greeb 0.1.2 → 0.2.0.pre1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 9320c86f24d2f6a40459a3bb6be6a8eedb21a822
-  data.tar.gz: 810aec1c57162b502c1fb0dd9568f98a75690f6d
+  metadata.gz: a2f7bcbf04e2f79d8b703f67cb79de1ac65bef94
+  data.tar.gz: 3af3b46980820730acbb00cdd2c2ff0ae9fd91d4
 SHA512:
-  metadata.gz: fbde05e3be7f071c9c7095bd8dfb1d1373694612ddcba2bc2a31014a02f2db6b1ed989c3e0d92f17076282bd8471b3c8bd8ed8325d9beaa26e0c68c887b24d86
-  data.tar.gz: c2f613064ce1cebf4e39212c96a5861d86e269a5c3593622e3ec06dbd82d238982e3bf5f0aaa050bd3807021c8cc7d46ce569cba75a33eae56ff3a19fd0fd884
+  metadata.gz: 2ee73b3c4a6fc65dcf9b4b30728fe7d14f3e271f339913d6353e8e8ff15c5844f65848bbeb13865573ac6514953860334bb68bdf7793b6fc5d28cd05b23bdb99
+  data.tar.gz: 2ce4047f35268480ccc357eb7152623ffc2379dd7bc4c2e24169ece3390d8b02c20ae45d5874b9cb2a052571cfb820af3daf947c7215faed59c19070e8e276f1

data/lib/greeb.rb

@@ -43,3 +43,4 @@ end
 require 'greeb/strscan'
 require 'greeb/tokenizer'
 require 'greeb/segmentator'
+require 'greeb/parser'

data/lib/greeb/parser.rb

@@ -0,0 +1,56 @@
+# encoding: utf-8
+
+# It is often necessary to find different entities in natural language
+# text. These entities are URLs, e-mail addresses, names, etc. This module
+# includes several helpers that could help to solve these problems.
+#
+module Greeb::Parser
+  extend self
+
+  # URL pattern. Not so precise, but IDN-compatible.
+  URL = /\b(([\w-]+:\/\/?|www[.])[^\s()<>]+(?:\([\p{L}\w\d]+\)|([^.\s]|\/)))/ui
+
+  # Horrible e-mail pattern. 
+  EMAIL = /[A-Z0-9._%+-]+@[A-Z0-9.-]+\.[A-Z]{2,4}/ui
+
+  # Recognize URLs in the input text. Actually, URL is obsolete standard
+  # and this code should be rewritten to use the URI concept.
+  #
+  # @param text [String] input text.
+  #
+  # @return [Array<Greeb::Entity>] found URLs.
+  #
+  def urls(text)
+    scan(text, URL, :url)
+  end
+
+  # Recognize e-mail addresses in the input text.
+  #
+  # @param text [String] input text.
+  #
+  # @return [Array<Greeb::Entity>] found e-mail addresses.
+  #
+  def emails(text)
+    scan(text, EMAIL, :email)
+  end
+
+  private
+  # Implementation of regexp-based {Greeb::Entity} scanner.
+  #
+  # @param text [String] input text.
+  # @param regexp [Regexp] regular expression to be used.
+  # @param type [Symbol] type field for the new {Greeb::Entity} instances.
+  # @param offset [Fixnum] offset of the next match.
+  #
+  # @return [Array<Greeb::Entity>] found entities.
+  #
+  def scan(text, regexp, type, offset = 0)
+    Array.new.tap do |matches|
+      while text and md = text.match(regexp)
+        start, stop = md.offset(0)
+        matches << Greeb::Entity.new(offset + start, offset + stop, type)
+        text, offset = text[stop + 1..-1], offset + stop
+      end
+    end
+  end
+end

data/lib/greeb/version.rb

@@ -5,5 +5,5 @@
 module Greeb
   # Version of Greeb.
   #
-  VERSION = '0.1.2'
+  VERSION = '0.2.0.pre1'
 end

data/spec/parser_spec.rb

@@ -0,0 +1,34 @@
+# encoding: utf-8
+
+require_relative 'spec_helper'
+
+module Greeb
+  describe Parser do
+    let(:text) do
+      'Hello there! My name is Vasya. My website is: http://вася.рф/. ' \
+      'And my e-mail is example@example.com! Also it is available by ' \
+      'URL: http://vasya.ru.'
+    end
+
+    describe 'URL' do
+      subject { Parser.urls(text) }
+
+      it 'recognizes URLs' do
+        subject.must_equal(
+          [Entity.new(46, 61, :url),
+           Entity.new(129, 144, :url)]
+        )
+      end
+    end
+
+    describe 'EMAIL' do
+      subject { Parser.emails(text) }
+
+      it 'recognizes e-mails' do
+        subject.must_equal(
+          [Entity.new(80, 99, :email)]
+        )
+      end
+    end
+  end
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: greeb
 version: !ruby/object:Gem::Version
-  version: 0.1.2
+  version: 0.2.0.pre1
 platform: ruby
 authors:
 - Dmitry Ustalov
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-04-08 00:00:00.000000000 Z
+date: 2013-04-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -83,10 +83,12 @@ files:
 - Rakefile
 - greeb.gemspec
 - lib/greeb.rb
+- lib/greeb/parser.rb
 - lib/greeb/segmentator.rb
 - lib/greeb/strscan.rb
 - lib/greeb/tokenizer.rb
 - lib/greeb/version.rb
+- spec/parser_spec.rb
 - spec/segmentator_spec.rb
 - spec/spec_helper.rb
 - spec/tokenizer_spec.rb
@@ -104,9 +106,9 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - '>'
     - !ruby/object:Gem::Version
-      version: '0'
+      version: 1.3.1
 requirements: []
 rubyforge_project: greeb
 rubygems_version: 2.0.3
@@ -114,6 +116,7 @@ signing_key:
 specification_version: 4
 summary: Greeb is a simple Unicode-aware regexp-based tokenizer.
 test_files:
+- spec/parser_spec.rb
 - spec/segmentator_spec.rb
 - spec/spec_helper.rb
 - spec/tokenizer_spec.rb