Merge branch 'Reza' into 'master' (79018720) · Commits · EC504 Spring 2024 Group Projects / Group6

CheckerCorrector/Checker.java

+8 −8

Original line number	Diff line number	Diff line
		@@ -68,7 +68,7 @@ public class Checker {
		for (String sentence : extractedSentences) {
		i++;
		//dbInterface.updateTokenInDatabase(sentence.toLowerCase(), graph);
		sentence = StringProcessor.handleApostrophe(sentence.toLowerCase());
		sentence = StringProcessor.handleApostrophe(sentence.toLowerCase(), argPars.isTurkish());
		PhraseExtractor extractorPhrase = PhraseExtractor.fromSentence(sentence, 3, 5);
		List<String> phrases = extractorPhrase.getPhrases();
		for (String phrase : phrases) {
		@@ -79,7 +79,7 @@ public class Checker {
		System.out.println("\n-------------------------------------------\n"+ "Number of update: "+ cntUpdate);
		}else if(argPars.isCheckSentence()){
		//dbInterface.updateTokenInDatabase(argPars.getSentence().toLowerCase(), graph);
		for (String phrase : PhraseExtractor.fromSentence(StringProcessor.handleApostrophe(argPars.getSentence()),3, 5).getPhrases()) {
		for (String phrase : PhraseExtractor.fromSentence(StringProcessor.handleApostrophe(argPars.getSentence(), argPars.isTurkish()),3, 5).getPhrases()) {
		dbInterface.updateTokenInDatabase(phrase.toLowerCase(), graph);
		}
		}
		@@ -105,7 +105,7 @@ public class Checker {
		manager = new HashTableMaker("SQLite/hash_database_english.db");
		}
		for (String sentence : extractedSentences) {
		sentence = StringProcessor.handleApostrophe(sentence.toLowerCase());
		sentence = StringProcessor.handleApostrophe(sentence.toLowerCase(), argPars.isTurkish());
		manager.updateDatabase(sentence.toLowerCase());
		PhraseExtractor extractorPhrase = PhraseExtractor.fromSentence(sentence, 1, 4);
		List<String> phrases = extractorPhrase.getPhrases();
		@@ -120,8 +120,8 @@ public class Checker {
		}else if(argPars.isCheckSentence()){
		try {
		HashTableMaker manager = new HashTableMaker("SQLite/hash_database_english.db");
		manager.updateDatabase(StringProcessor.handleApostrophe(argPars.getSentence().toLowerCase()));
		for (String phrase : PhraseExtractor.fromSentence(StringProcessor.handleApostrophe(argPars.getSentence().toLowerCase()),1, 4).getPhrases()) {
		manager.updateDatabase(StringProcessor.handleApostrophe(argPars.getSentence().toLowerCase(), argPars.isTurkish()));
		for (String phrase : PhraseExtractor.fromSentence(StringProcessor.handleApostrophe(argPars.getSentence().toLowerCase(), argPars.isTurkish()),1, 4).getPhrases()) {
		manager.updateDatabase(phrase.toLowerCase());
		}
		manager.closeConnection();
		@@ -136,7 +136,7 @@ public class Checker {
		HashTableMaker manager = new HashTableMaker("SQLite/hash_database_english.db");
		for (String sentence : extractedSentences) {
		System.out.println("Sentence: " + sentence);
		sentence = StringProcessor.handleApostrophe(sentence.toLowerCase());
		sentence = StringProcessor.handleApostrophe(sentence.toLowerCase(), argPars.isTurkish());
		System.out.println("*********************************************************");
		PhraseExtractor extractorPhrase = PhraseExtractor.fromSentence(sentence);
		List<String> phrases = extractorPhrase.getPhrases();
		@@ -165,13 +165,13 @@ public class Checker {
		try {
		HashTableMaker manager = new HashTableMaker("SQLite/hash_database_english.db");
		System.out.println("Sentence: " + argPars.getSentence());
		String sentence = StringProcessor.handleApostrophe(argPars.getSentence().toLowerCase());
		String sentence = StringProcessor.handleApostrophe(argPars.getSentence().toLowerCase(), argPars.isTurkish());
		int ngram = manager.nGram(sentence, 3);
		int stateMachine = dbInterface.checkTokenInDatabase(sentence.toLowerCase(), graph);
		int conf = (ngram>=0)?(int)(ngram0.2+stateMachine0.8):stateMachine;
		jsonMaker.addSentence(sentence, conf);
		System.out.println("*********************************************************");
		PhraseExtractor extractorPhrase = PhraseExtractor.fromSentence(StringProcessor.handleApostrophe(argPars.getSentence().toLowerCase()));
		PhraseExtractor extractorPhrase = PhraseExtractor.fromSentence(StringProcessor.handleApostrophe(argPars.getSentence().toLowerCase(), argPars.isTurkish()));
		List<String> phrases = extractorPhrase.getPhrases();
		for (String phrase : phrases) {
		ngram = manager.nGram(phrase.toLowerCase(), 3);

CheckerCorrector/Corrector.java

+12 −11

Original line number	Diff line number	Diff line
		@@ -2,6 +2,7 @@ import java.io.IOException;
		import java.util.ArrayList;
		import java.util.List;

		import Translator.DirectTranslatorEnglishToDutch;
		import DBinterface.DBinterface;
		import DirectedGraph.BasicGraph;
		import DirectedGraph.DirectedGraph;
		@@ -46,7 +47,7 @@ public class Corrector implements GUIListener {
		this.stringWriterGUI = StringFileWriter.of("corrected.txt");
		this.senteceIndGUI = 0;
		this.curSentenceGUI = extractedSentencesGUI.get(0);
		this.curSentenceGUI = StringProcessor.handleApostrophe(this.curSentenceGUI.toLowerCase());
		this.curSentenceGUI = StringProcessor.handleApostrophe(this.curSentenceGUI.toLowerCase(), this.argParsGUI.isTurkish());
		String tempString = dbInterfaceGUI.correctTokenInDatabase(this.curSentenceGUI.toLowerCase(), graphGUI, 1, false);
		SelectCorrectionGUI gui = new SelectCorrectionGUI(this, this.curSentenceGUI);
		}
		@@ -70,7 +71,7 @@ public class Corrector implements GUIListener {
		this.curSentenceGUI = tempString;
		String tempSentenceGUI = dbInterfaceGUI.correctTokenInDatabase(this.curSentenceGUI.toLowerCase(), graphGUI, 1, false);
		}
		this.curSentenceGUI = StringProcessor.handleApostrophe(this.curSentenceGUI.toLowerCase());
		this.curSentenceGUI = StringProcessor.handleApostrophe(this.curSentenceGUI.toLowerCase(), this.argParsGUI.isTurkish());
		return this.curSentenceGUI;
		}

		@@ -92,7 +93,7 @@ public class Corrector implements GUIListener {
		}

		this.curSentenceGUI = extractedSentencesGUI.get(senteceIndGUI);
		this.curSentenceGUI = StringProcessor.handleApostrophe(this.curSentenceGUI.toLowerCase());
		this.curSentenceGUI = StringProcessor.handleApostrophe(this.curSentenceGUI.toLowerCase(), this.argParsGUI.isTurkish());
		String tempSentenceGUI = dbInterfaceGUI.correctTokenInDatabase(this.curSentenceGUI.toLowerCase(), graphGUI, 1, false);
		return this.curSentenceGUI;

		@@ -129,7 +130,7 @@ public class Corrector implements GUIListener {
		if(argPars.isUpdateWordSimilarity()){
		if(argPars.isCheckFile()){
		wordPairDatabase.createTable();
		wordPairDatabase.processSentences(argPars.getFileName());
		wordPairDatabase.processSentences(argPars.getFileName(), argPars.isTurkish());
		}
		}else if(argPars.isTranslateToDutch()){
		DirectTranslatorEnglishToDutch directTranslator = DirectTranslatorEnglishToDutch.make();
		@@ -139,7 +140,7 @@ public class Corrector implements GUIListener {
		List<String> extractedSentences = extractor.getSentences();
		for (String sentence : extractedSentences) {
		System.out.println("Sentence: " + sentence);
		sentence = StringProcessor.handleApostrophe(sentence.toLowerCase());
		sentence = StringProcessor.handleApostrophe(sentence.toLowerCase(), argPars.isTurkish());
		String tempString = directTranslator.replaceWordsInSentence(sentence.toLowerCase());
		stringWriter.appendString(tempString);
		System.out.println("##########################################################");
		@@ -147,7 +148,7 @@ public class Corrector implements GUIListener {
		}else{

		System.out.println("Sentence: " + argPars.getSentence());
		String tempString = directTranslator.replaceWordsInSentence(StringProcessor.handleApostrophe(argPars.getSentence().toLowerCase()));
		String tempString = directTranslator.replaceWordsInSentence(StringProcessor.handleApostrophe(argPars.getSentence().toLowerCase(), argPars.isTurkish()));
		stringWriter.appendString(tempString);
		System.out.println("Translation: "+tempString);
		System.out.println("##########################################################");
		@@ -166,7 +167,7 @@ public class Corrector implements GUIListener {
		List<String> extractedSentences = extractor.getSentences();
		for (String sentence : extractedSentences) {
		System.out.println("Sentence: " + sentence);
		sentence = StringProcessor.handleApostrophe(sentence.toLowerCase());
		sentence = StringProcessor.handleApostrophe(sentence.toLowerCase(), argPars.isTurkish());
		String tempString = directTranslator.replaceWordsInSentence(sentence.toLowerCase());
		stringWriter.appendString(tempString);
		System.out.println("##########################################################");
		@@ -174,7 +175,7 @@ public class Corrector implements GUIListener {
		}else{

		System.out.println("Sentence: " + argPars.getSentence());
		String tempString = directTranslator.replaceWordsInSentence(StringProcessor.handleApostrophe(argPars.getSentence().toLowerCase()));
		String tempString = directTranslator.replaceWordsInSentence(StringProcessor.handleApostrophe(argPars.getSentence().toLowerCase(), argPars.isTurkish()));
		stringWriter.appendString(tempString);
		System.out.println("Translation: "+tempString);
		System.out.println("##########################################################");
		@@ -195,7 +196,7 @@ public class Corrector implements GUIListener {
		List<String> extractedSentences = extractor.getSentences();
		for (String sentence : extractedSentences) {
		System.out.println("Sentence: " + sentence);
		sentence = StringProcessor.handleApostrophe(sentence.toLowerCase());
		sentence = StringProcessor.handleApostrophe(sentence.toLowerCase(), argPars.isTurkish());
		String tempString = dbInterface.correctTokenInDatabase(sentence.toLowerCase(), graph, 2, true);
		stringWriter.appendString(tempString);

		@@ -211,11 +212,11 @@ public class Corrector implements GUIListener {
		}
		}else if(argPars.isCheckSentence()){
		if(argPars.isCorrectionGUI()){
		Corrector corrector = new Corrector(SentenceExtractor.ofLine(StringProcessor.handleApostrophe(argPars.getSentence().toLowerCase())), argPars);
		Corrector corrector = new Corrector(SentenceExtractor.ofLine(StringProcessor.handleApostrophe(argPars.getSentence().toLowerCase(), argPars.isTurkish())), argPars);
		corrector.start();
		}else{
		System.out.println("Sentence: " + argPars.getSentence());
		stringWriter.appendString(dbInterface.correctTokenInDatabase(StringProcessor.handleApostrophe(argPars.getSentence().toLowerCase()), graph, 2, true));
		stringWriter.appendString(dbInterface.correctTokenInDatabase(StringProcessor.handleApostrophe(argPars.getSentence().toLowerCase(), argPars.isTurkish()), graph, 2, true));
		try {
		stringWriter.writeToFile();
		System.out.println("Corrected version has been written to the file.");

CheckerCorrector/GUI/HighlighterGUI.java

+2 −2

Original line number	Diff line number	Diff line
		@@ -113,8 +113,8 @@ public class HighlighterGUI extends JFrame {
		}

		for (String phrase : phrases) {
		double conf = dbInterface.checkTokenInDatabase(StringProcessor.handleApostrophe(phrase), basicGraphClass.getGraph())*0.8;
		conf += manager.nGram(StringProcessor.handleApostrophe(phrase), 3)*0.2;
		double conf = dbInterface.checkTokenInDatabase(StringProcessor.handleApostrophe(phrase, isTurkish), basicGraphClass.getGraph())*0.8;
		conf += manager.nGram(StringProcessor.handleApostrophe(phrase, isTurkish), 3)*0.2;
		//System.out.println(phrase + "\| "+ conf);
		highlightPhrase(phrase, (int)conf);
		}

CheckerCorrector/SQLite/TurkishTranslation.txt

+261 −1

Original line number	Diff line number	Diff line
		@@ -56,3 +56,263 @@ biliyorum verb knowing
		biliyor verb knowing
		bildim verb knew
		bilmiş verb known

		ben pronoun i
		sen pronoun you (singular, informal)
		o pronoun he/she/it
		biz pronoun we
		siz pronoun you (plural or formal singular)
		onlar pronoun they
		bu pronoun this
		şu pronoun that (nearby/within sight)

		elma noun apple
		portakal noun orange
		muz noun banana
		telefon noun phone
		bilgisayar noun computer
		televizyon noun television
		araba noun car
		ev noun house
		bahçe noun garden
		ağaç noun tree
		çiçek noun flower
		kitap noun book
		kalem noun pen
		defter noun notebook
		masa noun table
		sandalye noun chair
		yatak noun bed
		yastık noun pillow
		kapı noun door
		pencere noun window
		halı noun carpet
		lamba noun lamp
		saat noun clock
		ayna noun mirror
		tablo noun painting
		fotoğraf noun photograph
		anahtar noun key
		şemsiye noun umbrella
		çanta noun bag
		ayakkabı noun shoe
		elbise noun dress
		gömlek noun shirt
		pantolon noun pants
		ceket noun coat
		çorap noun socks
		eldiven noun gloves
		şapka noun hat
		cüzdan noun wallet
		para noun money
		bilet noun ticket
		pasaport noun passport
		vize noun visa
		harita noun map
		pusula noun compass
		şişe noun bottle
		su noun water
		meyve noun fruit
		suyu noun juice
		kahve noun coffee
		çay noun tea
		süt noun milk
		ekmek noun bread
		peynir noun cheese
		yumurta noun egg
		et noun meat
		balık noun fish
		tavuk noun chicken
		pirinç noun rice
		makarna noun pasta
		salata noun salad
		çorba noun soup
		tuz noun salt
		biber noun pepper
		şeker noun sugar
		yağ noun oil
		sirke noun vinegar
		bıçak noun knife
		çatal noun fork
		kaşık noun spoon
		tabak noun plate
		bardak noun glass
		fincan noun cup
		okul noun school
		öğrenci noun student
		öğretmen noun teacher
		otobüs noun bus
		hastane noun hospital
		doktor noun doctor
		hemşire noun nurse
		polis noun police officer
		market noun market
		fırın noun bakery
		eczane noun pharmacy
		anne noun mother
		baba noun father
		kardeş noun sibling
		arkadaş noun friend
		güneş noun sun
		ay noun moon
		yıldız noun star
		gezegen noun planet
		gökyüzü noun sky
		bulut noun cloud
		yağmur noun rain
		kar noun snow
		rüzgar noun wind
		deniz noun sea
		sahil noun beach
		kum noun sand
		orman noun forest
		ağaç noun tree
		yaprak noun leaf
		çiçek noun flower
		hayvan noun animal
		kuş noun bird
		balık noun fish
		böcek noun insect
		yol noun road
		köprü noun bridge
		bina noun building
		sokak noun street
		dükkan noun shop
		restoran noun restaurant
		mutfak noun kitchen
		oda noun room
		yatak noun bed
		masa noun table
		sandalye noun chair
		televizyon noun television
		bilgisayar noun computer
		renk noun color
		kırmızı noun red
		mavi noun blue
		yeşil noun green
		sarı noun yellow
		turuncu noun orange
		mor noun purple
		siyah noun black
		beyaz noun white
		kahverengi noun brown
		pembe noun pink
		gri noun gray
		gün noun day
		hafta noun week
		ay noun month
		yıl noun year
		saat noun hour
		dakika noun minute
		saniye noun second
		zaman noun time
		sabah noun morning
		öğle noun noon
		akşam noun evening
		gece noun night
		sıcak noun hot
		soğuk noun cold
		iyi noun good
		kötü noun bad
		büyük noun big
		küçük noun small
		uzun noun long
		kısa noun short
		kolay noun easy
		zor noun difficult
		güzel adjective beautiful
		yakışıklı adjective handsome
		çirkin adjective ugly
		genç adjective young
		yaşlı adjective old
		uzun adjective tall
		kısa adjective short
		şişman adjective fat
		zayıf adjective thin
		akıllı adjective smart
		aptal adjective stupid
		zengin adjective rich
		fakir adjective poor
		mutlu adjective happy
		üzgün adjective sad
		kızgın adjective angry
		hasta adjective sick
		yorgun adjective tired
		aç adjective hungry
		tok adjective full
		temiz adjective clean
		kirli adjective dirty
		hızlı adjective fast
		yavaş adjective slow
		yeni adjective new
		eski adjective old (for objects)
		sıcak adjective hot
		soğuk adjective cold
		lezzetli adjective delicious
		tatsız adjective tasteless
		güçlü adjective strong
		zayıf adjective weak (not just physically)
		korkak adjective cowardly
		cesur adjective brave
		komik adjective funny
		sıkıcı adjective boring
		ilginç adjective interesting
		tehlikeli adjective dangerous
		güvenli adjective safe
		pahalı adjective expensive
		ucuz adjective cheap
		dolu adjective full
		boş adjective empty
		sert adjective hard
		yumuşak adjective soft
		kuru adjective dry
		ıslak adjective wet
		karanlık adjective dark
		aydınlık adjective light/bright
		çabuk adverb quickly
		yavaşça adverb slowly
		dikkatlice adverb carefully
		kolayca adverb easily
		sık sık adverb often
		bazen adverb sometimes
		asla adverb never
		her zaman adverb always
		burada adverb here
		orada adverb there
		şurada adverb nearby
		yukarıda adverb above
		aşağıda adverb below
		ileride adverb forward
		geride adverb behind
		neşeyle adverb happily
		üzgünce adverb sadly
		sessizce adverb quietly
		gürültüyle adverb loudly
		kibarca adverb politely
		kaba bir şekilde adverb rudely
		aceleyle adverb hurriedly
		sabırla adverb patiently
		birlikte adverb together
		yalnız adverb alone
		hemen adverb immediately
		şimdi adverb now
		sonra adverb later
		zaten adverb already
		henüz adverb yet (as in "not yet")
		hâlâ adverb still
		daha adverb more
		az adverb less
		çok adverb very
		biraz adverb a little
		yeterince adverb enough
		den preposition from
		dan preposition from
		ile preposition with
		la preposition with
		için preposition inside
		e preposition to
		a preposition a
		üzerine preposition on
		i preposition object

CheckerCorrector/SQLite/token_database_english.db

(48 KiB)

File changed.

No diff preview for this file type.

View original file

View changed file