SyntacticSynsConfig.java

/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You 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 org.tallison.lucene.syns;

import java.nio.file.Path;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.CharArraySet;
import org.apache.lucene.analysis.standard.StandardAnalyzer;

class SyntacticSynsConfig {

    private final static String NGRAM_FIELD = "ngrams";

    private final static String NGRAM_INDEX_NAME = "ngram_index";

    private final static String CONTEXT_FIELD = "c";
    private final static String CONTEXT_INDEX_NAME = "context_index";

    private final static String SYNS_TARGET_FIELD_NAME = "target";
    private final static String SYNS_PRE_FIELD_NAME = "pre";
    private final static String SYNS_POST_FIELD_NAME = "post";
    private final static String SYNS_INDEX_NAME = "syns_index";

    private final Path indexDir;

    private int maxKeyPhraseLength = 3;

    private int maxContextTokenCount = 9000;//max number of context tokens in a field, if > than this normalize
    private int maxTargetTypeCount = 50000;// if the key shows up this many times, ignore it; this is meant to keep, e.g. "the" from being a key
    private int minKeyPhraseTermFrequency = 1;// min term frequency of a given key phrase
    private int minTargetCount = 5;// min document frequency of a given key's contexts
    private int minContextTypeCount = 1;//minimum type for a context
    private int minContextTokenCount = 1;//minimum tokens for a context

    private int maxTermsPerFieldInQuery = 30;//how many types to include in both the pre and post queries
    private int minContextFrequencyInQuery = 5;

    private int preContextSize = 1;
    private int postContextSize = 1;
    private final int maxTokenToReadCount = -1;//max tokens to read from input string
    private final Analyzer baseAnalyzer = new StandardAnalyzer(CharArraySet.EMPTY_SET);


    public SyntacticSynsConfig(Path indexDir) {
        this.indexDir = indexDir;
    }

    public static String getNgramField() {
        return NGRAM_FIELD;
    }

    public static String getContextField() {
        return CONTEXT_FIELD;
    }

    public static String getSynsTargetFieldName() {
        return SYNS_TARGET_FIELD_NAME;
    }

    public static String getSynsPreFieldName() {
        return SYNS_PRE_FIELD_NAME;
    }

    public static String getSynsPostFieldName() {
        return SYNS_POST_FIELD_NAME;
    }

    public int getMaxTermsPerFieldInQuery() {
        return maxTermsPerFieldInQuery;
    }

    public void setMaxTermsPerFieldInQuery(int maxTermsPerFieldInQuery) {
        this.maxTermsPerFieldInQuery = maxTermsPerFieldInQuery;
    }

    public int getMaxKeyPhraseLength() {
        return maxKeyPhraseLength;
    }

    public void setMaxKeyPhraseLength(int maxKeyPhraseLength) {
        this.maxKeyPhraseLength = maxKeyPhraseLength;
    }

    public int getMaxContextTokenCount() {
        return maxContextTokenCount;
    }

    public void setMaxContextTokenCount(int maxContextTokenCount) {
        this.maxContextTokenCount = maxContextTokenCount;
    }

    public int getMaxTargetTypeCount() {
        return maxTargetTypeCount;
    }

    public void setMaxTargetTypeCount(int maxTargetTypeCount) {
        this.maxTargetTypeCount = maxTargetTypeCount;
    }

    public int getMinKeyPhraseTermFrequency() {
        return minKeyPhraseTermFrequency;
    }

    public void setMinKeyPhraseTermFrequency(int minKeyPhraseTermFrequency) {
        this.minKeyPhraseTermFrequency = minKeyPhraseTermFrequency;
    }

    public int getMinTargetCount() {
        return minTargetCount;
    }

    public void setMinTargetCount(int minTargetCount) {
        this.minTargetCount = minTargetCount;
    }

    public int getMinContextTypeCount() {
        return minContextTypeCount;
    }

    public void setMinContextTypeCount(int minContextTypeCount) {
        this.minContextTypeCount = minContextTypeCount;
    }

    public int getMinContextTokenCount() {
        return minContextTokenCount;
    }

    public void setMinContextTokenCount(int minContextTokenCount) {
        this.minContextTokenCount = minContextTokenCount;
    }

    public int getPreContextSize() {
        return preContextSize;
    }

    public void setPreContextSize(int preContextSize) {
        this.preContextSize = preContextSize;
    }

    public int getPostContextSize() {
        return postContextSize;
    }

    public void setPostContextSize(int postContextSize) {
        this.postContextSize = postContextSize;
    }

    public Path getNGramIndex() {
        return indexDir.resolve(NGRAM_INDEX_NAME);
    }

    public Path getContextIndex() {
        return indexDir.resolve(CONTEXT_INDEX_NAME);
    }

    public Path getSynsIndex() {
        return indexDir.resolve(SYNS_INDEX_NAME);
    }


    public Path getIndexDir() {
        return indexDir;
    }


    public int getMinContextFrequencyInQuery() {
        return minContextFrequencyInQuery;
    }


    public void setMinContextFrequencyInQuery(int minContextFrequencyInQuery) {
        this.minContextFrequencyInQuery = minContextFrequencyInQuery;
    }


    /**
     *
     * @return maximum number of tokens to read from the original string
     */
    public int getMaxTokenToReadCount() {
        return maxTokenToReadCount;
    }

    /**
     * This is the base analyzer to use for the initial input string.
     * The NGramIndexBuilders wrap this in a ShingleAnalyzerWrapper.
     *
     * @return analyzer to use for the initial input string
     */
    public Analyzer getBaseAnalyzer() {
        return baseAnalyzer;
    }
}