greeb 0.2.0.pre1 → 0.2.0.pre2
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/bin/greeb +23 -0
- data/lib/greeb/parser.rb +1 -1
- data/lib/greeb/version.rb +1 -1
- data/spec/parser_spec.rb +1 -1
- metadata +5 -3
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 80ad5b1112ea9576ba14eb52ce56a844e7ee1e94
|
4
|
+
data.tar.gz: 00cd04458ffaf7962d5ed828611cd1decc323852
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 965fc9a4d9ebbe6b2ed7601fa9aa7f34ccb82f722a48c8bf595786370ff1428c4cfcb4985fc5c9b9f83d5cee1a284e6ca6a440c772e071f0b3245f02717d01e8
|
7
|
+
data.tar.gz: 9a912f214f5c9b12eebbe7a834e3ce9c1e3d3735b1b5fcd9453029301061683019b6f02a2f8da6be70eac26b044a675d6fc87b23b44d3668efc454e7725cd2b0
|
data/bin/greeb
ADDED
@@ -0,0 +1,23 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
$:.unshift File.expand_path('../../lib', __FILE__)
|
4
|
+
require 'rubygems'
|
5
|
+
require 'greeb'
|
6
|
+
|
7
|
+
text = STDIN.read
|
8
|
+
text.chomp!
|
9
|
+
|
10
|
+
tokens = Greeb::Tokenizer.tokenize(text)
|
11
|
+
|
12
|
+
extract = proc do |entity|
|
13
|
+
from = tokens.index { |e| e.from == entity.from }
|
14
|
+
to = tokens.index { |e| e.to == entity.to }
|
15
|
+
tokens[from..to] = entity
|
16
|
+
end
|
17
|
+
|
18
|
+
Greeb::Parser.urls(text).each(&extract)
|
19
|
+
Greeb::Parser.emails(text).each(&extract)
|
20
|
+
|
21
|
+
tokens.each do |entity|
|
22
|
+
puts text[entity.from...entity.to] unless entity.type == :separ
|
23
|
+
end
|
data/lib/greeb/parser.rb
CHANGED
@@ -49,7 +49,7 @@ module Greeb::Parser
|
|
49
49
|
while text and md = text.match(regexp)
|
50
50
|
start, stop = md.offset(0)
|
51
51
|
matches << Greeb::Entity.new(offset + start, offset + stop, type)
|
52
|
-
text, offset = text[stop
|
52
|
+
text, offset = text[stop..-1], offset + stop
|
53
53
|
end
|
54
54
|
end
|
55
55
|
end
|
data/lib/greeb/version.rb
CHANGED
data/spec/parser_spec.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: greeb
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.2.0.
|
4
|
+
version: 0.2.0.pre2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Dmitry Ustalov
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2013-04-
|
11
|
+
date: 2013-04-21 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: rake
|
@@ -70,7 +70,8 @@ description: Greeb is a simple yet awesome and Unicode-aware regexp-based tokeni
|
|
70
70
|
written in Ruby.
|
71
71
|
email:
|
72
72
|
- dmitry@eveel.ru
|
73
|
-
executables:
|
73
|
+
executables:
|
74
|
+
- greeb
|
74
75
|
extensions: []
|
75
76
|
extra_rdoc_files: []
|
76
77
|
files:
|
@@ -81,6 +82,7 @@ files:
|
|
81
82
|
- LICENSE
|
82
83
|
- README.md
|
83
84
|
- Rakefile
|
85
|
+
- bin/greeb
|
84
86
|
- greeb.gemspec
|
85
87
|
- lib/greeb.rb
|
86
88
|
- lib/greeb/parser.rb
|