strings

Value Members

1. object EmptyStringSet extends StringSet

2. object PorterStemmer

   Rewritten from http://tartarus.

3. object Stopwords extends Stopwords

4. object alphaSegmenter extends RegexSegmenter

5. def charNGrams(word: String, min: Int, max: Int): Seq[String]

   Return Strings representing all possible character sub-sequences of length between "min" and "max", with prepended "<" and appended ">" to indicate start and end of the input string.

6. def collapseDigits(word: String): String

7. val containsDigitRegex: Regex

8. object csvSegmenter extends RegexSegmenter

   For segmenting fields of a comma-separated-value file.

9. val digitsRegex: Regex

10. def editDistance(s: String, s2: String, substCost: Int = 1, deleteCost: Int = 1, insertCost: Int = 1): Int

    Implements Levenshtein Distance, with specific operation costs to go from this String to String s2.

11. object foreignWordSegmenter extends RegexSegmenter

12. def inputStreamToString(is: InputStream, encoding: String = "UTF-8"): String

    Read the entire contents of the InputStream with the given encoding, and return them as a String.

13. object nonWhitespaceClassesSegmenter extends RegexSegmenter

14. object nonWhitespaceSegmenter extends RegexSegmenter

15. def porterStem(s: String): String

16. def prefix(word: String, length: Int): String

17. def readerToString(reader: Reader): String

    Read the entire contents of the Reader and return them as a String.

18. val recentYearRegex: Regex

19. def replaceDigits(word: String): String

20. def simplifyDigits(word: String): String

    Return input string, with digits replaced, either the whole string with "<YEAR>" or "<NUM>" or just the digits replaced with "#"

21. def stringShape(word: String, maxRepetitions: Int): String

    Return a string that captures the generic "shape" of the original word, mapping lowercase alphabetics to 'a', uppercase to 'A', digits to '1', whitespace to ' '.

    Return a string that captures the generic "shape" of the original word, mapping lowercase alphabetics to 'a', uppercase to 'A', digits to '1', whitespace to ' '. Skip more than 'maxRepetitions' of the same character class.

22. def suffix(word: String, length: Int): String

23. object urlSegmenter extends RegexSegmenter

24. object wordClassesSegmenter extends RegexSegmenter

25. object wordSegmenter extends RegexSegmenter