amatch 0.2.5 → 0.2.6
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +3 -0
- data/CHANGES +3 -0
- data/Gemfile +5 -0
- data/{README → README.rdoc} +7 -9
- data/Rakefile +25 -133
- data/VERSION +1 -1
- data/amatch.gemspec +33 -26
- data/ext/amatch.c +4 -1
- data/lib/amatch/.keep +0 -0
- data/lib/amatch/version.rb +1 -1
- metadata +66 -26
- data/lib/amatch.so +0 -0
data/.gitignore
ADDED
data/CHANGES
CHANGED
data/Gemfile
ADDED
data/{README → README.rdoc}
RENAMED
@@ -1,6 +1,6 @@
|
|
1
|
-
|
1
|
+
= amatch - Approximate Matching Extension for Ruby
|
2
2
|
|
3
|
-
|
3
|
+
== Description
|
4
4
|
|
5
5
|
This is a collection of classes that can be used for Approximate
|
6
6
|
matching, searching, and comparing of Strings. They implement algorithms
|
@@ -8,7 +8,7 @@ that compute the Levenshtein edit distance, Sellers edit distance, the
|
|
8
8
|
Hamming distance, the longest common subsequence length, the longest common
|
9
9
|
substring length, the pair distance metric, the Jaro-Winkler metric.
|
10
10
|
|
11
|
-
|
11
|
+
== Download
|
12
12
|
|
13
13
|
The latest version of <b>amatch</b> can be found at
|
14
14
|
|
@@ -18,7 +18,7 @@ Online Documentation should be located at
|
|
18
18
|
|
19
19
|
* http://amatch.rubyforge.org
|
20
20
|
|
21
|
-
|
21
|
+
== Installation
|
22
22
|
|
23
23
|
Just type into the command line as root:
|
24
24
|
|
@@ -32,7 +32,7 @@ To install this extension as a gem type
|
|
32
32
|
|
33
33
|
# gem install amatch
|
34
34
|
|
35
|
-
|
35
|
+
== Examples
|
36
36
|
require 'amatch'
|
37
37
|
# => true
|
38
38
|
include Amatch
|
@@ -117,14 +117,12 @@ To install this extension as a gem type
|
|
117
117
|
"pattern language".jarowinkler_similar("language of patterns")
|
118
118
|
# => 0.672222222222222
|
119
119
|
|
120
|
-
|
120
|
+
== Author
|
121
121
|
|
122
122
|
Florian Frank mailto:flori@ping.de
|
123
123
|
|
124
|
-
|
124
|
+
== License
|
125
125
|
|
126
126
|
This is free software; you can redistribute it and/or modify it under
|
127
127
|
the terms of the GNU General Public License Version 2 as published by
|
128
128
|
the Free Software Foundation: http://www.gnu.org/copyleft/gpl.html
|
129
|
-
|
130
|
-
|
data/Rakefile
CHANGED
@@ -1,141 +1,33 @@
|
|
1
1
|
# vim: set filetype=ruby et sw=2 ts=2:
|
2
2
|
|
3
|
-
|
4
|
-
|
5
|
-
|
6
|
-
|
7
|
-
|
8
|
-
|
9
|
-
|
10
|
-
|
11
|
-
|
12
|
-
require 'rake/clean'
|
13
|
-
CLEAN.include 'coverage', 'doc'
|
14
|
-
require 'rake/testtask'
|
15
|
-
|
16
|
-
MAKE = ENV['MAKE'] || %w[gmake make].find { |c| system(c, '-v') }
|
17
|
-
PKG_NAME = 'amatch'
|
18
|
-
PKG_VERSION = File.read('VERSION').chomp
|
19
|
-
PKG_FILES = FileList["**/*"].exclude(/^(pkg|coverage|doc|tmp)/)
|
20
|
-
PKG_DOC_FILES = [ "ext/amatch.c" ].concat(Dir['lib/**/*.rb']) << 'README'
|
21
|
-
|
22
|
-
desc "Run unit tests"
|
23
|
-
task :test => :compile_ext do
|
24
|
-
sh %{testrb -Iext:lib tests/test_*.rb}
|
25
|
-
end
|
26
|
-
|
27
|
-
desc "Compiling library"
|
28
|
-
task :compile_ext do
|
29
|
-
cd 'ext' do
|
30
|
-
ruby %{extconf.rb}
|
31
|
-
sh MAKE
|
32
|
-
end
|
33
|
-
end
|
34
|
-
|
35
|
-
desc "Installing library"
|
36
|
-
task :install => :test do
|
37
|
-
src, = Dir['ext/amatch.*'].reject { |x| /\.[co]$/.match x }
|
38
|
-
filename = File.basename(src)
|
39
|
-
dst = File.join(CONFIG["sitelibdir"], filename)
|
40
|
-
install(src, dst, :verbose => true)
|
41
|
-
end
|
42
|
-
|
43
|
-
desc "Removing generated files"
|
44
|
-
task :clean do
|
45
|
-
cd 'ext' do
|
46
|
-
ruby 'extconf.rb'
|
47
|
-
sh "#{MAKE} distclean" if File.exist?('Makefile')
|
48
|
-
end
|
49
|
-
end
|
50
|
-
|
51
|
-
desc "Build the documentation"
|
52
|
-
task :doc do
|
53
|
-
sh "rdoc -m README -t '#{PKG_NAME} - Approximate Matching' #{PKG_DOC_FILES * ' '}"
|
54
|
-
end
|
55
|
-
|
56
|
-
if defined?(Gem) and defined?(Rake::GemPackageTask) and
|
57
|
-
defined?(Rake::ExtensionTask)
|
58
|
-
then
|
59
|
-
spec_src = <<-GEM
|
60
|
-
Gem::Specification.new do |s|
|
61
|
-
s.name = '#{PKG_NAME}'
|
62
|
-
s.version = '#{PKG_VERSION}'
|
63
|
-
s.summary = "Approximate String Matching library"
|
64
|
-
s.description = <<EOF
|
3
|
+
require 'gem_hadar'
|
4
|
+
|
5
|
+
GemHadar do
|
6
|
+
name 'amatch'
|
7
|
+
author 'Florian Frank'
|
8
|
+
email 'flori@ping.de'
|
9
|
+
homepage "http://github.com/flori/#{name}"
|
10
|
+
summary 'Approximate String Matching library'
|
11
|
+
description <<EOT
|
65
12
|
Amatch is a library for approximate string matching and searching in strings.
|
66
13
|
Several algorithms can be used to do this, and it's also possible to compute a
|
67
14
|
similarity metric number between 0.0 and 1.0 for two given strings.
|
68
|
-
EOF
|
69
|
-
|
70
|
-
s.files = #{PKG_FILES.sort.inspect}
|
71
|
-
|
72
|
-
s.extensions << "ext/extconf.rb"
|
73
|
-
|
74
|
-
s.require_paths << 'ext' << 'lib'
|
75
|
-
|
76
|
-
s.bindir = "bin"
|
77
|
-
s.executables = ["agrep.rb"]
|
78
|
-
s.default_executable = "agrep.rb"
|
79
|
-
|
80
|
-
s.has_rdoc = true
|
81
|
-
s.extra_rdoc_files.concat #{PKG_DOC_FILES.sort.inspect}
|
82
|
-
s.rdoc_options << '--main' << 'README' <<
|
83
|
-
'--title' << "#{PKG_NAME} - Approximate Matching"
|
84
|
-
s.test_files.concat Dir['tests/test_*.rb']
|
85
|
-
|
86
|
-
s.author = "Florian Frank"
|
87
|
-
s.email = "flori@ping.de"
|
88
|
-
s.homepage = "http://amatch.rubyforge.org"
|
89
|
-
s.rubyforge_project = '#{PKG_NAME}'
|
90
|
-
end
|
91
|
-
GEM
|
92
|
-
|
93
|
-
desc 'Create a gemspec file'
|
94
|
-
task :gemspec do
|
95
|
-
File.open("#{PKG_NAME}.gemspec", 'w') do |f|
|
96
|
-
f.puts spec_src
|
97
|
-
end
|
98
|
-
end
|
99
|
-
|
100
|
-
spec = eval(spec_src)
|
101
|
-
Rake::GemPackageTask.new(spec) do |pkg|
|
102
|
-
pkg.need_tar = true
|
103
|
-
pkg.package_files = PKG_FILES
|
104
|
-
end
|
105
|
-
|
106
|
-
Rake::ExtensionTask.new do |ext|
|
107
|
-
ext.name = PKG_NAME
|
108
|
-
ext.gem_spec = spec
|
109
|
-
ext.cross_compile = true
|
110
|
-
ext.cross_platform = 'i386-mswin32'
|
111
|
-
ext.ext_dir = 'ext'
|
112
|
-
ext.lib_dir = 'lib'
|
113
|
-
end
|
114
|
-
end
|
115
|
-
|
116
|
-
desc m = "Writing version information for #{PKG_VERSION}"
|
117
|
-
task :version do
|
118
|
-
puts m
|
119
|
-
File.open(File.join('lib', 'amatch', 'version.rb'), 'w') do |v|
|
120
|
-
v.puts <<EOT
|
121
|
-
module Amatch
|
122
|
-
# Amatch version
|
123
|
-
VERSION = '#{PKG_VERSION}'
|
124
|
-
VERSION_ARRAY = VERSION.split(/\\./).map { |x| x.to_i } # :nodoc:
|
125
|
-
VERSION_MAJOR = VERSION_ARRAY[0] # :nodoc:
|
126
|
-
VERSION_MINOR = VERSION_ARRAY[1] # :nodoc:
|
127
|
-
VERSION_BUILD = VERSION_ARRAY[2] # :nodoc:
|
128
|
-
end
|
129
15
|
EOT
|
16
|
+
description 'Library to tail files in Ruby'
|
17
|
+
executables << 'agrep.rb'
|
18
|
+
bindir 'bin'
|
19
|
+
test_dir 'tests'
|
20
|
+
ignore '.*.sw[pon]', 'pkg', 'Gemfile.lock'
|
21
|
+
title "#{name.camelize} - Approximate Matching"
|
22
|
+
readme 'README.rdoc'
|
23
|
+
require_paths %w[lib ext]
|
24
|
+
dependency 'spruz', '~>0.2'
|
25
|
+
|
26
|
+
install_library do
|
27
|
+
libdir = CONFIG["sitelibdir"]
|
28
|
+
src, = Dir['ext/amatch.*'].reject { |x| x =~ /\.[co]$/ }
|
29
|
+
install(src, File.join(libdir, File.basename(src)), :verbose => true)
|
30
|
+
mkdir_p dst = File.join(libdir, 'amatch')
|
31
|
+
install('lib/amatch/version.rb', File.join(dst, 'version.rb'), :verbose => true)
|
130
32
|
end
|
131
33
|
end
|
132
|
-
|
133
|
-
|
134
|
-
desc "Default task"
|
135
|
-
task :default => [ :version, :gemspec, :test ]
|
136
|
-
|
137
|
-
desc "Build all gems and archives for a new release."
|
138
|
-
task :release => [ :clean, :version, :gemspec, :cross, :native, :gem ] do
|
139
|
-
system "#$0 clean native gem"
|
140
|
-
system "#$0 clean package"
|
141
|
-
end
|
data/VERSION
CHANGED
@@ -1 +1 @@
|
|
1
|
-
0.2.
|
1
|
+
0.2.6
|
data/amatch.gemspec
CHANGED
@@ -1,31 +1,38 @@
|
|
1
|
-
|
2
|
-
s.name = 'amatch'
|
3
|
-
s.version = '0.2.5'
|
4
|
-
s.summary = "Approximate String Matching library"
|
5
|
-
s.description = <<EOF
|
6
|
-
Amatch is a library for approximate string matching and searching in strings.
|
7
|
-
Several algorithms can be used to do this, and it's also possible to compute a
|
8
|
-
similarity metric number between 0.0 and 1.0 for two given strings.
|
9
|
-
EOF
|
1
|
+
# -*- encoding: utf-8 -*-
|
10
2
|
|
11
|
-
|
3
|
+
Gem::Specification.new do |s|
|
4
|
+
s.name = %q{amatch}
|
5
|
+
s.version = "0.2.6"
|
12
6
|
|
13
|
-
|
7
|
+
s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
|
8
|
+
s.authors = ["Florian Frank"]
|
9
|
+
s.date = %q{2011-07-16}
|
10
|
+
s.default_executable = %q{agrep.rb}
|
11
|
+
s.description = %q{Library to tail files in Ruby}
|
12
|
+
s.email = %q{flori@ping.de}
|
13
|
+
s.executables = ["agrep.rb"]
|
14
|
+
s.extensions = ["ext/extconf.rb"]
|
15
|
+
s.extra_rdoc_files = ["README.rdoc", "lib/amatch/version.rb", "ext/amatch.c", "ext/pair.c"]
|
16
|
+
s.files = [".gitignore", "CHANGES", "COPYING", "Gemfile", "README.rdoc", "Rakefile", "VERSION", "amatch.gemspec", "bin/agrep.rb", "ext/amatch.c", "ext/common.h", "ext/extconf.rb", "ext/pair.c", "ext/pair.h", "install.rb", "lib/amatch/.keep", "lib/amatch/version.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_sellers.rb"]
|
17
|
+
s.homepage = %q{http://github.com/flori/amatch}
|
18
|
+
s.rdoc_options = ["--title", "Amatch - Approximate Matching", "--main", "README.rdoc"]
|
19
|
+
s.require_paths = ["lib", "ext"]
|
20
|
+
s.rubygems_version = %q{1.6.2}
|
21
|
+
s.summary = %q{Approximate String Matching library}
|
22
|
+
s.test_files = ["tests/test_sellers.rb", "tests/test_jaro.rb", "tests/test_longest_subsequence.rb", "tests/test_longest_substring.rb", "tests/test_hamming.rb", "tests/test_pair_distance.rb", "tests/test_levenshtein.rb", "tests/test_jaro_winkler.rb"]
|
14
23
|
|
15
|
-
|
24
|
+
if s.respond_to? :specification_version then
|
25
|
+
s.specification_version = 3
|
16
26
|
|
17
|
-
|
18
|
-
s.
|
19
|
-
s.
|
20
|
-
|
21
|
-
s.
|
22
|
-
s.
|
23
|
-
s.rdoc_options << '--main' << 'README' <<
|
24
|
-
'--title' << "amatch - Approximate Matching"
|
25
|
-
s.test_files.concat Dir['tests/test_*.rb']
|
26
|
-
|
27
|
-
s.author = "Florian Frank"
|
28
|
-
s.email = "flori@ping.de"
|
29
|
-
s.homepage = "http://amatch.rubyforge.org"
|
30
|
-
s.rubyforge_project = 'amatch'
|
27
|
+
if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
|
28
|
+
s.add_development_dependency(%q<gem_hadar>, ["~> 0.0.3"])
|
29
|
+
s.add_runtime_dependency(%q<spruz>, ["~> 0.2"])
|
30
|
+
else
|
31
|
+
s.add_dependency(%q<gem_hadar>, ["~> 0.0.3"])
|
32
|
+
s.add_dependency(%q<spruz>, ["~> 0.2"])
|
31
33
|
end
|
34
|
+
else
|
35
|
+
s.add_dependency(%q<gem_hadar>, ["~> 0.0.3"])
|
36
|
+
s.add_dependency(%q<spruz>, ["~> 0.2"])
|
37
|
+
end
|
38
|
+
end
|
data/ext/amatch.c
CHANGED
@@ -690,7 +690,10 @@ static VALUE LongestSubstring_similar(General *amatch, VALUE string)
|
|
690
690
|
} \
|
691
691
|
t = t / 2; \
|
692
692
|
result = (((double)m)/a_len + ((double)m)/b_len + ((double)(m-t))/m)/3.0; \
|
693
|
-
}
|
693
|
+
} \
|
694
|
+
free(l[0]); \
|
695
|
+
free(l[1]);
|
696
|
+
|
694
697
|
|
695
698
|
#define LOWERCASE_STRINGS \
|
696
699
|
char *ying = ALLOC_N(char, a_len); \
|
data/lib/amatch/.keep
ADDED
File without changes
|
data/lib/amatch/version.rb
CHANGED
metadata
CHANGED
@@ -1,7 +1,13 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: amatch
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
|
4
|
+
hash: 27
|
5
|
+
prerelease:
|
6
|
+
segments:
|
7
|
+
- 0
|
8
|
+
- 2
|
9
|
+
- 6
|
10
|
+
version: 0.2.6
|
5
11
|
platform: ruby
|
6
12
|
authors:
|
7
13
|
- Florian Frank
|
@@ -9,28 +15,57 @@ autorequire:
|
|
9
15
|
bindir: bin
|
10
16
|
cert_chain: []
|
11
17
|
|
12
|
-
date:
|
13
|
-
default_executable:
|
14
|
-
dependencies:
|
15
|
-
|
16
|
-
|
17
|
-
|
18
|
-
|
19
|
-
|
20
|
-
|
18
|
+
date: 2011-07-16 00:00:00 +02:00
|
19
|
+
default_executable:
|
20
|
+
dependencies:
|
21
|
+
- !ruby/object:Gem::Dependency
|
22
|
+
name: gem_hadar
|
23
|
+
prerelease: false
|
24
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ~>
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
hash: 25
|
30
|
+
segments:
|
31
|
+
- 0
|
32
|
+
- 0
|
33
|
+
- 3
|
34
|
+
version: 0.0.3
|
35
|
+
type: :development
|
36
|
+
version_requirements: *id001
|
37
|
+
- !ruby/object:Gem::Dependency
|
38
|
+
name: spruz
|
39
|
+
prerelease: false
|
40
|
+
requirement: &id002 !ruby/object:Gem::Requirement
|
41
|
+
none: false
|
42
|
+
requirements:
|
43
|
+
- - ~>
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
hash: 15
|
46
|
+
segments:
|
47
|
+
- 0
|
48
|
+
- 2
|
49
|
+
version: "0.2"
|
50
|
+
type: :runtime
|
51
|
+
version_requirements: *id002
|
52
|
+
description: Library to tail files in Ruby
|
21
53
|
email: flori@ping.de
|
22
54
|
executables:
|
23
55
|
- agrep.rb
|
24
56
|
extensions:
|
25
57
|
- ext/extconf.rb
|
26
58
|
extra_rdoc_files:
|
27
|
-
- README
|
28
|
-
- ext/amatch.c
|
59
|
+
- README.rdoc
|
29
60
|
- lib/amatch/version.rb
|
61
|
+
- ext/amatch.c
|
62
|
+
- ext/pair.c
|
30
63
|
files:
|
64
|
+
- .gitignore
|
31
65
|
- CHANGES
|
32
66
|
- COPYING
|
33
|
-
-
|
67
|
+
- Gemfile
|
68
|
+
- README.rdoc
|
34
69
|
- Rakefile
|
35
70
|
- VERSION
|
36
71
|
- amatch.gemspec
|
@@ -41,7 +76,7 @@ files:
|
|
41
76
|
- ext/pair.c
|
42
77
|
- ext/pair.h
|
43
78
|
- install.rb
|
44
|
-
- lib/amatch
|
79
|
+
- lib/amatch/.keep
|
45
80
|
- lib/amatch/version.rb
|
46
81
|
- tests/test_hamming.rb
|
47
82
|
- tests/test_jaro.rb
|
@@ -52,44 +87,49 @@ files:
|
|
52
87
|
- tests/test_pair_distance.rb
|
53
88
|
- tests/test_sellers.rb
|
54
89
|
has_rdoc: true
|
55
|
-
homepage: http://amatch
|
90
|
+
homepage: http://github.com/flori/amatch
|
56
91
|
licenses: []
|
57
92
|
|
58
93
|
post_install_message:
|
59
94
|
rdoc_options:
|
60
|
-
- --main
|
61
|
-
- README
|
62
95
|
- --title
|
63
|
-
-
|
96
|
+
- Amatch - Approximate Matching
|
97
|
+
- --main
|
98
|
+
- README.rdoc
|
64
99
|
require_paths:
|
65
100
|
- lib
|
66
101
|
- ext
|
67
|
-
- lib
|
68
102
|
required_ruby_version: !ruby/object:Gem::Requirement
|
103
|
+
none: false
|
69
104
|
requirements:
|
70
105
|
- - ">="
|
71
106
|
- !ruby/object:Gem::Version
|
107
|
+
hash: 3
|
108
|
+
segments:
|
109
|
+
- 0
|
72
110
|
version: "0"
|
73
|
-
version:
|
74
111
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
112
|
+
none: false
|
75
113
|
requirements:
|
76
114
|
- - ">="
|
77
115
|
- !ruby/object:Gem::Version
|
116
|
+
hash: 3
|
117
|
+
segments:
|
118
|
+
- 0
|
78
119
|
version: "0"
|
79
|
-
version:
|
80
120
|
requirements: []
|
81
121
|
|
82
|
-
rubyforge_project:
|
83
|
-
rubygems_version: 1.
|
122
|
+
rubyforge_project:
|
123
|
+
rubygems_version: 1.6.2
|
84
124
|
signing_key:
|
85
125
|
specification_version: 3
|
86
126
|
summary: Approximate String Matching library
|
87
127
|
test_files:
|
128
|
+
- tests/test_sellers.rb
|
129
|
+
- tests/test_jaro.rb
|
130
|
+
- tests/test_longest_subsequence.rb
|
88
131
|
- tests/test_longest_substring.rb
|
89
132
|
- tests/test_hamming.rb
|
90
|
-
- tests/test_longest_subsequence.rb
|
91
133
|
- tests/test_pair_distance.rb
|
92
134
|
- tests/test_levenshtein.rb
|
93
|
-
- tests/test_jaro.rb
|
94
|
-
- tests/test_sellers.rb
|
95
135
|
- tests/test_jaro_winkler.rb
|
data/lib/amatch.so
DELETED
Binary file
|