rudge 0.0.2

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: a8ed66b8eeec5d42fc40a8dd59567508795bd056
+  data.tar.gz: c4e51bd25dd55ddd1ea5821b853dfa7d8df7e6f1
+SHA512:
+  metadata.gz: 8e62a34ee8f52c7ce5a6762d97fb973c94dd9a68f26935546ec66f4db6479b506a718c8cbe2b3b5f19536a74888229f03e7f96374ac20f7cfd8c7dbf063fa6b3
+  data.tar.gz: 4b7c58b69d7401a58c4e19339ac3c13866f80e46b7f9cd8dd9cd93438363da317a0a2fd2e1579a30b0ef6219f39c6457ca80ff2ca277745433678e8b99fc9637

data/lib/rudge.rb

@@ -0,0 +1,23 @@
+class Rudge
+  require 'rudge/abbreviations'
+
+  # end of sentence marker
+  EOS = "\001"
+
+  def self.sentences(text)
+    text = text.dup
+
+    # initial split after punctuation, 
+    # preserves trailing whitespace for the ellipsis correction
+    text.gsub!(/([\.?!](?:\"|\'|\)|\]|\})?)(\s+)/) { $1 << EOS << $2 }
+
+    # correct ellipsis marks and rows of stops
+    text.gsub!(/(\.\.\.*)#{EOS}/) { $1 }
+
+    # correct abbreviations - precompile regexp?
+    text.gsub!(/(#{Rudge::Abbreviations.list.join("|")})\.#{EOS}/i) { $1 << '.' }
+
+    # split on EOS marker, strip gets rid of trailing whitespace
+    text.split(EOS).map { | sentence | sentence.strip }
+  end
+end

data/lib/rudge/abbreviations.rb

@@ -0,0 +1,22 @@
+class Rudge
+  class Abbreviations
+    TITLES = %w(jr, mr, mrs, ms, dr, prof, sr, sen, rep, rev, gov, atty,
+                supt, det, rev, col, gen, lt, cmdr, adm, capt, sgt, cpl, maj)
+
+    ENTITIES = %w(dept, univ, uni, assn, bros, inc, ltd, co, corp, plc)
+
+    MONTHS = %w(jan, feb, mar, apr, may, jun, jul, aug, sep, sept, oct,
+                nov, dec)
+
+    DAYS = %w(mon, tue, wed, thu, fri, sat, sun)
+
+    ADDRESSES = %w(ave, bld, blvd, cl, ct, cres, dr, rd, st)
+
+    MISC = %w(vs, etc, no, esp, cf)
+
+    def self.list
+      TITLES + ENTITIES + MONTHS + DAYS + ADDRESSES + MISC
+    end
+
+  end
+end

metadata

@@ -0,0 +1,45 @@
+--- !ruby/object:Gem::Specification
+name: rudge
+version: !ruby/object:Gem::Version
+  version: 0.0.2
+platform: ruby
+authors:
+- bruno coelho
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-01-31 00:00:00.000000000 Z
+dependencies: []
+description: A Ruby Judge! Determines the sentences in a text.
+email: bruno.coelho@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/rudge.rb
+- lib/rudge/abbreviations.rb
+homepage: http://rubygems.org/gems/rudge
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.2.1
+signing_key: 
+specification_version: 4
+summary: Rudge - determines sentences.
+test_files: []