fonemas 0.0.2

checksums.yaml

@@ -0,0 +1,15 @@
+---
+!binary "U0hBMQ==":
+  metadata.gz: !binary |-
+    NGY2NWJiYTI0ZGM3NjM3MmIzN2FjMzhiZTNmYjM1YjRhMzUxMzNlYw==
+  data.tar.gz: !binary |-
+    OTAxZWJmYTkzMzVhYWE4OTcxNzMxMTE1ODdhOTc0NWNlNGJhMjkzOA==
+!binary "U0hBNTEy":
+  metadata.gz: !binary |-
+    N2Y3MmQ0YjI4ZTlkNjBhMjNmOTVjYjkxNmZlNDMwOWEyMzRhNmEyZmNhNThi
+    MGEyM2Y1N2MwYTU1NDE5MmE2ZDRjMjc5OTZkYWM0Mzg5NjhkMGM1NDNkZTE5
+    YjE5N2E3YjQ2ZjMzNmY5ZmZiYjhlOTc3Y2M4NWU2MjEwZjc1NzU=
+  data.tar.gz: !binary |-
+    NDE5NjU0ZjU4NmIyNTQ0ZWFiZTYwYjE0ZDM3YmRhMmU4MDM4Yjk4ZGRjZjM0
+    M2Q0YzIzM2ZkZjc2OTQ0ZDE0MjMzYjMyOTdlZWFmZTZiZWNlN2IzZjI1ZDU5
+    ZjIwZWIzMTk3NzQxM2M2ZTFhMWI2NjY5NTdiYWE3NGNlYzk4NTg=

data/.gitignore

@@ -0,0 +1,18 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp
+.idea*

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in fonemas.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2013 Manuel Bahamondez Honores
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,29 @@
+# Fonemas
+
+TODO: Write a gem description
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'fonemas'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install fonemas
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

@@ -0,0 +1 @@
+require "bundler/gem_tasks"

data/fonemas.gemspec

@@ -0,0 +1,23 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'fonemas/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "fonemas"
+  spec.version       = Fonemas::VERSION
+  spec.authors       = ["Manuel Bahamondez Honores"]
+  spec.email         = ["manuel@bahamondez.com"]
+  spec.description   = %q{Creación de fonemas para ser utilizadas en el reconocimiento de voz con cmu sphinx}
+  spec.summary       = %q{Lista todas las pronunciaciones posibles para una palabra en Chileno}
+  spec.homepage      = "http://www.b9.cl"
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files`.split($/)
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.3"
+  spec.add_development_dependency "rake"
+end

data/lib/fonemas.rb

@@ -0,0 +1,300 @@
+# coding: utf-8
+require "fonemas/version"
+
+module Fonemas
+  def self.clean(text)
+    s = text.gsub(/,/,' ')
+    s = s.gsub(/\s+/,' ')
+    s = s.chomp.strip
+    s = s.downcase
+    return s
+  end
+
+  def self.isTonica(word,i)
+    #falta considerar las palabras que poseen acento pero no tilde
+    tildes = %w(á é í ó ú)
+    if tildes.include? word[i]
+      return true
+    else
+      return false
+    end
+  end
+
+  def self.isFinal(word,i)
+    return word.size == i-1
+  end
+
+  def self.isFricativa(word,i)
+    fricativas = %w(f s c z j ll y g b w b v w s m b x d)
+    return fricativas.include? word[i]
+  end
+
+  def self.entreVocales(word,i)
+    if i == 0 || word.size - 1 == i
+      return false
+    else
+      return (isVocal(word,i-1) and isVocal(word,i+1))
+    end
+  end
+
+  def self.entreVocalyConsonante(word,i)
+    return ((isVocal(word,i-1) and !isVocal(word,i+1)) or (isVocal(word,i+1) and !isVocal(word,i-1)))
+
+  end
+
+  def self.isVocal(word,i)
+    vocales = %w(a e i o u á é í ó ú)
+    return vocales.include? word[i]
+  end
+
+  def self.isDiptongo(word,first,second)
+    f = word[first]
+    s = word[second]
+    abiertas = %w(a e o)
+    cerradas = %w(i u)
+    return ((abiertas.include? f and cerradas.include? s) or (abiertas.include? s and cerradas.include? f))
+
+  end
+
+  def self.separar(word)
+    word = word.downcase
+    output = []
+    i = 0
+    while(i < word.length)
+      if word[i] == 'c' and word[i+1] == 'h'
+        output << "ch"
+        i+=1
+      elsif word[i] == 'l' and word[i+1] == 'l'
+        output << 'll'
+        i+=1
+      elsif word[i] == 'r' and word[i+1] == 'r'
+        output << 'rr'
+        i+=1
+      else
+        output << word[i]
+      end
+      i +=1
+    end
+    return output
+  end
+
+  def self.fonemas(word)
+    word = separar(word)
+    fonema = []
+    for i in 0..(word.length-1)
+      letra = word[i]
+      case letra
+        when 'á' then
+          fonema << 'aa'
+        when 'é' then
+          fonema << 'ee'
+        when 'í' then
+          fonema << 'ii'
+        when 'ó' then
+          fonema << 'oo'
+        when 'ú' then
+          fonema << 'uu'
+        when 'a' then
+          if isTonica(word,i)
+            fonema << 'aa'
+          else
+            fonema << 'a'
+          end
+        when 'b' then
+          if word[i+1] == 'u' and isDiptongo(word,i+1,i+2)
+            if entreVocales(word,i)
+              fonema << ['b','g','']
+            else
+              fonema << ['B','g']
+            end
+          elsif isFricativa(word,i-1)
+            fonema << 'b'
+          elsif isFinal(word,i)
+            fonema << 'b'
+          elsif entreVocales(word,i)
+            fonema << ['b','']
+          else
+            fonema << 'B'
+          end
+        when 'c' then
+          if word[i+1] == 'e' or word[i+1] == 'i'
+            fonema << 's'
+          else
+            fonema << 'k'
+          end
+        when 'ch' then
+          if entreVocales(word,i)
+            fonema << ['ch','sh','tch','j']
+          else
+            fonema << ['ch','sh','tch']
+          end
+        when 'd' then
+          if entreVocales(word,i) || i == word.size-1
+            fonema << ['d','']
+          elsif entreVocalyConsonante(word,i)
+            fonema << ['D','d']
+          else
+            fonema << 'd'
+          end
+        when 'e' then
+          if isTonica(word,i)
+            fonema << 'ee'
+          else
+            fonema << 'e'
+          end
+        when 'f' then
+          fonema << 'f'
+        when 'g' then
+          if word[i+1] == 'e' or word[i+1] == 'i'
+            fonema << 'j'
+          else
+            if !entreVocales(word,i)
+              fonema << 'G'
+            else
+              fonema << 'g'
+            end
+          end
+        when 'h' then
+          #nada
+        when 'i' then
+          if isTonica(word,i)
+            fonema << 'ii'
+          else
+            fonema << 'i'
+          end
+        when 'j' then
+          fonema << 'j'
+        when 'k' then
+          fonema << 'k'
+        when 'l' then
+          fonema << 'l'
+        when 'll' then
+          fonema << ['ll','lli','i']
+        when 'm' then
+          fonema << 'm'
+        when 'n' then
+          fonema << 'n'
+        when 'ñ'  then
+          fonema << 'nh'
+        when 'o' then
+          if isTonica(word,i)
+            fonema << 'oo'
+          else
+            fonema << 'o'
+          end
+        when 'p' then
+          fonema << 'p'
+        when 'q' then
+          fonema << 'k'
+        when 'r' then
+          if i == 0
+            fonema << 'R'
+          else
+            fonema << 'r'
+          end
+        when 'rr' then
+          fonema << 'R'
+        when 's' then
+          if word[i-1] == 'r' or word[i-1] == 'd' or i == word.size-1
+            fonema << ['s','','h']
+          elsif entreVocalyConsonante(word,i)
+            fonema << ['s','h']
+          elsif word[i-1] == 'b' and word[i+1] == 't'
+            fonema << ['s','h']
+          elsif word[i-1] == 'b'
+            fonema << ['s','']
+          else
+            fonema << 's'
+          end
+        when 't' then
+          fonema << 't'
+        when 'ü' then
+          fonema << 'u'
+        when 'u' then
+          if word[i-1] == 'q' or word[i-1] == 'g'
+            #nada
+          else
+            if word[i-1] == 'h' || i == 0
+              fonema << 'gu'
+            elsif isTonica(word,i)
+              fonema << 'uu'
+            else
+              fonema << 'u'
+            end
+          end
+        when 'v' then
+          fonema << 'b'
+        when 'w' then
+          if i == 0
+            fonema << ['b','B']
+          elsif word[i-1] == 'o'
+            fonema << 'u'
+          elsif word[i+1] == 'i'
+            fonema << 'u'
+          elsif entreVocales(word,i)
+            fonema << 'gu'
+          else
+            fonema << 'Gu'
+          end
+        when 'x' then
+          fonema << ['ks','k','h']
+        when 'y' then
+          if i == word.size - 1
+            fonema << 'i'
+          else
+            fonema << ['ll','lli','i']
+          end
+        when 'z' then
+          if i == word.size - 1
+            fonema << ['s','h','']
+          else
+            fonema << 's'
+          end
+
+        else
+          fonema << letra
+      end
+
+
+
+    end
+
+    return generateFonemas(fonema)
+  end
+
+  def self.generateFonemas(fonema)
+    salidas = 1
+    for i in fonema
+      if i.class.name == 'Array'
+        salidas *= i.size
+      end
+    end
+    #puts "salidas: #{salidas}"
+
+    outputs = []
+    for j in 1..salidas
+      outputs[j-1] = []
+    end
+    for i in 0..(fonema.size-1)
+      c = fonema[i]
+      if c.class.name == 'Array'
+        for j in 1..salidas
+          t = c[(j-1)%c.size]
+          outputs[j-1] += [t] unless t.size == 0
+        end
+      else
+        for j in 1..salidas
+          outputs[j-1] += [c]
+        end
+      end
+
+    end
+
+    salida = []
+    for i in outputs
+      salida << i.join(" ")
+    end
+
+    return salida
+  end
+end

data/lib/fonemas/version.rb

@@ -0,0 +1,3 @@
+module Fonemas
+  VERSION = "0.0.2"
+end

metadata

@@ -0,0 +1,87 @@
+--- !ruby/object:Gem::Specification
+name: fonemas
+version: !ruby/object:Gem::Version
+  version: 0.0.2
+platform: ruby
+authors:
+- Manuel Bahamondez Honores
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-06-10 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+description: Creación de fonemas para ser utilizadas en el reconocimiento de voz con
+  cmu sphinx
+email:
+- manuel@bahamondez.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- .idea/encodings.xml
+- .idea/fonemas.iml
+- .idea/misc.xml
+- .idea/modules.xml
+- .idea/scopes/scope_settings.xml
+- .idea/vcs.xml
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- fonemas.gemspec
+- lib/fonemas.rb
+- lib/fonemas/version.rb
+homepage: http://www.b9.cl
+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: 2.0.3
+signing_key: 
+specification_version: 4
+summary: Lista todas las pronunciaciones posibles para una palabra en Chileno
+test_files: []