added readme

README.md

@@ -0,0 +1,13 @@
+__RLTK__
+
+An attempt to manually port some of nltk to rust.
+
+Currently in it's infancy: 
+* rltk::lm::preprocessing::pad_both_ends(\["a","b","c"], 2) -> "\<s>", "a", "b", "c", "\</s>"]
+* rltk::util::pad_sequence == same as above with customisation
+* rltk::util::pad_sequence_left == same
+* rltk::util::pad_sequence_right == same
+* rltk::util::ngrams(\["a","b","c"],2) -> \[\["a"], \["b"], \["b"], \["c"]]
+* rltk::util::bigrams(\["a","b","c"]) == ngrams(..., 2) 
+* rltk::util::trigrams(\["a","b","c"]) == ngrams(..., 3)
+

src/util/mod.rs

@@ -56,6 +56,13 @@ pub fn ngrams<'a>(sequence: impl Iterator<Item=&'a &'a str> + 'a, n: usize) -> i
     ngrams::NGramSequenceIter::new(sequence, n)
 }
 
+pub fn bigrams<'a>(sequence: impl Iterator<Item=&'a &'a str> + 'a) -> impl Iterator<Item=impl Iterator<Item=&'a &'a str> + 'a> + 'a {
+    ngrams::NGramSequenceIter::new(sequence, 2)
+}
+
+pub fn trigrams<'a>(sequence: impl Iterator<Item=&'a &'a str> + 'a) -> impl Iterator<Item=impl Iterator<Item=&'a &'a str> + 'a> + 'a {
+    ngrams::NGramSequenceIter::new(sequence, 3)
+}
 
 #[cfg(test)]
 mod tests {