nebrija 0.2.2 → 1.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 08639cd57c6f906d92468d3366cf2302cdbf2332
-  data.tar.gz: 1f288ad92cc4c1b451cfd5ec28737fa435420801
+  metadata.gz: 4e22c43f3c2a0f893f6e66a2f64337d3c813377a
+  data.tar.gz: 08bb77b1e7d90bf3a9201ec3b76b8c8a2275ec75
 SHA512:
-  metadata.gz: 6754e729f784cac1e9d3fe37e22e5f0a81cad4414116ce37a50ba7cc29079609932e2f5ed06051cb1eb48b3e49740284d8e92aa33a7b607c87d3bbe6ae8c3537
-  data.tar.gz: cd496967b0e218f27acc7c933d33350a5c0fa64793ab52e43f414b0149f2e6c3ee13e74ce6a13f78adc8ce9347d5334707f251453495e04d3f085e6e3bf68937
+  metadata.gz: bf5634e8b8e06f50578d525301947f9c728358ace2bed1a46c80e3582563c2f0670004dd8c275a53a3616abf06ef9e29fd4d8f9d4bc49db98591ae917bee56ca
+  data.tar.gz: 7992fbe7cbfee315992699ca37b6a830215fc50e754ff8def65c7fb025cbc511c09da0fc7ff0f8bfdd42cb54eb1f9afd2bcad706f48bc2f71c05be2477fd74a5

data/bin/nebrija

@@ -3,4 +3,5 @@
 require 'json'
 require_relative '../lib/nebrija/cli'
 
-Nebrija::cli(ARGV.first)
+raise NotImplementedError
+#Nebrija::cli(ARGV.first)

data/lib/nebrija/parser.rb

@@ -14,8 +14,8 @@ class Parser
     if valid?
       {
         :status => 'success',
-        :type => single? ? 'single' : 'multiple',
-        :response => single? ? parse_single : parse_multiple
+        :type => 'single',
+        :response => parse_single
       }
     else
       {
@@ -28,46 +28,69 @@ class Parser
   private
 
   def single?
-    @doc.css('body > ul').length.zero?
+    @doc.css('article').length == 1
   end
 
   def parse_single
-    single_data = []
-    state = :entry # TODO. Improve FSM syntax.
-    index = -1 # HACK(javierhonduco)
-
-    @doc.css('body > div > p').each do |entry|
-      if entry['class'] == 'p' and state == :entry
-        word = entry.css('span').inner_text
-        word = '=>' if word == ''
-        single_data << {
-          :word => word.strip.capitalize,
-          :meanings => [],
-          :etymology  => nil
-        }
-        index+=1
-      else
-        text = entry.inner_text.strip.gsub(/[0-9]+\.[ ]/, '')
-        if text[0] == '('
-          single_data[index][:etymology] = text
-          next
-        end
+    response = {
+      :basic_meanings => [],
+      :other_meanings => []
+    }
+
+    response[:word] = @doc.css('header').inner_text.sub('.', '')
+
+    @doc.css('body > div > article > p').each_with_index do |entry, index|
+      if index.zero? # Parsing etymology
+        response[:etymology] = entry.inner_text
+      elsif entry['class'] =~ /j[0-9]*/
+        # Parsing first meaning
+        response[:basic_meanings] << metadata(entry.inner_text)
+      elsif entry['class'] == 'm' || entry['class'] =~/k[0-9]*/
+        # Parsing other meanings
+        #   k is the expression with 1 element
+        #   m is the meaning with >= elements
+        type = (:meaning if entry['class'] == 'm') || :expression
+        response[:other_meanings] << [type, entry.inner_text]
+      end
+    end
 
-        unparsed_meta = text.scan META_REGEX
+    clean! response
+  end
+
+  def clean! response
+    parsed_meanings = []
+    state = :EXPR
+    temp = nil
 
-        text = text.gsub(META_REGEX, '')
-        single_data[index][:meanings] << {
-          :meaning    => text,
-          :meta       => (unparsed_meta.join.strip if unparsed_meta.join.strip != ''),
-        } if !text.nil? and text != '' and index >= 0
-        state = :definitions
+    response[:other_meanings].each do |type, text|
+      state = :EXPR if type == :expression
+      if state == :EXPR
+        unless temp.nil?
+          parsed_meanings << temp
+        end
+        temp = {
+          :expression => text,
+          :meanings => []
+        }
+        state = :MEAN
+      elsif state == :MEAN
+        temp[:meanings] << metadata(text)
       end
-      state = :entry
     end
+    response[:other_meanings] = parsed_meanings
 
-    single_data
+    response
   end
 
+  def metadata text
+    # To be implemented
+    # The idea would be to split the text in metadata
+    # and real text. It's seems quite tricky.
+    {
+      :meaning => text,
+      :meta => nil
+    }
+  end
   def parse_multiple
     @doc.css('body > ul > li > a').map do |word|
       {
@@ -78,13 +101,11 @@ class Parser
   end
 
   def valid?
-    valid_title = (@doc.css('title').inner_text =~/error/).nil?
-    valid_body  = (@doc.css('body').inner_text =~/No encontrado/).nil?
-
-    valid_title && valid_body && delete_pending?
+    !@doc.css('article').length.zero? # delete_pending?
   end
 
   def delete_pending?
+    # TODO: Check
     tb_deleted = true
     if !@doc.css('body > div > p').nil? && !@doc.css('body > div > p').first.nil?
       tb_deleted = (@doc.css('body > div > p').first.inner_text =~/suprimido/).nil?

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: nebrija
 version: !ruby/object:Gem::Version
-  version: 0.2.2
+  version: 1.0.0
 platform: ruby
 authors:
 - "@javierhonduco"
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-11-22 00:00:00.000000000 Z
+date: 2016-02-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri