ruby-stemmer 0.5.1 → 0.5.3

data/Manifest

@@ -0,0 +1,86 @@
+extconf.rb
+libstemmer_c/examples/stemwords.c
+libstemmer_c/include/libstemmer.h
+libstemmer_c/libstemmer/libstemmer.c
+libstemmer_c/libstemmer/libstemmer_utf8.c
+libstemmer_c/libstemmer/modules.h
+libstemmer_c/libstemmer/modules.txt
+libstemmer_c/libstemmer/modules_utf8.h
+libstemmer_c/libstemmer/modules_utf8.txt
+libstemmer_c/Makefile
+libstemmer_c/MANIFEST
+libstemmer_c/mkinc.mak
+libstemmer_c/mkinc_utf8.mak
+libstemmer_c/README
+libstemmer_c/runtime/api.c
+libstemmer_c/runtime/api.h
+libstemmer_c/runtime/header.h
+libstemmer_c/runtime/utilities.c
+libstemmer_c/src_c/stem_ISO_8859_1_danish.c
+libstemmer_c/src_c/stem_ISO_8859_1_danish.h
+libstemmer_c/src_c/stem_ISO_8859_1_dutch.c
+libstemmer_c/src_c/stem_ISO_8859_1_dutch.h
+libstemmer_c/src_c/stem_ISO_8859_1_english.c
+libstemmer_c/src_c/stem_ISO_8859_1_english.h
+libstemmer_c/src_c/stem_ISO_8859_1_finnish.c
+libstemmer_c/src_c/stem_ISO_8859_1_finnish.h
+libstemmer_c/src_c/stem_ISO_8859_1_french.c
+libstemmer_c/src_c/stem_ISO_8859_1_french.h
+libstemmer_c/src_c/stem_ISO_8859_1_german.c
+libstemmer_c/src_c/stem_ISO_8859_1_german.h
+libstemmer_c/src_c/stem_ISO_8859_1_hungarian.c
+libstemmer_c/src_c/stem_ISO_8859_1_hungarian.h
+libstemmer_c/src_c/stem_ISO_8859_1_italian.c
+libstemmer_c/src_c/stem_ISO_8859_1_italian.h
+libstemmer_c/src_c/stem_ISO_8859_1_norwegian.c
+libstemmer_c/src_c/stem_ISO_8859_1_norwegian.h
+libstemmer_c/src_c/stem_ISO_8859_1_porter.c
+libstemmer_c/src_c/stem_ISO_8859_1_porter.h
+libstemmer_c/src_c/stem_ISO_8859_1_portuguese.c
+libstemmer_c/src_c/stem_ISO_8859_1_portuguese.h
+libstemmer_c/src_c/stem_ISO_8859_1_spanish.c
+libstemmer_c/src_c/stem_ISO_8859_1_spanish.h
+libstemmer_c/src_c/stem_ISO_8859_1_swedish.c
+libstemmer_c/src_c/stem_ISO_8859_1_swedish.h
+libstemmer_c/src_c/stem_ISO_8859_2_romanian.c
+libstemmer_c/src_c/stem_ISO_8859_2_romanian.h
+libstemmer_c/src_c/stem_KOI8_R_russian.c
+libstemmer_c/src_c/stem_KOI8_R_russian.h
+libstemmer_c/src_c/stem_UTF_8_danish.c
+libstemmer_c/src_c/stem_UTF_8_danish.h
+libstemmer_c/src_c/stem_UTF_8_dutch.c
+libstemmer_c/src_c/stem_UTF_8_dutch.h
+libstemmer_c/src_c/stem_UTF_8_english.c
+libstemmer_c/src_c/stem_UTF_8_english.h
+libstemmer_c/src_c/stem_UTF_8_finnish.c
+libstemmer_c/src_c/stem_UTF_8_finnish.h
+libstemmer_c/src_c/stem_UTF_8_french.c
+libstemmer_c/src_c/stem_UTF_8_french.h
+libstemmer_c/src_c/stem_UTF_8_german.c
+libstemmer_c/src_c/stem_UTF_8_german.h
+libstemmer_c/src_c/stem_UTF_8_hungarian.c
+libstemmer_c/src_c/stem_UTF_8_hungarian.h
+libstemmer_c/src_c/stem_UTF_8_italian.c
+libstemmer_c/src_c/stem_UTF_8_italian.h
+libstemmer_c/src_c/stem_UTF_8_norwegian.c
+libstemmer_c/src_c/stem_UTF_8_norwegian.h
+libstemmer_c/src_c/stem_UTF_8_porter.c
+libstemmer_c/src_c/stem_UTF_8_porter.h
+libstemmer_c/src_c/stem_UTF_8_portuguese.c
+libstemmer_c/src_c/stem_UTF_8_portuguese.h
+libstemmer_c/src_c/stem_UTF_8_romanian.c
+libstemmer_c/src_c/stem_UTF_8_romanian.h
+libstemmer_c/src_c/stem_UTF_8_russian.c
+libstemmer_c/src_c/stem_UTF_8_russian.h
+libstemmer_c/src_c/stem_UTF_8_spanish.c
+libstemmer_c/src_c/stem_UTF_8_spanish.h
+libstemmer_c/src_c/stem_UTF_8_swedish.c
+libstemmer_c/src_c/stem_UTF_8_swedish.h
+libstemmer_c/src_c/stem_UTF_8_turkish.c
+libstemmer_c/src_c/stem_UTF_8_turkish.h
+MIT-LICENSE
+Rakefile
+README
+ruby-stemmer.c
+test.rb
+Manifest

data/Rakefile

@@ -4,7 +4,19 @@
 
 require 'rubygems'
 require 'rake'
-require 'rake/gempackagetask'
+require 'echoe'
+
+Echoe.new('ruby-stemmer', '0.5.3') do |p|
+    p.description    = "Stemmer implementation to ruby using libstemmer_c. Working with ruby 1.9.1"
+    p.url            = "http://github.com/yury/ruby-stemmer"
+    p.author         = "Yury Korolev"
+    p.email          = "yury.korolev@gmail.com"
+    p.extensions     = ["extconf.rb"]
+    p.ignore_pattern = ["*.o", "**/*.o", "stemwords", "*.bundle", "*.a", "*.so"]
+    p.development_dependencies = []
+    p.runtime_dependencies = []
+    p.has_rdoc = true
+end
 
 rm_rf 'Makefile'
 
@@ -23,35 +35,6 @@ PKG_FILES.exclude('*.bundle')
 PKG_FILES.exclude('*.a')
 PKG_FILES.exclude('*.so')
 
-spec = Gem::Specification.new do | s |
-  s.name = 'ruby-stemmer'
-  s.version = '0.5.1'
-  s.summary = "Stemmer implementation to ruby using SnowBall API from libstemmer_c."
-  s.description = <<-EOF
-    Stemmer implementation to ruby using libstemmer_c.
-  EOF
-
-  s.files = PKG_FILES.to_a
-  s.extensions << "extconf.rb"
-  s.has_rdoc = true
-  s.rdoc_options << '--title' <<  'Ruby-Stemmer' << 
-    '--exclude' << 'libstemmer_c' << '--exclude' << 'extconf.rb' <<
-    '--exclude' << 'test.rb' << '--inline-source' << 'ruby-stemmer.c' << 'README' << '--main' << 'README'
-  s.author = "Aurelian Oancea"
-  s.email = "aurelian@locknet.ro"
-  s.homepage = "http://nrr.rubyforge.org"
-  s.rubyforge_project = "nrr"
-end
-
-pt = Rake::GemPackageTask.new(spec) do |p|
-  p.need_tar = true
-  p.need_zip = true
-end
-
-task :default do
-  puts "Ok"
-end
-
 task :clean do
   `rm -rf Makefile mkmf.log ruby-stemmer.o stemmer.bundle stemmer.so`
   `cd libstemmer_c && make clean && cd ../`

data/libstemmer_c/examples/stemwords.c

@@ -0,0 +1,209 @@
+/* This is a simple program which uses libstemmer to provide a command
+ * line interface for stemming using any of the algorithms provided.
+ */
+
+#include <stdio.h>
+#include <stdlib.h> /* for malloc, free */
+#include <string.h> /* for memmove */
+#include <ctype.h>  /* for isupper, tolower */
+
+#include "libstemmer.h"
+
+const char * progname;
+static int pretty = 1;
+
+static void
+stem_file(struct sb_stemmer * stemmer, FILE * f_in, FILE * f_out)
+{
+#define INC 10
+    int lim = INC;
+    sb_symbol * b = (sb_symbol *) malloc(lim * sizeof(sb_symbol));
+
+    while(1) {
+        int ch = getc(f_in);
+        if (ch == EOF) {
+            free(b); return;
+        }
+        {
+            int i = 0;
+	    int inlen = 0;
+            while(1) {
+                if (ch == '\n' || ch == EOF) break;
+                if (i == lim) {
+                    sb_symbol * newb;
+		    newb = (sb_symbol *)
+			    realloc(b, (lim + INC) * sizeof(sb_symbol));
+		    if (newb == 0) goto error;
+		    b = newb;
+                    lim = lim + INC;
+                }
+		/* Update count of utf-8 characters. */
+		if (ch < 0x80 || ch > 0xBF) inlen += 1;
+                /* force lower case: */
+                if (isupper(ch)) ch = tolower(ch);
+
+                b[i] = ch;
+		i++;
+                ch = getc(f_in);
+            }
+
+	    {
+		const sb_symbol * stemmed = sb_stemmer_stem(stemmer, b, i);
+                if (stemmed == NULL)
+                {
+                    fprintf(stderr, "Out of memory");
+                    exit(1);
+                }
+                else
+		{
+		    if (pretty == 1) {
+			fwrite(b, i, 1, f_out);
+			fputs(" -> ", f_out);
+		    } else if (pretty == 2) {
+			fwrite(b, i, 1, f_out);
+			if (sb_stemmer_length(stemmer) > 0) {
+			    int j;
+			    if (inlen < 30) {
+				for (j = 30 - inlen; j > 0; j--)
+				    fputs(" ", f_out);
+			    } else {
+				fputs("\n", f_out);
+				for (j = 30; j > 0; j--)
+				    fputs(" ", f_out);
+			    }
+			}
+		    }
+
+		    fputs((char *)stemmed, f_out);
+		    putc('\n', f_out);
+		}
+            }
+        }
+    }
+error:
+    if (b != 0) free(b);
+    return;
+}
+
+/** Display the command line syntax, and then exit.
+ *  @param n The value to exit with.
+ */
+static void
+usage(int n)
+{
+    printf("usage: %s [-l <language>] [-i <input file>] [-o <output file>] [-c <character encoding>] [-p[2]] [-h]\n"
+	  "\n"
+	  "The input file consists of a list of words to be stemmed, one per\n"
+	  "line. Words should be in lower case, but (for English) A-Z letters\n"
+	  "are mapped to their a-z equivalents anyway. If omitted, stdin is\n"
+	  "used.\n"
+	  "\n"
+	  "If -c is given, the argument is the character encoding of the input\n"
+          "and output files.  If it is omitted, the UTF-8 encoding is used.\n"
+	  "\n"
+	  "If -p is given the output file consists of each word of the input\n"
+	  "file followed by \"->\" followed by its stemmed equivalent.\n"
+	  "If -p2 is given the output file is a two column layout containing\n"
+	  "the input words in the first column and the stemmed eqivalents in\n"
+	  "the second column.\n"
+	  "Otherwise, the output file consists of the stemmed words, one per\n"
+	  "line.\n"
+	  "\n"
+	  "-h displays this help\n",
+	  progname);
+    exit(n);
+}
+
+int
+main(int argc, char * argv[])
+{
+    char * in = 0;
+    char * out = 0;
+    FILE * f_in;
+    FILE * f_out;
+    struct sb_stemmer * stemmer;
+
+    char * language = "english";
+    char * charenc = NULL;
+
+    char * s;
+    int i = 1;
+    pretty = 0;
+
+    progname = argv[0];
+
+    while(i < argc) {
+	s = argv[i++];
+	if (s[0] == '-') {
+	    if (strcmp(s, "-o") == 0) {
+		if (i >= argc) {
+		    fprintf(stderr, "%s requires an argument\n", s);
+		    exit(1);
+		}
+		out = argv[i++];
+	    } else if (strcmp(s, "-i") == 0) {
+		if (i >= argc) {
+		    fprintf(stderr, "%s requires an argument\n", s);
+		    exit(1);
+		}
+		in = argv[i++];
+	    } else if (strcmp(s, "-l") == 0) {
+		if (i >= argc) {
+		    fprintf(stderr, "%s requires an argument\n", s);
+		    exit(1);
+		}
+		language = argv[i++];
+	    } else if (strcmp(s, "-c") == 0) {
+		if (i >= argc) {
+		    fprintf(stderr, "%s requires an argument\n", s);
+		    exit(1);
+		}
+		charenc = argv[i++];
+	    } else if (strcmp(s, "-p2") == 0) {
+		pretty = 2;
+	    } else if (strcmp(s, "-p") == 0) {
+		pretty = 1;
+	    } else if (strcmp(s, "-h") == 0) {
+		usage(0);
+	    } else {
+		fprintf(stderr, "option %s unknown\n", s);
+		usage(1);
+	    }
+	} else {
+	    fprintf(stderr, "unexpected parameter %s\n", s);
+	    usage(1);
+	}
+    }
+
+    /* prepare the files */
+    f_in = (in == 0) ? stdin : fopen(in, "r");
+    if (f_in == 0) {
+	fprintf(stderr, "file %s not found\n", in);
+	exit(1);
+    }
+    f_out = (out == 0) ? stdout : fopen(out, "w");
+    if (f_out == 0) {
+	fprintf(stderr, "file %s cannot be opened\n", out);
+	exit(1);
+    }
+
+    /* do the stemming process: */
+    stemmer = sb_stemmer_new(language, charenc);
+    if (stemmer == 0) {
+        if (charenc == NULL) {
+            fprintf(stderr, "language `%s' not available for stemming\n", language);
+            exit(1);
+        } else {
+            fprintf(stderr, "language `%s' not available for stemming in encoding `%s'\n", language, charenc);
+            exit(1);
+        }
+    }
+    stem_file(stemmer, f_in, f_out);
+    sb_stemmer_delete(stemmer);
+
+    if (in != 0) (void) fclose(f_in);
+    if (out != 0) (void) fclose(f_out);
+
+    return 0;
+}
+

data/ruby-stemmer.c

@@ -54,15 +54,15 @@ rb_stemmer_init(int argc, VALUE *argv, VALUE self) {
     renc  = rb_str_new2("UTF_8");
   }
   
-  stemmer = sb_stemmer_new( RSTRING(rlang)->ptr, RSTRING(renc)->ptr );
+  stemmer = sb_stemmer_new( RSTRING_PTR(rlang), RSTRING_PTR(renc) );
   if (stemmer == 0) {
     // printf(">>[libstemmer]: got a null stemmer!\n");
     if (renc == 0 ) {
-      rb_raise(rb_eRuntimeError, "Language %s not available for stemming", RSTRING(rlang)->ptr);
+      rb_raise(rb_eRuntimeError, "Language %s not available for stemming", RSTRING_PTR(rlang));
       exit(1);
     } else {
       rb_raise(rb_eRuntimeError, "Language %s not available for stemming in encoding %s", 
-                    RSTRING(rlang)->ptr, RSTRING(renc)->ptr);
+                    RSTRING_PTR(rlang), RSTRING_PTR(renc));
       exit(1);
     }
   }
@@ -70,8 +70,8 @@ rb_stemmer_init(int argc, VALUE *argv, VALUE self) {
   sb_data = ALLOC(struct sb_stemmer_data);
   DATA_PTR(self) = sb_data;
   sb_data->stemmer= stemmer;
-  sb_data->lang   = RSTRING(rlang)->ptr;
-  sb_data->enc    = RSTRING(renc)->ptr;
+  sb_data->lang   = RSTRING_PTR(rlang);
+  sb_data->enc    = RSTRING_PTR(renc);
 
   return self;
 }
@@ -91,8 +91,8 @@ rb_stemmer_stem(VALUE self, VALUE word) {
   struct sb_stemmer_data * sb_data;
   const  sb_symbol * stemmed;
   GetStemmer(self, sb_data);
-  stemmed = sb_stemmer_stem(sb_data->stemmer, (sb_symbol *)RSTRING(word)->ptr, RSTRING(word)->len);
-  // printf(">>[libstemmer %s/%s]: %s-> %s\n", sb_data->lang, sb_data->enc, RSTRING(word)->ptr, stemmed);
+  stemmed = sb_stemmer_stem(sb_data->stemmer, (sb_symbol *)RSTRING_PTR(word), RSTRING_LEN(word));
+  // printf(">>[libstemmer %s/%s]: %s-> %s\n", sb_data->lang, sb_data->enc, RSTRING_PTR(word), stemmed);
   return rb_str_new2((char *)stemmed);
 }
 

data/ruby-stemmer.gemspec

@@ -0,0 +1,32 @@
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = %q{ruby-stemmer}
+  s.version = "0.5.3"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 1.2") if s.respond_to? :required_rubygems_version=
+  s.authors = ["Yury Korolev"]
+  s.date = %q{2009-02-10}
+  s.description = %q{Stemmer implementation to ruby using libstemmer_c. Working with ruby 1.9.1}
+  s.email = %q{yury.korolev@gmail.com}
+  s.extensions = ["extconf.rb"]
+  s.extra_rdoc_files = ["extconf.rb", "libstemmer_c/examples/stemwords.c", "libstemmer_c/include/libstemmer.h", "libstemmer_c/libstemmer/libstemmer.c", "libstemmer_c/libstemmer/libstemmer_utf8.c", "libstemmer_c/libstemmer/modules.h", "libstemmer_c/libstemmer/modules.txt", "libstemmer_c/libstemmer/modules_utf8.h", "libstemmer_c/libstemmer/modules_utf8.txt", "libstemmer_c/Makefile", "libstemmer_c/MANIFEST", "libstemmer_c/mkinc.mak", "libstemmer_c/mkinc_utf8.mak", "libstemmer_c/README", "libstemmer_c/runtime/api.c", "libstemmer_c/runtime/api.h", "libstemmer_c/runtime/header.h", "libstemmer_c/runtime/utilities.c", "libstemmer_c/src_c/stem_ISO_8859_1_danish.c", "libstemmer_c/src_c/stem_ISO_8859_1_danish.h", "libstemmer_c/src_c/stem_ISO_8859_1_dutch.c", "libstemmer_c/src_c/stem_ISO_8859_1_dutch.h", "libstemmer_c/src_c/stem_ISO_8859_1_english.c", "libstemmer_c/src_c/stem_ISO_8859_1_english.h", "libstemmer_c/src_c/stem_ISO_8859_1_finnish.c", "libstemmer_c/src_c/stem_ISO_8859_1_finnish.h", "libstemmer_c/src_c/stem_ISO_8859_1_french.c", "libstemmer_c/src_c/stem_ISO_8859_1_french.h", "libstemmer_c/src_c/stem_ISO_8859_1_german.c", "libstemmer_c/src_c/stem_ISO_8859_1_german.h", "libstemmer_c/src_c/stem_ISO_8859_1_hungarian.c", "libstemmer_c/src_c/stem_ISO_8859_1_hungarian.h", "libstemmer_c/src_c/stem_ISO_8859_1_italian.c", "libstemmer_c/src_c/stem_ISO_8859_1_italian.h", "libstemmer_c/src_c/stem_ISO_8859_1_norwegian.c", "libstemmer_c/src_c/stem_ISO_8859_1_norwegian.h", "libstemmer_c/src_c/stem_ISO_8859_1_porter.c", "libstemmer_c/src_c/stem_ISO_8859_1_porter.h", "libstemmer_c/src_c/stem_ISO_8859_1_portuguese.c", "libstemmer_c/src_c/stem_ISO_8859_1_portuguese.h", "libstemmer_c/src_c/stem_ISO_8859_1_spanish.c", "libstemmer_c/src_c/stem_ISO_8859_1_spanish.h", "libstemmer_c/src_c/stem_ISO_8859_1_swedish.c", "libstemmer_c/src_c/stem_ISO_8859_1_swedish.h", "libstemmer_c/src_c/stem_ISO_8859_2_romanian.c", "libstemmer_c/src_c/stem_ISO_8859_2_romanian.h", "libstemmer_c/src_c/stem_KOI8_R_russian.c", "libstemmer_c/src_c/stem_KOI8_R_russian.h", "libstemmer_c/src_c/stem_UTF_8_danish.c", "libstemmer_c/src_c/stem_UTF_8_danish.h", "libstemmer_c/src_c/stem_UTF_8_dutch.c", "libstemmer_c/src_c/stem_UTF_8_dutch.h", "libstemmer_c/src_c/stem_UTF_8_english.c", "libstemmer_c/src_c/stem_UTF_8_english.h", "libstemmer_c/src_c/stem_UTF_8_finnish.c", "libstemmer_c/src_c/stem_UTF_8_finnish.h", "libstemmer_c/src_c/stem_UTF_8_french.c", "libstemmer_c/src_c/stem_UTF_8_french.h", "libstemmer_c/src_c/stem_UTF_8_german.c", "libstemmer_c/src_c/stem_UTF_8_german.h", "libstemmer_c/src_c/stem_UTF_8_hungarian.c", "libstemmer_c/src_c/stem_UTF_8_hungarian.h", "libstemmer_c/src_c/stem_UTF_8_italian.c", "libstemmer_c/src_c/stem_UTF_8_italian.h", "libstemmer_c/src_c/stem_UTF_8_norwegian.c", "libstemmer_c/src_c/stem_UTF_8_norwegian.h", "libstemmer_c/src_c/stem_UTF_8_porter.c", "libstemmer_c/src_c/stem_UTF_8_porter.h", "libstemmer_c/src_c/stem_UTF_8_portuguese.c", "libstemmer_c/src_c/stem_UTF_8_portuguese.h", "libstemmer_c/src_c/stem_UTF_8_romanian.c", "libstemmer_c/src_c/stem_UTF_8_romanian.h", "libstemmer_c/src_c/stem_UTF_8_russian.c", "libstemmer_c/src_c/stem_UTF_8_russian.h", "libstemmer_c/src_c/stem_UTF_8_spanish.c", "libstemmer_c/src_c/stem_UTF_8_spanish.h", "libstemmer_c/src_c/stem_UTF_8_swedish.c", "libstemmer_c/src_c/stem_UTF_8_swedish.h", "libstemmer_c/src_c/stem_UTF_8_turkish.c", "libstemmer_c/src_c/stem_UTF_8_turkish.h", "README"]
+  s.files = ["extconf.rb", "libstemmer_c/examples/stemwords.c", "libstemmer_c/include/libstemmer.h", "libstemmer_c/libstemmer/libstemmer.c", "libstemmer_c/libstemmer/libstemmer_utf8.c", "libstemmer_c/libstemmer/modules.h", "libstemmer_c/libstemmer/modules.txt", "libstemmer_c/libstemmer/modules_utf8.h", "libstemmer_c/libstemmer/modules_utf8.txt", "libstemmer_c/Makefile", "libstemmer_c/MANIFEST", "libstemmer_c/mkinc.mak", "libstemmer_c/mkinc_utf8.mak", "libstemmer_c/README", "libstemmer_c/runtime/api.c", "libstemmer_c/runtime/api.h", "libstemmer_c/runtime/header.h", "libstemmer_c/runtime/utilities.c", "libstemmer_c/src_c/stem_ISO_8859_1_danish.c", "libstemmer_c/src_c/stem_ISO_8859_1_danish.h", "libstemmer_c/src_c/stem_ISO_8859_1_dutch.c", "libstemmer_c/src_c/stem_ISO_8859_1_dutch.h", "libstemmer_c/src_c/stem_ISO_8859_1_english.c", "libstemmer_c/src_c/stem_ISO_8859_1_english.h", "libstemmer_c/src_c/stem_ISO_8859_1_finnish.c", "libstemmer_c/src_c/stem_ISO_8859_1_finnish.h", "libstemmer_c/src_c/stem_ISO_8859_1_french.c", "libstemmer_c/src_c/stem_ISO_8859_1_french.h", "libstemmer_c/src_c/stem_ISO_8859_1_german.c", "libstemmer_c/src_c/stem_ISO_8859_1_german.h", "libstemmer_c/src_c/stem_ISO_8859_1_hungarian.c", "libstemmer_c/src_c/stem_ISO_8859_1_hungarian.h", "libstemmer_c/src_c/stem_ISO_8859_1_italian.c", "libstemmer_c/src_c/stem_ISO_8859_1_italian.h", "libstemmer_c/src_c/stem_ISO_8859_1_norwegian.c", "libstemmer_c/src_c/stem_ISO_8859_1_norwegian.h", "libstemmer_c/src_c/stem_ISO_8859_1_porter.c", "libstemmer_c/src_c/stem_ISO_8859_1_porter.h", "libstemmer_c/src_c/stem_ISO_8859_1_portuguese.c", "libstemmer_c/src_c/stem_ISO_8859_1_portuguese.h", "libstemmer_c/src_c/stem_ISO_8859_1_spanish.c", "libstemmer_c/src_c/stem_ISO_8859_1_spanish.h", "libstemmer_c/src_c/stem_ISO_8859_1_swedish.c", "libstemmer_c/src_c/stem_ISO_8859_1_swedish.h", "libstemmer_c/src_c/stem_ISO_8859_2_romanian.c", "libstemmer_c/src_c/stem_ISO_8859_2_romanian.h", "libstemmer_c/src_c/stem_KOI8_R_russian.c", "libstemmer_c/src_c/stem_KOI8_R_russian.h", "libstemmer_c/src_c/stem_UTF_8_danish.c", "libstemmer_c/src_c/stem_UTF_8_danish.h", "libstemmer_c/src_c/stem_UTF_8_dutch.c", "libstemmer_c/src_c/stem_UTF_8_dutch.h", "libstemmer_c/src_c/stem_UTF_8_english.c", "libstemmer_c/src_c/stem_UTF_8_english.h", "libstemmer_c/src_c/stem_UTF_8_finnish.c", "libstemmer_c/src_c/stem_UTF_8_finnish.h", "libstemmer_c/src_c/stem_UTF_8_french.c", "libstemmer_c/src_c/stem_UTF_8_french.h", "libstemmer_c/src_c/stem_UTF_8_german.c", "libstemmer_c/src_c/stem_UTF_8_german.h", "libstemmer_c/src_c/stem_UTF_8_hungarian.c", "libstemmer_c/src_c/stem_UTF_8_hungarian.h", "libstemmer_c/src_c/stem_UTF_8_italian.c", "libstemmer_c/src_c/stem_UTF_8_italian.h", "libstemmer_c/src_c/stem_UTF_8_norwegian.c", "libstemmer_c/src_c/stem_UTF_8_norwegian.h", "libstemmer_c/src_c/stem_UTF_8_porter.c", "libstemmer_c/src_c/stem_UTF_8_porter.h", "libstemmer_c/src_c/stem_UTF_8_portuguese.c", "libstemmer_c/src_c/stem_UTF_8_portuguese.h", "libstemmer_c/src_c/stem_UTF_8_romanian.c", "libstemmer_c/src_c/stem_UTF_8_romanian.h", "libstemmer_c/src_c/stem_UTF_8_russian.c", "libstemmer_c/src_c/stem_UTF_8_russian.h", "libstemmer_c/src_c/stem_UTF_8_spanish.c", "libstemmer_c/src_c/stem_UTF_8_spanish.h", "libstemmer_c/src_c/stem_UTF_8_swedish.c", "libstemmer_c/src_c/stem_UTF_8_swedish.h", "libstemmer_c/src_c/stem_UTF_8_turkish.c", "libstemmer_c/src_c/stem_UTF_8_turkish.h", "MIT-LICENSE", "Rakefile", "README", "ruby-stemmer.c", "test.rb", "Manifest", "ruby-stemmer.gemspec"]
+  s.has_rdoc = true
+  s.homepage = %q{http://github.com/yury/ruby-stemmer}
+  s.rdoc_options = ["--line-numbers", "--inline-source", "--title", "Ruby-stemmer", "--main", "README"]
+  s.require_paths = ["lib"]
+  s.rubyforge_project = %q{ruby-stemmer}
+  s.rubygems_version = %q{1.3.1}
+  s.summary = %q{Stemmer implementation to ruby using libstemmer_c. Working with ruby 1.9.1}
+
+  if s.respond_to? :specification_version then
+    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
+    s.specification_version = 2
+
+    if Gem::Version.new(Gem::RubyGemsVersion) >= Gem::Version.new('1.2.0') then
+    else
+    end
+  else
+  end
+end

data/test.rb

@@ -1,11 +1,9 @@
 #!/usr/bin/env ruby
-
+# coding:utf-8
 #
 # $Id: test.rb 21 2008-04-30 10:57:37Z aurelian $
 #
 
-$kcode = "utf-8"
-
 require "stemmer.so"
 
 #puts "installation".stem

metadata

@@ -1,37 +1,110 @@
 --- !ruby/object:Gem::Specification 
 name: ruby-stemmer
 version: !ruby/object:Gem::Version 
-  version: 0.5.1
+  version: 0.5.3
 platform: ruby
 authors: 
-- Aurelian Oancea
+- Yury Korolev
 autorequire: 
 bindir: bin
 cert_chain: []
 
-date: 2008-05-10 00:00:00 +02:00
+date: 2009-02-10 00:00:00 +01:00
 default_executable: 
 dependencies: []
 
-description: Stemmer implementation to ruby using libstemmer_c.
-email: aurelian@locknet.ro
+description: Stemmer implementation to ruby using libstemmer_c. Working with ruby 1.9.1
+email: yury.korolev@gmail.com
 executables: []
 
 extensions: 
 - extconf.rb
-extra_rdoc_files: []
-
-files: 
+extra_rdoc_files: 
 - extconf.rb
-- ruby-stemmer.c
-- test.rb
-- MIT-LICENSE
-- Rakefile
+- libstemmer_c/examples/stemwords.c
+- libstemmer_c/include/libstemmer.h
+- libstemmer_c/libstemmer/libstemmer.c
+- libstemmer_c/libstemmer/libstemmer_utf8.c
+- libstemmer_c/libstemmer/modules.h
+- libstemmer_c/libstemmer/modules.txt
+- libstemmer_c/libstemmer/modules_utf8.h
+- libstemmer_c/libstemmer/modules_utf8.txt
+- libstemmer_c/Makefile
+- libstemmer_c/MANIFEST
+- libstemmer_c/mkinc.mak
+- libstemmer_c/mkinc_utf8.mak
+- libstemmer_c/README
+- libstemmer_c/runtime/api.c
+- libstemmer_c/runtime/api.h
+- libstemmer_c/runtime/header.h
+- libstemmer_c/runtime/utilities.c
+- libstemmer_c/src_c/stem_ISO_8859_1_danish.c
+- libstemmer_c/src_c/stem_ISO_8859_1_danish.h
+- libstemmer_c/src_c/stem_ISO_8859_1_dutch.c
+- libstemmer_c/src_c/stem_ISO_8859_1_dutch.h
+- libstemmer_c/src_c/stem_ISO_8859_1_english.c
+- libstemmer_c/src_c/stem_ISO_8859_1_english.h
+- libstemmer_c/src_c/stem_ISO_8859_1_finnish.c
+- libstemmer_c/src_c/stem_ISO_8859_1_finnish.h
+- libstemmer_c/src_c/stem_ISO_8859_1_french.c
+- libstemmer_c/src_c/stem_ISO_8859_1_french.h
+- libstemmer_c/src_c/stem_ISO_8859_1_german.c
+- libstemmer_c/src_c/stem_ISO_8859_1_german.h
+- libstemmer_c/src_c/stem_ISO_8859_1_hungarian.c
+- libstemmer_c/src_c/stem_ISO_8859_1_hungarian.h
+- libstemmer_c/src_c/stem_ISO_8859_1_italian.c
+- libstemmer_c/src_c/stem_ISO_8859_1_italian.h
+- libstemmer_c/src_c/stem_ISO_8859_1_norwegian.c
+- libstemmer_c/src_c/stem_ISO_8859_1_norwegian.h
+- libstemmer_c/src_c/stem_ISO_8859_1_porter.c
+- libstemmer_c/src_c/stem_ISO_8859_1_porter.h
+- libstemmer_c/src_c/stem_ISO_8859_1_portuguese.c
+- libstemmer_c/src_c/stem_ISO_8859_1_portuguese.h
+- libstemmer_c/src_c/stem_ISO_8859_1_spanish.c
+- libstemmer_c/src_c/stem_ISO_8859_1_spanish.h
+- libstemmer_c/src_c/stem_ISO_8859_1_swedish.c
+- libstemmer_c/src_c/stem_ISO_8859_1_swedish.h
+- libstemmer_c/src_c/stem_ISO_8859_2_romanian.c
+- libstemmer_c/src_c/stem_ISO_8859_2_romanian.h
+- libstemmer_c/src_c/stem_KOI8_R_russian.c
+- libstemmer_c/src_c/stem_KOI8_R_russian.h
+- libstemmer_c/src_c/stem_UTF_8_danish.c
+- libstemmer_c/src_c/stem_UTF_8_danish.h
+- libstemmer_c/src_c/stem_UTF_8_dutch.c
+- libstemmer_c/src_c/stem_UTF_8_dutch.h
+- libstemmer_c/src_c/stem_UTF_8_english.c
+- libstemmer_c/src_c/stem_UTF_8_english.h
+- libstemmer_c/src_c/stem_UTF_8_finnish.c
+- libstemmer_c/src_c/stem_UTF_8_finnish.h
+- libstemmer_c/src_c/stem_UTF_8_french.c
+- libstemmer_c/src_c/stem_UTF_8_french.h
+- libstemmer_c/src_c/stem_UTF_8_german.c
+- libstemmer_c/src_c/stem_UTF_8_german.h
+- libstemmer_c/src_c/stem_UTF_8_hungarian.c
+- libstemmer_c/src_c/stem_UTF_8_hungarian.h
+- libstemmer_c/src_c/stem_UTF_8_italian.c
+- libstemmer_c/src_c/stem_UTF_8_italian.h
+- libstemmer_c/src_c/stem_UTF_8_norwegian.c
+- libstemmer_c/src_c/stem_UTF_8_norwegian.h
+- libstemmer_c/src_c/stem_UTF_8_porter.c
+- libstemmer_c/src_c/stem_UTF_8_porter.h
+- libstemmer_c/src_c/stem_UTF_8_portuguese.c
+- libstemmer_c/src_c/stem_UTF_8_portuguese.h
+- libstemmer_c/src_c/stem_UTF_8_romanian.c
+- libstemmer_c/src_c/stem_UTF_8_romanian.h
+- libstemmer_c/src_c/stem_UTF_8_russian.c
+- libstemmer_c/src_c/stem_UTF_8_russian.h
+- libstemmer_c/src_c/stem_UTF_8_spanish.c
+- libstemmer_c/src_c/stem_UTF_8_spanish.h
+- libstemmer_c/src_c/stem_UTF_8_swedish.c
+- libstemmer_c/src_c/stem_UTF_8_swedish.h
+- libstemmer_c/src_c/stem_UTF_8_turkish.c
+- libstemmer_c/src_c/stem_UTF_8_turkish.h
 - README
-- libstemmer_c/examples
-- libstemmer_c/include
+files: 
+- extconf.rb
+- libstemmer_c/examples/stemwords.c
 - libstemmer_c/include/libstemmer.h
-- libstemmer_c/libstemmer
 - libstemmer_c/libstemmer/libstemmer.c
 - libstemmer_c/libstemmer/libstemmer_utf8.c
 - libstemmer_c/libstemmer/modules.h
@@ -43,12 +116,10 @@ files:
 - libstemmer_c/mkinc.mak
 - libstemmer_c/mkinc_utf8.mak
 - libstemmer_c/README
-- libstemmer_c/runtime
 - libstemmer_c/runtime/api.c
 - libstemmer_c/runtime/api.h
 - libstemmer_c/runtime/header.h
 - libstemmer_c/runtime/utilities.c
-- libstemmer_c/src_c
 - libstemmer_c/src_c/stem_ISO_8859_1_danish.c
 - libstemmer_c/src_c/stem_ISO_8859_1_danish.h
 - libstemmer_c/src_c/stem_ISO_8859_1_dutch.c
@@ -111,21 +182,21 @@ files:
 - libstemmer_c/src_c/stem_UTF_8_swedish.h
 - libstemmer_c/src_c/stem_UTF_8_turkish.c
 - libstemmer_c/src_c/stem_UTF_8_turkish.h
+- MIT-LICENSE
+- Rakefile
+- README
+- ruby-stemmer.c
+- test.rb
+- Manifest
+- ruby-stemmer.gemspec
 has_rdoc: true
-homepage: http://nrr.rubyforge.org
+homepage: http://github.com/yury/ruby-stemmer
 post_install_message: 
 rdoc_options: 
-- --title
-- Ruby-Stemmer
-- --exclude
-- libstemmer_c
-- --exclude
-- extconf.rb
-- --exclude
-- test.rb
+- --line-numbers
 - --inline-source
-- ruby-stemmer.c
-- README
+- --title
+- Ruby-stemmer
 - --main
 - README
 require_paths: 
@@ -140,14 +211,14 @@ required_rubygems_version: !ruby/object:Gem::Requirement
   requirements: 
   - - ">="
     - !ruby/object:Gem::Version 
-      version: "0"
+      version: "1.2"
   version: 
 requirements: []
 
-rubyforge_project: nrr
-rubygems_version: 1.0.1
+rubyforge_project: ruby-stemmer
+rubygems_version: 1.3.1
 signing_key: 
 specification_version: 2
-summary: Stemmer implementation to ruby using SnowBall API from libstemmer_c.
+summary: Stemmer implementation to ruby using libstemmer_c. Working with ruby 1.9.1
 test_files: []