grepper 0.9.2 → 0.9.3

data/History.txt

@@ -22,3 +22,8 @@
 * Added some logic to the Match and Result classes
 
 * Refactoring
+
+=== 0.9.3 / 2009-01-13
+
+* Added l/L, h/H, o options
+

data/Manifest.txt

@@ -2,6 +2,7 @@ History.txt
 Manifest.txt
 README.txt
 Rakefile
+TODO
 bin/grep.rb
 lib/grepper.rb
 lib/grepper/formatter.rb

data/README.txt

@@ -46,6 +46,8 @@ Available options are:
 * <tt>v</tt> -- negate the sense of the match
 * <tt>An</tt> -- provide n lines of after-context
 * <tt>Bn</tt> -- provide b lines of before-context
+* <tt>o</tt> -- store only the part of the line that matched the pattern
+* <tt>w</tt> -- count only complete-word matches
 
 == Generating the result set
 
@@ -84,7 +86,7 @@ and
 
 == Version
 
-0.9.2, December 24, 2008
+0.9.3, January 13, 2009
 
 == Author
 
@@ -92,7 +94,7 @@ David A. Black (dblack@rubypal.com)
 
 == Copyright and license
 
-Copyright (c) 2008, Ruby Power and Light, LLC
+Copyright (c) 2008-2009, Ruby Power and Light, LLC
 
 Released under the Ruby license. No warranty of any kind. Use
 entirely at your own risk. 

data/TODO

@@ -0,0 +1,14 @@
+Switches/options to add:
+
+* = done
+
+*  -H -- show filenames for all matches
+*  -h -- show no filenames
+*  -w -- select only matches that are made up of whole words
+*  -L -- invert -l (filenames with no matches)
+*  -o -- show only part of line that matches pattern
+  -x -- select only matches that match the whole line
+
+API considerations:
+
+  Should Grepper have an option for only finding n matches?

data/bin/grep.rb

@@ -1,17 +1,31 @@
-$: << '../lib'
+# grep.rb
+#
+# grep-like commandline script
+#
+# Part of the Grepper package
+#
+# David A. Black/Ruby Power and Light, LLC
+#
+# January 13, 2009
+
 require 'rubygems'
 require 'grepper'
 require 'grepper/formatter'
 
 require 'getoptlong'
 
-
 opts = GetoptLong.new(
-  ['--help',            '-h',   GetoptLong::NO_ARGUMENT],
-  ['--line-number',     '-n',   GetoptLong::NO_ARGUMENT],
-  ['--before-context',  '-B',   GetoptLong::REQUIRED_ARGUMENT],
-  ['--after-context',    '-A',  GetoptLong::REQUIRED_ARGUMENT],
-  ['--invert-match',     '-v',  GetoptLong::NO_ARGUMENT]
+  ['--line-number',         '-n',   GetoptLong::NO_ARGUMENT],
+  ['--files-with-match',    '-l',   GetoptLong::NO_ARGUMENT],
+  ['--files-without-match', '-L',   GetoptLong::NO_ARGUMENT],
+  ['--with-filename',       '-H',   GetoptLong::NO_ARGUMENT],
+  ['--no-filename',         '-h',   GetoptLong::NO_ARGUMENT],
+  ['--before-context',      '-B',   GetoptLong::REQUIRED_ARGUMENT],
+  ['--after-context',       '-A',   GetoptLong::REQUIRED_ARGUMENT],
+  ['--context',             '-C',   GetoptLong::REQUIRED_ARGUMENT],
+  ['--count',               '-c',   GetoptLong::NO_ARGUMENT],
+  ['--invert-match',        '-v',   GetoptLong::NO_ARGUMENT],
+  ['--help',                        GetoptLong::NO_ARGUMENT]
 )
 
 grepper = Grepper.new
@@ -19,26 +33,32 @@ formatter = Grepper::Formatter.new(grepper)
 
 opts.each do |opt,arg|
   case opt
-  when '--line-number'
-    formatter.options << "n"
   when '--before-context'
     grepper.options << "B#{arg}"
   when '--after-context'
     grepper.options << "A#{arg}"
+  when 'context'
+    grepper.options << "C#{arg}"
+  when '--count'
+    formatter.options << "c"
   when '--invert-match'
     grepper.options << "v"
+  when '--line-number'
+    formatter.options << "n"
+  when '--with-filename'
+    formatter.options << "H"
+  when '--no-filename'
+    formatter.options << "h"
+  when '--files-with-match'
+    formatter.options << "l"
+  when '--files-without-match'
+    formatter.options << "L"
   when '--help'
-    puts "Help"
+    usage
     exit 0
-  else
-    puts "Unknown option #{opt}"
   end
 end
 
-if ARGV.size < 2
-  puts "Sorry"
-  exit 0
-end
 
 grepper.pattern = Regexp.new(ARGV.shift)
 grepper.files = ARGV.dup
@@ -46,3 +66,71 @@ grepper.files = ARGV.dup
 grepper.run
 formatter.format
 puts formatter.output
+
+BEGIN {
+
+def usage
+  puts <<EOM
+
+  (This documentation comes from the GNU man page for grep(1). Please
+  let me know if the Ruby version doesn't conform to what's advertised
+  here.)
+
+  -A NUM, --after-context=NUM
+  
+  Print NUM lines of trailing context after matching lines.  Places
+  a line containing -- between contiguous groups of matches.
+
+  -B NUM, --before-context=NUM
+
+  Print NUM lines of leading context before matching lines.  Places
+  a line containing -- between contiguous groups of matches.
+
+  -C NUM, --context=NUM
+
+  Print  NUM lines of output context.  Places a line containing --
+  between contiguous groups of matches.
+
+  -H, --with-filename
+
+  Print the filename for each match.
+
+  -h, --no-filename
+
+  Suppress the prefixing of filenames on output when multiple files
+  are searched.
+
+  -c, --count
+
+  Suppress  normal  output;  instead  print  a count of matching
+  lines for each input file.  With the -v, --invert-match option
+  (see below), count non-matching lines.
+
+  -L, --files-without-match
+
+  Suppress normal output; instead print the name of each input  file
+  from  which  no output  would  normally  have  been  printed. 
+  The scanning will stop on the first match.
+
+  -l, --files-with-matches
+
+  Suppress normal output; instead print the name of each input file from which
+  output would normally have been printed.  The scanning will stop on the first
+  match.
+
+  -n, --line-number
+
+  Prefix each line of output with the line number within its input
+  file.
+
+  -o, --only-matching
+
+  Show only the part of a matching line that matches PATTERN.
+
+  -v, --invert-match
+
+  Invert the sense of matching, to select non-matching lines.
+
+EOM
+  end
+}

data/lib/grepper.rb

@@ -43,7 +43,9 @@
 #
 # Available options are:
 # 
+# * <tt>o</tt> -- store only the part of the line that matched the pattern
 # * <tt>v</tt> -- negate the sense of the match
+# * <tt>w</tt> -- count only complete-word matches
 # * <tt>An</tt> -- provide n lines of after-context
 # * <tt>Bn</tt> -- provide b lines of before-context
 #
@@ -84,7 +86,7 @@
 #
 # == Version
 #
-# 0.9.2, December 24, 2008
+# 0.9.3, January 13, 2009
 #
 # == Author
 #
@@ -92,16 +94,16 @@
 #
 # == Copyright and license
 #
-# Copyright (c) 2008, Ruby Power and Light, LLC
+# Copyright (c) 2008-2009, Ruby Power and Light, LLC
 #
 # Released under the Ruby license. No warranty of any kind. Use
 # entirely at your own risk. 
 #
 
 class Grepper
-  VERSION = '0.9.2'
+  VERSION = '0.9.3'
 
-  attr_accessor :files, :pattern, :options
+  attr_accessor :files, :options, :pattern
   attr_reader :results
 
   def initialize
@@ -113,14 +115,21 @@ class Grepper
 
   private 
 
+  def massage_pattern
+    if @options.include?('w')
+      @pattern = Regexp.new(/\b#{@pattern}\b/)
+    else
+      @pattern = /#{@pattern}/
+    end
+  end
+
   def get_after_context(fh, after_count)
 
     res = []
     after_count.times do |i|
       line = fh.gets
       break unless line
-
-      if match?(line)
+      if match_for(line)
         fh.pos -= line.size
         break
       else
@@ -130,19 +139,36 @@ class Grepper
     res.empty? ? nil : res
   end
 
-  def match?(line)
-    m = line =~ @pattern
-    @negate ? !m : m
+  def match_for(line)
+    m = @pattern.match(line)
+    if m && @negate
+      return false
+    elsif @negate
+      return line
+    elsif m
+      if options.include?('o')
+        return m[0]
+      else
+        return line
+      end
+    else
+      return false
+    end
   end
   
   public
 
 # Generate the result set. 
   def run
+    massage_pattern
     @negate = true if options.include?('v')
     
     after_count = $1.to_i if options.find {|o| /A(\d+)/.match(o) }
     before_count = $1.to_i if options.find {|o| /B(\d+)/.match(o) }
+    if options.find {|o| /C(\d+)/.match(o) }
+      after_count ||= $1.to_i
+      before_count ||= $1.to_i
+    end
 
     files.each do |file|
       result = Result.new(file)
@@ -153,13 +179,13 @@ class Grepper
         while line = fh.gets
           i += 1
           
-          if match?(line)
-            match = Match.new(line)
+          if matched = match_for(line)
+            match = Match.new(matched)
             match.lineno = i
 
             if after_count
               match.after = get_after_context(fh, after_count)
-              i += match.after.to_s.scan(/\n/).size
+              i += (match.after || []).size
             end
 
             if before_count
@@ -199,11 +225,11 @@ class Grepper
     end
 
     def absolute_start
-      lineno - before.to_s.scan(/\n/).size
+      lineno - (before || []).size
     end
   
     def absolute_end
-      lineno + after.to_s.scan(/\n/).size
+      lineno + (after || []).size
     end
   end
 
@@ -236,7 +262,7 @@ class Grepper
     end
     
     def context?
-      any? {|f,matches| matches.any? {|n,b,l,a| b || a } }
+      @context = any? {|f,matches| matches.any? {|n,b,l,a| b || a } }
     end
   end
 

data/lib/grepper/formatter.rb

@@ -32,6 +32,8 @@ class Grepper
 # * <tt>l</tt> -- show matching filenames only
 # * <tt>c</tt> -- show match count only
 # * <tt>n</tt> -- show the line number of the match
+# * <tt>H</tt> -- show the name of the file of each match
+# * <tt>h</tt> -- don't show the names of any files
 # 
 # Note that Grepper objects also have options ('v', 'A1', etc.).
 # Both the Formatter options and the Grepper options are pulled
@@ -75,7 +77,7 @@ class Grepper
     end
 
     def one_or_many(string, many_string)
-      multi? ? many_string + string : string
+      (multi? &&! options.include?("h")) || options.include?("H") ? many_string + string : string
     end
     
     def context_lines(lines,file,n,position)
@@ -126,7 +128,11 @@ class Grepper
 
 # 'l' -- filenames only
         if options.include?('l')
-          str << "#{file}\n"
+          str << "#{file}\n" unless matches.empty?
+          
+# 'L' -- filenames only, for non-matching files
+        elsif options.include?('L')
+          str << "#{file}\n" if matches.empty?
 
 # 'c' -- match count only
         elsif options.include?('c')

data/test/test_formatter.rb

@@ -11,7 +11,7 @@ class FormatterTest < Test::Unit::TestCase
   end
   
   def run_with_files(grepper,*files)
-    grepper.files = *files
+    grepper.files = Array(*files)
     grepper.run
   end
   
@@ -164,11 +164,11 @@ EOM
 EOM
   end
 
-    def test_after_context_with_line_numbers
-      @g.options = ["A2"]
-      run_with_files(@g, %w{ test/input.6 })
-      f = formatter_for(@g,["n"])
-      assert_equal(<<EOM, f.output)
+  def test_after_context_with_line_numbers
+    @g.options = ["A2"]
+    run_with_files(@g, %w{ test/input.6 })
+    f = formatter_for(@g,["n"])
+    assert_equal(<<EOM, f.output)
 3:abc
 4-three
 5-four
@@ -205,6 +205,235 @@ test/input.2:3:So does this abc.
 test/input.2-4-does.
 EOM
     end
-end
 
+  def test_add_filenames_to_output_from_single_file
+    run_with_files(@g, %w{ test/input.1 })
+    f = formatter_for(@g, ["H"])
+    assert_equal(<<EOM, f.output)
+test/input.1:This matches abc.
+EOM
+  end
+
+  def test_add_filenames_to_c_switch_single_file
+    run_with_files(@g, %w{ test/input.1 })
+    f = formatter_for(@g, ["H","c"])
+    assert_equal(<<EOM, f.output)
+test/input.1:1
+EOM
+  end
+
+  def test_add_filenames_to_output_from_multi_files
+    run_with_files(@g, %w{ test/input.1 test/input.2 test/input.4 })
+    f = formatter_for(@g, ["H"])
+    assert_equal(<<EOM, f.output)
+test/input.1:This matches abc.
+test/input.2:So does this abc.
+test/input.4:this abc
+test/input.4:that abc
+EOM
+  end
+
+  def test_add_filenames_to_c_switch_multi_files
+    run_with_files(@g, %w{ test/input.1 test/input.2 test/input.4 })
+    f = formatter_for(@g, ["H","c"])
+    assert_equal(<<EOM, f.output)
+test/input.1:1
+test/input.2:1
+test/input.4:2
+EOM
+  end
+
+  def test_combine_filenames_with_context_multi_files
+    @g.options = ["A2"]
+    run_with_files(@g, %w{ test/input.1 test/input.2 test/input.4 })
+    f = formatter_for(@g, ["H"])
+    assert_equal(<<EOM, f.output)
+test/input.1:This matches abc.
+test/input.1-This doesn't.
+--
+test/input.2:So does this abc.
+test/input.2-does.
+--
+test/input.4:this abc
+test/input.4-blah one
+test/input.4-blah two
+--
+test/input.4:that abc
+test/input.4-one
+test/input.4-two
+EOM
+  end
+
+  def test_combine_filenames_with_line_numbers_single_file
+    run_with_files(@g, %w{ test/input.1 })
+    f = formatter_for(@g, ["H", "n"])
+    assert_equal(<<EOM, f.output)
+test/input.1:2:This matches abc.
+EOM
+  end
+
+  def test_combine_filenames_with_line_numbers_multi_file
+    run_with_files(@g, %w{ test/input.1 test/input.2 test/input.4 })
+    f = formatter_for(@g, ["H", "n"])
+    assert_equal(<<EOM, f.output)
+test/input.1:2:This matches abc.
+test/input.2:3:So does this abc.
+test/input.4:1:this abc
+test/input.4:5:that abc
+EOM
+  end
+
+  def test_combine_filenames_with_line_numbers_and_context_multi_file
+    @g.options = ["A2"]
+    run_with_files(@g, %w{ test/input.1 test/input.2 test/input.4 })
+    f = formatter_for(@g, ["H", "n"])
+    assert_equal(<<EOM, f.output)
+test/input.1:2:This matches abc.
+test/input.1-3-This doesn't.
+--
+test/input.2:3:So does this abc.
+test/input.2-4-does.
+--
+test/input.4:1:this abc
+test/input.4-2-blah one
+test/input.4-3-blah two
+--
+test/input.4:5:that abc
+test/input.4-6-one
+test/input.4-7-two
+EOM
+  end
+
+  def test_suppress_filenames_multi_files
+    run_with_files(@g, %w{ test/input.1 test/input.2 test/input.4 })
+    f = formatter_for(@g, ["h"])
+    assert_equal(<<EOM, f.output)
+This matches abc.
+So does this abc.
+this abc
+that abc
+EOM
+  end
+
+  def test_suppress_filenames_with_line_numbers_multi_files
+    run_with_files(@g, %w{ test/input.1 test/input.2 test/input.4 })
+    f = formatter_for(@g, ["h", "n"])
+    assert_equal(<<EOM, f.output)
+2:This matches abc.
+3:So does this abc.
+1:this abc
+5:that abc
+EOM
+  end
+
+  def test_suppress_filenames_with_context_multi_files
+    @g.options = ["A2"]
+    run_with_files(@g, %w{ test/input.1 test/input.2 test/input.4 })
+    f = formatter_for(@g, ["h"])
+    assert_equal(<<EOM, f.output)
+This matches abc.
+This doesn't.
+--
+So does this abc.
+does.
+--
+this abc
+blah one
+blah two
+--
+that abc
+one
+two
+EOM
+  end
+
+  def test_double_context_C_switch_single_file
+    @g.options = ["C2"]
+    run_with_files(@g, %w{ test/input.4 })
+    f = formatter_for(@g)
+    assert_equal(<<EOM, f.output)
+this abc
+blah one
+blah two
+blah three
+that abc
+one
+two
+EOM
+  end
+
+  def test_double_context_C_switch_multi_files
+    @g.options = ["C2"]
+    run_with_files(@g, %w{ test/input.1 test/input.4 })
+    f = formatter_for(@g)
+    assert_equal(<<EOM, f.output)
+test/input.1-This is a file
+test/input.1:This matches abc.
+test/input.1-This doesn't.
+--
+test/input.4:this abc
+test/input.4-blah one
+test/input.4-blah two
+test/input.4-blah three
+test/input.4:that abc
+test/input.4-one
+test/input.4-two
+EOM
+  end
+
+  def test_double_context_loses_to_specific_A_or_b
+    @g.options = ["A1", "C2"]
+    run_with_files(@g, %w{ test/input.1 test/input.4 })
+    f = formatter_for(@g)
+    assert_equal(<<EOM, f.output)
+test/input.1-This is a file
+test/input.1:This matches abc.
+test/input.1-This doesn't.
+--
+test/input.4:this abc
+test/input.4-blah one
+test/input.4-blah two
+test/input.4-blah three
+test/input.4:that abc
+test/input.4-one
+EOM
+  end
+
+  def test_lots_of_switches_together
+    @g.options = ["A1", "B2"]
+    run_with_files(@g, %w{ test/input.1 test/input.4 })
+    f = formatter_for(@g, ["h", "n"])
+    assert_equal(<<EOM, f.output)
+1-This is a file
+2:This matches abc.
+3-This doesn't.
+--
+1:this abc
+2-blah one
+3-blah two
+4-blah three
+5:that abc
+6-one
+EOM
+  end
 
+    def test_listing_matching_files_where_some_dont_match
+      @g.pattern = "This"
+      run_with_files(@g, %w{ test/input.1 test/input.2 test/input.4 test/input.6 })
+      f = formatter_for(@g, ["l"])
+      assert_equal(<<EOM, f.output)
+test/input.1
+test/input.2
+EOM
+    end
+  
+  def test_listing_non_matching_files
+    @g.pattern = "This"
+    run_with_files(@g, %w{ test/input.1 test/input.2 test/input.4 test/input.6 })
+    f = formatter_for(@g, ["L"])
+    assert_equal(<<EOM, f.output)
+test/input.4
+test/input.6
+EOM
+  end
+end

data/test/test_grepper.rb

@@ -84,7 +84,7 @@ EOM
   end
   
   def test_overlapping_context_from_one_file
-    @g.options = "A4"
+    @g.options = ["A4"]
     @g.files = ["test/input.4"]
     @g.run
     assert_equal(1, @g.results.size)
@@ -104,7 +104,7 @@ EOM
   
   def test_before_buffer
     @g.files = ["test/input.4"]
-    @g.options = "B2"
+    @g.options = ["B2"]
     @g.run
     r = @g.results[0]
     assert_equal(1, @g.results.size)
@@ -145,4 +145,28 @@ EOM
     test_basic_lines_from_multiple_files
     assert_equal(3, @g.results[1].matches[0].lineno)
   end
+
+  def test_match_only_on_word_boundaries_fail
+    @g.pattern = "bc"
+    @g.files = ["test/input.4"]
+    @g.options = ["w"]
+    @g.run
+    assert_equal(0, @g.results[0].matches.size)
+  end
+
+  def test_match_only_on_word_boundaries_succeed
+    @g.options = ["w"]
+    @g.pattern = "abc"
+    @g.files = ["test/input.4"]
+    @g.run
+    assert_equal(2, @g.results[0].matches.size)
+  end
+  
+  def test_return_only_the_part_matched
+    @g.options = ["o"]
+    @g.pattern = "abc"
+    @g.files = ["test/input.4"]
+    @g.run
+    assert_equal("abc", @g.results[0].matches[0].line)
+  end
 end

data/test/test_match.rb

@@ -23,7 +23,7 @@ class Grepper::MatchTest < Test::Unit::TestCase
   end
   
   def test_before_context
-    @g.options = "B2"
+    @g.options = ["B2"]
     @g.run
     matches = @g.results[0].matches
     assert_match_stats(matches[0], 3,1,3)
@@ -32,7 +32,7 @@ class Grepper::MatchTest < Test::Unit::TestCase
   end
 
   def test_after_context
-    @g.options = "A2"
+    @g.options = ["A2"]
     @g.run
     matches = @g.results[0].matches
     assert_match_stats(matches[0], 3,3,5)
@@ -41,7 +41,7 @@ class Grepper::MatchTest < Test::Unit::TestCase
   end
   
   def test_both_contexts
-    @g.options = "A1B1"
+    @g.options = ["A1", "B1"]
     @g.run
     matches = @g.results[0].matches
     assert_match_stats(matches[0], 3,2,4)
@@ -51,4 +51,4 @@ class Grepper::MatchTest < Test::Unit::TestCase
     
 end
   
-  
+  

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: grepper
 version: !ruby/object:Gem::Version 
-  version: 0.9.2
+  version: 0.9.3
 platform: ruby
 authors: 
 - David A. Black
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2008-12-24 00:00:00 -05:00
+date: 2009-01-13 00:00:00 -05:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -38,6 +38,7 @@ files:
 - Manifest.txt
 - README.txt
 - Rakefile
+- TODO
 - bin/grep.rb
 - lib/grepper.rb
 - lib/grepper/formatter.rb