fonemas 0.4.16 → 0.5.0

checksums.yaml

@@ -1,15 +1,15 @@
 ---
 !binary "U0hBMQ==":
   metadata.gz: !binary |-
-    M2JiMjdhZGRkYjI5ZmRkNzM2ZWI1MmRjMTMwMjAwZTlmNmIzMzc3Yg==
+    ZjlhNGZlOWUyZjhlMDg4ZmM5OGZjZTRiYzY0NGRiYjVlMDk1NDVjOQ==
   data.tar.gz: !binary |-
-    YWI3ZTMwOTFkYmMxYzIwNzdjNDEzNzI1YzliMjEwYzk1M2M4MDQxNA==
+    YTRhMWRmZGQyNTFlYzllNWI0MzNiNDFiYmIyMzNmZmI0NjQ5NzA1ZA==
 !binary "U0hBNTEy":
   metadata.gz: !binary |-
-    OGU0Mzg4NGRkMzhkM2Y1ODJkOGVmNmY0MzQ2MTQyYmViY2M3OGQ0NWJlNmZl
-    NjdjMGI1ZmIzODJmMGY1NzcxYTU4MTIxYzk0Nzg3ZWYwNWI5ZjQ1YmQyNGM4
-    ZWI4NGE1ZDUxZDc3ZjQwNGRhMjBjYzcyMWUwZWExZGE3MzEwYWQ=
+    MGU1NmZmMzc0NDJhNGNlNjBjMzVmYzViOTljYmI2MWFiYjgyMzBlOWYxYThi
+    NWQwODk1YTViMmFjMThlMDU1YWEzYzQ4ZmUxOThkOGI5NGEwMmJkMzNiMmNh
+    ZWU1Y2VjNWZkYmE2MWU4OWQ3NWRlOWI3MDkwMWQyOTQ2OGRmMDI=
   data.tar.gz: !binary |-
-    ZGRlYmVkNmMxYTQ3NWIzZjE2MDI1MThmYTkwMzg4YjNmOGFmZjUxMzNlYThi
-    MGE5NzJlY2UyZWQ4NzQ5OWVmZTk2MDFlNzBjNzkxOTIxMTVjYjM4NjIyNDhm
-    NWJkOTNlNDcxMGYwNDQyMWYzNmEwNTcxYzVhZWVmMjcyNTdjYzA=
+    ZDU1YWI4YzZkNDkwYWNjMjE3MWVmNGFiNjk0MzFkMWE5MmY2MjM5ZWE4ZTBh
+    Zjc4ODcwMWVhN2NhMzA1NzBhNWQ2ODc0NzNiM2IyN2M3Y2I3YjMyMjM5MGM0
+    MTMzZDg1ZGY1MWM5OTk0NDc4N2M5OTgzNDg2OWJjYTdhZTJjMWM=

data/bin/audioupload

@@ -51,7 +51,7 @@ end
 
 
 
-if ARGV[3].nil?
+if f[3].nil?
     puts "uploading..."
     upload_audio(filename,ARGV[0],public,nil,ARGV[4])
 else
@@ -60,7 +60,7 @@ else
     lr = `ffmpeg -i "#{filename}" 2>&1 | grep 'Duration'| cut -d ' ' -f 4 | cut -d ',' -f 1`
     lr = lr.split(':')
     length = lr[0].to_i*3600 + lr[1].to_i*60 + lr[2].to_f
-    puts "largo original archivo: #{lr}"
+    puts "largo original archivo: #{length}"
     start_time = 0
     counter = 0
     max_parts = (length/limit).ceil

data/fonemas.gemspec

@@ -21,7 +21,6 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency "bundler", "~> 1.3"
   spec.add_development_dependency "rake"
   spec.add_development_dependency "rspec"
-  spec.add_runtime_dependency "text-hyphen", '~> 1.4.1'
   spec.add_runtime_dependency "unicode_utils", '~> 1.4.0'
   spec.add_runtime_dependency "rest-client", "~> 1.6.7"
   spec.add_runtime_dependency 'mime-types'

data/lib/fonemas.rb

@@ -2,7 +2,6 @@
 require "fonemas/version"
 
 module Fonemas
-  require 'text/hyphen'
   require 'unicode_utils'
 
   def self.version
@@ -33,18 +32,134 @@ module Fonemas
     return false
   end
 
+  def self.silabar(palabra)
+    #puts "silabar: #{palabra}"
+    #algoritmo adaptado desde python
+    #codigo original extraido desde:
+    #https://github.com/xergio/silabas/blob/master/home/silabea.py
+    silabas = []
+    letra = 0
+    salto = 0
+    while silabas.join('').length  < palabra.length
+      #puts "silabas antes: #{silabas}"
+      #puts "letra: #{letra}"
+      #puts "palabra length: #{palabra.length}"
+      silaba = ''
+      salto = 0
+      if isConsonante(palabra[letra])
+        if isInseparables(palabra[letra..letra+1])
+          salto += 2
+        else
+          salto += 1
+        end
+      else
+        salto += 0
+      end
+
+      #puts "salto: #{salto}"
+      if isDiptongoConH(palabra,letra+salto,letra+salto+2)
+        #puts "diptongo con h"
+        salto += 3
+      elsif isDiptongo(palabra,letra+salto,letra+salto+1)
+        salto += 2
+      elsif isTriptongo(palabra,letra+salto,letra+salto+2)
+        salto += 3
+      elsif isDieresis(palabra,letra+salto,letra+salto+1)
+        salto += 2
+      else
+        salto += 1
+      end
+      #puts "acoda silaba: #{palabra[letra,letra+salto]} letra: #{letra} salto: #{salto}"
+
+      salto += coda(palabra[letra+salto,palabra.length])
+
+      #puts "dcoda silaba: #{palabra[letra,letra+salto]} letra: #{letra} salto: #{salto}"
+
+
+      silaba = palabra[letra,salto]
+      letra += salto
+      silabas << silaba
+
+      #puts "Dletra: #{letra}"
+      #puts "Dsalto: #{salto}"
+
+    end
+    return silabas.join("-")
+  end
+
+  def self.isInseparables(trozo)
+    #puts "isInspearable? #{trozo}"
+    inseparables = %w(br bl cr cl dr fr fl gr gl kr ll pr pl tr rr ch)
+    return inseparables.include? trozo
+  end
+
+  def self.coda(trozo)
+    #puts "coda: #{trozo}"
+    l = trozo.length
+    if l == 0
+      return 0
+    elsif l == 1 and isConsonante(trozo)
+      return 1
+    elsif l > 1 and isInseparables(trozo[0,2])
+      return 0
+    elsif l > 1 and isConsonante(trozo,0) and isVocal(trozo,1)
+      return 0
+    elsif l > 2 and isConsonante(trozo,0) and isConsonante(trozo,1) and isVocal(trozo,2)
+      return 1
+    elsif l > 3 and isConsonante(trozo,0) and isInseparables(trozo[1,2]) and isVocal(trozo[3])
+      return 1
+    elsif l > 3 and isConsonante(trozo,0) and isConsonante(trozo,1) and isConsonante(trozo,2) and isVocal(trozo,3)
+      return 2
+    elsif l > 3 and isConsonante(trozo,0) and isConsonante(trozo,1) and isConsonante(trozo,2) and isConsonante(trozo,3)
+      return 2
+    else
+      return 0
+    end
+  end
+
+
+  def self.calcularPosicionSilabas(silabada)
+    #puts "calcular posicion #{silabada}."
+    output = []
+    text = silabada
+    while(!text.index("-").nil?)
+      i = text.index("-")
+      text = text.slice(0,i) + text.slice(i+1,text.length)
+      output << i
+    end
+    return output
+  end
+
+
   def self.isTonica(word,i)
+    test = _isTonica(word,i)
+    if test
+      if _isTonica(word,i+1)
+        return false
+      else
+        return test
+      end
+    else
+      return false
+    end
+  end
+
+
+  def self._isTonica(word,i)
+    return false if isConsonante(word,i)
     #falta considerar las palabras que poseen acento pero no tilde
-    return true if word.size == 1
     tildes = %w(á é í ó ú ã ä ë)
     w = word.join
-    if tildes.include? word[i]
+    #puts "isTonica? #{w}: #{i}"
+    return true if w.size == 1
+
+
+    if tildes.include? w[i]
       return true
     else
-      es = Text::Hyphen.new(:language => "es", :left => 0, :right => 1)
-      p = es.hyphenate(w)
-      #puts es.visualize(w)
-      hh = es.visualize(w).split("-")
+      g = silabar(w)
+      hh = g.split("-")
+      p = calcularPosicionSilabas(g)
 
       if hh.size == 1 and w.size > 4 and w.include? 'h' and w[0] != 'h'
         #caso johan
@@ -90,7 +205,8 @@ module Fonemas
             end
         elsif hh.size >= 3
           #puts hh.join("-")
-          if i > p[p.size-1]
+          #puts "hhsize3 i: #{i}, p:#{p}"
+          if i >= p[p.size-1]
             if w =~ /[nsaeiou]$/
               return false
             else
@@ -132,20 +248,58 @@ module Fonemas
 
   end
 
-  def self.isVocal(word,i)
+  def self.isVocal(word,i=0)
     vocales = %w(a e i o u á é í ó ú)
     return vocales.include? word[i]
   end
 
+  def self.isConsonante(word,i=0)
+    return !isVocal(word,i)
+  end
+
+  def self.isTriptongo(palabra,first,third)
+    t = palabra[first,third]
+    return false if t.length < 3
+    triptongos = %w(iai iei uai uei uau iau uay uey)
+    return triptongos.include? t
+  end
+
+  def self.isDieresis(palabra,first,second)
+    t = palabra[first,second]
+    return false if t.length < 2
+    dieresis = %w(ue ui)
+    return dieresis.include? t
+
+  end
+
   def self.isDiptongo(word,first,second)
+    trozo = word[first..second]
+    return false if trozo.length != 2
+    #puts "diptongo word #{word}, first: #{first}, second: #{second}"
+    #puts "test diptongo #{word[first] + word[second]}"
     f = word[first]
     s = word[second]
-    abiertas = %w(a e o)
-    cerradas = %w(i u)
+    abiertas = %w(a e o á é ó)
+    cerradas = %w(i u í ú)
     return ((abiertas.include? f and cerradas.include? s) or (abiertas.include? s and cerradas.include? f) or (cerradas.include? f and cerradas.include? s))
 
   end
 
+  def self.isDiptongoConH(word,first,third)
+    test = word[first..third]
+    #puts "test diptongo con h: #{test}"
+    if test[1] == 'h'
+      if test[2,2] == 'ue'
+        return false
+      else
+        test = test.gsub(/h/,'')
+      end
+    else
+      return false
+    end
+    return isDiptongo(test,0,1)
+  end
+
   def self.separar(word)
     word = downcase(word)
     output = []

data/lib/fonemas/version.rb

@@ -1,3 +1,3 @@
 module Fonemas
-  VERSION = '0.4.16'
+  VERSION = '0.5.0'
 end

data/spec/fonemas/fonema_spec.rb

@@ -1,7 +1,7 @@
 # encoding: utf-8
 require 'spec_helper'
 describe Fonemas do
-  it 'test acentos' do
+  it 'test acentos'  do
     Fonemas.fonemas('hasta').should include("aa s t a")
     Fonemas.fonemas('torta').should include("t oo r t a")
     Fonemas.fonemas('ungüento').should include("u n g u ee n t o")
@@ -29,7 +29,6 @@ describe Fonemas do
     Fonemas.fonemas('guatón').should include('g u a t oo n')
     Fonemas.fonemas('gu').should include('gg u')
     Fonemas.fonemas('guagua').should include('gu aa g u a')
-    Fonemas.fonemas('joão').should include('ll o aa o')
     Fonemas.fonemas('johan').should include('ll oo j a n')
     Fonemas.fonemas('adquirir').should include('a d k i r ii r')
     for i in Fonemas.fonemas('adskribir')
@@ -108,8 +107,36 @@ describe Fonemas do
     output.should include('a b e')
     output.should include('a c d')
     output.should include('a c e')
+  end
+
+  it 'debe saber separar silabas' do
+    Fonemas.silabar('áfrica').should eql('á-fri-ca')
+    Fonemas.silabar('abstraer').should eql('abs-tra-er')
+    Fonemas.silabar('ahuyentar').should eql('ahu-yen-tar')
+    Fonemas.silabar('acaban').should eql('a-ca-ban')
+    Fonemas.silabar('pino').should eql('pi-no')
+    Fonemas.silabar('camión').should eql('ca-mión')
+    Fonemas.silabar('holanda').should eql('ho-lan-da')
+    Fonemas.silabar('abuela').should eql('a-bue-la')
+
+  end
 
+  it 'marcar inicios de cada silaba' do
+    Fonemas.calcularPosicionSilabas('ho-lan-da').should eql([2,5])
+  end
+
+  it 'identificar sílaba tónica' do
+    word = Fonemas.separar('acaban')
+    Fonemas.isTonica(word,0).should be_false
+    Fonemas.isTonica(word,2).should be_true
+    Fonemas.isTonica(word,4).should be_false
+
+  end
 
+  it 'sólo debe existir una sílaba acentuada' do
+    fonemas = Fonemas.fonemas('acaban')
+    fonemas.should_not include('aa k aa b a n')
+    fonemas.should include('a k aa b a n')
   end
 
 end

data/spec/spec_helper.rb

@@ -1 +1,6 @@
-require 'fonemas'
+require 'fonemas'
+
+RSpec.configure do |config|
+  config.filter_run focus: true
+  config.run_all_when_everything_filtered = true
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: fonemas
 version: !ruby/object:Gem::Version
-  version: 0.4.16
+  version: 0.5.0
 platform: ruby
 authors:
 - Manuel Bahamondez Honores
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-09-02 00:00:00.000000000 Z
+date: 2013-09-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -52,20 +52,6 @@ dependencies:
     - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
-- !ruby/object:Gem::Dependency
-  name: text-hyphen
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ~>
-      - !ruby/object:Gem::Version
-        version: 1.4.1
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ~>
-      - !ruby/object:Gem::Version
-        version: 1.4.1
 - !ruby/object:Gem::Dependency
   name: unicode_utils
   requirement: !ruby/object:Gem::Requirement