Last active
March 4, 2018 16:07
-
-
Save mismatch/9d93bbca801a676e1b418ea0ae1d10b2 to your computer and use it in GitHub Desktop.
Calculate words frequencies in declarative way
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
import java.io.BufferedReader; | |
import java.io.Reader; | |
import java.util.Map; | |
import java.util.function.Function; | |
import java.util.regex.Pattern; | |
import static java.util.stream.Collectors.counting; | |
import static java.util.stream.Collectors.groupingBy; | |
public class WordsFrequencies { | |
private static final Pattern WORDS_REGEX = Pattern.compile("[^\\w]+"); | |
private static final List<String> IGNORED_WORDS = Arrays.asList( | |
"a", "an", "the", "in", "on", "at", "is", "are", "am", "as", "of", "if", "so"); | |
private final BufferedReader reader; | |
public WordsFrequencies(Reader reader) { | |
this.reader = reader instanceof BufferedReader | |
? (BufferedReader) reader | |
: new BufferedReader(reader); | |
} | |
public Map<String, Long> get() { | |
return reader.lines() | |
.map(String::toLowerCase) | |
.flatMap(WORDS_REGEX::splitAsStream) | |
.filter(w -> !IGNORED_WORDS.contains(w)) | |
.collect(groupingBy(Function.identity(), counting())); | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment