lkrsnik/list
1
0
Fork 0
Code Issues 1 Pull Requests Releases Wiki Activity

BIG REFACTOR - erasing unused code

Browse Source
This commit is contained in:
Luka
2019-03-19 15:09:46 +01:00
parent 10666b4453
commit 2c028cd334
50 changed files with 13 additions and 4317 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
src/main/java/data/CalculateFor.java
View File

@@ -3,24 +3,6 @@ package data;
import gui.I18N;
public enum CalculateFor {
// calculateFor.WORD=word
// calculateFor.NORMALIZED_WORD=normalized word
// calculateFor.LEMMA=lemma
// calculateFor.MORPHOSYNTACTIC_SPECS=msd
// calculateFor.MORPHOSYNTACTIC_PROPERTY=oblikoskladenjska lastnost
// calculateFor.WORD_TYPE=besedna vrsta
// calculateFor.DIST_WORDS=različnica
// calculateFor.DIST_LEMMAS=lema
// WORD("različnica"),
// NORMALIZED_WORD("normalizirana različnica"),
// LEMMA("lema"),
// MORPHOSYNTACTIC_SPECS("oblikoskladenjska oznaka"),
// MORPHOSYNTACTIC_PROPERTY("oblikoskladenjska lastnost"),
// WORD_TYPE("besedna vrsta"),
// DIST_WORDS("različnica"),
// DIST_LEMMAS("lema");
WORD("calculateFor.WORD"),
LOWERCASE_WORD("calculateFor.LOWERCASE_WORD"),
NORMALIZED_WORD("calculateFor.NORMALIZED_WORD"),
@@ -44,7 +26,6 @@ public enum CalculateFor {
public static CalculateFor factory(String cf) {
if (cf != null) {
// String name = I18N.findI18NString(cf, "calculateFor");
if (WORD.toString().equals(cf)) {
return WORD;
}
@@ -275,27 +256,4 @@ public enum CalculateFor {
return null;
}
}
// public String toPercentString() {
// switch(this){
// case WORD:
// return "Delež glede na vse različnice";
// case NORMALIZED_WORD:
// return "Delež glede na vse normalizirane različnice";
// case LEMMA:
// return "Delež glede na vse leme";
// case MORPHOSYNTACTIC_SPECS:
// return "Delež glede na vse oblikoskladenjske oznake";
// case MORPHOSYNTACTIC_PROPERTY:
// return "Delež glede na vse oblikoskladenjske lastnosti";
// case WORD_TYPE:
// return "Delež glede na vse besedne vrste";
// case DIST_WORDS:
// return "Delež glede na vse različnice";
// case DIST_LEMMAS:
// return "Delež glede na vse leme";
// default:
// return null;
// }
// }
}

9
src/main/java/data/Collocability.java
View File

@@ -74,13 +74,4 @@ public enum Collocability {
return null;
}
}
// public String toPercentString() {
// switch(this){
// case DICE:
// return "Delež glede na vse različnice";
// default:
// return null;
// }
// }
}

35
src/main/java/data/Corpus.java
View File

@@ -17,7 +17,6 @@ import org.apache.logging.log4j.Logger;
import data.Enums.solar.SolarFilters;
import gui.ValidationUtil;
import javafx.collections.ObservableList;
import org.controlsfx.control.CheckComboBox;
public class Corpus {
public final static Logger logger = LogManager.getLogger(Corpus.class);
@@ -33,7 +32,6 @@ public class Corpus {
public HashMap<String, ObservableList<String>> solarSelectedFilters; // if solar selected
private HashMap<String, HashSet<String>> solarFiltersForXML; // if solar - used while parsing xml
private boolean gosOrthMode;
boolean hasMsdData;
private ArrayList<String> validationErrors;
private String corpusName = "";
private String punctuation = "punctuation.COMMA";
@@ -48,7 +46,6 @@ public class Corpus {
}
public void setCorpusName(String corpusName) {
// System.out.println(corpusName);
this.corpusName = corpusName;
logger.info("Corpus.set: ", corpusName);
}
@@ -58,7 +55,6 @@ public class Corpus {
}
public void setPunctuation(String punctuation) {
// System.out.println(corpusName);
this.punctuation = punctuation;
logger.info("Punctuation.set: ", punctuation);
}
@@ -99,10 +95,6 @@ public class Corpus {
logger.info("Corpus.set: ", detectedCorpusFiles);
}
public boolean isHeaderRead() {
return headerRead;
}
public void setHeaderRead(boolean headerRead) {
this.headerRead = headerRead;
}
@@ -128,11 +120,6 @@ public class Corpus {
}
return FXCollections.observableArrayList(al);
}
//
// public ObservableList<String> getFormattedTaxonomy() {
// ArrayList<String> al = Tax.getTaxonomyFormatted(new ArrayList<>(taxonomy), corpusType);
// return FXCollections.observableArrayList(al);
// }
public void setTaxonomy(ObservableList<String> taxonomy) {
this.taxonomy = new ArrayList<>();
@@ -155,15 +142,6 @@ public class Corpus {
return solarSelectedFilters;
}
public void setSolarSelectedFilters(HashMap<String, ObservableList<String>> solarFilters) {
this.solarSelectedFilters = solarFilters;
logger.info("Corpus.set: ", solarFilters);
}
public HashMap<String, HashSet<String>> getSolarFiltersForXML() {
return solarFiltersForXML;
}
public void setSolarFiltersForXML(HashMap<String, HashSet<String>> solarFiltersForXML) {
this.solarFiltersForXML = solarFiltersForXML;
logger.info("Corpus.set: ", solarFiltersForXML);
@@ -173,23 +151,10 @@ public class Corpus {
return gosOrthMode;
}
public void setGosOrthMode(boolean gosOrthMode) {
this.gosOrthMode = gosOrthMode;
logger.info("Corpus.set: ", gosOrthMode);
}
public ArrayList<String> getValidationErrors() {
return validationErrors;
}
public String getValidationErrorsToString() {
return StringUtils.join(validationErrors, "\n - ");
}
public void setValidationErrors(ArrayList<String> validationErrors) {
this.validationErrors = validationErrors;
}
public boolean validate() {
if (corpusType == null) {
validationErrors.add(I18N.get("message.LABEL_RESULTS_CORPUS_TYPE_NOT_SET"));

12
src/main/java/data/Enums/InflectedJosTypes.java
View File

@@ -1,12 +0,0 @@
package data.Enums;
import java.util.Arrays;
import java.util.HashSet;
public class InflectedJosTypes {
public static final HashSet<Character> inflectedJosTypes = new HashSet<>();
static {
inflectedJosTypes.addAll(Arrays.asList('S', 'G', 'P'));
}
}

68
src/main/java/data/Enums/Msd.java
View File

@@ -1,68 +0,0 @@
package data.Enums;
import java.util.HashMap;
public enum Msd {
NOUN("samostalnik", 'S', "Noun", 'N', 5),
VERB("glagol", 'G', "Verb", 'V', 7),
ADJECTIVE("pridevnik", 'P', "Adjective", 'A', 6),
ADVERB("prislov", 'R', "Adverb", 'R', 2),
PRONOUN("zaimek", 'Z', "Pronoun", 'P', 8),
NUMERAL("števnik", 'K', "Numeral", 'M', 6),
PREPOSITION("predlog", 'D', "Preposition", 'S', 1),
CONJUNCTION("veznik", 'V', "Conjunction", 'C', 1),
PARTICLE("členek", 'L', "Particle", 'Q', 0),
INTERJECTION("medmet", 'M', "Interjection", 'I', 0),
ABBREVIATION("okrajšava", 'O', "Abbreviation", 'Y', 0),
RESIDUAL("neuvrščeno", 'N', "Residual", 'X', 1);
private final String siName;
private final Character siCode;
private final String enName;
private final Character enCode;
private final Integer nOfAttributes;
private static HashMap<Character, Integer> siCodeNOfAttributes;
static {
siCodeNOfAttributes = new HashMap<>();
for (Msd msd : Msd.values()) {
siCodeNOfAttributes.put(msd.getSiCode(), msd.nOfAttributes);
}
}
Msd(String siName, Character siCode, String enName, Character enCode, int nOfAttributes) {
this.siName = siName;
this.siCode = siCode;
this.enName = enName;
this.enCode = enCode;
this.nOfAttributes = nOfAttributes;
}
public String getSiName() {
return siName;
}
public Character getSiCode() {
return siCode;
}
public String getEnName() {
return enName;
}
public Character getEnCode() {
return enCode;
}
/**
* Returns the number of attributes for the given type.
*
* @param msd
*
* @return
*/
public static int getMsdLengthForType(String msd) {
return siCodeNOfAttributes.get(msd.charAt(0)) + 1;
}
}

3
src/main/java/data/Enums/solar/SolarFilters.java
View File

@@ -27,9 +27,6 @@ public class SolarFilters {
SOLAR_FILTERS.put(TIP, FXCollections.observableArrayList("esej/spis", "pisni izdelek (učna ura)", "test (daljše besedilo)", "test (odgovori na vprašanja)"));
}
public static final ObservableList<String> N_GRAM_COMPUTE_FOR_FULL = FXCollections.observableArrayList("različnica", "lema", "oblikoskladenjska oznaka", "oblikoskladenjska lastnost", "besedna vrsta");
public static final ObservableList<String> N_GRAM_COMPUTE_FOR_LIMITED = FXCollections.observableArrayList("različnica", "lema");
/**
* Returns filters with all possible values
*/

1
src/main/java/data/Filter.java
View File

@@ -349,7 +349,6 @@ public class Filter implements Cloneable {
}
public Object clone() throws CloneNotSupportedException{
Filter f = null;
try {

71
src/main/java/data/GigafidaJosWordType.java
View File

@@ -1,71 +0,0 @@
package data;
public enum GigafidaJosWordType {
SAMOSTALNIK("samostalnik", 'S'),
GLAGOL("glagol", 'G'),
PRIDEVNIK("pridevnik", 'P'),
PRISLOV("prislov", 'R'),
ZAIMEK("zaimek", 'Z'),
STEVNIK("stevnik", 'K'),
PREDLOG("predlog", 'D'),
VEZNIK("veznik", 'V'),
CLENEK("clenek", 'L'),
MEDMET("medmet", 'M'),
OKRAJSAVA("okrajsava", 'O');
private final String name;
private final char wordType;
GigafidaJosWordType(String name, char wordType) {
this.name = name;
this.wordType = wordType;
}
public String toString() {
return this.name;
}
public char getWordType() {
return wordType;
}
public static GigafidaJosWordType factory(String wType) {
if (wType != null) {
if (SAMOSTALNIK.toString().equals(wType)) {
return SAMOSTALNIK;
}
if (GLAGOL.toString().equals(wType)) {
return GLAGOL;
}
if (PRIDEVNIK.toString().equals(wType)) {
return PRIDEVNIK;
}
if (PRISLOV.toString().equals(wType)) {
return PRISLOV;
}
if (ZAIMEK.toString().equals(wType)) {
return ZAIMEK;
}
if (STEVNIK.toString().equals(wType)) {
return STEVNIK;
}
if (PREDLOG.toString().equals(wType)) {
return PREDLOG;
}
if (VEZNIK.toString().equals(wType)) {
return VEZNIK;
}
if (CLENEK.toString().equals(wType)) {
return CLENEK;
}
if (MEDMET.toString().equals(wType)) {
return MEDMET;
}
if (OKRAJSAVA.toString().equals(wType)) {
return OKRAJSAVA;
}
}
return null;
}
}

76
src/main/java/data/GigafidaTaxonomy.java
View File

@@ -1,76 +0,0 @@
package data;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.stream.Collectors;
import javafx.collections.FXCollections;
import javafx.collections.ObservableList;
public enum GigafidaTaxonomy {
TISK("tisk", "T"),
KNJIZNO("knjižno", "T.K"),
LEPOSLOVNO("leposlovno", "T.K.L"),
STROKOVNO("strokovno", "T.K.S"),
PERIODICNO("periodično", "T.P"),
CASOPIS("časopis", "T.P.C"),
REVIJA("revija", "T.P.R"),
INTERNET("internet", "I");
private final String name;
private final String taxonomy;
private static final ObservableList<String> FOR_COMBO_BOX;
static {
ArrayList<String> values = Arrays.stream(GigafidaTaxonomy.values()).map(x -> x.name).collect(Collectors.toCollection(ArrayList::new));
FOR_COMBO_BOX = FXCollections.observableArrayList(values);
}
GigafidaTaxonomy(String name, String taxonomy) {
this.name = name;
this.taxonomy = taxonomy;
}
public String toString() {
return this.name;
}
public String getTaxonomnyString() {
return this.taxonomy;
}
public static GigafidaTaxonomy factory(String tax) {
if (tax != null) {
if (TISK.toString().equals(tax)) {
return TISK;
}
if (KNJIZNO.toString().equals(tax)) {
return KNJIZNO;
}
if (LEPOSLOVNO.toString().equals(tax)) {
return LEPOSLOVNO;
}
if (STROKOVNO.toString().equals(tax)) {
return STROKOVNO;
}
if (PERIODICNO.toString().equals(tax)) {
return PERIODICNO;
}
if (CASOPIS.toString().equals(tax)) {
return CASOPIS;
}
if (REVIJA.toString().equals(tax)) {
return REVIJA;
}
if (INTERNET.toString().equals(tax)) {
return INTERNET;
}
}
return null;
}
public static ObservableList<String> getForComboBox() {
return FOR_COMBO_BOX;
}
}

85
src/main/java/data/GosTaxonomy.java
View File

@@ -1,85 +0,0 @@
package data;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.stream.Collectors;
import javafx.collections.FXCollections;
import javafx.collections.ObservableList;
public enum GosTaxonomy {
JAVNI("javni", "gos.T.J"),
INFORMATIVNO_IZOBRAZEVALNI("informativno-izobraževalni", "gos.T.J.I"),
RAZVEDRILNI("razvedrilni", "gos.T.J.R"),
NEJAVNI("nejavni", "gos.T.N"),
NEZASEBNI("nezasebni", "gos.T.N.N"),
ZASEBNI("zasebni", "gos.T.N.Z"),
OSEBNI_STIK("osebni stik", "gos.K.O"),
TELEFON("telefon", "gos.K.P"),
RADIO("radio", "gos.K.R"),
TELEVIZIJA("televizija", "gos.K.T");
private final String name;
private final String taxonomy;
private static final ObservableList<String> FOR_COMBO_BOX;
static {
ArrayList<String> values = Arrays.stream(GosTaxonomy.values()).map(x -> x.name).collect(Collectors.toCollection(ArrayList::new));
FOR_COMBO_BOX = FXCollections.observableArrayList(values);
}
GosTaxonomy(String name, String taxonomy) {
this.name = name;
this.taxonomy = taxonomy;
}
public String toString() {
return this.name;
}
public String getTaxonomnyString() {
return this.taxonomy;
}
public static GosTaxonomy factory(String tax) {
if (tax != null) {
if (JAVNI.toString().equals(tax)) {
return JAVNI;
}
if (INFORMATIVNO_IZOBRAZEVALNI.toString().equals(tax)) {
return INFORMATIVNO_IZOBRAZEVALNI;
}
if (RAZVEDRILNI.toString().equals(tax)) {
return RAZVEDRILNI;
}
if (NEJAVNI.toString().equals(tax)) {
return NEJAVNI;
}
if (NEZASEBNI.toString().equals(tax)) {
return NEZASEBNI;
}
if (ZASEBNI.toString().equals(tax)) {
return ZASEBNI;
}
if (OSEBNI_STIK.toString().equals(tax)) {
return OSEBNI_STIK;
}
if (TELEFON.toString().equals(tax)) {
return TELEFON;
}
if (RADIO.toString().equals(tax)) {
return RADIO;
}
if (TELEVIZIJA.toString().equals(tax)) {
return TELEVIZIJA;
}
}
return null;
}
public static ObservableList<String> getForComboBox() {
return FOR_COMBO_BOX;
}
}

3
src/main/java/data/MultipleHMKeys2.java
View File

@@ -36,15 +36,12 @@ public final class MultipleHMKeys2 implements MultipleHMKeys {
@Override
public int hashCode() {
return Objects.hash(k1, k2);
// return key.hashCode();
}
@Override
public boolean equals(Object obj) {
return (obj instanceof MultipleHMKeys2) && ((MultipleHMKeys2) obj).k1.equals(k1)
&& ((MultipleHMKeys2) obj).k2.equals(k2);
// return (obj instanceof MultipleHMKeys) && ((MultipleHMKeys) obj).key.equals(key);
}
public MultipleHMKeys[] splitNgramTo1grams(){

16
src/main/java/data/Sentence.java
View File

@@ -18,22 +18,6 @@ public class Sentence {
this.taxonomy = taxonomy;
}
// public Sentence(List<Word> words) {
// this.words = words;
// }
public Sentence(List<Word> words, List<Taxonomy> taxonomy, Map<String, String> properties) {
this.words = words;
this.taxonomy = taxonomy;
this.properties = properties;
}
public Sentence(List<Word> words, List<Taxonomy> taxonomy, String type) {
this.words = words;
this.taxonomy = taxonomy;
this.type = type;
}
public List<Word> getWords() {
return words;
}

3
src/main/java/data/Settings.java
View File

@@ -8,9 +8,6 @@ public class Settings {
public static final int CORPUS_SENTENCE_LIMIT = 50000;
public static final boolean PRINT_LOG = false;
public static final String FX_ACCENT_OK = "-fx-accent: forestgreen;";
public static final String FX_ACCENT_NOK = "-fx-accent: red;";
public static Collection<File> corpus;
public static File resultsFilePath;
}

299
src/main/java/data/Statistics.java
View File

@@ -1,299 +0,0 @@
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;
}
}

1
src/main/java/data/StatisticsNew.java
View File

@@ -18,7 +18,6 @@ import org.apache.commons.lang3.tuple.Pair;
import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import alg.inflectedJOS.WordFormation;
import data.Enums.WordLevelType;
import javafx.collections.ObservableList;
import util.Export;

78
src/main/java/data/Tax.java
View File

@@ -166,22 +166,6 @@ public class Tax {
}
}
// ArrayList<String> taxonomyString = new ArrayList<>();
// for (Taxonomy t : taxonomyResult.keySet()){
// taxonomyString.add(t.toString());
// }
// ObservableList<String> taxonomyObservableString = Tax.getTaxonomyForComboBox(corpus.getCorpusType(), new HashSet<>(taxonomyString));
// ArrayList<String> sortedTaxonomyString = new ArrayList<>();
// for (String t : taxonomyObservableString){
// sortedTaxonomyString.add(t);
// }
foundTaxHS.addAll(genFoundTax);
// assures same relative order
@@ -198,59 +182,6 @@ public class Tax {
return corpusTypesWithTaxonomy;
}
public static ArrayList<String> getTaxonomyCodes(ArrayList<Taxonomy> taxonomyNames, CorpusType corpusType) {
ArrayList<String> result = new ArrayList<>();
if (ValidationUtil.isEmpty(taxonomyNames)) {
return result;
}
LinkedHashMap<String, String> tax = new LinkedHashMap<>();
if (corpusType == CorpusType.GIGAFIDA || corpusType == CorpusType.CCKRES) {
tax = GIGAFIDA_TAXONOMY;
} else if (corpusType == CorpusType.GOS) {
tax = GOS_TAXONOMY;
}
// for easier lookup
Map<String, String> taxInversed = tax.entrySet()
.stream()
.collect(Collectors.toMap(Map.Entry::getValue, Map.Entry::getKey));
for (Taxonomy taxonomyName : taxonomyNames) {
result.add(taxInversed.get(taxonomyName.toString()));
}
return result;
}
// public static ArrayList<String> getTaxonomyFormatted(ArrayList<String> taxonomyNames, CorpusType corpusType) {
// ArrayList<String> result = new ArrayList<>();
//
// if (ValidationUtil.isEmpty(taxonomyNames)) {
// return result;
// }
//
// LinkedHashMap<String, String> tax = new LinkedHashMap<>();
//
// if (corpusType == CorpusType.GIGAFIDA || corpusType == CorpusType.CCKRES) {
// tax = GIGAFIDA_TAXONOMY;
// } else if (corpusType == CorpusType.GOS) {
// tax = GOS_TAXONOMY;
// }
//
// // for easier lookup
// Map<String, String> taxInversed = tax.entrySet()
// .stream()
// .collect(Collectors.toMap(Map.Entry::getValue, Map.Entry::getKey));
//
// for (String taxonomyName : taxonomyNames) {
// result.add(taxInversed.get(taxonomyName) + " - " + taxonomyName);
// }
//
// return result;
// }
/**
* Returns a list of proper names for codes
@@ -283,13 +214,4 @@ public class Tax {
return result;
}
public static String getLongTaxonomyName(String shortName){
if (GIGAFIDA_TAXONOMY.containsKey(shortName))
return GIGAFIDA_TAXONOMY.get(shortName);
else if(GOS_TAXONOMY.containsKey(shortName))
return GOS_TAXONOMY.get(shortName);
else
return null;
}
}

120
src/main/java/data/Taxonomy.java
View File

@@ -28,14 +28,6 @@ enum TaxonomyEnum {
// Gigafida
// KNJIZNO("knjižno", "T.K", "gigafida"),
// LEPOSLOVNO("leposlovno", "T.K.L", "gigafida"),
// STROKOVNO("strokovno", "T.K.S", "gigafida"),
// PERIODICNO("periodično", "T.P", "gigafida"),
// CASOPIS("časopis", "T.P.C", "gigafida"),
// REVIJA("revija", "T.P.R", "gigafida"),
// INTERNET("internet", "I", "gigafida"),
SSJ_TISK("SSJ.T", "SSJ.T - tisk"),
SSJ_KNJIZNO("SSJ.T.K", " SSJ.T.K - tisk-knjižno"),
SSJ_LEPOSLOVNO("SSJ.T.K.L", " SSJ.T.K.L - tisk-knjižno-leposlovno"),
@@ -148,9 +140,6 @@ enum TaxonomyEnum {
}
// Gigafida
// if (TISK.toString().equals(tax)) {
// return TISK;
// }
if (SSJ_TISK.toString().equals(tax)) {
return SSJ_TISK;
}
@@ -339,9 +328,6 @@ enum TaxonomyEnum {
}
// Gigafida
// if (TISK.toString().equals(tax)) {
// return TISK;
// }
if (SSJ_TISK.toLongNameString().equals(tax)) {
return SSJ_TISK;
}
@@ -483,7 +469,6 @@ enum TaxonomyEnum {
public static ArrayList<TaxonomyEnum> taxonomySelected(TaxonomyEnum disjointTaxonomy) {
ArrayList<TaxonomyEnum> r = new ArrayList<>();
// System.out.println(disjointTaxonomy);
if(disjointTaxonomy.equals(DISKURZ)){
r.add(DISKURZ_JAVNI);
r.add(DISKURZ_INFORMATIVNO_IZOBRAZEVALNI);
@@ -696,12 +681,8 @@ enum TaxonomyEnum {
}
public static ArrayList<TaxonomyEnum> convertStringListToTaxonomyList(ObservableList<String> stringList, Corpus corpus){
// System.out.println("1.");
// System.out.println(stringList);
ArrayList<TaxonomyEnum> taxonomyList = new ArrayList<>();
// System.out.println("INTERESTING STUFF");
// System.out.println(stringList);
for (String e : stringList) {
for (Taxonomy t : corpus.getTaxonomy()){
if (t.toLongNameString().equals(e)) {
@@ -709,18 +690,11 @@ enum TaxonomyEnum {
}
}
}
// System.out.println(taxonomyList);
// System.out.println("-----------------");
return taxonomyList;
}
public static void modifyingTaxonomy(ArrayList<TaxonomyEnum> taxonomy, ArrayList<TaxonomyEnum> checkedItemsTaxonomy, Corpus corpus){
// get taxonomies that were selected/deselected by user
// System.out.println("Print here:");
// System.out.println(taxonomy);
// System.out.println(checkedItemsTaxonomy);
// System.out.println("-------------");
Set<TaxonomyEnum> disjointTaxonomies = new HashSet<>(checkedItemsTaxonomy);
if (taxonomy != null) {
disjointTaxonomies.addAll(taxonomy);
@@ -739,7 +713,6 @@ enum TaxonomyEnum {
if(!TaxonomyEnum.convertStringListToTaxonomyList(corpus.getObservableListTaxonomy(), corpus).contains(s)){
disjointTaxonomies.remove(s);
disArr.remove(s);
// taxonomy.remove(s);
i--;
}
i++;
@@ -790,11 +763,6 @@ public class Taxonomy {
}
// public Taxonomy(String name, String longName) {
// this.name = name;
// this.longName = longName;
// }
public String toString() {
return this.name;
}
@@ -813,7 +781,6 @@ public class Taxonomy {
return t;
}
return null;
// return new Taxonomy(tax, false);
}
public static Taxonomy factoryLongName(String tax, Corpus corpus) {
@@ -822,87 +789,6 @@ public class Taxonomy {
return t;
}
return null;
// return new Taxonomy(tax, true);
}
// public static ArrayList<Taxonomy> taxonomySelected(Taxonomy disjointTaxonomy) {
// ArrayList<TaxonomyEnum> rTaxonomyEnum = TaxonomyEnum.taxonomySelected(disjointTaxonomy.getTaxonomyEnum());
//
// ArrayList<Taxonomy> r = new ArrayList<>();
//
// for(TaxonomyEnum t : rTaxonomyEnum){
// r.add(new Taxonomy(t.toString(), false));
// }
//
// return r;
// }
public static ArrayList<Taxonomy> taxonomyDeselected(Taxonomy disjointTaxonomy){
// ArrayList<TaxonomyEnum> r = new ArrayList<>();
// Map<TaxonomyEnum, TaxonomyEnum> connections = new ConcurrentHashMap<>();
// connections.put(DISKURZ_JAVNI, DISKURZ);
// connections.put(DISKURZ_INFORMATIVNO_IZOBRAZEVALNI, DISKURZ_JAVNI);
// connections.put(DISKURZ_RAZVEDRILNI, DISKURZ_JAVNI);
// connections.put(DISKURZ_NEJAVNI, DISKURZ);
// connections.put(DISKURZ_NEZASEBNI, DISKURZ_NEJAVNI);
// connections.put(DISKURZ_ZASEBNI, DISKURZ_NEJAVNI);
// connections.put(SITUACIJA_RADIO, SITUACIJA);
// connections.put(SITUACIJA_TELEVIZIJA, SITUACIJA);
// connections.put(KANAL_OSEBNI_STIK, KANAL);
// connections.put(KANAL_TELEFON, KANAL);
// connections.put(KANAL_RADIO, KANAL);
// connections.put(KANAL_TELEVIZIJA, KANAL);
//
// connections.put(SSJ_KNJIZNO, SSJ_TISK);
// connections.put(SSJ_LEPOSLOVNO, SSJ_KNJIZNO);
// connections.put(SSJ_STROKOVNO, SSJ_KNJIZNO);
// connections.put(SSJ_PERIODICNO, SSJ_TISK);
// connections.put(SSJ_CASOPIS, SSJ_PERIODICNO);
// connections.put(SSJ_REVIJA, SSJ_PERIODICNO);
// connections.put(SSJ_DRUGO, SSJ_TISK);
//
// connections.put(FT_P_GOVORNI, FT_P_PRENOSNIK);
// connections.put(FT_P_ELEKTRONSKI, FT_P_PRENOSNIK);
// connections.put(FT_P_PISNI, FT_P_PRENOSNIK);
// connections.put(FT_P_OBJAVLJENO, FT_P_PISNI);
// connections.put(FT_P_KNJIZNO, FT_P_OBJAVLJENO);
// connections.put(FT_P_PERIODICNO, FT_P_OBJAVLJENO);
// connections.put(FT_P_CASOPISNO, FT_P_OBJAVLJENO);
// connections.put(FT_P_DNEVNO, FT_P_CASOPISNO);
// connections.put(FT_P_VECKRAT_TEDENSKO, FT_P_CASOPISNO);
// connections.put(FT_P_CASOPISNO_TEDENSKO, FT_P_CASOPISNO);
// connections.put(FT_P_REVIALNO, FT_P_PERIODICNO);
// connections.put(FT_P_TEDENSKO, FT_P_REVIALNO);
// connections.put(FT_P_STIRINAJSTDNEVNO, FT_P_REVIALNO);
// connections.put(FT_P_MESECNO, FT_P_REVIALNO);
// connections.put(FT_P_REDKEJE_KOT_MESECNO, FT_P_REVIALNO);
// connections.put(FT_P_OBCASNO, FT_P_REVIALNO);
// connections.put(FT_P_NEOBJAVLJENO, FT_P_PISNI);
// connections.put(FT_P_JAVNO, FT_P_NEOBJAVLJENO);
// connections.put(FT_P_INTERNO, FT_P_NEOBJAVLJENO);
// connections.put(FT_P_ZASEBNO, FT_P_NEOBJAVLJENO);
// connections.put(FT_UMETNOSTNA, FT_ZVRST);
// connections.put(FT_PESNISKA, FT_UMETNOSTNA);
// connections.put(FT_PROZNA, FT_UMETNOSTNA);
// connections.put(FT_DRAMSKA, FT_UMETNOSTNA);
// connections.put(FT_NEUMETNOSTNA, FT_ZVRST);
// connections.put(FT_STROKOVNA, FT_NEUMETNOSTNA);
// connections.put(FT_HID, FT_STROKOVNA);
// connections.put(FT_NIT, FT_STROKOVNA);
// connections.put(FT_NESTROKOVNA, FT_NEUMETNOSTNA);
// connections.put(FT_PRAVNA, FT_NEUMETNOSTNA);
// connections.put(FT_DA, FT_LEKTORIRANO);
// connections.put(FT_NE, FT_LEKTORIRANO);
//
// TaxonomyEnum currentTaxonomy = disjointTaxonomy;
// r.add(currentTaxonomy);
// while(connections.containsKey(currentTaxonomy)){
// currentTaxonomy = connections.get(currentTaxonomy);
// r.add(currentTaxonomy);
// }
// Collections.reverse(r);
// return r;
return null;
}
public static ArrayList<Taxonomy> convertStringListToTaxonomyList(ObservableList<String> stringList, Corpus corpus){
@@ -919,7 +805,6 @@ public class Taxonomy {
}
public static ArrayList<TaxonomyEnum> taxonomyToTaxonomyEnum(ArrayList<Taxonomy> taxonomy){
// System.out.println(taxonomy);
if (taxonomy == null) {
return null;
}
@@ -934,11 +819,6 @@ public class Taxonomy {
}
public static ArrayList<Taxonomy> taxonomyEnumToTaxonomy(ArrayList<TaxonomyEnum> taxonomy, Corpus corpus){
// ArrayList<Taxonomy> r = new ArrayList<>();
// for (TaxonomyEnum t : taxonomy){
// r.add(new Taxonomy(t));
// }
// return r;
ArrayList<Taxonomy> r = new ArrayList<>();
for (TaxonomyEnum te : taxonomy){
for (Taxonomy t : corpus.getTaxonomy()){