[FEAT] ngrams extractor.

6189bebd · delanoe · 4d03ec71 · 6189bebd
Commit 6189bebd authored Nov 04, 2015 by delanoe
Hide whitespace changes
Inline Side-by-side

Showing with 2 additions and 0 deletions

NgramsExtractor.py parsing/NgramsExtractors/NgramsExtractor.py +2 -0

No files found.
--- a/parsing/NgramsExtractors/NgramsExtractor.py
+++ b/parsing/NgramsExtractors/NgramsExtractor.py
@@ -10,6 +10,8 @@ class NgramsExtractor:
    This method can be overriden.
    """
    def __init__(self, rule="{<JJ.*>*<NN.*|>+<JJ.*>*}"):
+    # TODO add this regex
+    #'^((VBD,|VBG,|VBN,|CD.?,|JJ.?,|\?,){0,2}?(N.?.?,|\?,)+?(CD.,)??)+?((PREP.?|DET.?,|IN.?,|CC.?,|\?,)((VBD,|VBG,|VBN,|CD.?,|JJ.?,|\?,){0,2}?(N.?.?,|\?,)+?)+?)*?$'
        self.start()
        self._label = "NP"
        self._rule = self._label + ": " + rule