syc-spector 0.0.2 → 0.0.3

data/README.rdoc

@@ -1,4 +1,4 @@
-= Welcome to syc-spector
+== Welcome to syc-spector
  home :: https://github.com/sugaryourcoffee/syc-spector
 
 == Description
@@ -6,10 +6,10 @@ The sycspector scans a file for patterns provided on the command line.
 Lines that match the pattern are saved to a file with valid values and those lines that don't match the pattern are added to a file with invalid values.
 The valid and invalid files as well as the used pattern are stored in a
 history file. The saved values are used for a subsequent call to sycspector
-with --show and -f for fix to show the results or to prompt the invalid values to fix them. Fixed values can appended to the valid values file.
+with --show and -f for fix to show the results or to prompt the invalid values to fix them. Fixed values can be appended to the valid values file.
 
 == Installation
-sycspector can be installed as a gem from [RubyGems](http://RubyGems.org) with
+sycspector can be installed as a gem from http://RubyGems.org with
   $ gem install syc-spector
 
 == Invokation Examples
@@ -51,4 +51,4 @@ To process all at once
   $ sycspector -fis inputfile -o outputfile -p "\A\w+, w+\Z" --show
 
 == License
-syc-spector is released under the {MIT License}[http://www.opensource.org/license/MIT].
+syc-spector is released under the {MIT License}[http://www.opensource.org/licenses/MIT].

data/lib/inspector/options.rb

@@ -98,9 +98,6 @@ module Inspector
         
         # Create a flag
 
-        @options[:pattern] = /\A.*\Z/
-        @options[:scan_pattern] = /\A.*\Z/
-
         opts.on("-p", "--pattern PATTERN",
                 "Values that match the pattern are",
                 "considered as valid values.",
@@ -165,8 +162,10 @@ module Inspector
             File.open(".sycspector.data", 'r') do |file|
               files = create_output_files file.gets.chomp            
               argv << file.gets.chomp
-              @options[:pattern] = Regexp.new(file.gets.chomp)
-              @options[:scan_pattern] = Regexp.new(file.gets.chomp)
+              unless @options[:pattern]
+                @options[:pattern] = Regexp.new(file.gets.chomp)
+                @options[:scan_pattern] = Regexp.new(file.gets.chomp)
+              end
             end
           else
             STDERR.puts "--> no sycspector history.\n" +
@@ -205,6 +204,11 @@ module Inspector
             @options[:valid_file] = files[:valid_file]
             @options[:invalid_file] = files[:invalid_file]
           end
+
+          unless @options[:pattern]
+            @options[:pattern] = DEFAULT_PATTERN
+            @options[:scan_pattern] = DEFAULT_PATTERN
+          end
         end
       end
     end

data/lib/inspector/pattern.rb

@@ -6,6 +6,9 @@ EMAIL_PATTERN = /\A[\w!#\$%&'*+\/=?`{|}~^-]+(?:\.[\w!#\$%&'*+\/=?`{|}~^-]+)*@(?:
 # Pattern that relizes an email within a line.
 ANY_EMAIL_PATTERN = /[\w!#\$%&'*+\/=?`{|}~^-]+(?:\.[\w!#\$%&'*+\/=?`{|}~^-]+)*@(?:[a-zA-Z0-9-]+\.)+[a-zA-Z]{2,6}/
 
+# Default pattern scanning whole lines
+DEFAULT_PATTERN = /\A.*\Z/
+
 # Pattern that relizes strings between \A and \Z that is beginning of line and
 # end of line patterns.
 FULL_LINE = /(?<=\\A).*(?=\\Z)/

data/lib/inspector/separator.rb

@@ -136,7 +136,7 @@ module Inspector
                 invalid_values << value
               end
             else
-              valid_values << match
+              valid_values << match.to_s
             end
           end
         end
@@ -145,7 +145,7 @@ module Inspector
       valid_counter = valid_values.size
 
       valid_values.uniq! {|value| value.downcase } if opts[:individualize]
-      valid_values.sort! if opts[:sort]
+      valid_values.sort! {|a,b| a.downcase <=> b.downcase } if opts[:sort]
 
       valid_values.each do |value|
           valid_file.puts value

data/sycspector.gemspec

@@ -1,11 +1,9 @@
 Gem::Specification.new do |s|
   s.name         = "syc-spector"
-  s.summary      = 
-    "Analyze a file and extract values matching a provided pattern.\n \
-     Allow to sort, remove double and manually fix values."
-  s.description  = File.read(File.join(File.dirname(__FILE__), 'README'))
+  s.summary      = "Extract, sort and individualize values from a file"
+  s.description  = File.read(File.join(File.dirname(__FILE__), 'README.rdoc'))
   s.requirements = ['No requirements']
-  s.version      = "0.0.2"
+  s.version      = "0.0.3"
   s.author       = "Pierre Sugar"
   s.email        = "pierre@sugaryourcoffee.de"
   s.homepage     = "http://syc.dyndns.org/drupal"
@@ -15,4 +13,5 @@ Gem::Specification.new do |s|
   s.executables  = ['sycspector']
   s.test_files   = Dir['test/test*.rb']
   s.has_rdoc     = true
+  s.extra_rdoc_files = ['README.rdoc']
 end

data/test/test_options.rb

@@ -30,7 +30,6 @@ class TestOptions < Test::Unit::TestCase
     
     # Intializes the input, valid, invalid and history file
     def setup
-      puts "in startup"
       File.open('existing', 'w') do |file|
         file.puts "pierre@thesugars.de"
         file.puts "amanda@thesugars.de und pierre@thesugars.de"
@@ -38,11 +37,11 @@ class TestOptions < Test::Unit::TestCase
       File.open('.sycspector.data', 'w') do |file|
         file.puts "20130113-121212_valid_values"
         file.puts "20130113-121212_invalid_values"
-        file.puts "(?-mix:\A[\w!#\$%&'*+\/=?`{|}~^-]+" +
-                  "(?:\.[\w!#\$%&'*+\/=?`{|}~^-]+)*@(?:[a-zA-Z0-9-]+\.)+" +
-                  "[a-zA-Z]{2,6}\Z)"
-        file.puts "(?-mix:[\w!#\$%&'*+\/=?`{|}~^-]+" +
-                  "(?:\.[\w!#\$%&'*+\/=?`{|}~^-]+)*@(?:[a-zA-Z0-9-]+\.)+" +
+        file.puts "(?-mix:\\A[\\w!#\\$%&'*+\/=?`{|}~^-]+" +
+                  "(?:\\.[\\w!#\\$%&'*+\/=?`{|}~^-]+)*@(?:[a-zA-Z0-9-]+\\.)+" +
+                  "[a-zA-Z]{2,6}\\Z)"
+        file.puts "(?-mix:[\\w!#\\$%&'*+\/=?`{|}~^-]+" +
+                  "(?:\\.[\\w!#\\$%&'*+\/=?`{|}~^-]+)*@(?:[a-zA-Z0-9-]+\\.)+" +
                   "[a-zA-Z]{2,6})"
       end
       File.open('20130113-121212_valid_values', 'w') do |file|
@@ -57,15 +56,16 @@ class TestOptions < Test::Unit::TestCase
 
     # Cleans up the test directory by deleting the files created in setup
     def teardown
-      puts "in shutdown"
       `rm existing`
       `rm 20130113-*`
       `rm .sycspector.data`
     end
  
-    should "return inputfile" do
+    should "return inputfile and default pattern" do
       opts = Inspector::Options.new(["existing"])
       assert_equal "existing", opts.options[:infile]
+      assert_equal DEFAULT_PATTERN, opts.options[:pattern]
+      assert_equal DEFAULT_PATTERN, opts.options[:scan_pattern]
     end
 
     should "return email pattern" do
@@ -104,12 +104,29 @@ class TestOptions < Test::Unit::TestCase
       assert_equal nil, opts.options[:infile]
     end
 
-    should "return fix and invalid file as input file from last invokation" do
+    should "return fix and invalid file as input file and pattern "+ 
+           "from last invokation" do
       opts = Inspector::Options.new(["-f"])
       assert_equal true, opts.options[:fix]
       assert_equal "20130113-121212_invalid_values", opts.options[:infile]
+
+      pattern_match = 
+        "a@b.c".match(EMAIL_PATTERN).to_s == 
+        "a@b.c".match(opts.options[:pattern]).to_s
+      scan_pattern_match = 
+        "is a@b.c here?".match(ANY_EMAIL_PATTERN).to_s == 
+        "is a@b.c here?".match(opts.options[:scan_pattern]).to_s
+
+      assert_equal true, pattern_match
+      assert_equal true, scan_pattern_match
     end
 
+    should "return fix and provided pattern and scan_pattern" do
+      opts = Inspector::Options.new(["-f", "-p", "\\A\\w+@\\w+\\.\\w+\\Z"])
+      assert_equal true, opts.options[:fix]
+      assert_equal /\A\w+@\w+\.\w+\Z/, opts.options[:pattern]
+      assert_equal /\w+@\w+\.\w+/, opts.options[:scan_pattern]
+    end
   end
 
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: syc-spector
 version: !ruby/object:Gem::Version
-  version: 0.0.2
+  version: 0.0.3
   prerelease: 
 platform: ruby
 authors:
@@ -9,18 +9,18 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-01-16 00:00:00.000000000 Z
+date: 2013-01-19 00:00:00.000000000 Z
 dependencies: []
-description: ! "= Welcome to syc-spector\n home :: https://github.com/sugaryourcoffee/syc-spector\n\n==
+description: ! "== Welcome to syc-spector\n home :: https://github.com/sugaryourcoffee/syc-spector\n\n==
   Description\nThe sycspector scans a file for patterns provided on the command line.\nLines
   that match the pattern are saved to a file with valid values and those lines that
   don't match the pattern are added to a file with invalid values.\nThe valid and
   invalid files as well as the used pattern are stored in a\nhistory file. The saved
   values are used for a subsequent call to sycspector\nwith --show and -f for fix
   to show the results or to prompt the invalid values to fix them. Fixed values can
-  appended to the valid values file.\n\n== Installation\nsycspector can be installed
-  as a gem from [RubyGems](http://RubyGems.org) with\n  $ gem install syc-spector\n\n==
-  Invokation Examples\nRearches for email addresses in the provided file 'email_addresses'\n
+  be appended to the valid values file.\n\n== Installation\nsycspector can be installed
+  as a gem from http://RubyGems.org with\n  $ gem install syc-spector\n\n== Invokation
+  Examples\nRearches for email addresses in the provided file 'email_addresses'\n
   \ $ sycspector email_addresses -p email\n\nLines that are not recognized can be
   prompted, fixed and appended to the\nvalid file with\n  $ sycspector -fa\n\nTo show
   the result of the invokation use\n  $ sycspector --show\n\nTo fix the values from
@@ -36,12 +36,13 @@ description: ! "= Welcome to syc-spector\n home :: https://github.com/sugaryourc
   the file where the results (valid and invalid) should go to\n  $ sycspector -fa
   -o outputfile\n\nTo process all at once\n  $ sycspector -fis inputfile -o outputfile
   -p \"\\A\\w+, w+\\Z\" --show\n\n== License\nsyc-spector is released under the {MIT
-  License}[http://www.opensource.org/license/MIT].\n"
+  License}[http://www.opensource.org/licenses/MIT].\n"
 email: pierre@sugaryourcoffee.de
 executables:
 - sycspector
 extensions: []
-extra_rdoc_files: []
+extra_rdoc_files:
+- README.rdoc
 files:
 - syc-spector-0.0.1.gem
 - README.rdoc
@@ -97,9 +98,10 @@ files:
 - doc/Inspector/Options.html
 - doc/Inspector/Runner.html
 - doc/TestConsole.html
+- syc-spector-0.0.3.gem
 - sycspector.gemspec
 - bin/sycspector
-- README
+- syc-spector-0.0.2.gem
 homepage: http://syc.dyndns.org/drupal
 licenses: []
 post_install_message: 
@@ -124,8 +126,7 @@ rubyforge_project:
 rubygems_version: 1.8.24
 signing_key: 
 specification_version: 3
-summary: Analyze a file and extract values matching a provided pattern. Allow to sort,
-  remove double and manually fix values.
+summary: Extract, sort and individualize values from a file
 test_files:
 - test/test_options.rb
 - test/test_separator.rb

data/README

@@ -1,54 +0,0 @@
-= Welcome to syc-spector
- home :: https://github.com/sugaryourcoffee/syc-spector
-
-== Description
-The sycspector scans a file for patterns provided on the command line.
-Lines that match the pattern are saved to a file with valid values and those lines that don't match the pattern are added to a file with invalid values.
-The valid and invalid files as well as the used pattern are stored in a
-history file. The saved values are used for a subsequent call to sycspector
-with --show and -f for fix to show the results or to prompt the invalid values to fix them. Fixed values can appended to the valid values file.
-
-== Installation
-sycspector can be installed as a gem from [RubyGems](http://RubyGems.org) with
-  $ gem install syc-spector
-
-== Invokation Examples
-Rearches for email addresses in the provided file 'email_addresses'
-  $ sycspector email_addresses -p email
-
-Lines that are not recognized can be prompted, fixed and appended to the
-valid file with
-  $ sycspector -fa
-
-To show the result of the invokation use
-  $ sycspector --show
-
-To fix the values from the input file at the first scan
-  $ sycspector -f email-addresses -p email
-
-To sort the values
-  $ sycspector -s email-addresses -p email
-
-To fix, sort and remove duplicates (individualize)
-  $ sycspector -fsi email-addresses -p email
-
-Matching patterns like 'name, firstname'
-  $ syscpector name -p "\w+, \w+"
-
-Scanning only whole lines use
-  $ sycspector name -p "\A\w+, \w+\A"
-
-If the file contains lines like "Doe, John and Doe, Jane" these won't be saved at the first scan but can be scanned with the --fix switch and appended to the valid values from the last run
-  $ sycspector -fa
-
-Fixing a specific file by specifying the invalid file as inputfile
-  $ sycspector -fa 2013016-083346_invalid_name -o 2013016-083346_valid_name
-
-Specifying the file where the results (valid and invalid) should go to
-  $ sycspector -fa -o outputfile
-
-To process all at once
-  $ sycspector -fis inputfile -o outputfile -p "\A\w+, w+\Z" --show
-
-== License
-syc-spector is released under the {MIT License}[http://www.opensource.org/license/MIT].