From 5a042ee0d3a571613d18c8b3038eeada0a0a902e Mon Sep 17 00:00:00 2001
From: Matthew Honnibal <honnibal@gmail.com>
Date: Mon, 20 Jul 2015 01:35:11 +0200
Subject: [PATCH] * Add function to predict number of bits needed to encode
 message

---
 spacy/serialize/huffman.pyx | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/spacy/serialize/huffman.pyx b/spacy/serialize/huffman.pyx
index 3b3a4ac09..27b88f5ae 100644
--- a/spacy/serialize/huffman.pyx
+++ b/spacy/serialize/huffman.pyx
@@ -1,6 +1,7 @@
 cimport cython
 from libcpp.queue cimport priority_queue
 from libcpp.pair cimport pair
+import numpy
 
 from ..typedefs cimport attr_t
 
@@ -59,6 +60,16 @@ cdef class HuffmanCodec:
             bits.extend(self.codes[i].bits, self.codes[i].length)
         return bits
 
+    def n_bits(self, msg, overhead=0):
+        cdef int i
+        length = 0
+        for word in msg:
+            if word not in self._map:
+                return numpy.nan
+            i = self._map[word]
+            length += self.codes[i].length
+        return length + overhead * len(msg)
+
     def decode(self, bits, msg):
         node = self.root
         cdef int i = 0