/*
* Copyright 2015 Themistoklis Mavridis <themis.mavridis@issel.ee.auth.gr>.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package com.thesmartweb.swebrank;
/**
* Class that can test whether a given string is a stop word.
* Lowercases all words before the test.
* The format for reading and writing is one word per line, lines starting
* with '#' are interpreted as comments and therefore skipped.
* The default Stopwords are based on <a href="http://www.cs.cmu.edu/~mccallum/bow/rainbow/" target="_blank">Rainbow</a>.
*
* Accepts the following parameter:
*
* -i file
* loads the Stopwords from the given file
*
* -o file
* saves the Stopwords to the given file
*
* -p
* outputs the current Stopwords on stdout
*
* Any additional parameters are interpreted as words to test as Stopwords.
*
* @author Eibe Frank (eibe@cs.waikato.ac.nz)
* @author Ashraf M. Kibriya (amk14@cs.waikato.ac.nz)
* @author FracPete (fracpete at waikato dot ac dot nz)
* @version $Revision: 1.4 $
*/
public class Stopwords {
/**
* Get a string without the stopwords
* @param input the string we would like to clean from stopwords
* @return the cleaned string
*/
public String stop(String input){
String[] stoparr={
"a",
"able",
"and",
"about",
"above",
"according",
"accordingly",
"across",
"actually",
"after",
"afterwards",
"again",
"against",
"all",
"allow",
"allows",
"almost",
"alone",
"along",
"already",
"also",
"although",
"always",
"am",
"among",
"amongst",
"an",
"and",
"another",
"any",
"anybody",
"anyhow",
"anyone",
"anything",
"anyway",
"anyways",
"anywhere",
"apart",
"appear",
"appreciate",
"appropriate",
"are",
"around",
"as",
"aside",
"ask",
"asking",
"associated",
"at",
"available",
"away",
"awfully",
"b",
"B",
"be",
"became",
"because",
"become",
"becomes",
"becoming",
"been",
"before",
"beforehand",
"behind",
"being",
"believe",
"below",
"beside",
"besides",
"best",
"better",
"between",
"beyond",
"both",
"brief",
"but",
"by",
"c",
"came",
"can",
"cannot",
"cant",
"cause",
"causes",
"certain",
"certainly",
"changes",
"clearly",
"co",
"com",
"come",
"comes",
"concerning",
"consequently",
"consider",
"considering",
"contain",
"containing",
"contains",
"corresponding",
"could",
"course",
"currently",
"d",
"definitely",
"described",
"despite",
"did",
"different",
"do",
"does",
"doing",
"done",
"down",
"downwards",
"during",
"e",
"each",
"edu",
"eg",
"eight",
"either",
"else",
"elsewhere",
"enough",
"entirely",
"especially",
"et",
"etc",
"even",
"ever",
"every",
"everybody",
"everyone",
"everything",
"everywhere",
"ex",
"exactly",
"example",
"except",
"f",
"far",
"few",
"fifth",
"first",
"five",
"followed",
"following",
"follows",
"for",
"former",
"formerly",
"forth",
"four",
"from",
"further",
"furthermore",
"g",
"get",
"gets",
"getting",
"given",
"gives",
"go",
"goes",
"going",
"gone",
"got",
"gotten",
"greetings",
"h",
"had",
"happens",
"hardly",
"has",
"have",
"having",
"he",
"hello",
"help",
"hence",
"her",
"here",
"hereafter",
"hereby",
"herein",
"hereupon",
"hers",
"herself",
"hi",
"him",
"himself",
"his",
"hither",
"hopefully",
//"how",
"howbeit",
"however",
"i",
"ie",
"if",
"ignored",
"immediate",
"in",
"inasmuch",
"inc",
"indeed",
"indicate",
"indicated",
"indicates",
"inner",
"insofar",
"instead",
"into",
"inward",
"is",
"it",
"its",
"itself",
"j",
"just",
"k",
"keep",
"keeps",
"kept",
"know",
"knows",
"known",
"l",
"last",
"lately",
"later",
"latter",
"latterly",
"least",
"less",
"lest",
"let",
"like",
"liked",
"likely",
"little",
"ll", //added to avoid words like you'll,I'll etc.
"look",
"looking",
"looks",
"ltd",
"m",
"mainly",
"many",
"may",
"maybe",
"me",
"mean",
"meanwhile",
"merely",
"might",
"more",
"moreover",
"most",
"mostly",
"much",
"must",
"my",
"myself",
"n",
"name",
"namely",
"nd",
"near",
"nearly",
"necessary",
"need",
"needs",
"neither",
"never",
"nevertheless",
"new",
"next",
"nine",
"no",
"nobody",
"non",
"none",
"noone",
"nor",
"normally",
"not",
"nothing",
"novel",
"now",
"nowhere",
"o",
"obviously",
"of",
"off",
"often",
"oh",
"ok",
"okay",
"old",
"on",
"once",
"one",
"ones",
"only",
"onto",
"or",
"other",
"others",
"otherwise",
"ought",
"our",
"ours",
"ourselves",
"out",
"outside",
"over",
"overall",
"own",
"p",
"particular",
"particularly",
"per",
"perhaps",
"placed",
"please",
"plus",
"possible",
"presumably",
"probably",
"provides",
"q",
"que",
"quite",
"qv",
"r",
"rather",
"rd",
"re",
"really",
"reasonably",
"regarding",
"regardless",
"regards",
"relatively",
"respectively",
"right",
"s",
"said",
"same",
"saw",
"say",
"saying",
"says",
"second",
"secondly",
"see",
"seeing",
"seem",
"seemed",
"seeming",
"seems",
"seen",
"self",
"selves",
"sensible",
"sent",
"serious",
"seriously",
"seven",
"several",
"shall",
"she",
"should",
"since",
"six",
"so",
"some",
"somebody",
"somehow",
"someone",
"something",
"sometime",
"sometimes",
"somewhat",
"somewhere",
"soon",
"sorry",
"specified",
"specify",
"specifying",
"still",
"sub",
"such",
"sup",
"sure",
"t",
"take",
"taken",
"tell",
"tends",
"th",
"than",
"thank",
"thanks",
"thanx",
"that",
"thats",
"the",
"their",
"theirs",
"them",
"themselves",
"then",
"thence",
"there",
"thereafter",
"thereby",
"therefore",
"therein",
"theres",
"thereupon",
"these",
"they",
"think",
"third",
"this",
"thorough",
"thoroughly",
"those",
"though",
"three",
"through",
"throughout",
"thru",
"thus",
"to",
"together",
"too",
"took",
"toward",
"towards",
"tried",
"tries",
"truly",
"try",
"trying",
"twice",
"two",
"u",
"un",
"under",
"unfortunately",
"unless",
"unlikely",
"until",
"unto",
"up",
"upon",
"us",
"use",
"used",
"useful",
"uses",
"using",
"usually",
"uucp",
"v",
"value",
"various",
"ve", //added to avoid words like I've,you've etc.
"very",
"via",
"viz",
"vs",
"w",
"want",
"wants",
"was",
"way",
"we",
"welcome",
"well",
"went",
"were",
"what",
"whatever",
"when",
"whence",
"whenever",
"where",
"whereafter",
"whereas",
"whereby",
"wherein",
"whereupon",
"wherever",
"whether",
"which",
"with",
"while",
"whither",
"who",
"whoever",
"whole",
"whom",
"whose",
"why",
"will",
"willing",
"wish",
"with",
"within",
"without",
"wonder",
"would",
"would",
"x",
"y",
"yes",
"yet",
"you",
"your",
"yours",
"yourself",
"yourselves",
"z",
"zero",
"-",
"_",
"+",
".",
"&",
"|"};
input=input.toLowerCase();
String[] inarr=input.split(" ");
for(int i=0;i<stoparr.length;i++)
{
for (int j = 0; j < inarr.length; j++)
{
if (inarr[j].equals(stoparr[i]))
{
inarr[j]=" ";
}
}
}
String output="";
for (int k=0;k<inarr.length;k++)
{
output=output+inarr[k]+" ";
}
return output;
}
}