unix_utils 0.0.4 → 0.0.5

data/History.txt

@@ -1,3 +1,13 @@
+== 0.0.5 / 2012-03-21
+
+* Enhancements
+
+  * Change pipe buffer size to 64kb (it was 4mb before), which seems to make everything run faster
+
+* Bug fixes
+
+  * Thanks to @leomao10, make sed work more reliably on large files by using its input-file argument rather than piping in data
+
 == 0.0.4 / 2012-03-19
 
 * Bug fixes

data/lib/unix_utils.rb

@@ -8,7 +8,7 @@ require "unix_utils/version"
 
 module UnixUtils
 
-  BUFSIZE = 4_194_304
+  BUFSIZE = 2**16
 
   def self.curl(url, form_data = nil)
     outfile = tmp_path url
@@ -192,12 +192,13 @@ module UnixUtils
     end
   end
 
+  # POSIX sed, whether it's provided by sed or gsed
   def self.sed(infile, *expr)
     infile = ::File.expand_path infile
     outfile = tmp_path infile
-    bin = available?('gsed') ? 'gsed' : 'sed'
-    argv = [ bin, expr.map { |e| ['-e', e] } ].flatten
-    spawn argv, :read_from => infile, :write_to => outfile
+    bin = available?('sed') ? 'sed' : ['gsed', '--posix']
+    argv = [ bin, expr.map { |e| ['-e', e] }, infile ].flatten
+    spawn argv, :write_to => outfile
     outfile
   end
 

data/lib/unix_utils/version.rb

@@ -1,3 +1,3 @@
 module UnixUtils
-  VERSION = "0.0.4"
+  VERSION = "0.0.5"
 end

data/test/regression/test_sed_large_file.rb

@@ -0,0 +1,32 @@
+# encoding: UTF-8
+require 'helper'
+require 'tempfile'
+
+describe "handle large file with sed" do
+  let(:normal_line_no)  { 124000 }
+  let(:invalid_line_no) { 10 }
+  let(:input_file)      { Tempfile.open('test', '/tmp') }
+
+  before do
+    begin
+      (1..normal_line_no).each do |i|
+        input_file.puts "\"psmith01\",\"CLASS2B\",\"Peter Smith 1\",\"YEAR2\",\"1\",\"N\",\"ADVANCED\",\"STAFF\",\"1\",\"Y\",\"Y\",\"psmith01\",\"CLASS2B\",\"Peter Smith 1\",\"YEAR2\",\"1\",\"N\",\"ADVANCED\",\"STAFF\",\"1\",\"Y\",\"Y\",\"psmith01\",\"CLASS2B\",\"Peter Smith 1\",\"YEAR2\",\"1\",\"N\",\"ADVANCED\",\"STAFF\",\"1\",\"Y\",\"Y\",\"psmith01\",\"CLASS2B\",\"Peter Smith 1\",\"YEAR2\",\"1\",\"N\",\"ADVANCED\",\"STAFF\",\"1\",\"Y\",\"Y\""
+      end
+      (1..invalid_line_no).each do |i|
+        input_file.puts "@!!@"
+      end
+      input_file.flush
+    ensure
+      input_file.close
+    end
+  end
+
+  it "should have 124000 lines in output file" do
+    output_path = UnixUtils.sed(input_file.path, ':a', "1,#{invalid_line_no}!{P;N;D;};N;ba")
+    UnixUtils.wc(output_path).first.must_equal normal_line_no
+  end
+
+  after do
+    input_file.unlink
+  end
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: unix_utils
 version: !ruby/object:Gem::Version
-  version: 0.0.4
+  version: 0.0.5
   prerelease: 
 platform: ruby
 authors:
@@ -9,11 +9,11 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-03-20 00:00:00.000000000 Z
+date: 2012-03-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: posix-spawn
-  requirement: &2154399440 !ruby/object:Gem::Requirement
+  requirement: &2154458300 !ruby/object:Gem::Requirement
     none: false
     requirements:
     - - ! '>='
@@ -21,7 +21,7 @@ dependencies:
         version: '0'
   type: :runtime
   prerelease: false
-  version_requirements: *2154399440
+  version_requirements: *2154458300
 description: Like FileUtils, but provides zip, unzip, bzip2, bunzip2, tar, untar,
   sed, du, md5sum, shasum, cut, head, tail, wc, unix2dos, dos2unix, iconv, curl, perl,
   etc.
@@ -39,6 +39,7 @@ files:
 - lib/unix_utils.rb
 - lib/unix_utils/version.rb
 - test/helper.rb
+- test/regression/test_sed_large_file.rb
 - test/target/directory-really-a-t_a_r-shh
 - test/target/directory-really-a-z_i_p-shh
 - test/target/directory.tar
@@ -84,6 +85,7 @@ summary: Like FileUtils, but provides zip, unzip, bzip2, bunzip2, tar, untar, se
   etc.
 test_files:
 - test/helper.rb
+- test/regression/test_sed_large_file.rb
 - test/target/directory-really-a-t_a_r-shh
 - test/target/directory-really-a-z_i_p-shh
 - test/target/directory.tar