ruby-stemmer 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/MIT-LICENSE +21 -0
- data/README +79 -0
- data/Rakefile +52 -0
- data/extconf.rb +14 -0
- data/libstemmer_c/MANIFEST +72 -0
- data/libstemmer_c/Makefile +9 -0
- data/libstemmer_c/README +125 -0
- data/libstemmer_c/include/libstemmer.h +79 -0
- data/libstemmer_c/libstemmer/libstemmer.c +93 -0
- data/libstemmer_c/libstemmer/libstemmer_utf8.c +93 -0
- data/libstemmer_c/libstemmer/modules.h +190 -0
- data/libstemmer_c/libstemmer/modules.txt +50 -0
- data/libstemmer_c/libstemmer/modules_utf8.h +121 -0
- data/libstemmer_c/libstemmer/modules_utf8.txt +49 -0
- data/libstemmer_c/mkinc.mak +82 -0
- data/libstemmer_c/mkinc_utf8.mak +52 -0
- data/libstemmer_c/runtime/api.c +66 -0
- data/libstemmer_c/runtime/api.h +26 -0
- data/libstemmer_c/runtime/header.h +58 -0
- data/libstemmer_c/runtime/utilities.c +478 -0
- data/libstemmer_c/src_c/stem_ISO_8859_1_danish.c +337 -0
- data/libstemmer_c/src_c/stem_ISO_8859_1_danish.h +16 -0
- data/libstemmer_c/src_c/stem_ISO_8859_1_dutch.c +624 -0
- data/libstemmer_c/src_c/stem_ISO_8859_1_dutch.h +16 -0
- data/libstemmer_c/src_c/stem_ISO_8859_1_english.c +1117 -0
- data/libstemmer_c/src_c/stem_ISO_8859_1_english.h +16 -0
- data/libstemmer_c/src_c/stem_ISO_8859_1_finnish.c +762 -0
- data/libstemmer_c/src_c/stem_ISO_8859_1_finnish.h +16 -0
- data/libstemmer_c/src_c/stem_ISO_8859_1_french.c +1246 -0
- data/libstemmer_c/src_c/stem_ISO_8859_1_french.h +16 -0
- data/libstemmer_c/src_c/stem_ISO_8859_1_german.c +503 -0
- data/libstemmer_c/src_c/stem_ISO_8859_1_german.h +16 -0
- data/libstemmer_c/src_c/stem_ISO_8859_1_hungarian.c +1230 -0
- data/libstemmer_c/src_c/stem_ISO_8859_1_hungarian.h +16 -0
- data/libstemmer_c/src_c/stem_ISO_8859_1_italian.c +1065 -0
- data/libstemmer_c/src_c/stem_ISO_8859_1_italian.h +16 -0
- data/libstemmer_c/src_c/stem_ISO_8859_1_norwegian.c +297 -0
- data/libstemmer_c/src_c/stem_ISO_8859_1_norwegian.h +16 -0
- data/libstemmer_c/src_c/stem_ISO_8859_1_porter.c +749 -0
- data/libstemmer_c/src_c/stem_ISO_8859_1_porter.h +16 -0
- data/libstemmer_c/src_c/stem_ISO_8859_1_portuguese.c +1017 -0
- data/libstemmer_c/src_c/stem_ISO_8859_1_portuguese.h +16 -0
- data/libstemmer_c/src_c/stem_ISO_8859_1_spanish.c +1093 -0
- data/libstemmer_c/src_c/stem_ISO_8859_1_spanish.h +16 -0
- data/libstemmer_c/src_c/stem_ISO_8859_1_swedish.c +307 -0
- data/libstemmer_c/src_c/stem_ISO_8859_1_swedish.h +16 -0
- data/libstemmer_c/src_c/stem_ISO_8859_2_romanian.c +998 -0
- data/libstemmer_c/src_c/stem_ISO_8859_2_romanian.h +16 -0
- data/libstemmer_c/src_c/stem_KOI8_R_russian.c +700 -0
- data/libstemmer_c/src_c/stem_KOI8_R_russian.h +16 -0
- data/libstemmer_c/src_c/stem_UTF_8_danish.c +339 -0
- data/libstemmer_c/src_c/stem_UTF_8_danish.h +16 -0
- data/libstemmer_c/src_c/stem_UTF_8_dutch.c +634 -0
- data/libstemmer_c/src_c/stem_UTF_8_dutch.h +16 -0
- data/libstemmer_c/src_c/stem_UTF_8_english.c +1125 -0
- data/libstemmer_c/src_c/stem_UTF_8_english.h +16 -0
- data/libstemmer_c/src_c/stem_UTF_8_finnish.c +768 -0
- data/libstemmer_c/src_c/stem_UTF_8_finnish.h +16 -0
- data/libstemmer_c/src_c/stem_UTF_8_french.c +1256 -0
- data/libstemmer_c/src_c/stem_UTF_8_french.h +16 -0
- data/libstemmer_c/src_c/stem_UTF_8_german.c +509 -0
- data/libstemmer_c/src_c/stem_UTF_8_german.h +16 -0
- data/libstemmer_c/src_c/stem_UTF_8_hungarian.c +1234 -0
- data/libstemmer_c/src_c/stem_UTF_8_hungarian.h +16 -0
- data/libstemmer_c/src_c/stem_UTF_8_italian.c +1073 -0
- data/libstemmer_c/src_c/stem_UTF_8_italian.h +16 -0
- data/libstemmer_c/src_c/stem_UTF_8_norwegian.c +299 -0
- data/libstemmer_c/src_c/stem_UTF_8_norwegian.h +16 -0
- data/libstemmer_c/src_c/stem_UTF_8_porter.c +755 -0
- data/libstemmer_c/src_c/stem_UTF_8_porter.h +16 -0
- data/libstemmer_c/src_c/stem_UTF_8_portuguese.c +1023 -0
- data/libstemmer_c/src_c/stem_UTF_8_portuguese.h +16 -0
- data/libstemmer_c/src_c/stem_UTF_8_romanian.c +1004 -0
- data/libstemmer_c/src_c/stem_UTF_8_romanian.h +16 -0
- data/libstemmer_c/src_c/stem_UTF_8_russian.c +694 -0
- data/libstemmer_c/src_c/stem_UTF_8_russian.h +16 -0
- data/libstemmer_c/src_c/stem_UTF_8_spanish.c +1097 -0
- data/libstemmer_c/src_c/stem_UTF_8_spanish.h +16 -0
- data/libstemmer_c/src_c/stem_UTF_8_swedish.c +309 -0
- data/libstemmer_c/src_c/stem_UTF_8_swedish.h +16 -0
- data/libstemmer_c/src_c/stem_UTF_8_turkish.c +2205 -0
- data/libstemmer_c/src_c/stem_UTF_8_turkish.h +16 -0
- data/ruby-stemmer.c +108 -0
- data/test.rb +31 -0
- metadata +141 -0
@@ -0,0 +1,16 @@
|
|
1
|
+
|
2
|
+
/* This file was generated automatically by the Snowball to ANSI C compiler */
|
3
|
+
|
4
|
+
#ifdef __cplusplus
|
5
|
+
extern "C" {
|
6
|
+
#endif
|
7
|
+
|
8
|
+
extern struct SN_env * turkish_UTF_8_create_env(void);
|
9
|
+
extern void turkish_UTF_8_close_env(struct SN_env * z);
|
10
|
+
|
11
|
+
extern int turkish_UTF_8_stem(struct SN_env * z);
|
12
|
+
|
13
|
+
#ifdef __cplusplus
|
14
|
+
}
|
15
|
+
#endif
|
16
|
+
|
data/ruby-stemmer.c
ADDED
@@ -0,0 +1,108 @@
|
|
1
|
+
//
|
2
|
+
// $Id: ruby-stemmer.c 17 2008-01-07 16:59:10Z aurelian $
|
3
|
+
//
|
4
|
+
|
5
|
+
#include "ruby.h"
|
6
|
+
#include <libstemmer.h>
|
7
|
+
|
8
|
+
#define GetStemmer(obj, sb_data) {\
|
9
|
+
Data_Get_Struct(obj, struct sb_stemmer_data, sb_data);\
|
10
|
+
}
|
11
|
+
|
12
|
+
VALUE rb_mLingua;
|
13
|
+
VALUE rb_cStemmer;
|
14
|
+
|
15
|
+
struct sb_stemmer_data {
|
16
|
+
struct sb_stemmer * stemmer;
|
17
|
+
const char * lang;
|
18
|
+
const char * enc;
|
19
|
+
};
|
20
|
+
|
21
|
+
static VALUE
|
22
|
+
rb_stemmer_init(int argc, VALUE *argv, VALUE self) {
|
23
|
+
VALUE roptions, rlang, renc;
|
24
|
+
|
25
|
+
struct sb_stemmer * stemmer;
|
26
|
+
struct sb_stemmer_data *sb_data;
|
27
|
+
|
28
|
+
rb_scan_args(argc, argv, "01", &roptions);
|
29
|
+
|
30
|
+
if(argc > 0) {
|
31
|
+
Check_Type(roptions, T_HASH);
|
32
|
+
if((rlang = rb_hash_aref(roptions, ID2SYM(rb_intern("language")))) != Qnil) {
|
33
|
+
Check_Type(rlang, T_STRING);
|
34
|
+
} else {
|
35
|
+
rlang = rb_str_new2("en");
|
36
|
+
}
|
37
|
+
if((renc = rb_hash_aref(roptions, ID2SYM(rb_intern("encoding")))) != Qnil) {
|
38
|
+
Check_Type(renc, T_STRING);
|
39
|
+
} else {
|
40
|
+
renc = rb_str_new2("UTF_8");
|
41
|
+
}
|
42
|
+
} else {
|
43
|
+
rlang = rb_str_new2("en");
|
44
|
+
renc = rb_str_new2("UTF_8");
|
45
|
+
}
|
46
|
+
|
47
|
+
stemmer = sb_stemmer_new( RSTRING(rlang)->ptr, RSTRING(renc)->ptr );
|
48
|
+
if (stemmer == 0) {
|
49
|
+
printf(">>[libstemmer]: got a null stemmer!\n");
|
50
|
+
if (renc == 0 ) {
|
51
|
+
rb_raise(rb_eRuntimeError, "Language %s not available for stemming", RSTRING(rlang)->ptr);
|
52
|
+
exit(1);
|
53
|
+
} else {
|
54
|
+
rb_raise(rb_eRuntimeError, "Language %s not available for stemming in encoding",
|
55
|
+
RSTRING(rlang)->ptr, RSTRING(renc)->ptr);
|
56
|
+
exit(1);
|
57
|
+
}
|
58
|
+
}
|
59
|
+
|
60
|
+
sb_data = ALLOC(struct sb_stemmer_data);
|
61
|
+
DATA_PTR(self) = sb_data;
|
62
|
+
sb_data->stemmer= stemmer;
|
63
|
+
sb_data->lang = RSTRING(rlang)->ptr;
|
64
|
+
sb_data->enc = RSTRING(renc)->ptr;
|
65
|
+
|
66
|
+
return self;
|
67
|
+
}
|
68
|
+
|
69
|
+
static VALUE
|
70
|
+
rb_stemmer_stem(VALUE self, VALUE word) {
|
71
|
+
struct sb_stemmer_data * sb_data;
|
72
|
+
const sb_symbol * stemmed;
|
73
|
+
GetStemmer(self, sb_data);
|
74
|
+
stemmed = sb_stemmer_stem(sb_data->stemmer, (sb_symbol *)RSTRING(word)->ptr, RSTRING(word)->len);
|
75
|
+
/* printf(">>[libstemmer %s/%s]: %s-> %s\n", sb_data->lang, sb_data->enc, RSTRING(word)->ptr, stemmed); */
|
76
|
+
return rb_str_new2((char *)stemmed);
|
77
|
+
}
|
78
|
+
|
79
|
+
static VALUE
|
80
|
+
rb_stemmer_length(VALUE self) {
|
81
|
+
struct sb_stemmer_data * sb_data;
|
82
|
+
int length;
|
83
|
+
GetStemmer(self, sb_data);
|
84
|
+
length = sb_stemmer_length(sb_data->stemmer);
|
85
|
+
return INT2FIX(length);
|
86
|
+
}
|
87
|
+
|
88
|
+
static void
|
89
|
+
sb_stemmer_free(struct sb_stemmer_data * sb_data)
|
90
|
+
{
|
91
|
+
sb_stemmer_delete(sb_data->stemmer);
|
92
|
+
}
|
93
|
+
|
94
|
+
static VALUE
|
95
|
+
sb_stemmer_alloc(VALUE klass)
|
96
|
+
{
|
97
|
+
return Data_Wrap_Struct(klass, 0, sb_stemmer_free, 0);
|
98
|
+
}
|
99
|
+
|
100
|
+
void Init_stemmer() {
|
101
|
+
rb_mLingua = rb_define_module("Lingua");
|
102
|
+
rb_cStemmer = rb_define_class_under(rb_mLingua, "Stemmer", rb_cObject);
|
103
|
+
rb_define_alloc_func(rb_cStemmer, sb_stemmer_alloc);
|
104
|
+
rb_define_method(rb_cStemmer, "initialize", rb_stemmer_init, -1);
|
105
|
+
rb_define_method(rb_cStemmer, "stem", rb_stemmer_stem, 1);
|
106
|
+
rb_define_method(rb_cStemmer, "length", rb_stemmer_length, 0);
|
107
|
+
}
|
108
|
+
|
data/test.rb
ADDED
@@ -0,0 +1,31 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
#
|
4
|
+
# $Id: test.rb 15 2008-01-05 11:56:57Z aurelian $
|
5
|
+
#
|
6
|
+
|
7
|
+
$kcode = "utf-8"
|
8
|
+
|
9
|
+
require "stemmer"
|
10
|
+
|
11
|
+
# puts ">>> test 1."
|
12
|
+
stemmer = Lingua::Stemmer.new()
|
13
|
+
puts stemmer.stem("installation")
|
14
|
+
puts stemmer.length
|
15
|
+
puts stemmer.stem("popularity")
|
16
|
+
|
17
|
+
puts ">>> test 2."
|
18
|
+
stemmer = Lingua::Stemmer.new(:language => 'en')
|
19
|
+
puts stemmer.stem("obnoxious")
|
20
|
+
|
21
|
+
puts ">>> test 3."
|
22
|
+
stemmer = Lingua::Stemmer.new(:encoding => 'UTF_8')
|
23
|
+
puts stemmer.stem("găinațul")
|
24
|
+
|
25
|
+
puts ">>> test 4."
|
26
|
+
stemmer = Lingua::Stemmer.new(:language => 'en', :encoding => 'UTF_8')
|
27
|
+
puts stemmer.stem("personalities")
|
28
|
+
|
29
|
+
puts ">>> test 5."
|
30
|
+
stemmer = Lingua::Stemmer.new(:encoding => 'UTF_8', :language => 'ro')
|
31
|
+
puts stemmer.stem("întrebător");
|
metadata
ADDED
@@ -0,0 +1,141 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: ruby-stemmer
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Aurelian Oancea
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
|
12
|
+
date: 2008-01-07 00:00:00 +02:00
|
13
|
+
default_executable:
|
14
|
+
dependencies: []
|
15
|
+
|
16
|
+
description: Stemmer implementation to ruby using libstemmer_c.
|
17
|
+
email: aurelian@locknet.ro
|
18
|
+
executables: []
|
19
|
+
|
20
|
+
extensions:
|
21
|
+
- extconf.rb
|
22
|
+
extra_rdoc_files: []
|
23
|
+
|
24
|
+
files:
|
25
|
+
- extconf.rb
|
26
|
+
- ruby-stemmer.c
|
27
|
+
- test.rb
|
28
|
+
- MIT-LICENSE
|
29
|
+
- Rakefile
|
30
|
+
- README
|
31
|
+
- libstemmer_c/examples
|
32
|
+
- libstemmer_c/include
|
33
|
+
- libstemmer_c/include/libstemmer.h
|
34
|
+
- libstemmer_c/libstemmer
|
35
|
+
- libstemmer_c/libstemmer/libstemmer.c
|
36
|
+
- libstemmer_c/libstemmer/libstemmer_utf8.c
|
37
|
+
- libstemmer_c/libstemmer/modules.h
|
38
|
+
- libstemmer_c/libstemmer/modules.txt
|
39
|
+
- libstemmer_c/libstemmer/modules_utf8.h
|
40
|
+
- libstemmer_c/libstemmer/modules_utf8.txt
|
41
|
+
- libstemmer_c/Makefile
|
42
|
+
- libstemmer_c/MANIFEST
|
43
|
+
- libstemmer_c/mkinc.mak
|
44
|
+
- libstemmer_c/mkinc_utf8.mak
|
45
|
+
- libstemmer_c/README
|
46
|
+
- libstemmer_c/runtime
|
47
|
+
- libstemmer_c/runtime/api.c
|
48
|
+
- libstemmer_c/runtime/api.h
|
49
|
+
- libstemmer_c/runtime/header.h
|
50
|
+
- libstemmer_c/runtime/utilities.c
|
51
|
+
- libstemmer_c/src_c
|
52
|
+
- libstemmer_c/src_c/stem_ISO_8859_1_danish.c
|
53
|
+
- libstemmer_c/src_c/stem_ISO_8859_1_danish.h
|
54
|
+
- libstemmer_c/src_c/stem_ISO_8859_1_dutch.c
|
55
|
+
- libstemmer_c/src_c/stem_ISO_8859_1_dutch.h
|
56
|
+
- libstemmer_c/src_c/stem_ISO_8859_1_english.c
|
57
|
+
- libstemmer_c/src_c/stem_ISO_8859_1_english.h
|
58
|
+
- libstemmer_c/src_c/stem_ISO_8859_1_finnish.c
|
59
|
+
- libstemmer_c/src_c/stem_ISO_8859_1_finnish.h
|
60
|
+
- libstemmer_c/src_c/stem_ISO_8859_1_french.c
|
61
|
+
- libstemmer_c/src_c/stem_ISO_8859_1_french.h
|
62
|
+
- libstemmer_c/src_c/stem_ISO_8859_1_german.c
|
63
|
+
- libstemmer_c/src_c/stem_ISO_8859_1_german.h
|
64
|
+
- libstemmer_c/src_c/stem_ISO_8859_1_hungarian.c
|
65
|
+
- libstemmer_c/src_c/stem_ISO_8859_1_hungarian.h
|
66
|
+
- libstemmer_c/src_c/stem_ISO_8859_1_italian.c
|
67
|
+
- libstemmer_c/src_c/stem_ISO_8859_1_italian.h
|
68
|
+
- libstemmer_c/src_c/stem_ISO_8859_1_norwegian.c
|
69
|
+
- libstemmer_c/src_c/stem_ISO_8859_1_norwegian.h
|
70
|
+
- libstemmer_c/src_c/stem_ISO_8859_1_porter.c
|
71
|
+
- libstemmer_c/src_c/stem_ISO_8859_1_porter.h
|
72
|
+
- libstemmer_c/src_c/stem_ISO_8859_1_portuguese.c
|
73
|
+
- libstemmer_c/src_c/stem_ISO_8859_1_portuguese.h
|
74
|
+
- libstemmer_c/src_c/stem_ISO_8859_1_spanish.c
|
75
|
+
- libstemmer_c/src_c/stem_ISO_8859_1_spanish.h
|
76
|
+
- libstemmer_c/src_c/stem_ISO_8859_1_swedish.c
|
77
|
+
- libstemmer_c/src_c/stem_ISO_8859_1_swedish.h
|
78
|
+
- libstemmer_c/src_c/stem_ISO_8859_2_romanian.c
|
79
|
+
- libstemmer_c/src_c/stem_ISO_8859_2_romanian.h
|
80
|
+
- libstemmer_c/src_c/stem_KOI8_R_russian.c
|
81
|
+
- libstemmer_c/src_c/stem_KOI8_R_russian.h
|
82
|
+
- libstemmer_c/src_c/stem_UTF_8_danish.c
|
83
|
+
- libstemmer_c/src_c/stem_UTF_8_danish.h
|
84
|
+
- libstemmer_c/src_c/stem_UTF_8_dutch.c
|
85
|
+
- libstemmer_c/src_c/stem_UTF_8_dutch.h
|
86
|
+
- libstemmer_c/src_c/stem_UTF_8_english.c
|
87
|
+
- libstemmer_c/src_c/stem_UTF_8_english.h
|
88
|
+
- libstemmer_c/src_c/stem_UTF_8_finnish.c
|
89
|
+
- libstemmer_c/src_c/stem_UTF_8_finnish.h
|
90
|
+
- libstemmer_c/src_c/stem_UTF_8_french.c
|
91
|
+
- libstemmer_c/src_c/stem_UTF_8_french.h
|
92
|
+
- libstemmer_c/src_c/stem_UTF_8_german.c
|
93
|
+
- libstemmer_c/src_c/stem_UTF_8_german.h
|
94
|
+
- libstemmer_c/src_c/stem_UTF_8_hungarian.c
|
95
|
+
- libstemmer_c/src_c/stem_UTF_8_hungarian.h
|
96
|
+
- libstemmer_c/src_c/stem_UTF_8_italian.c
|
97
|
+
- libstemmer_c/src_c/stem_UTF_8_italian.h
|
98
|
+
- libstemmer_c/src_c/stem_UTF_8_norwegian.c
|
99
|
+
- libstemmer_c/src_c/stem_UTF_8_norwegian.h
|
100
|
+
- libstemmer_c/src_c/stem_UTF_8_porter.c
|
101
|
+
- libstemmer_c/src_c/stem_UTF_8_porter.h
|
102
|
+
- libstemmer_c/src_c/stem_UTF_8_portuguese.c
|
103
|
+
- libstemmer_c/src_c/stem_UTF_8_portuguese.h
|
104
|
+
- libstemmer_c/src_c/stem_UTF_8_romanian.c
|
105
|
+
- libstemmer_c/src_c/stem_UTF_8_romanian.h
|
106
|
+
- libstemmer_c/src_c/stem_UTF_8_russian.c
|
107
|
+
- libstemmer_c/src_c/stem_UTF_8_russian.h
|
108
|
+
- libstemmer_c/src_c/stem_UTF_8_spanish.c
|
109
|
+
- libstemmer_c/src_c/stem_UTF_8_spanish.h
|
110
|
+
- libstemmer_c/src_c/stem_UTF_8_swedish.c
|
111
|
+
- libstemmer_c/src_c/stem_UTF_8_swedish.h
|
112
|
+
- libstemmer_c/src_c/stem_UTF_8_turkish.c
|
113
|
+
- libstemmer_c/src_c/stem_UTF_8_turkish.h
|
114
|
+
has_rdoc: false
|
115
|
+
homepage: http://nrr.rubyforge.org
|
116
|
+
post_install_message:
|
117
|
+
rdoc_options: []
|
118
|
+
|
119
|
+
require_paths:
|
120
|
+
- lib
|
121
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
122
|
+
requirements:
|
123
|
+
- - ">="
|
124
|
+
- !ruby/object:Gem::Version
|
125
|
+
version: "0"
|
126
|
+
version:
|
127
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
128
|
+
requirements:
|
129
|
+
- - ">="
|
130
|
+
- !ruby/object:Gem::Version
|
131
|
+
version: "0"
|
132
|
+
version:
|
133
|
+
requirements: []
|
134
|
+
|
135
|
+
rubyforge_project: nrr
|
136
|
+
rubygems_version: 1.0.1
|
137
|
+
signing_key:
|
138
|
+
specification_version: 2
|
139
|
+
summary: Stemmer implementation to ruby using libstemmer_c.
|
140
|
+
test_files: []
|
141
|
+
|