perseus_match 0.0.1 → 0.0.2
Sign up to get free protection for your applications and to get access to all the features.
- data/README +7 -1
- data/Rakefile +1 -1
- data/bin/perseus_match +42 -12
- data/lib/perseus_match/cluster.rb +31 -1
- data/lib/perseus_match/list.rb +34 -10
- data/lib/perseus_match/token_set.rb +28 -0
- data/lib/perseus_match/version.rb +1 -1
- data/lib/perseus_match.rb +28 -0
- metadata +13 -4
data/README
CHANGED
@@ -2,7 +2,7 @@
|
|
2
2
|
|
3
3
|
== VERSION
|
4
4
|
|
5
|
-
This documentation refers to perseus_match version 0.0.
|
5
|
+
This documentation refers to perseus_match version 0.0.2
|
6
6
|
|
7
7
|
|
8
8
|
== DESCRIPTION
|
@@ -15,6 +15,12 @@ Fuzzy string matching based on linguistic analysis.
|
|
15
15
|
* Jens Wille <mailto:jens.wille@uni-koeln.de>
|
16
16
|
|
17
17
|
|
18
|
+
== LINKS
|
19
|
+
|
20
|
+
* <http://prometheus.rubyforge.org/perseus_match>
|
21
|
+
* <http://github.com/blackwinter/perseus_match>
|
22
|
+
|
23
|
+
|
18
24
|
== LICENSE AND COPYRIGHT
|
19
25
|
|
20
26
|
Copyright (C) 2008 Cologne University of Applied Sciences,
|
data/Rakefile
CHANGED
@@ -14,7 +14,7 @@ begin
|
|
14
14
|
:summary => %q{Fuzzy string matching based on linguistic analysis},
|
15
15
|
:files => FileList['lib/**/*.rb', 'bin/*'].to_a,
|
16
16
|
:extra_files => FileList['[A-Z]*'].to_a,
|
17
|
-
:dependencies =>
|
17
|
+
:dependencies => [['ruby-nuggets', '>= 0.3.0']]
|
18
18
|
}
|
19
19
|
}}
|
20
20
|
rescue LoadError
|
data/bin/perseus_match
CHANGED
@@ -1,6 +1,10 @@
|
|
1
1
|
#! /usr/bin/ruby
|
2
2
|
|
3
3
|
require 'optparse'
|
4
|
+
require 'benchmark'
|
5
|
+
|
6
|
+
require 'rubygems'
|
7
|
+
require 'nuggets/numeric/duration'
|
4
8
|
|
5
9
|
$: << File.join(File.dirname(__FILE__), '..', 'lib')
|
6
10
|
|
@@ -10,8 +14,9 @@ USAGE = "Usage: #{$0} [-h|--help] [options] <file>"
|
|
10
14
|
abort USAGE if ARGV.empty?
|
11
15
|
|
12
16
|
options = {
|
13
|
-
:
|
14
|
-
:threshold => 0
|
17
|
+
:stats => false,
|
18
|
+
:threshold => 0,
|
19
|
+
:sort => false
|
15
20
|
}
|
16
21
|
|
17
22
|
OptionParser.new { |opts|
|
@@ -20,6 +25,10 @@ OptionParser.new { |opts|
|
|
20
25
|
opts.separator ''
|
21
26
|
opts.separator 'Options:'
|
22
27
|
|
28
|
+
opts.on('--stats', 'Output some statistics at the end') {
|
29
|
+
options[:stats] = true
|
30
|
+
}
|
31
|
+
|
23
32
|
opts.on('-t', '--threshold NUM', Float, "Similarity threshold [Default: #{options[:threshold]}]") { |t|
|
24
33
|
options[:threshold] = t
|
25
34
|
}
|
@@ -49,16 +58,37 @@ end
|
|
49
58
|
PerseusMatch::TokenSet.tokenize(file)
|
50
59
|
|
51
60
|
phrases = File.readlines(file).map { |line| line.chomp }
|
52
|
-
threshold = options[:threshold]
|
53
61
|
|
54
|
-
|
55
|
-
|
62
|
+
threshold, count, count_all = options[:threshold], 0, 0
|
63
|
+
|
64
|
+
time = Benchmark.realtime {
|
65
|
+
if options[:sort]
|
66
|
+
require 'pp'
|
67
|
+
|
68
|
+
pp PerseusMatch::Cluster.new(phrases).sort { |pm|
|
69
|
+
if pm.similarity >= threshold
|
70
|
+
[pm.target, pm.distance, pm.similarity]
|
71
|
+
count += 1
|
72
|
+
end
|
73
|
+
count_all += 1
|
74
|
+
}.compact
|
75
|
+
else
|
76
|
+
PerseusMatch::List.pair(phrases) { |pm|
|
77
|
+
if pm.similarity >= threshold
|
78
|
+
p [pm.phrase, pm.target, pm.distance, pm.similarity]
|
79
|
+
count += 1
|
80
|
+
end
|
81
|
+
count_all += 1
|
82
|
+
}
|
83
|
+
end
|
84
|
+
}
|
85
|
+
|
86
|
+
if options[:stats]
|
87
|
+
hms, x, y = time.to_hms(2), time / count, time / count_all
|
56
88
|
|
57
|
-
|
58
|
-
|
59
|
-
}
|
60
|
-
|
61
|
-
|
62
|
-
p [pm.phrase, pm.target, pm.distance, pm.similarity] if pm.similarity >= threshold
|
63
|
-
}
|
89
|
+
precision = lambda { |i| i.to_s.sub(/\./, '')[/\A0*/].length + 2 }
|
90
|
+
|
91
|
+
warn "%d (%d/%d): %s => %0.#{precision[x]}fs/%0.#{precision[y]}fs" % [
|
92
|
+
phrases.size, count, count_all, hms, x, y
|
93
|
+
]
|
64
94
|
end
|
@@ -1,3 +1,31 @@
|
|
1
|
+
#--
|
2
|
+
###############################################################################
|
3
|
+
# #
|
4
|
+
# A component of perseus_match, the fuzzy string matcher #
|
5
|
+
# #
|
6
|
+
# Copyright (C) 2008 Cologne University of Applied Sciences #
|
7
|
+
# Claudiusstr. 1 #
|
8
|
+
# 50678 Cologne, Germany #
|
9
|
+
# #
|
10
|
+
# Authors: #
|
11
|
+
# Jens Wille <jens.wille@uni-koeln.de> #
|
12
|
+
# #
|
13
|
+
# perseus_match is free software: you can redistribute it and/or modify it #
|
14
|
+
# under the terms of the GNU General Public License as published by the Free #
|
15
|
+
# Software Foundation, either version 3 of the License, or (at your option) #
|
16
|
+
# any later version. #
|
17
|
+
# #
|
18
|
+
# perseus_match is distributed in the hope that it will be useful, but #
|
19
|
+
# WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY #
|
20
|
+
# or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License #
|
21
|
+
# for more details. #
|
22
|
+
# #
|
23
|
+
# You should have received a copy of the GNU General Public License along #
|
24
|
+
# with perseus_match. If not, see <http://www.gnu.org/licenses/>. #
|
25
|
+
# #
|
26
|
+
###############################################################################
|
27
|
+
#++
|
28
|
+
|
1
29
|
class PerseusMatch
|
2
30
|
|
3
31
|
class Cluster < Hash
|
@@ -17,7 +45,7 @@ class PerseusMatch
|
|
17
45
|
def sort_by(attribute, *args, &block)
|
18
46
|
options = args.last.is_a?(Hash) ? args.pop : {}
|
19
47
|
|
20
|
-
map { |phrase, matches|
|
48
|
+
_ = map { |phrase, matches|
|
21
49
|
res = {}
|
22
50
|
|
23
51
|
matches = matches.sort_by { |match|
|
@@ -47,6 +75,8 @@ class PerseusMatch
|
|
47
75
|
|
48
76
|
[phrase, matches]
|
49
77
|
}.sort
|
78
|
+
|
79
|
+
_ # rcov hack :-(
|
50
80
|
end
|
51
81
|
|
52
82
|
def sort(options = {}, &block)
|
data/lib/perseus_match/list.rb
CHANGED
@@ -1,3 +1,31 @@
|
|
1
|
+
#--
|
2
|
+
###############################################################################
|
3
|
+
# #
|
4
|
+
# A component of perseus_match, the fuzzy string matcher #
|
5
|
+
# #
|
6
|
+
# Copyright (C) 2008 Cologne University of Applied Sciences #
|
7
|
+
# Claudiusstr. 1 #
|
8
|
+
# 50678 Cologne, Germany #
|
9
|
+
# #
|
10
|
+
# Authors: #
|
11
|
+
# Jens Wille <jens.wille@uni-koeln.de> #
|
12
|
+
# #
|
13
|
+
# perseus_match is free software: you can redistribute it and/or modify it #
|
14
|
+
# under the terms of the GNU General Public License as published by the Free #
|
15
|
+
# Software Foundation, either version 3 of the License, or (at your option) #
|
16
|
+
# any later version. #
|
17
|
+
# #
|
18
|
+
# perseus_match is distributed in the hope that it will be useful, but #
|
19
|
+
# WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY #
|
20
|
+
# or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License #
|
21
|
+
# for more details. #
|
22
|
+
# #
|
23
|
+
# You should have received a copy of the GNU General Public License along #
|
24
|
+
# with perseus_match. If not, see <http://www.gnu.org/licenses/>. #
|
25
|
+
# #
|
26
|
+
###############################################################################
|
27
|
+
#++
|
28
|
+
|
1
29
|
class PerseusMatch
|
2
30
|
|
3
31
|
class List < Array
|
@@ -5,17 +33,13 @@ class PerseusMatch
|
|
5
33
|
class << self
|
6
34
|
|
7
35
|
def pair(phrases)
|
8
|
-
|
9
|
-
|
10
|
-
|
11
|
-
phrases.
|
12
|
-
|
13
|
-
phrases.each { |phrase|
|
14
|
-
phrases.each { |target|
|
15
|
-
yield PerseusMatch.new(phrase, target)
|
16
|
-
}
|
36
|
+
phrases.uniq!
|
37
|
+
|
38
|
+
phrases.each { |phrase|
|
39
|
+
phrases.each { |target|
|
40
|
+
yield PerseusMatch.new(phrase, target)
|
17
41
|
}
|
18
|
-
|
42
|
+
}
|
19
43
|
end
|
20
44
|
|
21
45
|
end
|
@@ -1,3 +1,31 @@
|
|
1
|
+
#--
|
2
|
+
###############################################################################
|
3
|
+
# #
|
4
|
+
# A component of perseus_match, the fuzzy string matcher #
|
5
|
+
# #
|
6
|
+
# Copyright (C) 2008 Cologne University of Applied Sciences #
|
7
|
+
# Claudiusstr. 1 #
|
8
|
+
# 50678 Cologne, Germany #
|
9
|
+
# #
|
10
|
+
# Authors: #
|
11
|
+
# Jens Wille <jens.wille@uni-koeln.de> #
|
12
|
+
# #
|
13
|
+
# perseus_match is free software: you can redistribute it and/or modify it #
|
14
|
+
# under the terms of the GNU General Public License as published by the Free #
|
15
|
+
# Software Foundation, either version 3 of the License, or (at your option) #
|
16
|
+
# any later version. #
|
17
|
+
# #
|
18
|
+
# perseus_match is distributed in the hope that it will be useful, but #
|
19
|
+
# WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY #
|
20
|
+
# or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License #
|
21
|
+
# for more details. #
|
22
|
+
# #
|
23
|
+
# You should have received a copy of the GNU General Public License along #
|
24
|
+
# with perseus_match. If not, see <http://www.gnu.org/licenses/>. #
|
25
|
+
# #
|
26
|
+
###############################################################################
|
27
|
+
#++
|
28
|
+
|
1
29
|
$KCODE = 'u'
|
2
30
|
|
3
31
|
LINGO_BASE = '/home/jw/devel/lingo/trunk'
|
data/lib/perseus_match.rb
CHANGED
@@ -1,3 +1,31 @@
|
|
1
|
+
#--
|
2
|
+
###############################################################################
|
3
|
+
# #
|
4
|
+
# perseus_match -- Fuzzy string matching based on linguistic analysis #
|
5
|
+
# #
|
6
|
+
# Copyright (C) 2008 Cologne University of Applied Sciences #
|
7
|
+
# Claudiusstr. 1 #
|
8
|
+
# 50678 Cologne, Germany #
|
9
|
+
# #
|
10
|
+
# Authors: #
|
11
|
+
# Jens Wille <jens.wille@uni-koeln.de> #
|
12
|
+
# #
|
13
|
+
# perseus_match is free software: you can redistribute it and/or modify it #
|
14
|
+
# under the terms of the GNU General Public License as published by the Free #
|
15
|
+
# Software Foundation, either version 3 of the License, or (at your option) #
|
16
|
+
# any later version. #
|
17
|
+
# #
|
18
|
+
# perseus_match is distributed in the hope that it will be useful, but #
|
19
|
+
# WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY #
|
20
|
+
# or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License #
|
21
|
+
# for more details. #
|
22
|
+
# #
|
23
|
+
# You should have received a copy of the GNU General Public License along #
|
24
|
+
# with perseus_match. If not, see <http://www.gnu.org/licenses/>. #
|
25
|
+
# #
|
26
|
+
###############################################################################
|
27
|
+
#++
|
28
|
+
|
1
29
|
require 'perseus_match/list'
|
2
30
|
require 'perseus_match/cluster'
|
3
31
|
require 'perseus_match/token_set'
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: perseus_match
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Jens Wille
|
@@ -9,10 +9,19 @@ autorequire:
|
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
11
|
|
12
|
-
date: 2008-08-
|
12
|
+
date: 2008-08-15 00:00:00 +02:00
|
13
13
|
default_executable:
|
14
|
-
dependencies:
|
15
|
-
|
14
|
+
dependencies:
|
15
|
+
- !ruby/object:Gem::Dependency
|
16
|
+
name: ruby-nuggets
|
17
|
+
type: :runtime
|
18
|
+
version_requirement:
|
19
|
+
version_requirements: !ruby/object:Gem::Requirement
|
20
|
+
requirements:
|
21
|
+
- - ">="
|
22
|
+
- !ruby/object:Gem::Version
|
23
|
+
version: 0.3.0
|
24
|
+
version:
|
16
25
|
description: Fuzzy string matching based on linguistic analysis
|
17
26
|
email: jens.wille@uni-koeln.de
|
18
27
|
executables:
|