amatch 0.2.4 → 0.2.5

data/CHANGES

@@ -1,3 +1,6 @@
+2009-09-23 (0.2.5)
+    * Added lib to gem's require_paths.
+    * Using rake-compiler now.
 2009-08-25 (0.2.4)
     * Included Jaro and Jaro-Winkler metrics implementation of Kevin Ballard
       <kevin@rapleaf.com>. Thanks a lot.

data/README

@@ -1,25 +1,130 @@
-Installation
-============
+== amatch - Approximate Matching Extension for Ruby
+
+=== Description
+
+This is a collection of classes that can be used for Approximate
+matching, searching, and comparing of Strings. They implement algorithms
+that compute the Levenshtein edit distance, Sellers edit distance, the
+Hamming distance, the longest common subsequence length, the longest common
+substring length, the pair distance metric, the Jaro-Winkler metric.
+
+=== Download
+
+The latest version of <b>amatch</b> can be found at
+
+* http://rubyforge.org/frs/?group_id=390
+
+Online Documentation should be located at
+
+* http://amatch.rubyforge.org
+
+=== Installation
 
 Just type into the command line as root:
 
-# ruby install.rb
+ # ruby install.rb
 
 If you have installed rake (rake.rubyforge.org), you can also type:
 
-# rake install
+ # rake install
 
 To install this extension as a gem type
 
-# gem install amatch
+ # gem install amatch
+
+=== Examples
+ require 'amatch'
+ # => true
+ include Amatch
+ # => Object
+ 
+ m = Sellers.new("pattern")
+ # => #<Amatch::Sellers:0x40366324>
+ m.match("pattren")
+ # => 2.0
+ m.substitution = m.insertion = 3
+ # => 3
+ m.match("pattren")
+ # => 4.0
+ m.reset_weights
+ # => #<Amatch::Sellers:0x40366324>
+ m.match(["pattren","parent"])
+ # => [2.0, 4.0]
+ m.search("abcpattrendef")
+ # => 2.0
+ 
+ m = Levenshtein.new("pattern")
+ # => #<Amatch::Levenshtein:0x4035919c>
+ m.match("pattren")
+ # => 2
+ m.search("abcpattrendef")
+ # => 2
+ "pattern language".levenshtein_similar("language of patterns")
+ # => 0.2
+ 
+ m = Hamming.new("pattern")
+ # => #<Amatch::Hamming:0x40350858>
+ m.match("pattren")
+ # => 2
+ "pattern language".hamming_similar("language of patterns")
+ # => 0.1
+ 
+ m = PairDistance.new("pattern")
+ # => #<Amatch::PairDistance:0x40349be8>
+ m.match("pattr en")
+ # => 0.545454545454545
+ m.match("pattr en", nil)
+ # => 0.461538461538462
+ m.match("pattr en", /t+/)
+ # => 0.285714285714286
+ "pattern language".pair_distance_similar("language of patterns")
+ # => 0.928571428571429
+ 
+ m = LongestSubsequence.new("pattern")
+ # => #<Amatch::LongestSubsequence:0x4033e900>
+ m.match("pattren")
+ # => 6
+ "pattern language".longest_subsequence_similar("language of patterns")
+ # => 0.4
+ 
+ m = LongestSubstring.new("pattern")
+ # => #<Amatch::LongestSubstring:0x403378d0>
+ m.match("pattren")
+ # => 4
+ "pattern language".longest_substring_similar("language of patterns")
+ # => 0.4
+
+ m = Jaro.new("pattern")
+ # => #<Amatch::Jaro:0x363b70>
+ m.match("paTTren")
+ # => 0.952380952380952
+ m.ignore_case = false
+ m.match("paTTren")
+ # => 0.742857142857143
+ "pattern language".jaro_similar("language of patterns")
+ # => 0.672222222222222
+
+ m = JaroWinkler.new("pattern")
+ # #<Amatch::JaroWinkler:0x3530b8>
+ m.match("paTTren")
+ # => 0.971428571712403
+ m.ignore_case = false
+ m.match("paTTren")
+ # => 0.79428571505206
+ m.scaling_factor = 0.05
+ m.match("pattren")
+ # => 0.961904762046678
+ "pattern language".jarowinkler_similar("language of patterns")
+ # => 0.672222222222222
+
+=== Author
 
-Author
-======
+Florian Frank mailto:flori@ping.de
 
-Florian Frank <flori@ping.de>
+=== License
 
-License
-=======
+This is free software; you can redistribute it and/or modify it under
+the terms of the GNU General Public License Version 2 as published by
+the Free Software Foundation: http://www.gnu.org/copyleft/gpl.html
 
-GNU General Public License, Version 2 (GPLv2)
 

data/Rakefile

@@ -2,10 +2,13 @@
 
 begin
   require 'rake/gempackagetask'
+  require 'rake/extensiontask'
 rescue LoadError
 end
+
 require 'rbconfig'
 include Config
+
 require 'rake/clean'
 CLEAN.include 'coverage', 'doc'
 require 'rake/testtask'
@@ -13,10 +16,8 @@ require 'rake/testtask'
 MAKE        = ENV['MAKE'] || %w[gmake make].find { |c| system(c, '-v') }
 PKG_NAME    = 'amatch'
 PKG_VERSION = File.read('VERSION').chomp
-PKG_FILES   = FileList["**/*"].exclude(/^(pkg|coverage|doc)/)
-PKG_DOC_FILES = [ "ext/amatch.c" ].concat(Dir['lib/**/*.rb']) << 'doc-main.txt'
-
-task :default => :test
+PKG_FILES   = FileList["**/*"].exclude(/^(pkg|coverage|doc|tmp)/)
+PKG_DOC_FILES = [ "ext/amatch.c" ].concat(Dir['lib/**/*.rb']) << 'README'
 
 desc "Run unit tests"
 task :test => :compile_ext do
@@ -49,45 +50,66 @@ end
 
 desc "Build the documentation"
 task :doc do
-  sh "rdoc -m doc-main.txt -t '#{PKG_NAME} - Approximate Matching' #{PKG_DOC_FILES * ' '}"
+  sh "rdoc -m README -t '#{PKG_NAME} - Approximate Matching' #{PKG_DOC_FILES * ' '}"
 end
 
-if defined? Gem
-  spec = Gem::Specification.new do |s|
-    s.name = 'amatch'
-    s.version = PKG_VERSION
-    s.summary = "Approximate String Matching library"
-    s.description = <<EOF
+if defined?(Gem) and defined?(Rake::GemPackageTask) and
+  defined?(Rake::ExtensionTask)
+then
+  spec_src = <<-GEM
+    Gem::Specification.new do |s|
+      s.name = '#{PKG_NAME}'
+      s.version = '#{PKG_VERSION}'
+      s.summary = "Approximate String Matching library"
+      s.description = <<EOF
 Amatch is a library for approximate string matching and searching in strings.
 Several algorithms can be used to do this, and it's also possible to compute a
 similarity metric number between 0.0 and 1.0 for two given strings.
 EOF
 
-    s.files = PKG_FILES
+      s.files = #{PKG_FILES.sort.inspect}
+
+      s.extensions << "ext/extconf.rb"
 
-    s.extensions << "ext/extconf.rb"
+      s.require_paths << 'ext' << 'lib'
 
-    s.require_path = 'ext'
+      s.bindir = "bin"
+      s.executables = ["agrep.rb"]
+      s.default_executable = "agrep.rb"
 
-    s.bindir = "bin"
-    s.executables = ["agrep.rb"]
-    s.default_executable = "agrep.rb"
+      s.has_rdoc = true
+      s.extra_rdoc_files.concat #{PKG_DOC_FILES.sort.inspect}
+      s.rdoc_options << '--main' << 'README' <<
+        '--title' << "#{PKG_NAME} - Approximate Matching"
+      s.test_files.concat Dir['tests/test_*.rb']
 
-    s.has_rdoc = true
-    s.extra_rdoc_files.concat PKG_DOC_FILES
-    s.rdoc_options << '--main' << 'doc-main.txt' <<
-      '--title' << "#{PKG_NAME} - Approximate Matching"
-    s.test_files.concat Dir['tests/test_*.rb']
+      s.author = "Florian Frank"
+      s.email = "flori@ping.de"
+      s.homepage = "http://amatch.rubyforge.org"
+      s.rubyforge_project = '#{PKG_NAME}'
+    end
+  GEM
 
-    s.author = "Florian Frank"
-    s.email = "flori@ping.de"
-    s.homepage = "http://amatch.rubyforge.org"
-    s.rubyforge_project = "amatch"
+  desc 'Create a gemspec file'
+  task :gemspec do
+    File.open("#{PKG_NAME}.gemspec", 'w') do |f|
+      f.puts spec_src
+    end
   end
 
+  spec = eval(spec_src)
   Rake::GemPackageTask.new(spec) do |pkg|
     pkg.need_tar      = true
-    pkg.package_files += PKG_FILES
+    pkg.package_files = PKG_FILES
+  end
+
+  Rake::ExtensionTask.new do |ext|
+    ext.name            = PKG_NAME
+    ext.gem_spec        = spec
+    ext.cross_compile   = true
+    ext.cross_platform  = 'i386-mswin32'
+    ext.ext_dir         = 'ext'
+    ext.lib_dir         = 'lib'
   end
 end
 
@@ -109,5 +131,11 @@ EOT
 end
 
 
-desc "Prepare a new release"
-task :release => [ :clean, :version, :package ]
+desc "Default task"
+task :default => [ :version, :gemspec, :test ]
+
+desc "Build all gems and archives for a new release."
+task :release => [ :clean, :version, :gemspec, :cross, :native, :gem ] do
+  system "#$0 clean native gem"
+  system "#$0 clean package"
+end

data/VERSION

@@ -1 +1 @@
-0.2.4
+0.2.5

data/amatch.gemspec

@@ -0,0 +1,31 @@
+    Gem::Specification.new do |s|
+      s.name = 'amatch'
+      s.version = '0.2.5'
+      s.summary = "Approximate String Matching library"
+      s.description = <<EOF
+Amatch is a library for approximate string matching and searching in strings.
+Several algorithms can be used to do this, and it's also possible to compute a
+similarity metric number between 0.0 and 1.0 for two given strings.
+EOF
+
+      s.files = ["CHANGES", "COPYING", "README", "Rakefile", "VERSION", "amatch.gemspec", "bin", "bin/agrep.rb", "ext", "ext/amatch.c", "ext/common.h", "ext/extconf.rb", "ext/pair.c", "ext/pair.h", "install.rb", "lib", "lib/amatch", "lib/amatch/version.rb", "tests", "tests/test_hamming.rb", "tests/test_jaro.rb", "tests/test_jaro_winkler.rb", "tests/test_levenshtein.rb", "tests/test_longest_subsequence.rb", "tests/test_longest_substring.rb", "tests/test_pair_distance.rb", "tests/test_sellers.rb"]
+
+      s.extensions << "ext/extconf.rb"
+
+      s.require_paths << 'ext' << 'lib'
+
+      s.bindir = "bin"
+      s.executables = ["agrep.rb"]
+      s.default_executable = "agrep.rb"
+
+      s.has_rdoc = true
+      s.extra_rdoc_files.concat ["README", "ext/amatch.c", "lib/amatch/version.rb"]
+      s.rdoc_options << '--main' << 'README' <<
+        '--title' << "amatch - Approximate Matching"
+      s.test_files.concat Dir['tests/test_*.rb']
+
+      s.author = "Florian Frank"
+      s.email = "flori@ping.de"
+      s.homepage = "http://amatch.rubyforge.org"
+      s.rubyforge_project = 'amatch'
+    end

data/lib/amatch/version.rb

@@ -1,6 +1,6 @@
 module Amatch
   # Amatch version
-  VERSION         = '0.2.4'
+  VERSION         = '0.2.5'
   VERSION_ARRAY   = VERSION.split(/\./).map { |x| x.to_i } # :nodoc:
   VERSION_MAJOR   = VERSION_ARRAY[0] # :nodoc:
   VERSION_MINOR   = VERSION_ARRAY[1] # :nodoc:

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: amatch
 version: !ruby/object:Gem::Version 
-  version: 0.2.4
+  version: 0.2.5
 platform: ruby
 authors: 
 - Florian Frank
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2009-08-26 00:00:00 +02:00
+date: 2009-09-25 00:00:00 +02:00
 default_executable: agrep.rb
 dependencies: []
 
@@ -24,32 +24,33 @@ executables:
 extensions: 
 - ext/extconf.rb
 extra_rdoc_files: 
+- README
 - ext/amatch.c
 - lib/amatch/version.rb
-- doc-main.txt
 files: 
 - CHANGES
-- bin/agrep.rb
-- VERSION
+- COPYING
 - README
+- Rakefile
+- VERSION
+- amatch.gemspec
+- bin/agrep.rb
+- ext/amatch.c
 - ext/common.h
 - ext/extconf.rb
-- ext/amatch.c
-- ext/pair.h
 - ext/pair.c
-- Rakefile
+- ext/pair.h
+- install.rb
+- lib/amatch.so
 - lib/amatch/version.rb
-- tests/test_longest_substring.rb
 - tests/test_hamming.rb
+- tests/test_jaro.rb
+- tests/test_jaro_winkler.rb
+- tests/test_levenshtein.rb
 - tests/test_longest_subsequence.rb
+- tests/test_longest_substring.rb
 - tests/test_pair_distance.rb
-- tests/test_levenshtein.rb
-- tests/test_jaro.rb
 - tests/test_sellers.rb
-- tests/test_jaro_winkler.rb
-- COPYING
-- install.rb
-- doc-main.txt
 has_rdoc: true
 homepage: http://amatch.rubyforge.org
 licenses: []
@@ -57,11 +58,13 @@ licenses: []
 post_install_message: 
 rdoc_options: 
 - --main
-- doc-main.txt
+- README
 - --title
 - amatch - Approximate Matching
 require_paths: 
+- lib
 - ext
+- lib
 required_ruby_version: !ruby/object:Gem::Requirement 
   requirements: 
   - - ">="

data/doc-main.txt

@@ -1,115 +0,0 @@
-== amatch - Approximate Matching Extension for Ruby
-
-=== Description
-
-This is a collection of classes that can be used for Approximate
-matching, searching, and comparing of Strings. They implement algorithms
-that compute the Levenshtein edit distance, Sellers edit distance, the
-Hamming distance, the longest common subsequence length, the longest common
-substring length, the pair distance metric, the Jaro-Winkler metric.
-
-=== Author
-
-Florian Frank mailto:flori@ping.de
-
-=== License
-
-This is free software; you can redistribute it and/or modify it under
-the terms of the GNU General Public License Version 2 as published by
-the Free Software Foundation: http://www.gnu.org/copyleft/gpl.html
-
-=== Download
-
-The latest version of <b>amatch</b> can be found at
-
-* http://rubyforge.org/frs/?group_id=390
-
-Online Documentation should be located at
-
-* http://amatch.rubyforge.org
-
-=== Examples
- require 'amatch'
- # => true
- include Amatch
- # => Object
- 
- m = Sellers.new("pattern")
- # => #<Amatch::Sellers:0x40366324>
- m.match("pattren")
- # => 2.0
- m.substitution = m.insertion = 3
- # => 3
- m.match("pattren")
- # => 4.0
- m.reset_weights
- # => #<Amatch::Sellers:0x40366324>
- m.match(["pattren","parent"])
- # => [2.0, 4.0]
- m.search("abcpattrendef")
- # => 2.0
- 
- m = Levenshtein.new("pattern")
- # => #<Amatch::Levenshtein:0x4035919c>
- m.match("pattren")
- # => 2
- m.search("abcpattrendef")
- # => 2
- "pattern language".levenshtein_similar("language of patterns")
- # => 0.2
- 
- m = Hamming.new("pattern")
- # => #<Amatch::Hamming:0x40350858>
- m.match("pattren")
- # => 2
- "pattern language".hamming_similar("language of patterns")
- # => 0.1
- 
- m = PairDistance.new("pattern")
- # => #<Amatch::PairDistance:0x40349be8>
- m.match("pattr en")
- # => 0.545454545454545
- m.match("pattr en", nil)
- # => 0.461538461538462
- m.match("pattr en", /t+/)
- # => 0.285714285714286
- "pattern language".pair_distance_similar("language of patterns")
- # => 0.928571428571429
- 
- m = LongestSubsequence.new("pattern")
- # => #<Amatch::LongestSubsequence:0x4033e900>
- m.match("pattren")
- # => 6
- "pattern language".longest_subsequence_similar("language of patterns")
- # => 0.4
- 
- m = LongestSubstring.new("pattern")
- # => #<Amatch::LongestSubstring:0x403378d0>
- m.match("pattren")
- # => 4
- "pattern language".longest_substring_similar("language of patterns")
- # => 0.4
-
- m = Jaro.new("pattern")
- # => #<Amatch::Jaro:0x363b70>
- m.match("paTTren")
- # => 0.952380952380952
- m.ignore_case = false
- m.match("paTTren")
- # => 0.742857142857143
- "pattern language".jaro_similar("language of patterns")
- # => 0.672222222222222
-
- m = JaroWinkler.new("pattern")
- # #<Amatch::JaroWinkler:0x3530b8>
- m.match("paTTren")
- # => 0.971428571712403
- m.ignore_case = false
- m.match("paTTren")
- # => 0.79428571505206
- m.scaling_factor = 0.05
- m.match("pattren")
- # => 0.961904762046678
- "pattern language".jarowinkler_similar("language of patterns")
- # => 0.672222222222222
-