aurelian-ruby-stemmer 0.5.4

data/MIT-LICENSE

@@ -0,0 +1,21 @@
+Copyright (c) 2008,2009 Aurelian Oancea
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+

data/Manifest

@@ -0,0 +1,87 @@
+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
+Manifest
+MIT-LICENSE
+Rakefile
+README.textile
+ruby-stemmer.c
+ruby-stemmer.gemspec
+test.rb

data/README.textile

@@ -0,0 +1,66 @@
+h3. About
+
+*ruby-stemmer* exposes SnowBall API stemmer implementation to ruby.
+
+This package includes *libstemmer_c* library - released under BSD licence and available for download at: "http://snowball.tartarus.org/dist/libstemmer_c.tgz":http://snowball.tartarus.org/dist/libstemmer_c.tgz.
+
+For details about *libstemmer_c* please check libstemmer_c/README file or "http://snowball.tartarus.org":http://snowball.tartarus.org.
+
+author: Aurelian Oancea, oancea at gmail.com
+
+licence: MIT, see MIT-LICENSE file for details
+
+
+h4. Install
+
+
+Please use sudo or run as root if you get in to _Permission Deny_ issues.
+
+h5. Stable version - with rubygems:
+
+  @$ gem install ruby-stemmer@
+
+h5. Development version - from source
+
+  $ ruby extconf.rb # => compile libstemmer_c and generate a Makefile
+  $ make # => compile the library
+  $ ./test.rb # => test it :)
+  $ make install # => to install
+
+
+h4. Usage
+
+Please refer to @test.rb@.
+
+
+h4. API
+
+<pre>
+  module Lingua
+    class Steemer
+
+      # creates a new Steemer,
+      # defaults: language => en, encoding => UTF_8
+      # pass :language or :encoding to change them 
+      def initialize
+      end
+    
+      # stemms the word
+      def stem(word)
+      end
+    
+      # gets the length of the last stemmed word
+      # same as: 
+      # word = Lingua::Steemer.new.stem("installation") # ==> install (string)
+      # word.length # ==> 6 (int)
+      def length
+      end
+    end
+  end
+</pre>
+
+
+h4. Todo
+
+* Add (Array of Hashes) Lingua::Stemmer.list to list available languages/encodings
+* Windows?

data/Rakefile

@@ -0,0 +1,39 @@
+require 'rubygems'
+require 'rake'
+require 'echoe'
+
+Echoe.new('ruby-stemmer', '0.5.4') do |p|
+    p.description    = "Stemmer implementation to ruby using libstemmer_c. Working with ruby 1.9.1"
+    p.url            = "http://github.com/aurelian/ruby-stemmer"
+    p.author         = "Aurelian Oancea, Yury Korolev"
+    p.email          = "oancea@gmail.com, 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'
+
+PKG_FILES = FileList[
+  'extconf.rb',
+  'ruby-stemmer.c',
+  'test.rb',
+  '[A-Z]*',
+  'libstemmer_c/**/*'
+]
+
+PKG_FILES.exclude('*.o')
+PKG_FILES.exclude('**/*.o')
+PKG_FILES.exclude('stemwords')
+PKG_FILES.exclude('*.bundle')
+PKG_FILES.exclude('*.a')
+PKG_FILES.exclude('*.so')
+
+desc "Cleans the workspace"
+task :clean do
+  `rm -rf Makefile mkmf.log ruby-stemmer.o stemmer.bundle stemmer.so`
+  `cd libstemmer_c && make clean && cd ../`
+end
+

data/extconf.rb

@@ -0,0 +1,13 @@
+require "mkmf"
+
+system "cd libstemmer_c; make libstemmer.o; cd #{File.dirname(__FILE__)};"
+
+$CFLAGS  += " -I#{File.join(File.dirname(__FILE__),'libstemmer_c','include')} "
+$libs    += " -L#{File.join(File.dirname(__FILE__),'libstemmer_c')} #{File.join(File.dirname(__FILE__),'libstemmer_c','libstemmer.o')} "
+
+# dir_config("libstemmer")
+
+if have_header("libstemmer.h") # && have_library('libstemmer')
+  create_makefile("lingua/stemmer")
+end
+

data/libstemmer_c/MANIFEST

@@ -0,0 +1,72 @@
+README
+src_c/stem_ISO_8859_1_danish.c
+src_c/stem_ISO_8859_1_danish.h
+src_c/stem_ISO_8859_1_dutch.c
+src_c/stem_ISO_8859_1_dutch.h
+src_c/stem_ISO_8859_1_english.c
+src_c/stem_ISO_8859_1_english.h
+src_c/stem_ISO_8859_1_finnish.c
+src_c/stem_ISO_8859_1_finnish.h
+src_c/stem_ISO_8859_1_french.c
+src_c/stem_ISO_8859_1_french.h
+src_c/stem_ISO_8859_1_german.c
+src_c/stem_ISO_8859_1_german.h
+src_c/stem_ISO_8859_1_hungarian.c
+src_c/stem_ISO_8859_1_hungarian.h
+src_c/stem_ISO_8859_1_italian.c
+src_c/stem_ISO_8859_1_italian.h
+src_c/stem_ISO_8859_1_norwegian.c
+src_c/stem_ISO_8859_1_norwegian.h
+src_c/stem_ISO_8859_1_porter.c
+src_c/stem_ISO_8859_1_porter.h
+src_c/stem_ISO_8859_1_portuguese.c
+src_c/stem_ISO_8859_1_portuguese.h
+src_c/stem_ISO_8859_1_spanish.c
+src_c/stem_ISO_8859_1_spanish.h
+src_c/stem_ISO_8859_1_swedish.c
+src_c/stem_ISO_8859_1_swedish.h
+src_c/stem_ISO_8859_2_romanian.c
+src_c/stem_ISO_8859_2_romanian.h
+src_c/stem_KOI8_R_russian.c
+src_c/stem_KOI8_R_russian.h
+src_c/stem_UTF_8_danish.c
+src_c/stem_UTF_8_danish.h
+src_c/stem_UTF_8_dutch.c
+src_c/stem_UTF_8_dutch.h
+src_c/stem_UTF_8_english.c
+src_c/stem_UTF_8_english.h
+src_c/stem_UTF_8_finnish.c
+src_c/stem_UTF_8_finnish.h
+src_c/stem_UTF_8_french.c
+src_c/stem_UTF_8_french.h
+src_c/stem_UTF_8_german.c
+src_c/stem_UTF_8_german.h
+src_c/stem_UTF_8_hungarian.c
+src_c/stem_UTF_8_hungarian.h
+src_c/stem_UTF_8_italian.c
+src_c/stem_UTF_8_italian.h
+src_c/stem_UTF_8_norwegian.c
+src_c/stem_UTF_8_norwegian.h
+src_c/stem_UTF_8_porter.c
+src_c/stem_UTF_8_porter.h
+src_c/stem_UTF_8_portuguese.c
+src_c/stem_UTF_8_portuguese.h
+src_c/stem_UTF_8_romanian.c
+src_c/stem_UTF_8_romanian.h
+src_c/stem_UTF_8_russian.c
+src_c/stem_UTF_8_russian.h
+src_c/stem_UTF_8_spanish.c
+src_c/stem_UTF_8_spanish.h
+src_c/stem_UTF_8_swedish.c
+src_c/stem_UTF_8_swedish.h
+src_c/stem_UTF_8_turkish.c
+src_c/stem_UTF_8_turkish.h
+runtime/api.c
+runtime/api.h
+runtime/header.h
+runtime/utilities.c
+libstemmer/libstemmer.c
+libstemmer/libstemmer_utf8.c
+libstemmer/modules.h
+libstemmer/modules_utf8.h
+include/libstemmer.h

data/libstemmer_c/Makefile

@@ -0,0 +1,9 @@
+include mkinc.mak
+CFLAGS=-Iinclude -fPIC
+all: libstemmer.o stemwords
+libstemmer.o: $(snowball_sources:.c=.o)
+	$(AR) -cru $@ $^
+stemwords: examples/stemwords.o libstemmer.o
+	$(CC) -o $@ $^
+clean:
+	rm -f stemwords *.o src_c/*.o runtime/*.o libstemmer/*.o

data/libstemmer_c/README

@@ -0,0 +1,125 @@
+libstemmer_c
+============
+
+This document pertains to the C version of the libstemmer distribution,
+available for download from:
+
+http://snowball.tartarus.org/dist/libstemmer_c.tgz
+
+
+Compiling the library
+=====================
+
+A simple makefile is provided for Unix style systems.  On such systems, it
+should be possible simply to run "make", and the file "libstemmer.o"
+and the example program "stemwords" will be generated.
+
+If this doesn't work on your system, you need to write your own build
+system (or call the compiler directly).  The files to compile are
+all contained in the "libstemmer", "runtime" and "src_c" directories,
+and the public header file is contained in the "include" directory.
+
+The library comes in two flavours; UTF-8 only, and UTF-8 plus other character
+sets.  To use the utf-8 only flavour, compile "libstemmer_utf8.c" instead of
+"libstemmer.c".
+
+For convenience "mkinc.mak" is a makefile fragment listing the source files and
+header files used to compile the standard version of the library.
+"mkinc_utf8.mak" is a comparable makefile fragment listing just the source
+files for the UTF-8 only version of the library.
+
+
+Using the library
+=================
+
+The library provides a simple C API.  Essentially, a new stemmer can
+be obtained by using "sb_stemmer_new".  "sb_stemmer_stem" is then
+used to stem a word, "sb_stemmer_length" returns the stemmed
+length of the last word processed, and "sb_stemmer_delete" is
+used to delete a stemmer.
+
+Creating a stemmer is a relatively expensive operation - the expected
+usage pattern is that a new stemmer is created when needed, used
+to stem many words, and deleted after some time.
+
+Stemmers are re-entrant, but not threadsafe.  In other words, if
+you wish to access the same stemmer object from multiple threads,
+you must ensure that all access is protected by a mutex or similar
+device.
+
+libstemmer does not currently incorporate any mechanism for caching the results
+of stemming operations.  Such caching can greatly increase the performance of a
+stemmer under certain situations, so suitable patches will be considered for
+inclusion.
+
+The standard libstemmer sources contain an algorithm for each of the supported
+languages.  The algorithm may be selected using the english name of the
+language, or using the 2 or 3 letter ISO 639 language codes.  In addition,
+the traditional "Porter" stemming algorithm for english is included for
+backwards compatibility purposes, but we recommend use of the "English"
+stemmer in preference for new projects.
+
+(Some minor algorithms which are included only as curiosities in the snowball
+website, such as the Lovins stemmer and the Kraaij Pohlmann stemmer, are not
+included in the standard libstemmer sources.  These are not really supported by
+the snowball project, but it would be possible to compile a modified libstemmer
+library containing these if desired.)
+
+
+The stemwords example
+=====================
+
+The stemwords example program allows you to run any of the stemmers
+compiled into the libstemmer library on a sample vocabulary.  For
+details on how to use it, run it with the "-h" command line option.
+
+
+Using the library in a larger system
+====================================
+
+If you are incorporating the library into the build system of a larger
+program, I recommend copying the unpacked tarball without modification into
+a subdirectory of the sources of your program.  Future versions of the
+library are intended to keep the same structure, so this will keep the
+work required to move to a new version of the library to a minimum.
+
+As an additional convenience, the list of source and header files used
+in the library is detailed in mkinc.mak - a file which is in a suitable
+format for inclusion by a Makefile.  By including this file in your build
+system, you can link the snowball system into your program with a few
+extra rules.
+
+Using the library in a system using GNU autotools
+=================================================
+
+The libstemmer_c library can be integrated into a larger system which uses the
+GNU autotool framework (and in particular, automake and autoconf) as follows:
+
+1) Unpack libstemmer_c.tgz in the top level project directory so that there is
+   a libstemmer_c subdirectory of the top level directory of the project.
+
+2) Add a file "Makefile.am" to the unpacked libstemmer_c folder, containing:
+   
+noinst_LTLIBRARIES = libstemmer.la
+include $(srcdir)/mkinc.mak
+noinst_HEADERS = $(snowball_headers)
+libstemmer_la_SOURCES = $(snowball_sources) 
+
+(You may also need to add other lines to this, for example, if you are using
+compiler options which are not compatible with compiling the libstemmer
+library.)
+
+3) Add libstemmer_c to the AC_CONFIG_FILES declaration in the project's
+   configure.ac file.
+
+4) Add to the top level makefile the following lines (or modify existing
+   assignments to these variables appropriately):
+
+AUTOMAKE_OPTIONS = subdir-objects
+AM_CPPFLAGS = -I$(top_srcdir)/libstemmer_c/include
+SUBDIRS=libstemmer_c
+<name>_LIBADD = libstemmer_c/libstemmer.la
+
+(Where <name> is the name of the library or executable which links against
+libstemmer.) 
+

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;
+}
+