estem 0.2.0
Sign up to get free protection for your applications and to get access to all the features.
- data/Rakefile +18 -0
- data/bin/es_stem.rb +178 -0
- data/lib/estem.rb +196 -0
- data/test/diffs.txt +28390 -0
- data/test/test_estem.rb +23 -0
- metadata +54 -0
data/Rakefile
ADDED
@@ -0,0 +1,18 @@
|
|
1
|
+
require 'rake/testtask'
|
2
|
+
|
3
|
+
Rake::TestTask.new do |t|
|
4
|
+
t.libs << 'test'
|
5
|
+
end
|
6
|
+
|
7
|
+
desc "Run tests"
|
8
|
+
task :default => :test
|
9
|
+
|
10
|
+
# Generate documentation.
|
11
|
+
require 'rdoc/task'
|
12
|
+
RDoc::Task.new do |rdoc|
|
13
|
+
rdoc.rdoc_files.include('README.rdoc',
|
14
|
+
'lib/**/*',
|
15
|
+
'bin/**/*')
|
16
|
+
rdoc.options = ['--main', 'README.rdoc']
|
17
|
+
rdoc.rdoc_dir = 'rdoc'
|
18
|
+
end
|
data/bin/es_stem.rb
ADDED
@@ -0,0 +1,178 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
# encoding: UTF-8
|
3
|
+
|
4
|
+
# Copyright (c) 2012 Manuel A. Güílamo
|
5
|
+
#
|
6
|
+
# Permission is hereby granted, free of charge, to any person obtaining a copy
|
7
|
+
# of this software and associated documentation files (the "Software"), to deal
|
8
|
+
# in the Software without restriction, including without limitation the rights
|
9
|
+
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
10
|
+
# copies of the Software, and to permit persons to whom the Software is
|
11
|
+
# furnished to do so, subject to the following conditions:
|
12
|
+
#
|
13
|
+
# The above copyright notice and this permission notice shall be included in
|
14
|
+
# all copies or substantial portions of the Software.
|
15
|
+
#
|
16
|
+
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
17
|
+
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
18
|
+
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
19
|
+
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
20
|
+
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
21
|
+
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
22
|
+
# SOFTWARE.
|
23
|
+
|
24
|
+
require 'estem.rb'
|
25
|
+
require 'getoptlong'
|
26
|
+
require 'iconv'
|
27
|
+
|
28
|
+
$version = "0.1.9"
|
29
|
+
|
30
|
+
def usage(error=false)
|
31
|
+
out = error ? $stderr : $stdout
|
32
|
+
out.puts DATA.read()
|
33
|
+
end
|
34
|
+
|
35
|
+
opts = GetoptLong.new(
|
36
|
+
['--help', '-h', GetoptLong::NO_ARGUMENT],
|
37
|
+
['--version', '-v', GetoptLong::NO_ARGUMENT],
|
38
|
+
['--file', '-f', GetoptLong::REQUIRED_ARGUMENT],
|
39
|
+
['--in-enc', '-i', GetoptLong::REQUIRED_ARGUMENT],
|
40
|
+
['--out-enc', '-o', GetoptLong::REQUIRED_ARGUMENT])
|
41
|
+
|
42
|
+
opts.quiet = true
|
43
|
+
|
44
|
+
filename = nil
|
45
|
+
ienc = nil
|
46
|
+
oenc = nil
|
47
|
+
|
48
|
+
begin
|
49
|
+
opts.each do |op, arg|
|
50
|
+
case op
|
51
|
+
when '--help'
|
52
|
+
usage()
|
53
|
+
exit
|
54
|
+
when '--version'
|
55
|
+
puts "EStem\nSpanish stemmer // lexemador\nVer: #{$version}"
|
56
|
+
exit
|
57
|
+
when '--file'
|
58
|
+
filename = arg
|
59
|
+
when '--in-enc'
|
60
|
+
ienc = arg
|
61
|
+
when '--out-enc'
|
62
|
+
oenc = arg
|
63
|
+
end
|
64
|
+
end
|
65
|
+
rescue GetoptLong::MissingArgument
|
66
|
+
$stderr.puts 'Option requires an argument // La opción requiere un argumento'
|
67
|
+
exit
|
68
|
+
rescue GetoptLong::InvalidOption
|
69
|
+
$stderr.puts 'Unknown option // Opción desconocida.'
|
70
|
+
usage(true)
|
71
|
+
exit
|
72
|
+
rescue
|
73
|
+
puts $!
|
74
|
+
exit
|
75
|
+
end
|
76
|
+
|
77
|
+
if filename
|
78
|
+
begin
|
79
|
+
if ienc and ienc!='UTF-8'
|
80
|
+
file = File.open(filename, "r:#{ienc}:UTF-8")
|
81
|
+
else
|
82
|
+
file = File.open(filename, 'r:UTF-8')
|
83
|
+
end
|
84
|
+
rescue
|
85
|
+
$stderr.puts $!
|
86
|
+
exit
|
87
|
+
end
|
88
|
+
|
89
|
+
begin
|
90
|
+
hsh = {}
|
91
|
+
file.each_line do|line|
|
92
|
+
line.split(/[^a-záéíóúüñÁÉÍÓÚÜÑ]+/ui).each do|word|
|
93
|
+
hsh[word] = word.es_stem unless hsh[word]
|
94
|
+
end
|
95
|
+
end
|
96
|
+
rescue
|
97
|
+
puts $!
|
98
|
+
exit
|
99
|
+
ensure
|
100
|
+
file.close
|
101
|
+
end
|
102
|
+
else
|
103
|
+
hsh = {}
|
104
|
+
$stdin.each_line do|line|
|
105
|
+
if ienc
|
106
|
+
line = Iconv.conv('UTF-8', ienc, line)
|
107
|
+
else
|
108
|
+
# Just in case the terminal mess with the encoding name.
|
109
|
+
# Por si la terminal juega con el nombre de la codificación.
|
110
|
+
line.force_encoding('UTF-8')
|
111
|
+
end
|
112
|
+
|
113
|
+
begin
|
114
|
+
line.split(/[^a-záéíóúüñÁÉÍÓÚÜÑ]+/ui).each do|word|
|
115
|
+
hsh[word] = word.es_stem unless hsh[word]
|
116
|
+
end
|
117
|
+
rescue Encoding::CompatibilityError
|
118
|
+
if ienc
|
119
|
+
msg = "incompatible encoding, please use option " +
|
120
|
+
"`--in-inc' correctly. //\n" +
|
121
|
+
"codificación incompatible, por favor use la " +
|
122
|
+
"opción `--in-inc' correctamente."
|
123
|
+
else
|
124
|
+
msg="incompatible encoding, please use option `--in-inc'."+
|
125
|
+
" //\ncodificación incompatible, por favor use la " +
|
126
|
+
"opción `--in-inc'."
|
127
|
+
end
|
128
|
+
|
129
|
+
if oenc
|
130
|
+
msg = Iconv.conv(oenc, 'UTF-8', msg)
|
131
|
+
end
|
132
|
+
|
133
|
+
$stderr.puts msg
|
134
|
+
exit
|
135
|
+
rescue
|
136
|
+
puts $!
|
137
|
+
exit
|
138
|
+
end
|
139
|
+
end
|
140
|
+
end
|
141
|
+
|
142
|
+
if oenc
|
143
|
+
begin
|
144
|
+
hsh.each_pair do |k,v|
|
145
|
+
puts Iconv.conv(oenc, 'UTF-8', "#{k} => #{v}")
|
146
|
+
end
|
147
|
+
rescue
|
148
|
+
puts $!
|
149
|
+
exit
|
150
|
+
end
|
151
|
+
else
|
152
|
+
hsh.each_pair{ |k,v| puts "#{k} => #{v}" }
|
153
|
+
end
|
154
|
+
|
155
|
+
__END__
|
156
|
+
Use: es_stem [OPTION]...
|
157
|
+
|
158
|
+
Options:
|
159
|
+
--help, -h display this help and exit. // Presenta esta ayuda y termina.
|
160
|
+
--version, -v output version information and exit //
|
161
|
+
Muestra la versión y termina.
|
162
|
+
--file, -f file of words. // fichero de palabras.
|
163
|
+
--in-enc, -i encoding of the file. // codificación del fichero.
|
164
|
+
--out-enc, -o output encoding // codificación de salida.
|
165
|
+
|
166
|
+
By default UTF-8 is used as input encoding, and if no file is specified,
|
167
|
+
standard input will be used instead.
|
168
|
+
|
169
|
+
You should set the option `--out-enc' if you are experimenting problems
|
170
|
+
visualizing the output text.
|
171
|
+
|
172
|
+
//
|
173
|
+
|
174
|
+
Por defecto se usará UTF-8 como codificación de entrada, si no se especifica un
|
175
|
+
fichero, la entrada estándard se usará en su lugar.
|
176
|
+
|
177
|
+
Debería establecer la opción `--out-enc' si está experimentando problemas para
|
178
|
+
visualizar el texto de salida.
|
data/lib/estem.rb
ADDED
@@ -0,0 +1,196 @@
|
|
1
|
+
# encoding: UTF-8
|
2
|
+
#
|
3
|
+
# Porter, Spanish stemmer in Ruby.
|
4
|
+
#
|
5
|
+
# :title: EStem - Ruby based Porter Spanish Stemmer
|
6
|
+
|
7
|
+
module EStem
|
8
|
+
def es_stem
|
9
|
+
str = self.dup
|
10
|
+
return remove_accent(str) if str.length == 1
|
11
|
+
tmp = step0(str)
|
12
|
+
str = tmp ? tmp : str
|
13
|
+
|
14
|
+
unless tmp = step1(str)
|
15
|
+
unless tmp = step2a(str)
|
16
|
+
tmp = step2b(str)
|
17
|
+
str = tmp ? tmp : str
|
18
|
+
else
|
19
|
+
str = tmp
|
20
|
+
end
|
21
|
+
end
|
22
|
+
tmp = step3(str)
|
23
|
+
str = tmp.nil? ? str : tmp
|
24
|
+
remove_accent(str)
|
25
|
+
end
|
26
|
+
|
27
|
+
private
|
28
|
+
|
29
|
+
def vowel?(c)
|
30
|
+
VOWEL.include?(c)
|
31
|
+
end
|
32
|
+
|
33
|
+
def consonant?(c)
|
34
|
+
CONSONANT.include?(c)
|
35
|
+
end
|
36
|
+
|
37
|
+
def remove_accent(str)
|
38
|
+
str.tr('áéíóúÁÉÍÓÚ','aeiouAEIOU')
|
39
|
+
end
|
40
|
+
|
41
|
+
def rv(str)
|
42
|
+
if consonant? str[1]
|
43
|
+
i=2
|
44
|
+
i+=1 while str[i] and consonant? str[i]
|
45
|
+
return str.nil? ? str.length-1 : i+1
|
46
|
+
end
|
47
|
+
|
48
|
+
if vowel? str[0] and vowel? str[1]
|
49
|
+
i=2
|
50
|
+
i+=1 while str[i] and vowel? str[i]
|
51
|
+
return str.nil? ? str.length-1 : i+1
|
52
|
+
end
|
53
|
+
|
54
|
+
return 3 if consonant? str[0] and vowel? str[1]
|
55
|
+
|
56
|
+
str.length - 1
|
57
|
+
end
|
58
|
+
|
59
|
+
def r(str, i=0)
|
60
|
+
i+=1 while str[i] and consonant?(str[i])
|
61
|
+
i+=1
|
62
|
+
i+=1 while str[i] and vowel? str[i]
|
63
|
+
str[i].nil? ? str.length : i+1
|
64
|
+
end
|
65
|
+
|
66
|
+
def r12(str)
|
67
|
+
r1 = r(str)
|
68
|
+
r2 = r(str,r1)
|
69
|
+
[r1,r2]
|
70
|
+
end
|
71
|
+
|
72
|
+
def step0(str)
|
73
|
+
return nil unless str =~ /(se(l[ao]s?)?|l([aeo]s?)|me|nos)$/i
|
74
|
+
|
75
|
+
suffix = $&
|
76
|
+
rv_text = str[rv(str)..-1]
|
77
|
+
|
78
|
+
case rv_text
|
79
|
+
when %r{((?<=i[éÉ]ndo|[áÁ]ndo|[áéíÁÉÍ]r)#{suffix})$}ui
|
80
|
+
str[%r{#$&$}]=''
|
81
|
+
str = remove_accent(str)
|
82
|
+
return str
|
83
|
+
when %r{((?<=iendo|ando|[aei]r)#{suffix})$}i
|
84
|
+
str[%r{#$&$}]=''
|
85
|
+
return str
|
86
|
+
end
|
87
|
+
|
88
|
+
if rv_text =~ /yendo/i and str =~ /uyendo/i
|
89
|
+
str[suffix]=''
|
90
|
+
return str
|
91
|
+
end
|
92
|
+
nil
|
93
|
+
end
|
94
|
+
|
95
|
+
#=> new_str or nil
|
96
|
+
def step1(str)
|
97
|
+
r1,r2 = r12(str)
|
98
|
+
r1_text = str[r1..-1]
|
99
|
+
r2_text = str[r2..-1]
|
100
|
+
|
101
|
+
case r2_text
|
102
|
+
when /(anzas?|ic[oa]s?|ismos?|[ai]bles?|istas?|os[oa]s?|[ai]mientos?)$/i
|
103
|
+
str[%r{#$&$}]=''
|
104
|
+
return str
|
105
|
+
when /(ic)?(ador([ae]s?)?|aci[óÓ]n|aciones|antes?|ancias?)$/ui
|
106
|
+
str[%r{#$&$}]=''
|
107
|
+
return str
|
108
|
+
when /log[íÍ]as?/ui
|
109
|
+
str[%r{#$&$}]='log'
|
110
|
+
return str
|
111
|
+
when /(uci([óÓ]n|ones))$/ui
|
112
|
+
str[%r{#$&$}]='u'
|
113
|
+
return str
|
114
|
+
when /(encias?)$/i
|
115
|
+
str[%r{#$&$}]='ente'
|
116
|
+
return str
|
117
|
+
end
|
118
|
+
|
119
|
+
if r2_text =~ /(ativ|iv|os|ic|ad)amente$/i or r1_text =~ /amente$/i
|
120
|
+
str[%r{#$&$}]=''
|
121
|
+
return str
|
122
|
+
end
|
123
|
+
|
124
|
+
case r2_text
|
125
|
+
when /((ante|[ai]ble)?mente)$/i, /((abil|i[cv])?idad(es)?)$/i, /((at)?iv[ao]s?)$/i
|
126
|
+
str[%r{#$&$}]=''
|
127
|
+
return str
|
128
|
+
end
|
129
|
+
nil
|
130
|
+
end
|
131
|
+
|
132
|
+
#=> nil or new_str
|
133
|
+
def step2a(str)
|
134
|
+
rv_pos = rv(str)
|
135
|
+
idx = str[rv_pos..-1] =~ /(y[oóÓ]|ye(ron|ndo)|y[ae][ns]?|ya(is|mos))$/ui
|
136
|
+
|
137
|
+
return nil unless idx
|
138
|
+
|
139
|
+
if 'u' == str[rv_pos+idx-1].downcase
|
140
|
+
str[%r{#$&$}] = ''
|
141
|
+
return str
|
142
|
+
end
|
143
|
+
nil
|
144
|
+
end
|
145
|
+
|
146
|
+
STEP2B_REGEXP = /(
|
147
|
+
ar([áÁ][ns]?|a(n|s|is)?|on)? | ar([éÉ]is|emos|é|É) | ar[íÍ]a(n|s|is|mos)? |
|
148
|
+
er([áÁ][sn]?|[éÉ](is)?|emos|[íÍ]a(n|s|is|mos)?)? |
|
149
|
+
ir([íÍ]a(s|n|is|mos)?|[áÁ][ns]?|emos|[éÉ]|éis)? | aba(s|n|is)? |
|
150
|
+
ad([ao]s?)? | ed | id(a|as|o|os)? | [íÍ]a(n|s|is|mos)? | [íÍ]s |
|
151
|
+
as(e[ns]?|te|eis|teis)? | [áÁ](is|bamos|semos|ramos) | a(n|ndo|mos) |
|
152
|
+
ie(ra|se|ran|sen|ron|ndo|ras|ses|rais|seis) | i(ste|steis|[óÓ]|mos|[éÉ]ramos|[éÉ]semos) |
|
153
|
+
en|es|[éÉ]is|emos
|
154
|
+
)$/xiu
|
155
|
+
|
156
|
+
def step2b(str)
|
157
|
+
rv_pos = rv(str)
|
158
|
+
|
159
|
+
if idx = str[rv_pos..-1] =~ STEP2B_REGEXP
|
160
|
+
suffix = $&
|
161
|
+
if suffix =~ /^(en|es|[éÉ]is|emos)$/ui
|
162
|
+
str[%r{#{suffix}$}]=''
|
163
|
+
str[rv_pos+idx-1]='' if str[rv_pos+idx-2] =~ /g/i and str[rv_pos+idx-1] =~ /u/i
|
164
|
+
else
|
165
|
+
str[%r{#{suffix}$}]=''
|
166
|
+
end
|
167
|
+
return str
|
168
|
+
end
|
169
|
+
nil
|
170
|
+
end
|
171
|
+
|
172
|
+
def step3(str)
|
173
|
+
rv_pos = rv(str)
|
174
|
+
rv_text = str[rv_pos..-1]
|
175
|
+
|
176
|
+
if rv_text =~ /(os|[aoáíóÁÍÓ])$/ui
|
177
|
+
str[%r{#$&$}]=''
|
178
|
+
return str
|
179
|
+
elsif idx = rv_text =~ /(u?[eéÉ])$/i
|
180
|
+
if $&[0].downcase == 'u' and str[rv_pos+idx-1].downcase == 'g'
|
181
|
+
str[%r{#$&$}]=''
|
182
|
+
else
|
183
|
+
str.chop!
|
184
|
+
end
|
185
|
+
return str
|
186
|
+
end
|
187
|
+
nil
|
188
|
+
end
|
189
|
+
|
190
|
+
VOWEL = 'aeiouáéíóúüAEIOUÁÉÍÓÚÜ'
|
191
|
+
CONSONANT = "bcdfghjklmnñpqrstvwxyzABCDEFGHIJKLMNÑOPQRSTUVWXYZ"
|
192
|
+
end
|
193
|
+
|
194
|
+
class String
|
195
|
+
include EStem
|
196
|
+
end
|