Created
April 28, 2021 14:37
-
-
Save samiraghayarov/072ffe5006db2ec5f257c08d7ef49ed8 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
package com.octagon; | |
import java.io.BufferedReader; | |
import java.io.IOException; | |
import java.io.InputStream; | |
import java.io.InputStreamReader; | |
import java.net.URISyntaxException; | |
import java.nio.charset.StandardCharsets; | |
import java.util.Arrays; | |
import java.util.HashSet; | |
import java.util.List; | |
import java.util.Set; | |
import java.util.stream.Collectors; | |
import java.util.stream.Stream; | |
public class ApplicationMain { | |
private static final String DELIMITER = " "; | |
public static void main(String[] args) throws URISyntaxException, IOException { | |
Set<String> stopwords = new HashSet<>(); | |
Set<String> fileNames = new HashSet<>(); | |
Boolean upperCaseFlag = Boolean.FALSE; | |
for (int i = 0; i < args.length; i += 2) { | |
if ("-F".equals(args[i])) { | |
fileNames = paramsToSet(args[i + 1]); | |
System.out.println(fileNames); | |
} else if ("-S".equals(args[i])) { | |
stopwords = paramsToSet(args[i + 1]); | |
System.out.println(stopwords); | |
} else if ("-L".equals(args[i])) { | |
upperCaseFlag = Boolean.TRUE; | |
System.out.println(upperCaseFlag); | |
} | |
} | |
for (String fileName : fileNames) { | |
int count = countWords(stopwords, upperCaseFlag, fileName); | |
System.out.printf("%s has %d words , stopwordsFlag %b , upperCaseFlag %b", fileName, count, | |
!stopwords.isEmpty(), upperCaseFlag); | |
} | |
} | |
private static Set<String> paramsToSet(String arg) { | |
return Arrays.stream(arg.split(",")) | |
.collect(Collectors.toSet()); | |
} | |
private static int countWords(Set<String> stopwords, Boolean upperCaseFlag, String fileName) throws IOException, URISyntaxException { | |
Stream<String> lines = readFile(fileName); | |
//flattened words | |
List<String> words = lines.flatMap(line -> Arrays.stream(line.trim().split(DELIMITER))) | |
.filter(word -> isStopWord(word, stopwords)) | |
.filter(word -> isUpperCase(word, upperCaseFlag)) | |
.collect(Collectors.toList()); | |
return words.size(); | |
} | |
public static Stream<String> readFile(String fileName) throws IOException, URISyntaxException { | |
InputStream resource = ApplicationMain.class.getClassLoader().getResourceAsStream(fileName); | |
InputStreamReader inputStreamReader = new InputStreamReader( | |
resource, | |
StandardCharsets.UTF_8 | |
); | |
return new BufferedReader(inputStreamReader).lines(); | |
} | |
private static boolean isUpperCase(String word, boolean upperCaseFlag) { | |
if (!upperCaseFlag) return true; | |
return !word.isEmpty() && Character.isUpperCase(word.charAt(0)); | |
} | |
private static boolean isStopWord(String word, Set<String> stopwords) { | |
return !word.isEmpty() && !stopwords.contains(word); | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment