From 68acbb9a0c7967cb90a7e3756fc94fdd8a73d154 Mon Sep 17 00:00:00 2001
From: Patrick Simianer <p@simianer.de>
Date: Wed, 29 Jan 2014 19:14:08 +0100
Subject: make use of nlp_ruby, LICENSE

---
 min_max | 42 ++++++++++++++++++------------------------
 1 file changed, 18 insertions(+), 24 deletions(-)

(limited to 'min_max')

diff --git a/min_max b/min_max
index f27de88..653cde3 100755
--- a/min_max
+++ b/min_max
@@ -1,33 +1,26 @@
 #!/usr/bin/ruby
 
+require 'nlp_ruby'
 require 'trollop'
 
 
-STDIN.set_encoding 'utf-8'
-STDOUT.set_encoding 'utf-8'
-
-def usage
-  puts "filter-min-max.rb --min <min> --max <max> --in_f <in f> --in_e <in e> --out_f <out f> --out_e <out e> --out_id <out ids>" 
-end
-usage if ARGV.size!=14
-
-opts = Trollop::options do
+cfg = Trollop::options do
   opt :min, "minimum #tokens", :type => :int, :default => 1
-  opt :max, "maximum #tokens", :type => :int, :default => 80
-  opt :in_f "input 'French' file", :type => string
-  opt :in_e "input 'English' file", :type => string
-  opt :out_f "output 'French' file", :type => string
-  opt :out_e "output 'English' file", :type => string
-  opt :out_id "output line Nos", :type => string
+  opt :max, "maximum #tokens", :type => :int, :default => 80, :short => '-n'
+  opt :in_f, "input 'French' file", :type => :string, :required => true
+  opt :in_e, "input 'English' file", :type => :string, :required => true
+  opt :out_f, "output 'French' file", :type => :string, :required => true
+  opt :out_e, "output 'English' file", :type => :string, :required => true
+  opt :out_id, "output line Nos", :type => :string, :required => true
 end
 
 
 files = {}
-files[:f_file] = File.new opts[:in_f], 'r:UTF-8'
-files[:e_file] = File.new opts[:in_e], 'r:UTF-8'
-files[:f_out_file] = File.new opts[:out_f], 'w:UTF-8'
-files[:e_out_file] = File.new opts[:out_e], 'w:UTF-8'
-files[:id_out_file] = File.new opts[:out_id], 'w'
+files[:f_file] = ReadFile.new cfg[:in_f]
+files[:e_file] = ReadFile.new cfg[:in_e]
+files[:f_out_file] = WriteFile.new cfg[:out_f]
+files[:e_out_file] = WriteFile.new cfg[:out_e]
+files[:id_out_file] = WriteFile.new cfg[:out_id]
 i = 0
 while f_line = files[:f_file].gets
   e_line = files[:e_file].gets
@@ -35,13 +28,14 @@ while f_line = files[:f_file].gets
   e_line.strip!
   a = f_line.split
   b = e_line.split
-  if a.size >= opts[:min] and a.size <= opts[:max] and \
-      b.size >= opts[:min] and b.size <= opts[:max]
+  if a.size >= cfg[:min] and a.size <= cfg[:max] and \
+      b.size >= cfg[:min] and b.size <= cfg[:max]
     files[:f_out_file].write "#{f_line}\n"
     files[:e_out_file].write "#{e_line}\n"
     files[:id_out_file].write "#{i}\n"
-  end  
+  end
   i+=1
 end
-files.values.each{|f|f.close}
+
+files.values.each{ |f| f.close }
 
-- 
cgit v1.2.3