private static String unescapeKeywords(String term) {
return splitIdentifiers
.splitAsStream(term + " ") // add space such that the ending "::" is not lost
.map(BaseRascalREPL::unescapeKeyword)
.collect(Collectors.joining("::"))
.trim();
}
public static void main(String[] args) throws IOException {
Pattern wordSeparator = Pattern.compile("[\\P{L}]+");
try (Stream<String> lines = Files.lines(Paths.get("frankenstein.txt"))) {
System.out.println(
lines.flatMap(l -> wordSeparator.splitAsStream(l)).filter(x -> x.length() > 10).count());
}
}
private static Collection<String> escapeKeywords(Collection<String> suggestions) {
return suggestions
.stream()
.map(
s ->
splitIdentifiers
.splitAsStream(s + " ") // add space such that the ending "::" is not lost
.map(BaseRascalREPL::escapeKeyword)
.collect(Collectors.joining("::"))
.trim())
.collect(Collectors.toList());
}
private Set<Word> addTweetToCloud(Tweet tweet) {
// System.out.println("Add tweet to cloud");
String text =
tweet
.getTextWithout(UrlTweetEntry.class)
.getTextWithout(UserMentionTweetEntry.class)
.get();
Set<Word> tweetWords =
pattern
.splitAsStream(text)
.map(l -> trimTail(l)) // no bad word tails
.filter(l -> l.length() > 2) // longer than 2 characters
.filter(l -> !urlPattern.matcher(l).matches()) // no url
.filter(l -> !StopList.contains(l)) // not in stoplist
.map(l -> new Word(l, -2)) // convert to Word
.collect(Collectors.toSet()); // collect
List<Word> words = new ArrayList<>(wordle.wordsProperty().get());
tweetWords.removeAll(words);
words.addAll(tweetWords);
Platform.runLater(() -> wordle.wordsProperty().set(words));
return tweetWords;
}
public Stream<String> parse(String text) {
return SPLIT_PATTERN.splitAsStream(text).map(String::toLowerCase);
}