Last active
November 30, 2021 08:39
-
-
Save uzilan/a0da4f1dd152f7d96804fe68425f150f 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 zer.ubba.bel; | |
import java.nio.file.Files; | |
import java.nio.file.Paths; | |
import java.util.List; | |
import java.util.Map; | |
import java.util.regex.Pattern; | |
import static java.lang.ClassLoader.getSystemResource; | |
import static java.util.Arrays.stream; | |
import static java.util.function.Function.identity; | |
import static java.util.stream.Collectors.counting; | |
import static java.util.stream.Collectors.groupingBy; | |
public class JavaBible { | |
private final List<String> boringWords = List.of(("the,and,of,to,that,for,in,i,his,a,with,it,be,is,not,they,thou") | |
.split(",")); | |
Map<String, Long> readTheBible() throws Exception { | |
final var path = Paths.get(getSystemResource("bible.txt").toURI()); | |
return Files.lines(path) | |
.flatMap(line -> stream(line.split(" "))) | |
.filter(Pattern.compile("^\\w+").asMatchPredicate()) | |
.map(String::toLowerCase) | |
.filter(word -> !boringWords.contains(word)) | |
.collect(groupingBy(identity(), counting())); | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment