txt_tm_importer 0.4.0 → 0.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 8a437d5112648108747b10abbaf3b2253ba2bf78
-  data.tar.gz: 86f0997da5a86514c9c3b11ef1a9a251795f769e
+  metadata.gz: fd3e21f0db8fdc8d66a5d30a7af0d3adcbab92df
+  data.tar.gz: 05e34ce94dd18bb7339bb623822330cc611ade04
 SHA512:
-  metadata.gz: 975b00b591daa6f1561be0e7541dae0a92d1dbc485419c5981a594903ebfc61bb561936484d52499f776a2d9a01b1ceec2f28a595f4e01d4fec0aad0739b0a6b
-  data.tar.gz: c399dbc772ab1764988718efda2c3d6fb291b79dedadf4d468ec68411cbb66ac18293986da19323991e6b9b2ee5ca406bc8b250c52a72beeb12504c1b6a02015
+  metadata.gz: 41f3e80b4578c8709df95962e541c56c0a47792662a63a4686cb8e3253dc4bf06fe40b61545da092c17754e4571735d8b806be7732b79ef6f653de8e38c2c612
+  data.tar.gz: 7bf1d31a1372156e1ef825ffa3b1fb26ba053f6bf49c6e15b3d90c46e8bcf2c66dcb8943147a08df2edadbe32ac1e1e7846435a6a57336163fd3790c7f616498

data/lib/txt_tm_importer.rb

@@ -75,18 +75,32 @@ module TxtTmImporter
       wordfast_lines.each_with_index do |line, index|
         next if line.empty? || line.gsub(/\s+/, '').empty?
         line_array = line.split("\t")
-        @doc[:source_language] = line_array[3].gsub(/%/, '').gsub(/\s/, '') if index.eql?(0)
-        @doc[:target_language] = line_array[5].gsub(/%/, '').gsub(/\s/, '') if index.eql?(0)
+        @doc[:source_language] = line_array[3].gsub(/%/, '').gsub(/\s/, '')
+        @doc[:target_language] = line_array[5].gsub(/%/, '').gsub(/\s/, '')
         next if index.eql?(0)
         timestamp = create_timestamp(line.split("\t")[0])
         @doc[:tu][:creation_date] = timestamp unless timestamp.nil?
         generate_unique_id
         write_tu
-        write_seg(remove_wordfast_tags(line_array[4]), 'source', line_array[3]) unless line_array[4].nil?
-        write_seg(remove_wordfast_tags(line_array[6]), 'target', line_array[5]) unless line_array[6].nil?
+        write_seg(remove_wordfast_tags(line_array[4]), 'source', @doc[:source_language]) unless line_array[4].nil?
+        write_seg(remove_wordfast_tags(line_array[6]), 'target', @doc[:target_language]) unless line_array[6].nil?
       end
     end
 
+    def wordfast_stats
+      lines = wordfast_lines
+      lines.each_with_index do |line, index|
+        next if line.empty? || line.gsub(/\s+/, '').empty?
+        next if index.eql?(0)
+        @doc[:tu][:counter] += 1
+        @doc[:source_language] = line.split("\t")[3].gsub(/%/, '').gsub(/\s/, '')
+        @doc[:target_language] = line.split("\t")[5].gsub(/%/, '').gsub(/\s/, '')
+        @doc[:language_pairs] << [@doc[:source_language], @doc[:target_language]]
+        @doc[:language_pairs] =  @doc[:language_pairs].uniq
+      end
+      @doc[:seg][:counter] = @doc[:tu][:counter] * 2
+    end
+
     def import_twb_file
       role_counter = 0
       tu_tracker = 0
@@ -110,19 +124,6 @@ module TxtTmImporter
       end
     end
 
-    def wordfast_stats
-      lines = wordfast_lines
-      lines.each_with_index do |line, index|
-        next if line.empty? || line.gsub(/\s+/, '').empty?
-        next if index.eql?(0)
-        @doc[:tu][:counter] += 1
-      end
-      @doc[:seg][:counter] = @doc[:tu][:counter] * 2
-      @doc[:source_language] = lines[0].split("\t")[3].gsub(/%/, '').gsub(/\s/, '')
-      @doc[:target_language] = lines[0].split("\t")[5].gsub(/%/, '').gsub(/\s/, '')
-      @doc[:language_pairs] << [@doc[:source_language], @doc[:target_language]]
-    end
-
     def twb_export_file_stats
       @doc[:tu][:counter] = @text.scan(/<\/TrU>/).count
       @doc[:seg][:counter] = @text.scan(/<Seg/).count

data/lib/txt_tm_importer/version.rb

@@ -1,3 +1,3 @@
 module TxtTmImporter
-  VERSION = "0.4.0"
+  VERSION = "0.5.0"
 end

data/spec/txt_tm_importer_spec.rb

@@ -29,6 +29,12 @@ describe TxtTmImporter do
       txt = TxtTmImporter::Tm.new(file_path: file_path).stats
       expect(txt).to eq({:tu_count=>2, :seg_count=>4, :language_pairs=>[['ES-EM', 'EN-US']]})
     end
+
+    it 'reports the stats of a wordfast txt file 5' do
+      file_path = File.expand_path('../txt_tm_importer/spec/sample_files/wordfast_multiple.txt')
+      txt = TxtTmImporter::Tm.new(file_path: file_path).stats
+      expect(txt).to eq({:tu_count=>407, :seg_count=>814, :language_pairs=>[["PT-BR", "EN-US"], ["IT-IT", "EN-US"], ["PT-BR", "EN-GB"]]})
+    end
   end
 
   describe '#import' do
@@ -151,5 +157,17 @@ describe TxtTmImporter do
       txt = TxtTmImporter::Tm.new(file_path: file_path).import
       expect(txt[1][2][4]).to eq("La renovación de procesos con nuevos equipamientos beneficiará directamente a clientes y pacientes que utilizan medicamentos y alimentación parenteral suministrados por el grupo")
     end
+
+    it 'imports a txt file 21' do
+      file_path = File.expand_path('../txt_tm_importer/spec/sample_files/wordfast_multiple.txt')
+      txt = TxtTmImporter::Tm.new(file_path: file_path).import
+      expect(txt[1][2][4]).to eq("Mundo Físico VS Contratual")
+    end
+
+    it 'imports a txt file 22' do
+      file_path = File.expand_path('../txt_tm_importer/spec/sample_files/wordfast_multiple.txt')
+      txt = TxtTmImporter::Tm.new(file_path: file_path).import
+      expect(txt[0][-1][0]).to eq(txt[1][-1][0])
+    end
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: txt_tm_importer
 version: !ruby/object:Gem::Version
-  version: 0.4.0
+  version: 0.5.0
 platform: ruby
 authors:
 - Kevin S. Dias
@@ -100,6 +100,7 @@ files:
 - spec/sample_files/wordfast_1(utf-8).txt
 - spec/sample_files/wordfast_1.txt
 - spec/sample_files/wordfast_2.txt
+- spec/sample_files/wordfast_multiple.txt
 - spec/spec_helper.rb
 - spec/txt_tm_importer_spec.rb
 - txt_tm_importer.gemspec
@@ -131,5 +132,6 @@ test_files:
 - spec/sample_files/wordfast_1(utf-8).txt
 - spec/sample_files/wordfast_1.txt
 - spec/sample_files/wordfast_2.txt
+- spec/sample_files/wordfast_multiple.txt
 - spec/spec_helper.rb
 - spec/txt_tm_importer_spec.rb