file_sort 0.0.2 → 0.0.3

data/lib/file_sort.rb

@@ -162,4 +162,5 @@ class FileSort
 end
 
 #Run as
-#FileSort.new("large-file-10000000.csv", {parse_as: :int, replace_original: false}).sort!
+#FileSort.new("large-file-1000000.csv", {replace_original: false, lines_per_split: 100000}).sort!
+#FileSort.new("large-file-10000000.csv", {replace_original: false}).sort!

data/lib/merger.rb

@@ -13,45 +13,42 @@ class Merger
     f1 = File.open(@filename1)
     f2 = File.open(@filename2)
 
-    f1_line = self.get_line(f1)
-    f2_line = self.get_line(f2)
+    f1_line, f1_col = self.get_line(f1)
+    f2_line, f2_col = self.get_line(f2)
     while !f1_line.nil? and !f2_line.nil?
-      if f1_line[@sort_column] < f2_line[@sort_column]
-        self.write_line(outfile, f1_line)
-        f1_line = self.get_line(f1)
+      if f1_col < f2_col
+        outfile.print f1_line
+        f1_line, f1_col = self.get_line(f1)
       else
-        self.write_line(outfile, f2_line)
-        f2_line = self.get_line(f2)
+        outfile.print f2_line
+        f2_line, f2_col = self.get_line(f2)
       end
     end
 
     while !f1_line.nil?
-      self.write_line(outfile, f1_line)
-      f1_line = self.get_line(f1)
+      outfile.print f1_line
+      f1_line, f1_col = self.get_line(f1, false)
     end
 
     while !f2_line.nil?
-      self.write_line(outfile, f2_line)
-      f2_line = self.get_line(f2)
+      outfile.print f2_line
+      f2_line, f2_col = self.get_line(f2, false)
     end
 
-
     f1.close
     f2.close
     outfile.close
   end
 
-  def get_line(stream)
+  def get_line(stream, parse_cols = true)
     line = stream.gets
-    return nil if line.nil?
-    line = line.chomp.split(@column_separator)
-    line[@sort_column] = line[@sort_column].to_i if @sort_as_int
-    return line
+    return [nil, nil] if line.nil?
+    return [line, nil] unless parse_cols
+    cols = line.chomp.split(@column_separator, @sort_column + 2)
+    cols[@sort_column] = cols[@sort_column].to_i if @sort_as_int
+    return [line, cols[@sort_column]]
   end
 
-  def write_line(stream, line)
-    stream.puts line.join(@column_separator)
-  end
 end
 
 Merger.new.merge!

data/lib/sorter.rb

@@ -12,14 +12,14 @@ class Sorter
     lines = []
     infile = File.open(@input_filename)
     while line = infile.gets
-      line = line.chomp.split(@column_separator)
-      line[@sort_column] = line[@sort_column].to_i if @sort_as_int
-      lines << line
+      col = line.split(@column_separator, @sort_column + 2)[@sort_column]
+      col = col.to_i if @sort_as_int
+      lines << [col, line]
     end
     infile.close
-    lines.sort!{ |a, b| a[@sort_column] <=> b[@sort_column] }
+    lines.sort!{ |a, b| a[0] <=> b[0] }
     outfile = File.open(@sorted_filename, "w")
-    lines.each{ |line| outfile.puts(line.join(@column_separator)) }
+    lines.each{ |line| outfile.print line[1] }
     outfile.close
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: file_sort
 version: !ruby/object:Gem::Version
-  version: 0.0.2
+  version: 0.0.3
   prerelease: 
 platform: ruby
 authors:
@@ -12,6 +12,7 @@ cert_chain: []
 date: 2013-01-27 00:00:00.000000000 Z
 dependencies: []
 description: Sorts large files using merge sort on temporary files on the hard drive.
+  Also known as an external sort.
 email: tom.oneill@live.com
 executables: []
 extensions: []