Merge branch 'Reza' into 'master' (bd7ea480) · Commits · EC504 Spring 2024 Group Projects / Group6

CheckerCorrector/Checker.java

+8 −6

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();
		@@ -151,9 +153,9 @@ public class Checker {
		}else if(argPars.isCheckSentence()){

		System.out.println("Sentence: " + argPars.getSentence());
		jsonMaker.addSentence(argPars.getSentence().toLowerCase(), dbInterface.checkTokenInDatabase(argPars.getSentence().toLowerCase(), graph));
		jsonMaker.addSentence(StringProcessor.handleApostrophe(argPars.getSentence().toLowerCase()), dbInterface.checkTokenInDatabase(argPars.getSentence().toLowerCase(), graph));
		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) {
		System.out.println("Phrase: " + phrase);

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.of(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/util/StringProcessor.java

+52 −0

Original line number	Diff line number	Diff line
		@@ -19,4 +19,56 @@ public class StringProcessor {
		return "";
		}
		}
		public static String handleApostrophe(String text) {
		String[][] contractions = {
		{"won't", "will not"},
		{"can't", "cannot"},
		{"isn't", "is not"},
		{"aren't", "are not"},
		{"wasn't", "was not"},
		{"weren't", "were not"},
		{"haven't", "have not"},
		{"hasn't", "has not"},
		{"hadn't", "had not"},
		{"doesn't", "does not"},
		{"don't", "do not"},
		{"didn't", "did not"},
		{"shouldn't", "should not"},
		{"couldn't", "could not"},
		{"mustn't", "must not"},
		{"mightn't", "might not"},
		{"wouldn't", "would not"},
		{"it's", "it is"},
		{"he's", "he is"},
		{"she's", "she is"},
		{"that's", "that is"},
		{"who's", "who is"},
		{"what's", "what is"},
		{"there's", "there is"},
		{"here's", "here is"},
		{"let's", "let us"},
		{"they're", "they are"},
		{"we're", "we are"},
		{"you're", "you are"}

		};
		for (String[] contraction : contractions) {
		text = text.replaceAll("\\b" + contraction[0] + "\\b", contraction[1]);
		}
		String regex = "(\\w+)'s\\s+(\\w+)";
		Pattern pattern = Pattern.compile(regex);
		Matcher matcher = pattern.matcher(text);
		StringBuilder result = new StringBuilder();
		int lastEnd = 0;
		while (matcher.find()) {
		result.append(text, lastEnd, matcher.start());
		result.append(matcher.group(2)).append(" of ").append(matcher.group(1));
		lastEnd = matcher.end();
		}
		result.append(text.substring(lastEnd));
		text = result.toString();
		text = text.replaceAll("[\\'’]", "");

		return text;
		}
		}