l|
|
21
|
-
if l.nil?
|
22
|
-
yield nil
|
23
|
-
else
|
24
|
-
yield hashify_values( values_from_line l )
|
25
|
-
end
|
26
|
-
}
|
17
|
+
@keys = values_from_line next_line
|
27
18
|
end
|
28
19
|
|
29
20
|
def each
|
30
|
-
|
31
|
-
|
32
|
-
|
33
|
-
|
34
|
-
}
|
21
|
+
return self.to_enum if !block_given?
|
22
|
+
|
23
|
+
until (hash = next_item).nil?
|
24
|
+
yield hash
|
35
25
|
end
|
36
26
|
end
|
37
27
|
|
38
28
|
private
|
29
|
+
def next_item
|
30
|
+
if (l = next_line).nil?
|
31
|
+
return nil
|
32
|
+
else
|
33
|
+
return hashify_values( values_from_line l )
|
34
|
+
end
|
35
|
+
end
|
36
|
+
|
39
37
|
def next_line
|
40
|
-
|
38
|
+
@file.gets(@separator) ? $_.chomp : $_
|
41
39
|
end
|
42
40
|
|
43
41
|
def hashify_values values
|
data/test/test_hasherize_csv.rb
CHANGED
@@ -25,6 +25,13 @@ class HasherizeCsvTest < Test::Unit::TestCase
|
|
25
25
|
assert_equal ["Heading1", "Heading2", "H_EA_3__c"], @csv.keys
|
26
26
|
end
|
27
27
|
|
28
|
+
def test_hash_file_enumerator
|
29
|
+
result = []
|
30
|
+
enumerator = @csv.each
|
31
|
+
|
32
|
+
assert_equal({"Heading1"=>"Item1", "Heading2"=>"Item2", "H_EA_3__c"=>"Item3"}, enumerator.next)
|
33
|
+
end
|
34
|
+
|
28
35
|
def test_hash_file
|
29
36
|
result = []
|
30
37
|
@csv.each { |hash|
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: hasherize_csv
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0
|
4
|
+
version: 0.1.0
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -9,7 +9,7 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2013-
|
12
|
+
date: 2013-10-05 00:00:00.000000000 Z
|
13
13
|
dependencies: []
|
14
14
|
description: Turns csv files into hashes without reading the entire csv into memory
|
15
15
|
email:
|