pcut 0.0.2 → 0.1.0

data/History.txt

@@ -1,3 +1,12 @@
+
+=== 0.1.0 2012-03-29
+
+* Add 2 features:
+  * -c to skip continuous delimiters
+  * -j to specifies char to join cut result
+
+=== 0.0.2 2012-03-29
+
 === 0.0.1 2012-03-29
 
 * 1 major enhancement:

data/Manifest.txt

@@ -1,4 +1,3 @@
-.README.rdoc.swp
 History.txt
 Manifest.txt
 PostInstall.txt

data/README.rdoc

@@ -64,9 +64,25 @@ You can set multiple chars to quote.
 
 === sub queries
 
-
-
-
+You can get partial string by cutting the cut result again
+with original syntax [/#{delimiter}/, #{index}].
+This is useful for getting platform from UserAgent, or getting file extention
+string from PATH.
+
+  $ cat test | pcut -d " " --preview --vertical -q "D[" -k -f "4, 5"
+  [4][10/Oct/2000:13:55:36 -0700]
+  [5]"GET /apache_pb.gif HTTP/1.0"
+  
+  $ cat test | pcut -d " " --preview --vertical -q "D[" -k -f "4, 5.[/ /,2]"
+  [4][10/Oct/2000:13:55:36 -0700]
+  [5.[/ /,2]]/apache_pb.gif
+  
+  $ cat test | pcut -d " " --preview --vertical -q "D[" -k -f "4, 5.[/ /,2].[/./,2]"
+  [4][10/Oct/2000:13:55:36 -0700]
+  [5.[/ /,2].[/./,2]]gif
+  
+  $ cat test | pcut -d " " -q "D[" -k -f "4, 5.[/ /,2].[/./,2]"
+  [10/Oct/2000:13:55:36 -0700] gif
 
 == SYNOPSIS:
 

data/bin/pcut

@@ -50,6 +50,15 @@ end
 opt.on('-n', '--no-color', 'turn colot output off') do
   cli.color = false
 end
+opt.on('-c', '--skip-continuous-deimiters',
+  'treat continuous delimiters as one delimiter') do
+  cli.skip_continuous_delimiters = true
+end
+opt.on('-j JOIN', '--join JOIN',
+  'JOIN specifies the letter used to join cut result.',
+  'You can use "TAB" to specify tab character.') do |v|
+  cli.set_joiner(v)
+end
 
 begin
   opt.parse!(ARGV)

data/lib/pcut.rb

@@ -2,5 +2,5 @@ $:.unshift(File.dirname(__FILE__)) unless
   $:.include?(File.dirname(__FILE__)) || $:.include?(File.expand_path(File.dirname(__FILE__)))
 
 module Pcut
-  VERSION = '0.0.2'
+  VERSION = '0.1.0'
 end

data/lib/pcut/cli.rb

@@ -19,7 +19,8 @@ module Pcut
       :keep_quote,
       :preview,
       :vertical,
-      :color
+      :color,
+      :skip_continuous_delimiters
     
     def initialize
       @delimiter  = "\t"
@@ -30,6 +31,19 @@ module Pcut
       @preview    = false
       @vertical   = false
       @color      = true
+      @skip_continuous_delimiters = false
+    end
+
+    def set_joiner(char)
+      if char == "TAB"
+        @joiner = "\t"
+        return
+      end
+      if char.size != 1
+        STDERR.puts "join char must be 1 byte char or 'TAB'"
+        exit(1)
+      end
+      @joiner = char
     end
 
     def parse_field(str)
@@ -74,6 +88,7 @@ module Pcut
       begin
         parser = Pcut::LineParser.new
         parser.set_delimiter(@delimiter)
+        parser.skip_continuous_delimiters = @skip_continuous_delimiters
         @quote.each_char { |c| parser.set_quote_guard(c) } if @quote
         parser.keep_quotes = true if @keep_quote
       rescue => e

data/lib/pcut/line_parser.rb

@@ -17,13 +17,18 @@ module Pcut
     }
     DELIMITER = "\t"
 
-    attr_reader :quote_guard
-    attr_accessor :keep_quotes
+    attr_accessor \
+      :quote_guard,
+      :keep_quotes,
+      :skip_continuous_delimiters
 
     def initialize
       @quote_guard  = {}
       @delimiter    = DELIMITER
-      @keep_quotes  = false # do not delete quoting chars
+      # do not delete quoting chars
+      @keep_quotes  = false
+      # treat continuous delimiters as one delimiters
+      @skip_continuous_delimiters = false
     end
 
     def set_quote_guard(quote)
@@ -49,6 +54,13 @@ module Pcut
 
       str.each_char do |c|
 
+        # skip continuous delimiters
+        if skip_continuous_delimiters &&
+          @delimiter == c &&
+          @delimiter == previous_char
+          next
+        end
+
         # check starting quote
         if @quote_guard.include?(c) &&
           previous_char != "\\" # not escaped

data/spec/lib/pcut/line_parser_spec.rb

@@ -182,6 +182,13 @@ describe Pcut::LineParser do
 
   end
 
+  it 'skips continuous delimiters if needed' do
+    @parser.skip_continuous_delimiters = true
+    @parser.set_delimiter(" ")
+    result = @parser.parse("1979   8  23   bonar   ")
+    result.should == ['1979', '8', '23', 'bonar']
+  end
+
   describe 'real world sample' do
 
     before(:each) do

metadata

@@ -5,9 +5,9 @@ version: !ruby/object:Gem::Version
   prerelease: 
   segments: 
   - 0
+  - 1
   - 0
-  - 2
-  version: 0.0.2
+  version: 0.1.0
 platform: ruby
 authors: 
 - Nakano Kyohei (bonar)
@@ -94,7 +94,6 @@ extra_rdoc_files:
 - PostInstall.txt
 - README.rdoc
 files: 
-- .README.rdoc.swp
 - History.txt
 - Manifest.txt
 - PostInstall.txt