estem 0.2.4 → 0.2.5

data/test/test_estem.rb

@@ -1,23 +1,28 @@
-# encoding: UTF-8
-
 require 'test/unit'
 require 'estem'
 
+# NOTE:
+# assuming we will run the test from the root directory of the project
+# using "rake test" from the command-line
+
 class EStemTest < Test::Unit::TestCase
-	def get_content(filename)
+	def get_content(filename, encoding='UTF-8')
 		content = nil
-		File.open(filename, 'r:UTF-8') do |f|
+		File.open(filename, "r:#{encoding}") do |f|
 			content = f.read()
 		end
 		content.scan(/(\S+)(?:\s+)(\S+)/)
 	end
 
-	def test_stem
-		# assuming we will run the test from the root directory of the project
-		# using "rake test" from the command-line
-		for word, good in get_content('test/diffs.txt')
+	def test_estem
+		for word, good in get_content('test/diffs_UTF8.txt')
 			assert_equal(good, word.es_stem, "input: " + word)
-		end  
+		end
+
+		for word, good in get_content('test/diffs_ISO88591.txt', 'ISO-8859-1')
+			ret = word.safe_es_stem
+			assert_equal(good, ret, "input: " + word)
+			assert_equal('ISO-8859-1', ret.encoding.name.upcase)
+		end
 	end
-  
 end

data/test/test_estem.rb~

@@ -0,0 +1,27 @@
+require 'test/unit'
+require 'estem'
+
+# NOTE:
+# assuming we will run the test from the root directory of the project
+# using "rake test" from the command-line
+
+class EStemTest < Test::Unit::TestCase
+	def get_content(filename, encoding='UTF-8')
+		content = nil
+		File.open(filename, "r:#{encoding}") do |f|
+			content = f.read()
+		end
+		content.scan(/(\S+)(?:\s+)(\S+)/)
+	end
+
+	def test_estem
+		for word, good in get_content('test/diffs_UTF8.txt')
+			assert_equal(good, word.es_stem, "input: " + word)
+		end
+
+		for word, good in get_content('test/diffs_ISO88591.txt', 'ISO-8859-1')
+			assert_equal(good, word.safe_es_stem, "input: " + word)
+			assert_equal(2,3)
+		end
+	end
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: estem
 version: !ruby/object:Gem::Version
-  version: 0.2.4
+  version: 0.2.5
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-06-25 00:00:00.000000000 Z
+date: 2012-08-02 00:00:00.000000000 Z
 dependencies: []
 description: Spanish stemming. Based on Martin Porter's specifications. See README
   file for more information.
@@ -19,14 +19,17 @@ extensions: []
 extra_rdoc_files: []
 files:
 - Rakefile
-- bin/es_stem.rb
 - lib/estem.rb
+- lib/estem.rb~
 - examples/usage.rb
+- examples/usage.rb~
 - COPYRIGHT
 - README.rdoc
 - ChangeLog
-- test/diffs.txt
+- test/diffs_ISO88591.txt
+- test/diffs_UTF8.txt
 - test/test_estem.rb
+- test/test_estem.rb~
 homepage: https://github.com/MaG21/estem
 licenses: []
 post_install_message: 
@@ -52,5 +55,7 @@ signing_key:
 specification_version: 3
 summary: Spanish stemming. Based on Martin Porter's specifications.
 test_files:
-- test/diffs.txt
+- test/diffs_ISO88591.txt
+- test/diffs_UTF8.txt
 - test/test_estem.rb
+- test/test_estem.rb~

data/bin/es_stem.rb

@@ -1,179 +0,0 @@
-#!/usr/bin/env ruby
-# encoding: UTF-8
-# :stopdoc:
-
-# Copyright (c) 2012 Manuel A. Güílamo
-# 
-# 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.
-
-require 'estem'
-require 'getoptlong'
-require 'iconv'
-
-$version = "0.1.10"
-
-def usage(error=false)
-	out = error ? $stderr : $stdout
-	out.puts DATA.read()
-end
-
-opts = GetoptLong.new(
-	['--help', '-h', GetoptLong::NO_ARGUMENT],
-	['--version', '-v', GetoptLong::NO_ARGUMENT],
-	['--file', '-f', GetoptLong::REQUIRED_ARGUMENT],
-	['--in-enc', '-i', GetoptLong::REQUIRED_ARGUMENT],
-	['--out-enc', '-o', GetoptLong::REQUIRED_ARGUMENT])
-
-opts.quiet = true
-
-filename = nil
-ienc = nil
-oenc = nil
-
-begin
-	opts.each do |op, arg|
-		case op
-		when '--help'
-			usage()
-			exit
-		when '--version'
-			puts "EStem\nSpanish stemmer // lexemador\nVer: #{$version}"
- 			exit
-		when '--file'
-			filename = arg
-		when '--in-enc'
-			ienc =  arg
-		when '--out-enc'
-			oenc = arg
-		end
-	end
-rescue GetoptLong::MissingArgument
-	$stderr.puts 'Option requires an argument // La opción requiere un argumento'
-	exit
-rescue GetoptLong::InvalidOption
-	$stderr.puts 'Unknown option // Opción desconocida.'
-	usage(true)
-	exit
-rescue
-	puts $!
-	exit
-end
-
-if filename
-	begin
-		if ienc and ienc.upcase !='UTF-8'
-			file = File.open(filename, "r:#{ienc}:UTF-8")
-		else
-			file = File.open(filename, 'r:UTF-8')
-		end
-	rescue
-		$stderr.puts $!
-		exit
-	end
-
-	begin
-		hsh = {}
-		file.each_line do|line|
-			line.split(/[^a-záéíóúüñÁÉÍÓÚÜÑ]+/ui).each do|word|
-				hsh[word] = word.es_stem unless hsh[word]
-			end
-		end
-	rescue
-		puts $!
-		exit
-	ensure
-		file.close
-	end
-else
-	hsh = {}
-	$stdin.each_line do|line|
-		if ienc
-			line = Iconv.conv('UTF-8', ienc, line)
-		else
-			# Just in case the terminal mess with the encoding name.
-			# Por si la terminal juega con el nombre de la codificación.
-			line.force_encoding('UTF-8')
-		end
-
-		begin
-			line.split(/[^a-záéíóúüñÁÉÍÓÚÜÑ]+/ui).each do|word|
-				hsh[word] = word.es_stem unless hsh[word]
-			end
-		rescue Encoding::CompatibilityError
-			if ienc
-				msg = "incompatible encoding, please use option " +
-				      "`--in-inc' correctly. //\n" +
-				      "codificación incompatible, por favor use la " +
-				      "opción `--in-inc' correctamente."
-			else
-				msg="incompatible encoding, please use option `--in-inc'."+
-				    " //\ncodificación incompatible, por favor use la " +
-				    "opción `--in-inc'."
-			end
-
-			if oenc
-				msg = Iconv.conv(oenc, 'UTF-8', msg)
-			end
-
-			$stderr.puts msg
-			exit
-		rescue
-			puts $!
-			exit
-		end
-	end
-end
-
-if oenc
-	begin
-		hsh.each_pair do |k,v|
-			puts Iconv.conv(oenc, 'UTF-8', "#{k} => #{v}")
-		end
-	rescue
-		puts $!
-		exit
-	end
-else
-	hsh.each_pair{ |k,v| puts "#{k} => #{v}" }
-end
-
-__END__
-Use: es_stem [OPTION]...
-
-Options:
-  --help, -h     display this help and exit. // Presenta esta ayuda y termina.
-  --version, -v  output version information and exit //
-                 Muestra la versión y termina.
-  --file, -f     file of words. // fichero de palabras.
-  --in-enc, -i   encoding of the file. // codificación del fichero.
-  --out-enc, -o  output encoding // codificación de salida.
-
-By default UTF-8 is used as input encoding, and if no file is specified,
-standard input will be used instead.
-
-You should set the option `--out-enc' if you are experimenting problems
-visualizing the output text.
-
-//
-
-Por defecto se usará UTF-8 como codificación de entrada, si no se especifica un
-fichero, la entrada estándard se usará en su lugar.
-
-Debería establecer la opción `--out-enc' si está experimentando problemas para
-visualizar el texto de salida.