diff --git a/languedoc.py b/languedoc.py
--- a/languedoc.py
+++ b/languedoc.py
@@ -3,11 +3,12 @@ import re
 import random
 import itertools
 
+from shared import identify, extract_ngram_freqs, TOP_NGRAM_COUNT
+
 random.seed(19181028)
 
 CROSSVALIDATION_SOURCE_COUNT = 5
 TEST_LENS = [8, 16, 32, 64]
-TOP_NGRAM_COUNT = 6000
 
 
 def preprocess(text):
@@ -15,22 +16,6 @@ def preprocess(text):
 	return text.lower()
 
 
-def extract_ngram_freqs(text, k):
-	n = len(text)
-	d = dict()
-
-	for i in range(0, n-k+1):
-		key = text[i:i+k]
-		if key.isspace():
-			continue
-
-		d[key] = d.get(key, 0) + 1
-
-	count = sum(d.values())
-
-	return {key: val/count for (key, val) in d.items()}
-
-
 def merge_ngram_freqs(freqs):
 	n = len(freqs)
 	res = dict()
@@ -141,12 +126,6 @@ def cross_validate(sample_sets):
 	return score / max_score, (score, max_score)
 
 
-def identify(text, models):
-	sample = Sample(text=text)
-
-	return min(map(lambda m: (m.compare(sample), m.language), models))[1]
-
-
 DATA_DIR = os.path.join(os.path.dirname(__file__), "data")
 LANG_DIRS = sorted([x.path for x in os.scandir(DATA_DIR)])