Resolved merge conflict (e4d135c1) · Commits · EC504 Spring 2024 Group Projects / Group6

.gitignore

+1 −0

Original line number	Diff line number	Diff line
		@@ -11,6 +11,7 @@ Crawler/target/classes/ScratchCrawler.class
		Crawler/target/classes/crawledData.txt
		*.db
		*.java
		*.class
		!CheckerCorrector/manifest*
		!CheckerCorrector/*/.java
		!Crawler/src/main/java/RobotsTXT.java

CheckerCorrector/Checker.java

+29 −16

Original line number	Diff line number	Diff line
		@@ -61,6 +61,7 @@ public class Checker {
		for (String sentence : extractedSentences) {
		i++;
		//dbInterface.updateTokenInDatabase(sentence.toLowerCase(), graph);
		sentence = StringProcessor.handleApostrophe(sentence.toLowerCase());
		PhraseExtractor extractorPhrase = PhraseExtractor.fromSentence(sentence, 3, 5);
		List<String> phrases = extractorPhrase.getPhrases();
		for (String phrase : phrases) {
		@@ -71,7 +72,7 @@ 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(argPars.getSentence(),3, 5).getPhrases()) {
		for (String phrase : PhraseExtractor.fromSentence(StringProcessor.handleApostrophe(argPars.getSentence()),3, 5).getPhrases()) {
		dbInterface.updateTokenInDatabase(phrase.toLowerCase(), graph);
		}
		}
		@@ -93,6 +94,7 @@ public class Checker {
		manager = new HashTableMaker("SQLite/hash_database_english.db");
		}
		for (String sentence : extractedSentences) {
		sentence = StringProcessor.handleApostrophe(sentence.toLowerCase());
		manager.updateDatabase(sentence.toLowerCase());
		PhraseExtractor extractorPhrase = PhraseExtractor.fromSentence(sentence, 1, 4);
		List<String> phrases = extractorPhrase.getPhrases();
		@@ -107,8 +109,8 @@ public class Checker {
		}else if(argPars.isCheckSentence()){
		try {
		HashTableMaker manager = new HashTableMaker("SQLite/hash_database_english.db");
		manager.updateDatabase(argPars.getSentence().toLowerCase());
		for (String phrase : PhraseExtractor.fromSentence(argPars.getSentence(),1, 4).getPhrases()) {
		manager.updateDatabase(StringProcessor.handleApostrophe(argPars.getSentence().toLowerCase()));
		for (String phrase : PhraseExtractor.fromSentence(StringProcessor.handleApostrophe(argPars.getSentence().toLowerCase()),1, 4).getPhrases()) {
		manager.updateDatabase(phrase.toLowerCase());
		}
		manager.closeConnection();
		@@ -123,7 +125,7 @@ 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());
		System.out.println("*********************************************************");
		PhraseExtractor extractorPhrase = PhraseExtractor.fromSentence(sentence);
		List<String> phrases = extractorPhrase.getPhrases();
		@@ -149,19 +151,30 @@ public class Checker {
		e.printStackTrace();
		}
		}else if(argPars.isCheckSentence()){

		try {
		HashTableMaker manager = new HashTableMaker("SQLite/hash_database_english.db");
		System.out.println("Sentence: " + argPars.getSentence());
		jsonMaker.addSentence(argPars.getSentence().toLowerCase(), dbInterface.checkTokenInDatabase(argPars.getSentence().toLowerCase(), graph));
		String sentence = StringProcessor.handleApostrophe(argPars.getSentence().toLowerCase());
		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(argPars.getSentence().toLowerCase());
		PhraseExtractor extractorPhrase = PhraseExtractor.fromSentence(StringProcessor.handleApostrophe(argPars.getSentence().toLowerCase()));
		List<String> phrases = extractorPhrase.getPhrases();
		for (String phrase : phrases) {
		ngram = manager.nGram(phrase.toLowerCase(), 3);
		stateMachine = dbInterface.checkTokenInDatabase(phrase.toLowerCase(), graph);
		conf = (ngram>=0)?(int)(ngram0.2+stateMachine0.8):stateMachine;
		System.out.println("Phrase: " + phrase);
		jsonMaker.addPhrase(phrase, dbInterface.checkTokenInDatabase(phrase.toLowerCase(), graph));
		jsonMaker.addPhrase(phrase, conf);
		System.out.println("------------------------------------------------------------");
		}
		jsonMaker.toJson("confidence_ourChecker.json");
		System.out.println("##########################################################");
		} catch (SQLException e) {
		e.printStackTrace();
		}
		}else if(argPars.isCheckGUI()){
		SwingUtilities.invokeLater(new Runnable() {
		@Override

CheckerCorrector/Corrector.java

+11 −4

Original line number	Diff line number	Diff line
		@@ -12,6 +12,7 @@ import util.JsonMaker;
		import util.PhraseExtractor;
		import util.SentenceExtractor;
		import util.StringFileWriter;
		import util.StringProcessor;
		import Translator.*;
		import StateMachine.*;

		@@ -36,6 +37,7 @@ 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());
		String tempString = dbInterfaceGUI.correctTokenInDatabase(this.curSentenceGUI.toLowerCase(), graphGUI, 1, false);
		SelectCorrectionGUI gui = new SelectCorrectionGUI(this, this.curSentenceGUI);
		}
		@@ -59,6 +61,7 @@ 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());
		return this.curSentenceGUI;
		}

		@@ -80,6 +83,7 @@ public class Corrector implements GUIListener {
		}

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

		@@ -112,6 +116,7 @@ public class Corrector implements GUIListener {
		List<String> extractedSentences = extractor.getSentences();
		for (String sentence : extractedSentences) {
		System.out.println("Sentence: " + sentence);
		sentence = StringProcessor.handleApostrophe(sentence.toLowerCase());
		String tempString = directTranslator.replaceWordsInSentence(sentence.toLowerCase());
		stringWriter.appendString(tempString);
		System.out.println("##########################################################");
		@@ -119,7 +124,7 @@ public class Corrector implements GUIListener {
		}else{

		System.out.println("Sentence: " + argPars.getSentence());
		String tempString = directTranslator.replaceWordsInSentence(argPars.getSentence().toLowerCase());
		String tempString = directTranslator.replaceWordsInSentence(StringProcessor.handleApostrophe(argPars.getSentence().toLowerCase()));
		stringWriter.appendString(tempString);
		System.out.println("Translation: "+tempString);
		System.out.println("##########################################################");
		@@ -138,6 +143,7 @@ public class Corrector implements GUIListener {
		List<String> extractedSentences = extractor.getSentences();
		for (String sentence : extractedSentences) {
		System.out.println("Sentence: " + sentence);
		sentence = StringProcessor.handleApostrophe(sentence.toLowerCase());
		String tempString = directTranslator.replaceWordsInSentence(sentence.toLowerCase());
		stringWriter.appendString(tempString);
		System.out.println("##########################################################");
		@@ -145,7 +151,7 @@ public class Corrector implements GUIListener {
		}else{

		System.out.println("Sentence: " + argPars.getSentence());
		String tempString = directTranslator.replaceWordsInSentence(argPars.getSentence().toLowerCase());
		String tempString = directTranslator.replaceWordsInSentence(StringProcessor.handleApostrophe(argPars.getSentence().toLowerCase()));
		stringWriter.appendString(tempString);
		System.out.println("Translation: "+tempString);
		System.out.println("##########################################################");
		@@ -166,6 +172,7 @@ public class Corrector implements GUIListener {
		List<String> extractedSentences = extractor.getSentences();
		for (String sentence : extractedSentences) {
		System.out.println("Sentence: " + sentence);
		sentence = StringProcessor.handleApostrophe(sentence.toLowerCase());
		String tempString = dbInterface.correctTokenInDatabase(sentence.toLowerCase(), graph, 2, true);
		stringWriter.appendString(tempString);

		@@ -181,11 +188,11 @@ public class Corrector implements GUIListener {
		}
		}else if(argPars.isCheckSentence()){
		if(argPars.isCorrectionGUI()){
		Corrector corrector = new Corrector(SentenceExtractor.of(argPars.getSentence()), argPars);
		Corrector corrector = new Corrector(SentenceExtractor.ofLine(StringProcessor.handleApostrophe(argPars.getSentence().toLowerCase())), argPars);
		corrector.start();
		}else{
		System.out.println("Sentence: " + argPars.getSentence());
		stringWriter.appendString(dbInterface.correctTokenInDatabase(argPars.getSentence().toLowerCase(), graph, 2, true));
		stringWriter.appendString(dbInterface.correctTokenInDatabase(StringProcessor.handleApostrophe(argPars.getSentence().toLowerCase()), graph, 2, true));
		try {
		stringWriter.writeToFile();
		System.out.println("Corrected version has been written to the file.");

CheckerCorrector/DBinterface/DBinterface.java

+16 −9

Original line number	Diff line number	Diff line
		@@ -85,7 +85,7 @@ public class DBinterface {

		int confidence = SM.isStateMachineFollowed(graph, actions, initialState, initialConf);
		//System.out.print("The confidence score is: "+ confidence + "\n");
		return confidence;
		return ((int)((double)confidence100.0/(actions.size()15)));
		} catch (SQLException e) {
		e.printStackTrace();
		}
		@@ -128,6 +128,9 @@ public class DBinterface {
		int flagsCorrectioncnt = 0;
		boolean flagTypoCorrectionAccepted = true;
		StringFileWriter sfw = StringFileWriter.of("correction_details.txt", "\n", isNotGUI);

		//System.out.println(flagsCorrection);

		try (Connection connection = DriverManager.getConnection(this.url)) {

		// Lookup each token in the database and categorize it
		@@ -152,7 +155,7 @@ public class DBinterface {

		initialConf += 5;
		if(flagsCorrection.isEmpty()){
		sfw.appendString(token + " -> "+ tokenCorrected + "*");
		sfw.appendString(token + " (REPLACE WITH) -> "+ tokenCorrected + "*");
		}else if(!flagsCorrection.get(flagsCorrectioncnt) && isNotGUI){
		flagTypoCorrectionAccepted = false;
		//tokenList.set(i, "nan");
		@@ -162,7 +165,7 @@ public class DBinterface {
		}
		flagsCorrectioncnt++;
		}
		// ////System.out.print("Corrected token: " + token + " -> " + tokenCorrected);
		//System.out.println("Corrected token: " + token + " -> " + tokenCorrected);

		query = "SELECT role FROM word_roles WHERE word = '" + tokenCorrected + "';";
		// Replace the token with its role
		@@ -172,6 +175,8 @@ public class DBinterface {
		role = resultSet.getString("role");
		// ////System.out.print("\| Second try: "+ token + " -> " + role);
		tokens[i] = role;
		}else{
		tokenList.set(i,tokenCorrected);
		}
		}

		@@ -203,7 +208,8 @@ public class DBinterface {
		int biasToken = 0;

		//if(!isNotGUI)
		// System.out.println(flagsCorrection);
		//System.out.println(flags);
		//System.out.println(suggested);
		for(int i=0; i<suggested.size(); i++){
		if(seenDot){
		//indDotseen = i;
		@@ -224,8 +230,8 @@ public class DBinterface {
		if(i+biasToken<tokenList.size()){

		if(flagsCorrection.isEmpty()){
		sfw.appendString(tokenList.get(i) + " (REPLACE WITH) -> "+ word);
		tokenList.set(i+biasToken,word);
		sfw.appendString(tokenList.get(i) + " -> "+ word);
		}else if(flagsCorrection.get(flagsCorrectioncnt)){

		tokenList.set(i+biasToken,word);
		@@ -234,7 +240,7 @@ public class DBinterface {

		}else{
		if(flagsCorrection.isEmpty()){
		sfw.appendString("IND: "+ i + " -> "+ word);
		sfw.appendString("(INSERTION INTO INDEX): "+ i + " -> "+ word);
		tokenList.add(word);
		}else if(flagsCorrection.get(flagsCorrectioncnt)){
		tokenList.add(word);
		@@ -247,7 +253,7 @@ public class DBinterface {
		}else if(flags.get(i+delCnt)==2){
		delCnt++;
		if(flagsCorrection.isEmpty()){
		sfw.appendString(tokenList.get(i) + " -> X");
		sfw.appendString(tokenList.get(i) + "-> (REMOVE)");
		tokenList.remove(i+biasToken);
		}else if(flagsCorrection.get(flagsCorrectioncnt)){
		tokenList.remove(i+biasToken);
		@@ -267,7 +273,7 @@ public class DBinterface {
		////System.out.println("Here I am: "+ word);

		if(flagsCorrection.isEmpty()){
		sfw.appendString("IND: "+ i + " -> "+ word);
		sfw.appendString("(INSERTION INTO THE END) -> "+ word);
		if(i<tokenList.size()){
		tokenList.add(i+biasToken,word);
		}else{
		@@ -304,6 +310,7 @@ public class DBinterface {
		StringBuilder result = new StringBuilder();
		boolean flagStart = false;
		int i = 0;
		//System.out.println(tokenList);
		for (String token : tokenList) {
		if(i==indDotseen)
		break;

CheckerCorrector/DirectedGraph/BasicGraph.java

+4 −4

Original line number	Diff line number	Diff line
		@@ -168,11 +168,11 @@ public class BasicGraph {
		graph.addEdge(State.ADVERB, State.VERB);
		edgeList.put(State.ADVERB.toString(), State.VERB.toString());

		graph.addEdge(State.NOUN, State.NOUN);
		edgeList.put(State.NOUN.toString(), State.NOUN.toString());
		//graph.addEdge(State.NOUN, State.NOUN);
		//edgeList.put(State.NOUN.toString(), State.NOUN.toString());

		graph.addEdge(State.ADJECTIVE, State.ADJECTIVE);
		edgeList.put(State.ADJECTIVE.toString(), State.ADJECTIVE.toString());
		//graph.addEdge(State.ADJECTIVE, State.ADJECTIVE);
		//edgeList.put(State.ADJECTIVE.toString(), State.ADJECTIVE.toString());
		}
		public DirectedGraph<State> getGraph() {
		return graph;