1/* Part of SWI-Prolog 2 3 Author: Jan Wielemaker 4 E-mail: J.Wielemaker@vu.nl 5 WWW: http://www.swi-prolog.org 6 Copyright (c) 2010-2015, VU University, Amsterdam 7 All rights reserved. 8 9 Redistribution and use in source and binary forms, with or without 10 modification, are permitted provided that the following conditions 11 are met: 12 13 1. Redistributions of source code must retain the above copyright 14 notice, this list of conditions and the following disclaimer. 15 16 2. Redistributions in binary form must reproduce the above copyright 17 notice, this list of conditions and the following disclaimer in 18 the documentation and/or other materials provided with the 19 distribution. 20 21 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 22 "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT 23 LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS 24 FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 25 COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, 26 INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, 27 BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; 28 LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER 29 CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 30 LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN 31 ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE 32 POSSIBILITY OF SUCH DAMAGE. 33*/ 34 35:- module(snowball, 36 [ snowball/3, % +Algorithm, +In, -Out 37 snowball_current_algorithm/1 % ?algorithm 38 ]). 39:- use_module(library(sandbox)). 40 41/** <module> The Snowball multi-lingual stemmer library 42 43This module encapsulates "The C version of the libstemmer library" from 44the Snowball project. This library provides stemmers in a variety of 45languages. The interface to this library is very simple: 46 47 * snowball/3 stems a word with a given algorithm 48 * snowball_current_algorithm/1 enumerates the provided algorithms. 49 50Here is an example: 51 52 == 53 ?- snowball(english, walking, S). 54 S = walk. 55 == 56 57@see http://snowball.tartarus.org/ 58*/ 59 60:- use_foreign_library(foreign(snowball)). 61 62%! snowball(+Algorithm, +Input, -Stem) is det. 63% 64% Apply the Snowball Algorithm on Input and unify the result 65% (an atom) with Stem. 66% 67% The implementation maintains a cache of stemmers for each thread 68% that accesses snowball/3, providing high-perfomance and 69% thread-safety without locking. 70% 71% @param Algorithm is the (english) name for desired algorithm 72% or an 2 or 3 letter ISO 639 language code. 73% @param Input is the word to be stemmed. It is either an 74% atom, string or list of chars/codes. The library 75% accepts Unicode characters. Input must be 76% _lowercase_. See downcase_atom/2. 77% @error domain_error(snowball_algorithm, Algorithm) 78% @error type_error(atom, Algorithm) 79% @error type_error(text, Input) 80 81%! snowball_current_algorithm(?Algorithm) is nondet. 82% 83% True if Algorithm is the official name of an algorithm suported 84% by snowball/3. The predicate is =semidet= if Algorithm is given. 85 86term_expansion(snowball_current_algorithm(dummy), Clauses) :- 87 snowball_algorithms(Algos), 88 maplist(wrap, Algos, Clauses). 89 90wrap(X, snowball_current_algorithm(X)). 91 92snowball_current_algorithm(dummy). 93 94:- multifile 95 sandbox:safe_primitive/1. 96 97sandbox:safe_primitive(snowball:snowball(_,_,_))