estem 0.2.4 → 0.2.5
Sign up to get free protection for your applications and to get access to all the features.
- data/ChangeLog +37 -10
- data/README.rdoc +7 -38
- data/examples/usage.rb +0 -2
- data/examples/usage.rb~ +11 -0
- data/lib/estem.rb +59 -60
- data/lib/estem.rb~ +271 -0
- data/test/diffs_ISO88591.txt +28390 -0
- data/test/{diffs.txt → diffs_UTF8.txt} +0 -0
- data/test/test_estem.rb +15 -10
- data/test/test_estem.rb~ +27 -0
- metadata +10 -5
- data/bin/es_stem.rb +0 -179
File without changes
|
data/test/test_estem.rb
CHANGED
@@ -1,23 +1,28 @@
|
|
1
|
-
# encoding: UTF-8
|
2
|
-
|
3
1
|
require 'test/unit'
|
4
2
|
require 'estem'
|
5
3
|
|
4
|
+
# NOTE:
|
5
|
+
# assuming we will run the test from the root directory of the project
|
6
|
+
# using "rake test" from the command-line
|
7
|
+
|
6
8
|
class EStemTest < Test::Unit::TestCase
|
7
|
-
def get_content(filename)
|
9
|
+
def get_content(filename, encoding='UTF-8')
|
8
10
|
content = nil
|
9
|
-
File.open(filename,
|
11
|
+
File.open(filename, "r:#{encoding}") do |f|
|
10
12
|
content = f.read()
|
11
13
|
end
|
12
14
|
content.scan(/(\S+)(?:\s+)(\S+)/)
|
13
15
|
end
|
14
16
|
|
15
|
-
def
|
16
|
-
|
17
|
-
# using "rake test" from the command-line
|
18
|
-
for word, good in get_content('test/diffs.txt')
|
17
|
+
def test_estem
|
18
|
+
for word, good in get_content('test/diffs_UTF8.txt')
|
19
19
|
assert_equal(good, word.es_stem, "input: " + word)
|
20
|
-
end
|
20
|
+
end
|
21
|
+
|
22
|
+
for word, good in get_content('test/diffs_ISO88591.txt', 'ISO-8859-1')
|
23
|
+
ret = word.safe_es_stem
|
24
|
+
assert_equal(good, ret, "input: " + word)
|
25
|
+
assert_equal('ISO-8859-1', ret.encoding.name.upcase)
|
26
|
+
end
|
21
27
|
end
|
22
|
-
|
23
28
|
end
|
data/test/test_estem.rb~
ADDED
@@ -0,0 +1,27 @@
|
|
1
|
+
require 'test/unit'
|
2
|
+
require 'estem'
|
3
|
+
|
4
|
+
# NOTE:
|
5
|
+
# assuming we will run the test from the root directory of the project
|
6
|
+
# using "rake test" from the command-line
|
7
|
+
|
8
|
+
class EStemTest < Test::Unit::TestCase
|
9
|
+
def get_content(filename, encoding='UTF-8')
|
10
|
+
content = nil
|
11
|
+
File.open(filename, "r:#{encoding}") do |f|
|
12
|
+
content = f.read()
|
13
|
+
end
|
14
|
+
content.scan(/(\S+)(?:\s+)(\S+)/)
|
15
|
+
end
|
16
|
+
|
17
|
+
def test_estem
|
18
|
+
for word, good in get_content('test/diffs_UTF8.txt')
|
19
|
+
assert_equal(good, word.es_stem, "input: " + word)
|
20
|
+
end
|
21
|
+
|
22
|
+
for word, good in get_content('test/diffs_ISO88591.txt', 'ISO-8859-1')
|
23
|
+
assert_equal(good, word.safe_es_stem, "input: " + word)
|
24
|
+
assert_equal(2,3)
|
25
|
+
end
|
26
|
+
end
|
27
|
+
end
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: estem
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.2.
|
4
|
+
version: 0.2.5
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -9,7 +9,7 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2012-
|
12
|
+
date: 2012-08-02 00:00:00.000000000 Z
|
13
13
|
dependencies: []
|
14
14
|
description: Spanish stemming. Based on Martin Porter's specifications. See README
|
15
15
|
file for more information.
|
@@ -19,14 +19,17 @@ extensions: []
|
|
19
19
|
extra_rdoc_files: []
|
20
20
|
files:
|
21
21
|
- Rakefile
|
22
|
-
- bin/es_stem.rb
|
23
22
|
- lib/estem.rb
|
23
|
+
- lib/estem.rb~
|
24
24
|
- examples/usage.rb
|
25
|
+
- examples/usage.rb~
|
25
26
|
- COPYRIGHT
|
26
27
|
- README.rdoc
|
27
28
|
- ChangeLog
|
28
|
-
- test/
|
29
|
+
- test/diffs_ISO88591.txt
|
30
|
+
- test/diffs_UTF8.txt
|
29
31
|
- test/test_estem.rb
|
32
|
+
- test/test_estem.rb~
|
30
33
|
homepage: https://github.com/MaG21/estem
|
31
34
|
licenses: []
|
32
35
|
post_install_message:
|
@@ -52,5 +55,7 @@ signing_key:
|
|
52
55
|
specification_version: 3
|
53
56
|
summary: Spanish stemming. Based on Martin Porter's specifications.
|
54
57
|
test_files:
|
55
|
-
- test/
|
58
|
+
- test/diffs_ISO88591.txt
|
59
|
+
- test/diffs_UTF8.txt
|
56
60
|
- test/test_estem.rb
|
61
|
+
- test/test_estem.rb~
|
data/bin/es_stem.rb
DELETED
@@ -1,179 +0,0 @@
|
|
1
|
-
#!/usr/bin/env ruby
|
2
|
-
# encoding: UTF-8
|
3
|
-
# :stopdoc:
|
4
|
-
|
5
|
-
# Copyright (c) 2012 Manuel A. Güílamo
|
6
|
-
#
|
7
|
-
# Permission is hereby granted, free of charge, to any person obtaining a copy
|
8
|
-
# of this software and associated documentation files (the "Software"), to deal
|
9
|
-
# in the Software without restriction, including without limitation the rights
|
10
|
-
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
11
|
-
# copies of the Software, and to permit persons to whom the Software is
|
12
|
-
# furnished to do so, subject to the following conditions:
|
13
|
-
#
|
14
|
-
# The above copyright notice and this permission notice shall be included in
|
15
|
-
# all copies or substantial portions of the Software.
|
16
|
-
#
|
17
|
-
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
18
|
-
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
19
|
-
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
20
|
-
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
21
|
-
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
22
|
-
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
23
|
-
# SOFTWARE.
|
24
|
-
|
25
|
-
require 'estem'
|
26
|
-
require 'getoptlong'
|
27
|
-
require 'iconv'
|
28
|
-
|
29
|
-
$version = "0.1.10"
|
30
|
-
|
31
|
-
def usage(error=false)
|
32
|
-
out = error ? $stderr : $stdout
|
33
|
-
out.puts DATA.read()
|
34
|
-
end
|
35
|
-
|
36
|
-
opts = GetoptLong.new(
|
37
|
-
['--help', '-h', GetoptLong::NO_ARGUMENT],
|
38
|
-
['--version', '-v', GetoptLong::NO_ARGUMENT],
|
39
|
-
['--file', '-f', GetoptLong::REQUIRED_ARGUMENT],
|
40
|
-
['--in-enc', '-i', GetoptLong::REQUIRED_ARGUMENT],
|
41
|
-
['--out-enc', '-o', GetoptLong::REQUIRED_ARGUMENT])
|
42
|
-
|
43
|
-
opts.quiet = true
|
44
|
-
|
45
|
-
filename = nil
|
46
|
-
ienc = nil
|
47
|
-
oenc = nil
|
48
|
-
|
49
|
-
begin
|
50
|
-
opts.each do |op, arg|
|
51
|
-
case op
|
52
|
-
when '--help'
|
53
|
-
usage()
|
54
|
-
exit
|
55
|
-
when '--version'
|
56
|
-
puts "EStem\nSpanish stemmer // lexemador\nVer: #{$version}"
|
57
|
-
exit
|
58
|
-
when '--file'
|
59
|
-
filename = arg
|
60
|
-
when '--in-enc'
|
61
|
-
ienc = arg
|
62
|
-
when '--out-enc'
|
63
|
-
oenc = arg
|
64
|
-
end
|
65
|
-
end
|
66
|
-
rescue GetoptLong::MissingArgument
|
67
|
-
$stderr.puts 'Option requires an argument // La opción requiere un argumento'
|
68
|
-
exit
|
69
|
-
rescue GetoptLong::InvalidOption
|
70
|
-
$stderr.puts 'Unknown option // Opción desconocida.'
|
71
|
-
usage(true)
|
72
|
-
exit
|
73
|
-
rescue
|
74
|
-
puts $!
|
75
|
-
exit
|
76
|
-
end
|
77
|
-
|
78
|
-
if filename
|
79
|
-
begin
|
80
|
-
if ienc and ienc.upcase !='UTF-8'
|
81
|
-
file = File.open(filename, "r:#{ienc}:UTF-8")
|
82
|
-
else
|
83
|
-
file = File.open(filename, 'r:UTF-8')
|
84
|
-
end
|
85
|
-
rescue
|
86
|
-
$stderr.puts $!
|
87
|
-
exit
|
88
|
-
end
|
89
|
-
|
90
|
-
begin
|
91
|
-
hsh = {}
|
92
|
-
file.each_line do|line|
|
93
|
-
line.split(/[^a-záéíóúüñÁÉÍÓÚÜÑ]+/ui).each do|word|
|
94
|
-
hsh[word] = word.es_stem unless hsh[word]
|
95
|
-
end
|
96
|
-
end
|
97
|
-
rescue
|
98
|
-
puts $!
|
99
|
-
exit
|
100
|
-
ensure
|
101
|
-
file.close
|
102
|
-
end
|
103
|
-
else
|
104
|
-
hsh = {}
|
105
|
-
$stdin.each_line do|line|
|
106
|
-
if ienc
|
107
|
-
line = Iconv.conv('UTF-8', ienc, line)
|
108
|
-
else
|
109
|
-
# Just in case the terminal mess with the encoding name.
|
110
|
-
# Por si la terminal juega con el nombre de la codificación.
|
111
|
-
line.force_encoding('UTF-8')
|
112
|
-
end
|
113
|
-
|
114
|
-
begin
|
115
|
-
line.split(/[^a-záéíóúüñÁÉÍÓÚÜÑ]+/ui).each do|word|
|
116
|
-
hsh[word] = word.es_stem unless hsh[word]
|
117
|
-
end
|
118
|
-
rescue Encoding::CompatibilityError
|
119
|
-
if ienc
|
120
|
-
msg = "incompatible encoding, please use option " +
|
121
|
-
"`--in-inc' correctly. //\n" +
|
122
|
-
"codificación incompatible, por favor use la " +
|
123
|
-
"opción `--in-inc' correctamente."
|
124
|
-
else
|
125
|
-
msg="incompatible encoding, please use option `--in-inc'."+
|
126
|
-
" //\ncodificación incompatible, por favor use la " +
|
127
|
-
"opción `--in-inc'."
|
128
|
-
end
|
129
|
-
|
130
|
-
if oenc
|
131
|
-
msg = Iconv.conv(oenc, 'UTF-8', msg)
|
132
|
-
end
|
133
|
-
|
134
|
-
$stderr.puts msg
|
135
|
-
exit
|
136
|
-
rescue
|
137
|
-
puts $!
|
138
|
-
exit
|
139
|
-
end
|
140
|
-
end
|
141
|
-
end
|
142
|
-
|
143
|
-
if oenc
|
144
|
-
begin
|
145
|
-
hsh.each_pair do |k,v|
|
146
|
-
puts Iconv.conv(oenc, 'UTF-8', "#{k} => #{v}")
|
147
|
-
end
|
148
|
-
rescue
|
149
|
-
puts $!
|
150
|
-
exit
|
151
|
-
end
|
152
|
-
else
|
153
|
-
hsh.each_pair{ |k,v| puts "#{k} => #{v}" }
|
154
|
-
end
|
155
|
-
|
156
|
-
__END__
|
157
|
-
Use: es_stem [OPTION]...
|
158
|
-
|
159
|
-
Options:
|
160
|
-
--help, -h display this help and exit. // Presenta esta ayuda y termina.
|
161
|
-
--version, -v output version information and exit //
|
162
|
-
Muestra la versión y termina.
|
163
|
-
--file, -f file of words. // fichero de palabras.
|
164
|
-
--in-enc, -i encoding of the file. // codificación del fichero.
|
165
|
-
--out-enc, -o output encoding // codificación de salida.
|
166
|
-
|
167
|
-
By default UTF-8 is used as input encoding, and if no file is specified,
|
168
|
-
standard input will be used instead.
|
169
|
-
|
170
|
-
You should set the option `--out-enc' if you are experimenting problems
|
171
|
-
visualizing the output text.
|
172
|
-
|
173
|
-
//
|
174
|
-
|
175
|
-
Por defecto se usará UTF-8 como codificación de entrada, si no se especifica un
|
176
|
-
fichero, la entrada estándard se usará en su lugar.
|
177
|
-
|
178
|
-
Debería establecer la opción `--out-enc' si está experimentando problemas para
|
179
|
-
visualizar el texto de salida.
|