separa 0.0.2 → 0.0.3
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.gitignore +1 -1
- data/CHANGELOG.md +9 -0
- data/README.md +62 -1
- data/lib/Separa/obj.rb +26 -11
- data/lib/separa.rb +2 -0
- data/makefile +1 -1
- data/separa.gemspec +2 -2
- data/tests/separa_test.rb +8 -8
- metadata +4 -3
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 3f1473a4f606c3fe324c23ef40d6415774476fef
|
4
|
+
data.tar.gz: 59f26263e9ab27476361ebe6723ed9bbdb1f1990
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 79710d6e1abe160fd512d4c8a2ce6176ddcdee2e401c1d2836b50a5d5df36a97d3f8599dabea7f2a4edc8e9ad336e8eff901e0d908b5bbcb77ac95242436cdb6
|
7
|
+
data.tar.gz: d5b64d73087a76e06f00159cb0a16dd90098fdfbb1121c816ce30c8bd31e52aa71912093486e10954e11c6ace7711aca782981bbef25da2f2a13bbc68461f642
|
data/.gitignore
CHANGED
@@ -1 +1 @@
|
|
1
|
-
|
1
|
+
*.gem
|
data/CHANGELOG.md
ADDED
data/README.md
CHANGED
@@ -6,7 +6,7 @@ Separa splits chunks of text into tokens to be indexed
|
|
6
6
|
Description
|
7
7
|
-----------
|
8
8
|
|
9
|
-
Separa splits chunks of text or ruby objects into tokens to be indexed by [Busca](https://github.com/Porta/busca), the simple redis search
|
9
|
+
Separa splits chunks of text or ruby objects into tokens to be indexed by [Busca](https://github.com/Porta/busca), the simple redis search.
|
10
10
|
|
11
11
|
## Installation
|
12
12
|
|
@@ -18,3 +18,64 @@ $ gem install separa
|
|
18
18
|
|
19
19
|
## Usage
|
20
20
|
|
21
|
+
The simplest possible usage is with default options:
|
22
|
+
|
23
|
+
```ruby
|
24
|
+
separa = Separa.new
|
25
|
+
words = "This is a bunch of words. Separated"
|
26
|
+
result = separa.call(words)
|
27
|
+
puts result.inspect
|
28
|
+
# ["This", "is", "a", "bunch", "of", "words", "", "Separated"]
|
29
|
+
```
|
30
|
+
|
31
|
+
You'll notice a few things here:
|
32
|
+
* There's an empty element between `words` and `Separated`
|
33
|
+
* Words kept their capitalization
|
34
|
+
|
35
|
+
That's all intended. Separa only takes care of spliting the string into an array. It is up to you to filter later that array.
|
36
|
+
|
37
|
+
Separa comes bundled with two 'Separators', but you can roll your own (more on that later).
|
38
|
+
The separator usage is fairly simple, just pass the separator to the `Separa.new` constructor.
|
39
|
+
|
40
|
+
[Separa::Text](./lib/Separa/text.rb) Splits a string of text into an array. You can pass a regexp to be used on the split.
|
41
|
+
|
42
|
+
[Separa::Obj](./lib/Separa/obj.rb) Splits a ruby hash into an array. This is where things get interesting.
|
43
|
+
Let's see a example:
|
44
|
+
|
45
|
+
```ruby
|
46
|
+
separa = Separa.new(Separa::Obj)
|
47
|
+
h = { uno: 1, dos: 2, tres: {uno: 'one', dos: 'two'} }
|
48
|
+
result = separa.call(h)
|
49
|
+
puts result.inspect
|
50
|
+
# ["uno:1", "dos:2", "tres.uno:one", "tres.dos:two"]
|
51
|
+
```
|
52
|
+
|
53
|
+
By default, Separa::Obj will use a semicollon divide the object key and it's value. You can change that passing a different divider.
|
54
|
+
|
55
|
+
```ruby
|
56
|
+
separa = Separa.new(Separa::Obj, divider: '-')
|
57
|
+
h = { uno: 1, dos: 2, tres: {uno: 'one', dos: 'two'} }
|
58
|
+
result = separa.call(h)
|
59
|
+
puts result.inspect
|
60
|
+
# ["uno-1", "dos-2", "tres.uno-one", "tres.dos-two"]
|
61
|
+
```
|
62
|
+
|
63
|
+
|
64
|
+
## Roll your own separator
|
65
|
+
|
66
|
+
Writting your own separator is fairly simple. You only need to take care of 3 things.
|
67
|
+
|
68
|
+
* It should respond to a `call` method.
|
69
|
+
* The `call` method should receive 2 parameters. The string to split and a hash with options.
|
70
|
+
* It should return an array. (Actually, returning an array isn't required, but recommended. I mean, that's *half* of the objective of this library, right?)
|
71
|
+
|
72
|
+
Take a look at the bundled separators if you need inspiration:
|
73
|
+
|
74
|
+
[Separa::Text](./lib/Separa/text.rb)
|
75
|
+
|
76
|
+
[Separa::Obj](./lib/Separa/obj.rb)
|
77
|
+
|
78
|
+
The code is pretty straightforward.
|
79
|
+
|
80
|
+
Have fun splitting your strings, and drop a line to julian@porta.sh if you have something to say.
|
81
|
+
|
data/lib/Separa/obj.rb
CHANGED
@@ -1,15 +1,30 @@
|
|
1
1
|
class Separa
|
2
|
-
|
3
|
-
|
4
|
-
|
5
|
-
|
6
|
-
|
7
|
-
|
8
|
-
|
2
|
+
module Obj
|
3
|
+
|
4
|
+
def self.call(obj, opts)
|
5
|
+
divider = opts[:divider] || ':'
|
6
|
+
res = wonderflat(obj)
|
7
|
+
res.map{|pair,_| "#{pair.keys[0].to_s}#{divider}#{pair.values[0].to_s}"}
|
8
|
+
end
|
9
|
+
|
10
|
+
def self.wonderflat(obj, memo = [])
|
11
|
+
return {
|
12
|
+
memo.join('.') => obj
|
13
|
+
} unless obj.respond_to?(:inject)
|
9
14
|
|
10
|
-
|
11
|
-
|
12
|
-
|
13
|
-
|
15
|
+
obj.inject([]) do |out_array, _val|
|
16
|
+
(head, *_tail) = _val
|
17
|
+
tail = _tail.pop
|
18
|
+
case tail
|
19
|
+
when Array
|
20
|
+
tail.map do |tail_elem|
|
21
|
+
out_array.push self.wonderflat(tail_elem, memo + [ head ])
|
22
|
+
end
|
23
|
+
else
|
24
|
+
out_array.push self.wonderflat( tail, memo + [ head ])
|
25
|
+
end
|
26
|
+
out_array.flatten
|
27
|
+
end
|
14
28
|
end
|
29
|
+
end
|
15
30
|
end
|
data/lib/separa.rb
CHANGED
data/makefile
CHANGED
@@ -1,2 +1,2 @@
|
|
1
1
|
test:
|
2
|
-
|
2
|
+
cutest ./tests/*_test.rb
|
data/separa.gemspec
CHANGED
@@ -2,12 +2,12 @@
|
|
2
2
|
|
3
3
|
Gem::Specification.new do |s|
|
4
4
|
s.name = "separa"
|
5
|
-
s.version = "0.0.
|
5
|
+
s.version = "0.0.3"
|
6
6
|
s.summary = "Separa splits chunks of text into tokens to be indexed"
|
7
7
|
s.description = "Separa splits chunks of text into tokens to be indexed by Busca, the simple redis search"
|
8
8
|
s.authors = ["Julián Porta"]
|
9
9
|
s.email = ["julian@porta.sh"]
|
10
|
-
s.homepage = "
|
10
|
+
s.homepage = "https://github.com/Porta/separa"
|
11
11
|
s.files = `git ls-files`.split("\n")
|
12
12
|
s.license = "MIT"
|
13
13
|
s.add_development_dependency "cutest", '~>1.2'
|
data/tests/separa_test.rb
CHANGED
@@ -1,12 +1,11 @@
|
|
1
1
|
require File.expand_path("../lib/separa", File.dirname(__FILE__))
|
2
2
|
|
3
|
-
|
4
3
|
setup do
|
5
4
|
|
6
5
|
end
|
7
6
|
|
8
7
|
test "default separator should be text" do
|
9
|
-
|
8
|
+
sep = Separa.new()
|
10
9
|
assert_equal sep.separador, Separa::Text
|
11
10
|
end
|
12
11
|
|
@@ -51,9 +50,10 @@ test "Separa::Obj should separate Obj into key:value pairs" do
|
|
51
50
|
assert_equal result, ['uno:1', 'dos:2', 'tres.uno:one', 'tres.dos:two']
|
52
51
|
end
|
53
52
|
|
54
|
-
test "Separa::Obj should separate Obj into key
|
55
|
-
sep = Separa.new(Separa::Obj
|
56
|
-
h = { uno: 1, dos: 2, tres:
|
57
|
-
result = sep.call(h)
|
58
|
-
assert_equal result, ['uno
|
59
|
-
end
|
53
|
+
test "Separa::Obj should separate Obj into key:value pairs, even with arrays" do
|
54
|
+
sep = Separa.new(Separa::Obj)
|
55
|
+
h = { uno: 1, dos: 2, tres: [:uno, :dos, :tres] }
|
56
|
+
result = sep.call(h)
|
57
|
+
assert_equal result, ['uno:1', 'dos:2', 'tres:uno', 'tres:dos', 'tres:tres']
|
58
|
+
end
|
59
|
+
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: separa
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.3
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Julián Porta
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2015-
|
11
|
+
date: 2015-06-23 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: cutest
|
@@ -33,6 +33,7 @@ extensions: []
|
|
33
33
|
extra_rdoc_files: []
|
34
34
|
files:
|
35
35
|
- ".gitignore"
|
36
|
+
- CHANGELOG.md
|
36
37
|
- LICENSE
|
37
38
|
- README.md
|
38
39
|
- lib/Separa/obj.rb
|
@@ -41,7 +42,7 @@ files:
|
|
41
42
|
- makefile
|
42
43
|
- separa.gemspec
|
43
44
|
- tests/separa_test.rb
|
44
|
-
homepage:
|
45
|
+
homepage: https://github.com/Porta/separa
|
45
46
|
licenses:
|
46
47
|
- MIT
|
47
48
|
metadata: {}
|