list/src/main/java/data/Statistics.java

package data;

import java.io.UnsupportedEncodingException;
import java.time.LocalDateTime;
import java.time.format.DateTimeFormatter;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;
import java.util.concurrent.ConcurrentHashMap;
import java.util.concurrent.atomic.AtomicLong;
import java.util.regex.Pattern;

import util.Util;
import util.db.RDB;

public class Statistics {
	private CorpusType corpusType;
	private AnalysisLevel analysisLevel;
	private boolean useDB;
	private RDB db;

	private boolean analysisProducedResults;

	private String taxonomy;
	private boolean taxonomyIsSet;

	private char JOSType;
	private boolean JOSTypeIsSet;

	private String resultTitle;
	public Map<String, AtomicLong> result = new ConcurrentHashMap<>();

	// nGrams
	private int nGramLevel;
	private Integer skip;
	private CalculateFor cf;
	private List<Pattern> morphosyntacticFilter;

	// distributions
	private String distributionTaxonomy;
	private char distributionJosWordType;
	private boolean vcc;
	private Integer substringLength;

	// inflected JOS
	private String inflectedJosTaxonomy;

	// GOS
	boolean gosOrthMode;

	// šolar
	Map<String, Object> solarHeadBlockFilter;


	// for ngrams
	public Statistics(AnalysisLevel al, int nGramLevel, Integer skip, CalculateFor cf) {
		String dateTime = LocalDateTime.now().format(DateTimeFormatter.ofPattern("dd.MM.yyyy_hh.mm"));
		this.cf = cf;
		this.analysisLevel = al;
		this.nGramLevel = nGramLevel;
		this.skip = skip == null || skip == 0 ? null : skip;

		this.resultTitle = String.format("%s%d-gram_%s_%s",
				this.skip != null ? String.format("%d-%s-", skip, "skip") : "",
				nGramLevel,
				cf.toString(),
				dateTime);
	}

	// for words distributions
//	public Statistics(AnalysisLevel al, Taxonomy distributionTaxonomy, GigafidaJosWordType distributionJosWordType, CalculateFor cf) {
//		String dateTime = LocalDateTime.now().format(DateTimeFormatter.ofPattern("dd.MM.yyyy_hh.mm"));
//
//		this.resultTitle = String.format("%s_%s_%s",
//				distributionTaxonomy != null ? distributionTaxonomy.toString() : "",
//				distributionJosWordType != null ? distributionJosWordType.toString() : "",
//				dateTime);
//
//		this.analysisLevel = al;
//		this.cf = cf;
//		this.distributionTaxonomy = distributionTaxonomy != null ? distributionTaxonomy.getTaxonomnyString() : null;
//		this.taxonomyIsSet = distributionTaxonomy != null;
//
//		this.JOSTypeIsSet = distributionJosWordType != null;
//		this.distributionJosWordType = this.JOSTypeIsSet ? distributionJosWordType.getWordType() : ' ';
//	}

	public Statistics(AnalysisLevel al, CalculateFor cf, Integer substringLength) {
		String dateTime = LocalDateTime.now().format(DateTimeFormatter.ofPattern("dd.MM.yyyy_hh.mm"));

		this.resultTitle = String.format("%s_%d_%s",
				"Distribucija zaporedij samoglasnikov in soglasnikov",
				substringLength,
				dateTime);

		this.analysisLevel = al;
		this.cf = cf;
		this.substringLength = substringLength;
		this.vcc = true;
	}

//	public Statistics(AnalysisLevel al, Taxonomy inflectedJosTaxonomy) {
//		String dateTime = LocalDateTime.now().format(DateTimeFormatter.ofPattern("dd.MM.yyyy_hh.mm"));
//
//		this.resultTitle = String.format("InflectedJOS_%s_%s",
//				distributionTaxonomy != null ? distributionTaxonomy : "",
//				dateTime);
//
//		this.analysisLevel = al;
//		this.inflectedJosTaxonomy = inflectedJosTaxonomy != null ? inflectedJosTaxonomy.getTaxonomnyString() : null;
//		this.taxonomyIsSet = inflectedJosTaxonomy != null;
//	}

	public Integer getSkip() {
		return skip;
	}

	public Integer getSubstringLength() {
		return substringLength;
	}

	public String getInflectedJosTaxonomy() {
		return inflectedJosTaxonomy;
	}

	public void setSubstringLength(Integer substringLength) {
		this.substringLength = substringLength;
	}

	public boolean isVcc() {
		return vcc;
	}

	public void setVcc(boolean vcc) {
		this.vcc = vcc;
	}

	public String getDistributionTaxonomy() {
		return distributionTaxonomy;
	}

	public void setDistributionTaxonomy(String distributionTaxonomy) {
		this.distributionTaxonomy = distributionTaxonomy;
	}

	public char getDistributionJosWordType() {
		return distributionJosWordType;
	}

	public void setDistributionJosWordType(char distributionJosWordType) {
		this.distributionJosWordType = distributionJosWordType;
	}

	public void setMorphosyntacticFilter(List<String> morphosyntacticFilter) {
		// change filter strings to regex patterns
		this.morphosyntacticFilter = new ArrayList<>();
		for (String s : morphosyntacticFilter) {
			this.morphosyntacticFilter.add(Pattern.compile(s.replaceAll("\\*", ".")));
		}
	}

	public List<Pattern> getMsd() {
		return morphosyntacticFilter;
	}

	public Map<String, AtomicLong> getResult() {
		return result;
	}

	public void setTaxonomy(String taxonomy) {
		this.taxonomy = taxonomy;
	}

	public void setTaxonomyIsSet(boolean taxonomyIsSet) {
		this.taxonomyIsSet = taxonomyIsSet;
	}

	public char getJOSType() {
		return JOSType;
	}

	public void setJOSType(char JOSType) {
		this.JOSType = JOSType;
	}

	public boolean isJOSTypeSet() {
		return JOSTypeIsSet;
	}

	public void setJOSType(boolean JOSTypeIsSet) {
		this.JOSTypeIsSet = JOSTypeIsSet;
	}

	public void saveResultToDisk(int... limit) throws UnsupportedEncodingException {
		// Set<Pair<String, Map<String, Long>>> stats = new HashSet<>();
		//
		// if (useDB) {
		// 	result = db.getDump();
		// 	db.delete();
		// }
		//
		// // if no results and nothing to save, return false
		// if (!(result.size() > 0)) {
		// 	analysisProducedResults = false;
		// 	return;
		// } else {
		// 	analysisProducedResults = true;
		// }
		//
		// stats.add(ImmutablePair.of(resultTitle, getSortedResult(result, Util.getValidInt(limit))));
		// Export.SetToCSV(stats);
	}

	// private Map<String, Integer> getSortedResultInflected(Map map) {
	// 	// first convert to <String, Integer>
	// 	Map<String, Integer> m = Util.sortByValue(Util.atomicInt2StringAndInt(map), 0);
	//
	// 	Map<String, Integer> sortedM = new TreeMap<>();
	//
	// 	sortedM.putAll(m);
	//
	// 	return sortedM;
	// }

	private Map<MultipleHMKeys, Long> getSortedResult(Map<MultipleHMKeys, AtomicLong> map, int limit) {
		return Util.sortByValue(Util.atomicInt2StringAndInt(map), limit);
	}

	public String getTaxonomy() {
		return taxonomy;
	}

	public boolean isTaxonomySet() {
		return taxonomyIsSet;
	}

	public int getnGramLevel() {
		return nGramLevel;
	}

	public CalculateFor getCf() {
		return cf;
	}

	public AnalysisLevel getAnalysisLevel() {
		return analysisLevel;
	}

	public CorpusType getCorpusType() {
		return corpusType;
	}

	public void setCorpusType(CorpusType corpusType) {
		this.corpusType = corpusType;
	}

	public boolean isGosOrthMode() {
		return gosOrthMode;
	}

	public void setGosOrthMode(boolean gosOrthMode) {
		this.gosOrthMode = gosOrthMode;
	}

	public Map<String, Object> getSolarHeadBlockFilter() {
		return solarHeadBlockFilter;
	}

	public void setSolarHeadBlockFilter(Map<String, Object> solarHeadBlockFilter) {
		this.solarHeadBlockFilter = solarHeadBlockFilter;
	}

	public boolean isUseDB() {
		return useDB;
	}

	public void setUseDB(boolean useDB) {
		if (useDB && db == null) {
			db = new RDB();
		}
		this.useDB = useDB;
	}

	/**
	 * Stores results from this batch to a database and clears results map
	 */
	public void storeTmpResultsToDB() {
		try {
			db.writeBatch(result);
			result = new ConcurrentHashMap<>();
		} catch (UnsupportedEncodingException e) {
			e.printStackTrace();
		}
	}

	public boolean isAnalysisProducedResults() {
		return analysisProducedResults;
	}
}