Set window length constant

Signed-off-by: Jono Yang <jyang@nexb.com>

Author: JonoYang

src/matchcode_toolkit/fingerprinting.py

@@ -10,9 +10,8 @@
 import binascii
 import re
 
-from samecode.halohash import BitAverageHaloHash
 from licensedcode.tokenize import query_lines
-
+from samecode.halohash import BitAverageHaloHash
 
 # A collection of directory fingerprints that we want to avoid
 IGNORED_DIRECTORY_FINGERPRINTS = [
@@ -21,6 +20,8 @@
     "0000000000000000000000000000000000000000",
 ]
 
+SNIPPET_WINDOW_LENGTH = 16
+
 
 def _create_directory_fingerprint(inputs):
     """
@@ -166,6 +167,7 @@ def create_halohash_chunks(bah128):
 query_pattern = "[^_\\W]+"
 word_splitter = re.compile(query_pattern, re.UNICODE).findall
 
+
 # TODO: return line numbers from where the token was taken
 def _tokenizer(text):
     """
@@ -196,7 +198,9 @@ def tokenizer(text):
     return _tokenizer(text.lower())
 
 
-def get_file_fingerprint_hashes(location, ngram_length=5, window_length=16, include_ngrams=False, **kwargs):
+def get_file_fingerprint_hashes(
+    location, ngram_length=5, window_length=SNIPPET_WINDOW_LENGTH, include_ngrams=False, **kwargs
+):
     """
     Return a mapping of fingerprint hashes for the file at `location`
 
@@ -227,7 +231,9 @@ def get_file_fingerprint_hashes(location, ngram_length=5, window_length=16, incl
     )
 
 
-def create_file_fingerprints(content, ngram_length=5, window_length=16, include_ngrams=False):
+def create_file_fingerprints(
+    content, ngram_length=5, window_length=SNIPPET_WINDOW_LENGTH, include_ngrams=False
+):
     """
     Return a mapping of halo1 and snippet hashes from content string
     """

src/matchcode_toolkit/plugin_fingerprint.py

@@ -8,7 +8,6 @@
 #
 
 import attr
-
 from commoncode.cliutils import SCAN_GROUP
 from commoncode.cliutils import PluggableCommandLineOption
 from plugincode.scan import ScanPlugin

tests/test_fingerprinting.py

@@ -13,6 +13,7 @@
 from commoncode.resource import VirtualCodebase
 from commoncode.testcase import FileBasedTesting
 from commoncode.testcase import check_against_expected_json_file
+from samecode.halohash import byte_hamming_distance
 
 from matchcode_toolkit.fingerprinting import _create_directory_fingerprint
 from matchcode_toolkit.fingerprinting import _get_resource_subpath
@@ -22,7 +23,6 @@
 from matchcode_toolkit.fingerprinting import create_structure_fingerprint
 from matchcode_toolkit.fingerprinting import get_file_fingerprint_hashes
 from matchcode_toolkit.fingerprinting import split_fingerprint
-from samecode.halohash import byte_hamming_distance
 
 
 class Resource:
@@ -193,10 +193,13 @@ def test_snippets_similarity(self, regen=False):
         results1_snippet_mappings_by_snippets = self._create_snippet_mappings_by_snippets(
             results1_snippets
         )
-        results2_snippet_mappings_by_snippets = self._create_snippet_mappings_by_snippets(results2_snippets)
+        results2_snippet_mappings_by_snippets = self._create_snippet_mappings_by_snippets(
+            results2_snippets
+        )
 
         matching_snippets = (
-            results1_snippet_mappings_by_snippets.keys() & results2_snippet_mappings_by_snippets.keys()
+            results1_snippet_mappings_by_snippets.keys()
+            & results2_snippet_mappings_by_snippets.keys()
         )
         expected_matching_snippets = {
             "33b1d50de7e1701bd4beb706bf25970e",
@@ -247,10 +250,13 @@ def test_snippets_similarity_2(self, regen=False):
         results1_snippet_mappings_by_snippets = self._create_snippet_mappings_by_snippets(
             results1_snippets
         )
-        results2_snippet_mappings_by_snippets = self._create_snippet_mappings_by_snippets(results2_snippets)
+        results2_snippet_mappings_by_snippets = self._create_snippet_mappings_by_snippets(
+            results2_snippets
+        )
 
         matching_snippets = (
-            results1_snippet_mappings_by_snippets.keys() & results2_snippet_mappings_by_snippets.keys()
+            results1_snippet_mappings_by_snippets.keys()
+            & results2_snippet_mappings_by_snippets.keys()
         )
 
         # jaccard coefficient