From 8b8ef8dab34254e619af25996cba10bce50c380e Mon Sep 17 00:00:00 2001
From: Jono Yang <jyang@nexb.com>
Date: Thu, 17 Oct 2024 17:38:15 -0700
Subject: [PATCH 1/6] Implement hailstorm

Signed-off-by: Jono Yang <jyang@nexb.com>
---
 src/matchcode_toolkit/fingerprinting.py | 59 +++++++++++--------------
 1 file changed, 26 insertions(+), 33 deletions(-)

diff --git a/src/matchcode_toolkit/fingerprinting.py b/src/matchcode_toolkit/fingerprinting.py
index 2b9f16d..0885eb9 100644
--- a/src/matchcode_toolkit/fingerprinting.py
+++ b/src/matchcode_toolkit/fingerprinting.py
@@ -195,7 +195,7 @@ def tokenizer(text):
     return _tokenizer(text.lower())
 
 
-def get_file_fingerprint_hashes(location, ngram_length=8, **kwargs):
+def get_file_fingerprint_hashes(location, ngram_length=8, window_length=64, **kwargs):
     """
     Return a mapping of fingerprint hashes for the file at `location`
 
@@ -218,50 +218,43 @@ def get_file_fingerprint_hashes(location, ngram_length=8, **kwargs):
     with open(location) as f:
         content = f.read()
 
-    file_fingerprint = create_file_fingerprint(
+    return create_file_fingerprints(
         content,
-        ngram_length=ngram_length
-    )
-    return dict(
-        halo1=file_fingerprint
+        ngram_length=ngram_length,
+        window_length=window_length,
     )
 
 
-def create_content_hash(content, ngram_length=8):
+def create_file_fingerprints(content, ngram_length=8, window_length=64):
     """
-    Return a 128-bit BitAverageHaloHash from file `content` and the number of
-    ngrams inserted into the hash
+    Return a mapping of halo1 and hailstorm hashes from content
     """
     from licensedcode.tokenize import ngrams
+    from licensedcode.tokenize import select_ngrams
+
+    fingerprints = {
+        "halo1": "",
+        "hailstorm": [],
+    }
 
-    # Break content into words, then create ngrams from words
+    # Create fingerprint
     words = tokenizer(content)
     ngs = ngrams(words, ngram_length)
-
-    # Convert each list of ngrams to a sequence of bytes
     ngs_bytes = [[g.encode('utf-8') for g in ng] for ng in ngs]
-
-    # Join all ngrams into a single bytearray
-    ngs_bytes = [b''.join(ng) for ng in ngs_bytes]
-
-    # Create fingerprints and return fingerprint hashes
-    if ngs_bytes:
-        return BitAverageHaloHash(ngs_bytes), len(ngs_bytes)
-    else:
-        return None, 0
-
-
-def create_file_fingerprint(content, ngram_length=8):
-    """
-    Return a 128-bit BitAverageHaloHash fingerprint in hex from file `content`
-    """
-    # Create fingerprint
-    content_hash, ngs_count = create_content_hash(
-        content,
-        ngram_length=ngram_length
-    )
+    content_hash, ngs_count = BitAverageHaloHash(ngs_bytes), len(ngs_bytes)
     if content_hash:
         content_fingerprint = content_hash.hexdigest().decode('utf-8')
         ngs_count_hex_str = '%08x' % ngs_count
         file_fingerprint = ngs_count_hex_str + content_fingerprint
-        return file_fingerprint
+        fingerprints['halo1'] = file_fingerprint
+
+    windows = ngrams(ngs, window_length)
+    selected_windows = select_ngrams(windows)
+    hailstorm_hashes = [
+        BitAverageHaloHash(window).hexdigest().decode('utf-8')
+        for window in selected_windows
+    ]
+    if hailstorm_hashes:
+        fingerprints['hailstorm'] = hailstorm_hashes
+
+    return fingerprints

From 99d2b0c254ef9d6361eb383b892c04a5e8852d9a Mon Sep 17 00:00:00 2001
From: Jono Yang <jyang@nexb.com>
Date: Fri, 18 Oct 2024 13:49:00 -0700
Subject: [PATCH 2/6] Properly create hashes

Signed-off-by: Jono Yang <jyang@nexb.com>
---
 src/matchcode_toolkit/fingerprinting.py     | 8 ++++++--
 src/matchcode_toolkit/plugin_fingerprint.py | 1 +
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/src/matchcode_toolkit/fingerprinting.py b/src/matchcode_toolkit/fingerprinting.py
index 0885eb9..90b7ad3 100644
--- a/src/matchcode_toolkit/fingerprinting.py
+++ b/src/matchcode_toolkit/fingerprinting.py
@@ -241,6 +241,7 @@ def create_file_fingerprints(content, ngram_length=8, window_length=64):
     words = tokenizer(content)
     ngs = ngrams(words, ngram_length)
     ngs_bytes = [[g.encode('utf-8') for g in ng] for ng in ngs]
+    ngs_bytes = [b''.join(ng) for ng in ngs_bytes]
     content_hash, ngs_count = BitAverageHaloHash(ngs_bytes), len(ngs_bytes)
     if content_hash:
         content_fingerprint = content_hash.hexdigest().decode('utf-8')
@@ -248,11 +249,14 @@ def create_file_fingerprints(content, ngram_length=8, window_length=64):
         file_fingerprint = ngs_count_hex_str + content_fingerprint
         fingerprints['halo1'] = file_fingerprint
 
-    windows = ngrams(ngs, window_length)
+    words = tokenizer(content)
+    windows = ngrams(words, window_length)
     selected_windows = select_ngrams(windows)
+    selected_windows_bytes = [[g.encode('utf-8') for g in window] for window in selected_windows]
+    selected_windows_bytes = [b''.join(window) for window in selected_windows_bytes]
     hailstorm_hashes = [
         BitAverageHaloHash(window).hexdigest().decode('utf-8')
-        for window in selected_windows
+        for window in selected_windows_bytes
     ]
     if hailstorm_hashes:
         fingerprints['hailstorm'] = hailstorm_hashes
diff --git a/src/matchcode_toolkit/plugin_fingerprint.py b/src/matchcode_toolkit/plugin_fingerprint.py
index 175edfb..6046fd6 100644
--- a/src/matchcode_toolkit/plugin_fingerprint.py
+++ b/src/matchcode_toolkit/plugin_fingerprint.py
@@ -23,6 +23,7 @@ class FingerprintScanner(ScanPlugin):
         directory_content_fingerprint=attr.ib(default=None, repr=False),
         directory_structure_fingerprint=attr.ib(default=None, repr=False),
         halo1=attr.ib(default=None, repr=False),
+        hailstorm=attr.ib(default=None, repr=False),
     )
     sort_order = 6
     options = [

From cf0107beb7a1e8073dd5b09c366b64536b3982f9 Mon Sep 17 00:00:00 2001
From: Jono Yang <jyang@nexb.com>
Date: Tue, 22 Oct 2024 12:12:58 -0700
Subject: [PATCH 3/6] Do not tokenize content twice

    * Update formatting

Signed-off-by: Jono Yang <jyang@nexb.com>
---
 src/matchcode_toolkit/fingerprinting.py     |  49 ++++----
 src/matchcode_toolkit/halohash.py           |  22 +++-
 src/matchcode_toolkit/plugin_fingerprint.py |  13 +-
 tests/test_fingerprinting.py                | 132 +++++++++-----------
 tests/test_halohash.py                      | 132 ++++++++++----------
 tests/test_plugin_fingerprinting.py         |  22 ++--
 6 files changed, 188 insertions(+), 182 deletions(-)

diff --git a/src/matchcode_toolkit/fingerprinting.py b/src/matchcode_toolkit/fingerprinting.py
index 90b7ad3..aeef5d6 100644
--- a/src/matchcode_toolkit/fingerprinting.py
+++ b/src/matchcode_toolkit/fingerprinting.py
@@ -12,12 +12,11 @@
 
 from matchcode_toolkit.halohash import BitAverageHaloHash
 
-
 # A collection of directory fingerprints that we want to avoid
 IGNORED_DIRECTORY_FINGERPRINTS = [
     # This is both the directory content and directory structure fingerprint for
     # an empty directory.
-    '0000000000000000000000000000000000000000',
+    "0000000000000000000000000000000000000000",
 ]
 
 
@@ -25,11 +24,11 @@ def _create_directory_fingerprint(inputs):
     """
     Return a 128-bit BitAverageHaloHash fingerprint in hex from `inputs`
     """
-    inputs = [i.encode('utf-8') for i in inputs if i]
+    inputs = [i.encode("utf-8") for i in inputs if i]
     bah128 = BitAverageHaloHash(inputs, size_in_bits=128).hexdigest()
     inputs_count = len(inputs)
-    inputs_count_hex_str = '%08x' % inputs_count
-    bah128 = bah128.decode('utf-8')
+    inputs_count_hex_str = "%08x" % inputs_count
+    bah128 = bah128.decode("utf-8")
     directory_fingerprint = inputs_count_hex_str + bah128
     return directory_fingerprint
 
@@ -55,7 +54,7 @@ def _get_resource_subpath(resource, top):
     The subpath returned would be 'baz.c'
     """
     _, _, subpath = resource.path.partition(top.path)
-    subpath = subpath.lstrip('/')
+    subpath = subpath.lstrip("/")
     return subpath
 
 
@@ -88,16 +87,16 @@ def _compute_directory_fingerprints(directory, codebase):
         return
 
     directory_content_fingerprint = create_content_fingerprint(children)
-    if hasattr(directory, 'directory_content_fingerprint'):
+    if hasattr(directory, "directory_content_fingerprint"):
         directory.directory_content_fingerprint = directory_content_fingerprint
     else:
-        directory.extra_data['directory_content'] = directory_content_fingerprint
+        directory.extra_data["directory_content"] = directory_content_fingerprint
 
     directory_structure_fingerprint = create_structure_fingerprint(directory, children)
-    if hasattr(directory, 'directory_structure_fingerprint'):
+    if hasattr(directory, "directory_structure_fingerprint"):
         directory.directory_structure_fingerprint = directory_structure_fingerprint
     else:
-        directory.extra_data['directory_structure'] = directory_structure_fingerprint
+        directory.extra_data["directory_structure"] = directory_structure_fingerprint
 
     directory.save(codebase)
     return directory
@@ -162,7 +161,7 @@ def create_halohash_chunks(bah128):
 
 
 # Split on whitespace and punctuations: keep only characters and numbers
-query_pattern = '[^_\\W]+'
+query_pattern = "[^_\\W]+"
 word_splitter = re.compile(query_pattern, re.UNICODE).findall
 
 
@@ -237,28 +236,30 @@ def create_file_fingerprints(content, ngram_length=8, window_length=64):
         "hailstorm": [],
     }
 
-    # Create fingerprint
-    words = tokenizer(content)
+    # tokenize content intow words
+    words = list(tokenizer(content))
+
+    # Create a file fingerprint from the number of elements in the content hash
+    # and the content hash digest iteself.
     ngs = ngrams(words, ngram_length)
-    ngs_bytes = [[g.encode('utf-8') for g in ng] for ng in ngs]
-    ngs_bytes = [b''.join(ng) for ng in ngs_bytes]
+    ngs_bytes = [[g.encode("utf-8") for g in ng] for ng in ngs]
+    ngs_bytes = [b"".join(ng) for ng in ngs_bytes]
     content_hash, ngs_count = BitAverageHaloHash(ngs_bytes), len(ngs_bytes)
     if content_hash:
-        content_fingerprint = content_hash.hexdigest().decode('utf-8')
-        ngs_count_hex_str = '%08x' % ngs_count
+        content_fingerprint = content_hash.hexdigest().decode("utf-8")
+        ngs_count_hex_str = "%08x" % ngs_count
         file_fingerprint = ngs_count_hex_str + content_fingerprint
-        fingerprints['halo1'] = file_fingerprint
+        fingerprints["halo1"] = file_fingerprint
 
-    words = tokenizer(content)
+    # Select windows from the content to find snippet similarities
     windows = ngrams(words, window_length)
     selected_windows = select_ngrams(windows)
-    selected_windows_bytes = [[g.encode('utf-8') for g in window] for window in selected_windows]
-    selected_windows_bytes = [b''.join(window) for window in selected_windows_bytes]
+    selected_windows_bytes = [[g.encode("utf-8") for g in window] for window in selected_windows]
+    selected_windows_bytes = [b"".join(window) for window in selected_windows_bytes]
     hailstorm_hashes = [
-        BitAverageHaloHash(window).hexdigest().decode('utf-8')
-        for window in selected_windows_bytes
+        BitAverageHaloHash(window).hexdigest().decode("utf-8") for window in selected_windows_bytes
     ]
     if hailstorm_hashes:
-        fingerprints['hailstorm'] = hailstorm_hashes
+        fingerprints["hailstorm"] = hailstorm_hashes
 
     return fingerprints
diff --git a/src/matchcode_toolkit/halohash.py b/src/matchcode_toolkit/halohash.py
index 538db55..36aa00f 100644
--- a/src/matchcode_toolkit/halohash.py
+++ b/src/matchcode_toolkit/halohash.py
@@ -176,8 +176,10 @@ def __init__(self, msg=None, size_in_bits=128):
             # TODO: pick one hash algorithm
             self.hashmodule = commoncode_hash.get_hasher(size_in_bits)
         except:
-            raise Exception('No available hash module for the requested '
-                            'hash size in bits: %(size_in_bits)d' % locals())
+            raise Exception(
+                "No available hash module for the requested "
+                "hash size in bits: %(size_in_bits)d" % locals()
+            )
         self.update(msg)
 
     @property
@@ -190,7 +192,13 @@ def update(self, msg):
         """
         if not msg:
             return
-        if isinstance(msg, (list, tuple,)):
+        if isinstance(
+            msg,
+            (
+                list,
+                tuple,
+            ),
+        ):
             for m in msg:
                 self.__hashup(m)
         else:
@@ -242,7 +250,9 @@ def combine(cls, hashes):
         """
         size_in_bits = hashes[0].size_in_bits
         for h in hashes:
-            assert isinstance(hash, cls), 'all hashes should be a BitAverageHaloHash, not {}'.format(type(h))
+            assert isinstance(
+                hash, cls
+            ), "all hashes should be a BitAverageHaloHash, not {}".format(type(h))
             assert h.size_in_bits == size_in_bits
 
         all_columns = [h.columns for h in hashes]
@@ -313,7 +323,9 @@ def slices(s, size):
     ...    pass
     """
     length = len(s)
-    assert length % size == 0, 'Invalid slice size: len(%(s)r) is not a multiple of %(size)r' % locals()
+    assert length % size == 0, (
+        "Invalid slice size: len(%(s)r) is not a multiple of %(size)r" % locals()
+    )
     # TODO: time alternative
     # return [s[index:index + size] for index in range(0, length, size)]
     chunks = [iter(s)] * size
diff --git a/src/matchcode_toolkit/plugin_fingerprint.py b/src/matchcode_toolkit/plugin_fingerprint.py
index 6046fd6..ee972ef 100644
--- a/src/matchcode_toolkit/plugin_fingerprint.py
+++ b/src/matchcode_toolkit/plugin_fingerprint.py
@@ -9,13 +9,14 @@
 
 import attr
 
-from commoncode.cliutils import PluggableCommandLineOption
 from commoncode.cliutils import SCAN_GROUP
-from matchcode_toolkit.fingerprinting import compute_codebase_directory_fingerprints
-from matchcode_toolkit.fingerprinting import get_file_fingerprint_hashes
+from commoncode.cliutils import PluggableCommandLineOption
 from plugincode.scan import ScanPlugin
 from plugincode.scan import scan_impl
 
+from matchcode_toolkit.fingerprinting import compute_codebase_directory_fingerprints
+from matchcode_toolkit.fingerprinting import get_file_fingerprint_hashes
+
 
 @scan_impl
 class FingerprintScanner(ScanPlugin):
@@ -28,12 +29,10 @@ class FingerprintScanner(ScanPlugin):
     sort_order = 6
     options = [
         PluggableCommandLineOption(
-            (
-                '--fingerprint',
-            ),
+            ("--fingerprint",),
             is_flag=True,
             default=False,
-            help='Compute directory and resource fingerprints that are used for matching',
+            help="Compute directory and resource fingerprints that are used for matching",
             help_group=SCAN_GROUP,
             sort_order=20,
         )
diff --git a/tests/test_fingerprinting.py b/tests/test_fingerprinting.py
index 19bb9c6..dd4bc6e 100644
--- a/tests/test_fingerprinting.py
+++ b/tests/test_fingerprinting.py
@@ -23,160 +23,150 @@
 from matchcode_toolkit.halohash import byte_hamming_distance
 
 
-class Resource():
-    def __init__(self, path='', size=0, sha1=''):
+class Resource:
+    def __init__(self, path="", size=0, sha1=""):
         self.path = path
         self.size = size
         self.sha1 = sha1
 
 
 class TestFingerprintingFunctions(FileBasedTesting):
-    test_data_dir = os.path.join(os.path.dirname(
-        __file__), 'testfiles/fingerprinting')
+    test_data_dir = os.path.join(os.path.dirname(__file__), "testfiles/fingerprinting")
 
     def test__create_directory_fingerprint(self):
         test_input = [
-            'package',
-            'package/readme.txt',
-            'package/index.js',
-            'package/package.json',
+            "package",
+            "package/readme.txt",
+            "package/index.js",
+            "package/package.json",
         ]
         directory_fingerprint = _create_directory_fingerprint(test_input)
-        expected_directory_fingerprint = '0000000410d24471969646cb5402032288493126'
+        expected_directory_fingerprint = "0000000410d24471969646cb5402032288493126"
         self.assertEqual(expected_directory_fingerprint, directory_fingerprint)
         indexed_elements_count, _ = split_fingerprint(directory_fingerprint)
         self.assertEqual(len(test_input), indexed_elements_count)
 
     def test_split_fingerprint(self):
-        directory_fingerprint = '0000000410d24471969646cb5402032288493126'
-        indexed_elements_count, bah128 = split_fingerprint(
-            directory_fingerprint)
+        directory_fingerprint = "0000000410d24471969646cb5402032288493126"
+        indexed_elements_count, bah128 = split_fingerprint(directory_fingerprint)
 
         expected_indexed_elements_count = 4
-        self.assertEqual(expected_indexed_elements_count,
-                         indexed_elements_count)
+        self.assertEqual(expected_indexed_elements_count, indexed_elements_count)
 
-        expected_bah128 = '10d24471969646cb5402032288493126'
+        expected_bah128 = "10d24471969646cb5402032288493126"
         self.assertEqual(expected_bah128, bah128)
 
     def test_create_content_fingerprint(self):
         test_resources = [
-            Resource(sha1='d4e4abbe8e2a8169d6a52907152c2c80ec884745'),
-            Resource(sha1='0c94f137f6e0536db8cb2622a9dc84253b91b90c'),
-            Resource(sha1='10cab45fe6f353b47b587a576c1077a96ce348f5'),
-            Resource(sha1='134f2b052b6e5f56b631be2eded70f89d44cf381'),
+            Resource(sha1="d4e4abbe8e2a8169d6a52907152c2c80ec884745"),
+            Resource(sha1="0c94f137f6e0536db8cb2622a9dc84253b91b90c"),
+            Resource(sha1="10cab45fe6f353b47b587a576c1077a96ce348f5"),
+            Resource(sha1="134f2b052b6e5f56b631be2eded70f89d44cf381"),
         ]
         fingerprint = create_content_fingerprint(test_resources)
-        expected_fingerprint = '00000004005b88c2800f0044044781ae05680419'
+        expected_fingerprint = "00000004005b88c2800f0044044781ae05680419"
         self.assertEqual(expected_fingerprint, fingerprint)
 
     def test__get_resource_subpath(self):
-        test_resource = Resource(path='foo/bar/baz/qux.c')
-        test_top_resource = Resource(path='foo/bar/')
+        test_resource = Resource(path="foo/bar/baz/qux.c")
+        test_top_resource = Resource(path="foo/bar/")
         subpath = _get_resource_subpath(test_resource, test_top_resource)
-        expected_subpath = 'baz/qux.c'
+        expected_subpath = "baz/qux.c"
         self.assertEqual(expected_subpath, subpath)
 
     def test_create_structure_fingerprint(self):
-        test_top_resource = Resource(path='package')
+        test_top_resource = Resource(path="package")
         test_child_resources = [
-            Resource(path='package/readme.txt', size=771),
-            Resource(path='package/index.js', size=608),
-            Resource(path='package/package.json', size=677),
+            Resource(path="package/readme.txt", size=771),
+            Resource(path="package/index.js", size=608),
+            Resource(path="package/package.json", size=677),
         ]
-        fingerprint = create_structure_fingerprint(
-            test_top_resource, test_child_resources)
-        expected_fingerprint = '00000003ce72f4308a1bc1afb0fb47ed590b5c53'
+        fingerprint = create_structure_fingerprint(test_top_resource, test_child_resources)
+        expected_fingerprint = "00000003ce72f4308a1bc1afb0fb47ed590b5c53"
         self.assertEqual(expected_fingerprint, fingerprint)
 
     def test_create_halohash_chunks(self):
-        test_bah128 = 'ce72f4308a1bc1afb0fb47ed590b5c53'
+        test_bah128 = "ce72f4308a1bc1afb0fb47ed590b5c53"
         chunk1, chunk2, chunk3, chunk4 = create_halohash_chunks(test_bah128)
-        expected_chunk1 = bytearray(b'\xcer\xf40')
-        expected_chunk2 = bytearray(b'\x8a\x1b\xc1\xaf')
-        expected_chunk3 = bytearray(b'\xb0\xfbG\xed')
-        expected_chunk4 = bytearray(b'Y\x0b\\S')
+        expected_chunk1 = bytearray(b"\xcer\xf40")
+        expected_chunk2 = bytearray(b"\x8a\x1b\xc1\xaf")
+        expected_chunk3 = bytearray(b"\xb0\xfbG\xed")
+        expected_chunk4 = bytearray(b"Y\x0b\\S")
         self.assertEqual(chunk1, expected_chunk1)
         self.assertEqual(chunk2, expected_chunk2)
         self.assertEqual(chunk3, expected_chunk3)
         self.assertEqual(chunk4, expected_chunk4)
 
     def test_compute_codebase_directory_fingerprints(self):
-        scan_loc = self.get_test_loc('abbrev-1.0.3-i.json')
+        scan_loc = self.get_test_loc("abbrev-1.0.3-i.json")
         vc = VirtualCodebase(location=scan_loc)
         vc = compute_codebase_directory_fingerprints(vc)
-        directory_content = vc.root.extra_data['directory_content']
-        directory_structure = vc.root.extra_data['directory_structure']
-        expected_directory_content = '0000000346ce04751a3c98f00086f16a91d9790b'
-        expected_directory_structure = '000000034f9bf110673bdf06197cd514a799a66c'
+        directory_content = vc.root.extra_data["directory_content"]
+        directory_structure = vc.root.extra_data["directory_structure"]
+        expected_directory_content = "0000000346ce04751a3c98f00086f16a91d9790b"
+        expected_directory_structure = "000000034f9bf110673bdf06197cd514a799a66c"
         self.assertEqual(expected_directory_content, directory_content)
         self.assertEqual(expected_directory_structure, directory_structure)
 
     def test_do_not_compute_fingerprint_for_empty_dirs(self):
-        scan_loc = self.get_test_loc('test.json')
+        scan_loc = self.get_test_loc("test.json")
         vc = VirtualCodebase(location=scan_loc)
         vc = compute_codebase_directory_fingerprints(vc)
-        directory_content = vc.root.extra_data['directory_content']
-        directory_structure = vc.root.extra_data['directory_structure']
-        expected_directory_content = '000000032a5fa8d01922536b53e8fc6e3d43766f'
-        expected_directory_structure = '000000030a399ce2b947a6f611821965a4fcc577'
+        directory_content = vc.root.extra_data["directory_content"]
+        directory_structure = vc.root.extra_data["directory_structure"]
+        expected_directory_content = "000000032a5fa8d01922536b53e8fc6e3d43766f"
+        expected_directory_structure = "000000030a399ce2b947a6f611821965a4fcc577"
         self.assertEqual(expected_directory_content, directory_content)
         self.assertEqual(expected_directory_structure, directory_structure)
         # These directories should not have fingerprints generated or stored in
         # extra_data
-        empty_dir_1 = vc.get_resource('test/test')
-        empty_dir_2 = vc.get_resource('test/test/test2')
+        empty_dir_1 = vc.get_resource("test/test")
+        empty_dir_2 = vc.get_resource("test/test/test2")
         self.assertEqual({}, empty_dir_1.extra_data)
         self.assertEqual({}, empty_dir_1.extra_data)
         self.assertEqual({}, empty_dir_2.extra_data)
         self.assertEqual({}, empty_dir_2.extra_data)
 
     def test_get_file_fingerprint_hashes_one_line_removed(self):
-        test_file1 = self.get_test_loc('inflate.c')
-        test_file2 = self.get_test_loc('inflate-mod.c')
+        test_file1 = self.get_test_loc("inflate.c")
+        test_file2 = self.get_test_loc("inflate-mod.c")
         result1 = get_file_fingerprint_hashes(test_file1)
         result2 = get_file_fingerprint_hashes(test_file2)
-        result1 = result1.get('halo1')
-        result2 = result2.get('halo1')
-        result1_indexed_elements_count, result1_fingerprint = split_fingerprint(
-            result1)
-        result2_indexed_elements_count, result2_fingerprint = split_fingerprint(
-            result2)
+        result1 = result1.get("halo1")
+        result2 = result2.get("halo1")
+        result1_indexed_elements_count, result1_fingerprint = split_fingerprint(result1)
+        result2_indexed_elements_count, result2_fingerprint = split_fingerprint(result2)
 
         expected_result1_indexed_elements_count = 6395
         expected_result2_indexed_elements_count = 6388
         assert result1_indexed_elements_count == expected_result1_indexed_elements_count
         assert result2_indexed_elements_count == expected_result2_indexed_elements_count
 
-        expected_result1_fingerprint = 'a23a49e4cd40718d1297be719e6564a4'
-        expected_result2_fingerprint = 'aa3a49e4cd40718d1297be519e6564a4'
+        expected_result1_fingerprint = "a23a49e4cd40718d1297be719e6564a4"
+        expected_result2_fingerprint = "aa3a49e4cd40718d1297be519e6564a4"
         assert result1_fingerprint == expected_result1_fingerprint
         assert result2_fingerprint == expected_result2_fingerprint
 
-        assert byte_hamming_distance(
-            result1_fingerprint, result2_fingerprint) == 2
+        assert byte_hamming_distance(result1_fingerprint, result2_fingerprint) == 2
 
     def test_get_file_fingerprint_hashes_one_line_added(self):
-        test_file1 = self.get_test_loc('inflate.c')
-        test_file2 = self.get_test_loc('inflate-mod2.c')
+        test_file1 = self.get_test_loc("inflate.c")
+        test_file2 = self.get_test_loc("inflate-mod2.c")
         result1 = get_file_fingerprint_hashes(test_file1)
         result2 = get_file_fingerprint_hashes(test_file2)
-        result1 = result1.get('halo1')
-        result2 = result2.get('halo1')
-        result1_indexed_elements_count, result1_fingerprint = split_fingerprint(
-            result1)
-        result2_indexed_elements_count, result2_fingerprint = split_fingerprint(
-            result2)
+        result1 = result1.get("halo1")
+        result2 = result2.get("halo1")
+        result1_indexed_elements_count, result1_fingerprint = split_fingerprint(result1)
+        result2_indexed_elements_count, result2_fingerprint = split_fingerprint(result2)
 
         expected_result1_indexed_elements_count = 6395
         expected_result2_indexed_elements_count = 6398
         assert result1_indexed_elements_count == expected_result1_indexed_elements_count
         assert result2_indexed_elements_count == expected_result2_indexed_elements_count
 
-        expected_result1_fingerprint = 'a23a49e4cd40718d1297be719e6564a4'
-        expected_result2_fingerprint = 'a23b49e4cd40708d1297be719c6564a4'
+        expected_result1_fingerprint = "a23a49e4cd40718d1297be719e6564a4"
+        expected_result2_fingerprint = "a23b49e4cd40708d1297be719c6564a4"
         assert result1_fingerprint == expected_result1_fingerprint
         assert result2_fingerprint == expected_result2_fingerprint
 
-        assert byte_hamming_distance(
-            result1_fingerprint, result2_fingerprint) == 3
+        assert byte_hamming_distance(result1_fingerprint, result2_fingerprint) == 3
diff --git a/tests/test_halohash.py b/tests/test_halohash.py
index cb45ae2..5bfe7a5 100644
--- a/tests/test_halohash.py
+++ b/tests/test_halohash.py
@@ -7,20 +7,18 @@
 # See https://aboutcode.org for more information about nexB OSS projects.
 #
 
-from collections import defaultdict
-
+import copy
 import csv
 import math
-import copy
 import os
 import random
 import subprocess
+from collections import defaultdict
 
 from commoncode.testcase import FileBasedTesting
 
 from matchcode_toolkit import halohash
 
-
 SIZE_IN_BITS = 128
 
 
@@ -30,10 +28,7 @@ def load_csv(location):
     mappings field->value).
     """
     with open(location) as csvin:
-        reader = csv.DictReader(
-            csvin,
-            quoting=csv.QUOTE_NONNUMERIC
-        )
+        reader = csv.DictReader(csvin, quoting=csv.QUOTE_NONNUMERIC)
         fields = reader.fieldnames
         values = sorted(reader, key=lambda d: d.items())
         return fields, values
@@ -49,12 +44,8 @@ def check_results(
     Load and compare the CSV at `expected_file` against `results`.
     """
     if regen:
-        with open(expected_file, 'w') as f:
-            writer = csv.DictWriter(
-                f,
-                fieldnames=fieldnames,
-                quoting=csv.QUOTE_NONNUMERIC
-            )
+        with open(expected_file, "w") as f:
+            writer = csv.DictWriter(f, fieldnames=fieldnames, quoting=csv.QUOTE_NONNUMERIC)
             writer.writeheader()
             writer.writerows(results)
 
@@ -64,11 +55,11 @@ def check_results(
     # check results line by line for more compact results
     for exp, res in zip(expected, results):
         assert exp[column1_name] == res[column1_name]
-        expected_mean_hamming_distance = exp['mean hamming distance']
-        expected_standard_deviation = exp['standard deviation']
+        expected_mean_hamming_distance = exp["mean hamming distance"]
+        expected_standard_deviation = exp["standard deviation"]
         exp_min = expected_mean_hamming_distance - expected_standard_deviation
         exp_max = expected_mean_hamming_distance + expected_standard_deviation
-        assert exp_min <= res['mean hamming distance'] <= exp_max
+        assert exp_min <= res["mean hamming distance"] <= exp_max
 
 
 def calculate_hamming_distance(content_hash, modified_content):
@@ -85,13 +76,11 @@ def calculate_mean_and_standard_deviation(hamming_distances):
     number_of_hamming_distances = len(hamming_distances)
 
     # 1: Find the mean.
-    mean_hamming_distance = sum(hamming_distances) / \
-        number_of_hamming_distances
+    mean_hamming_distance = sum(hamming_distances) / number_of_hamming_distances
 
     # 2: For each data point, find the square of its distance to the mean, then sum the values.
     s0 = sum(
-        (hamming_distance - mean_hamming_distance) ** 2
-        for hamming_distance in hamming_distances
+        (hamming_distance - mean_hamming_distance) ** 2 for hamming_distance in hamming_distances
     )
 
     # 3: Divide by the number of data points.
@@ -104,16 +93,17 @@ def calculate_mean_and_standard_deviation(hamming_distances):
 
 
 class TestHalohash(FileBasedTesting):
-    test_data_dir = os.path.join(
-        os.path.dirname(__file__), 'testfiles/halohash')
+    test_data_dir = os.path.join(os.path.dirname(__file__), "testfiles/halohash")
 
     def setUp(self):
-        words_loc = self.get_test_loc('words.txt')
+        words_loc = self.get_test_loc("words.txt")
         with open(words_loc) as f:
-            self.original_content = [bytes(x.strip(), 'utf-8') for x in f]
+            self.original_content = [bytes(x.strip(), "utf-8") for x in f]
 
     def test_halohash_random_delete(self, regen=False):
-        for number_of_words in [500,]:
+        for number_of_words in [
+            500,
+        ]:
             content = copy.copy(self.original_content[:number_of_words])
             original_hash = halohash.BitAverageHaloHash(content)
 
@@ -125,36 +115,44 @@ def test_halohash_random_delete(self, regen=False):
                 # we are moving towards unrelated files past that
                 n = int(math.floor(len(modified_content) * 0.10))
                 for _ in range(n):
-                    hamming_distance = calculate_hamming_distance(
-                        original_hash,
-                        modified_content
-                    )
+                    hamming_distance = calculate_hamming_distance(original_hash, modified_content)
                     number_of_elements = len(modified_content)
                     hamming_distance_by_number_of_elements[number_of_elements].append(
-                        hamming_distance)
-                    modified_content.pop(random.randint(
-                        0, len(modified_content) - 1))
+                        hamming_distance
+                    )
+                    modified_content.pop(random.randint(0, len(modified_content) - 1))
 
             # Take mean and standard deviation
             results = []
-            for number_of_elements, hamming_distances in hamming_distance_by_number_of_elements.items():
+            for (
+                number_of_elements,
+                hamming_distances,
+            ) in hamming_distance_by_number_of_elements.items():
                 mean_hamming_distance, standard_deviation = calculate_mean_and_standard_deviation(
-                    hamming_distances)
+                    hamming_distances
+                )
                 results.append(
                     {
-                        'number of hashed elements': int(number_of_elements),
-                        'mean hamming distance': round(mean_hamming_distance, 1),
-                        'standard deviation': round(standard_deviation, 1)
+                        "number of hashed elements": int(number_of_elements),
+                        "mean hamming distance": round(mean_hamming_distance, 1),
+                        "standard deviation": round(standard_deviation, 1),
                     }
                 )
 
             expected_results_loc = self.get_test_loc(
-                f'{number_of_words}-delete-expected-results.csv')
-            check_results(results, expected_results_loc, [
-                          'number of hashed elements', 'mean hamming distance', 'standard deviation'], regen=regen)
+                f"{number_of_words}-delete-expected-results.csv"
+            )
+            check_results(
+                results,
+                expected_results_loc,
+                ["number of hashed elements", "mean hamming distance", "standard deviation"],
+                regen=regen,
+            )
 
     def test_halohash_random_replace(self, regen=False):
-        for number_of_words in [500,]:
+        for number_of_words in [
+            500,
+        ]:
             content = copy.copy(self.original_content[:number_of_words])
             original_hash = halohash.BitAverageHaloHash(content)
 
@@ -168,43 +166,49 @@ def test_halohash_random_replace(self, regen=False):
                 # we are moving towards unrelated files past that
                 n = int(math.floor(len(modified_content) * 0.10))
                 for _ in range(n):
-                    hamming_distance = calculate_hamming_distance(
-                        original_hash,
-                        modified_content
-                    )
+                    hamming_distance = calculate_hamming_distance(original_hash, modified_content)
                     hamming_distance_by_number_of_words_replaced[words_replaced].append(
-                        hamming_distance)
+                        hamming_distance
+                    )
 
-                    modified_content.pop(random.randint(
-                        0, len(modified_content) - 1))
+                    modified_content.pop(random.randint(0, len(modified_content) - 1))
                     new_word = (
                         subprocess.run(
-                            ['shuf', '-n', '1', '/usr/share/dict/american-english'],
-                            stdout=subprocess.PIPE
+                            ["shuf", "-n", "1", "/usr/share/dict/american-english"],
+                            stdout=subprocess.PIPE,
                         )
-                        .stdout
-                        .decode('utf-8')
+                        .stdout.decode("utf-8")
                         .strip()
-                        .replace('"', '')
+                        .replace('"', "")
+                    )
+                    modified_content[random.randint(0, len(modified_content) - 1)] = bytes(
+                        new_word, "utf-8"
                     )
-                    modified_content[random.randint(
-                        0, len(modified_content) - 1)] = bytes(new_word, 'utf-8')
                     words_replaced += 1
 
             # Take mean and standard deviation
             results = []
-            for words_replaced, hamming_distances in hamming_distance_by_number_of_words_replaced.items():
+            for (
+                words_replaced,
+                hamming_distances,
+            ) in hamming_distance_by_number_of_words_replaced.items():
                 mean_hamming_distance, standard_deviation = calculate_mean_and_standard_deviation(
-                    hamming_distances)
+                    hamming_distances
+                )
                 results.append(
                     {
-                        'words replaced': int(words_replaced),
-                        'mean hamming distance': round(mean_hamming_distance, 1),
-                        'standard deviation': round(standard_deviation, 1)
+                        "words replaced": int(words_replaced),
+                        "mean hamming distance": round(mean_hamming_distance, 1),
+                        "standard deviation": round(standard_deviation, 1),
                     }
                 )
 
             expected_results_loc = self.get_test_loc(
-                f'{number_of_words}-replaced-expected-results.csv')
-            check_results(results, expected_results_loc, [
-                          'words replaced', 'mean hamming distance', 'standard deviation'], regen=regen)
+                f"{number_of_words}-replaced-expected-results.csv"
+            )
+            check_results(
+                results,
+                expected_results_loc,
+                ["words replaced", "mean hamming distance", "standard deviation"],
+                regen=regen,
+            )
diff --git a/tests/test_plugin_fingerprinting.py b/tests/test_plugin_fingerprinting.py
index 1f9b35a..65c4510 100644
--- a/tests/test_plugin_fingerprinting.py
+++ b/tests/test_plugin_fingerprinting.py
@@ -16,36 +16,36 @@
 
 from matchcode_toolkit.fingerprinting import get_file_fingerprint_hashes
 
-
 """
 These tests spawn new process as if launched from the command line.
 """
 
 
 class TestPluginFingerprinting(FileBasedTesting):
-    test_data_dir = os.path.join(os.path.dirname(__file__), 'testfiles')
+    test_data_dir = os.path.join(os.path.dirname(__file__), "testfiles")
 
     def test_plugin_fingerprinting_api_works(self):
-        test_loc = self.get_test_loc('fingerprinting/inflate.c')
+        test_loc = self.get_test_loc("fingerprinting/inflate.c")
         detections = list(get_file_fingerprint_hashes(location=test_loc))
         assert detections
 
     def test_fingerprinting_plugin_works(self):
-        test_dir = self.get_test_loc('fingerprinting', copy=True)
-        result_file = self.get_temp_file('json')
+        test_dir = self.get_test_loc("fingerprinting", copy=True)
+        result_file = self.get_temp_file("json")
         args = [
-            '--info',
-            '--fingerprint',
-            '--verbose',
-            '--json', result_file,
+            "--info",
+            "--fingerprint",
+            "--verbose",
+            "--json",
+            result_file,
             test_dir,
         ]
         run_scan_click(args)
-        test_loc = self.get_test_loc('fingerprinting-expected.json')
+        test_loc = self.get_test_loc("fingerprinting-expected.json")
         check_json_scan(
             test_loc,
             result_file,
             remove_file_date=True,
             check_headers=False,
-            regen=REGEN_TEST_FIXTURES
+            regen=REGEN_TEST_FIXTURES,
         )

From a2ab3e048ef224d45afcef6c6ea2b8d09821978c Mon Sep 17 00:00:00 2001
From: Jono Yang <jyang@nexb.com>
Date: Wed, 23 Oct 2024 14:41:56 -0700
Subject: [PATCH 4/6] Add test for hailstorm snippet match

Signed-off-by: Jono Yang <jyang@nexb.com>
---
 tests/test_fingerprinting.py                  |  34 +-
 .../fingerprinting/hailstorm/adler32.c        | 179 +++++++++
 .../fingerprinting/hailstorm/zutil.c          | 352 ++++++++++++++++++
 3 files changed, 554 insertions(+), 11 deletions(-)
 create mode 100755 tests/testfiles/fingerprinting/hailstorm/adler32.c
 create mode 100755 tests/testfiles/fingerprinting/hailstorm/zutil.c

diff --git a/tests/test_fingerprinting.py b/tests/test_fingerprinting.py
index dd4bc6e..a1eb7a5 100644
--- a/tests/test_fingerprinting.py
+++ b/tests/test_fingerprinting.py
@@ -139,15 +139,15 @@ def test_get_file_fingerprint_hashes_one_line_removed(self):
 
         expected_result1_indexed_elements_count = 6395
         expected_result2_indexed_elements_count = 6388
-        assert result1_indexed_elements_count == expected_result1_indexed_elements_count
-        assert result2_indexed_elements_count == expected_result2_indexed_elements_count
+        self.assertEqual(expected_result1_indexed_elements_count, result1_indexed_elements_count)
+        self.assertEqual(expected_result2_indexed_elements_count, result2_indexed_elements_count)
 
         expected_result1_fingerprint = "a23a49e4cd40718d1297be719e6564a4"
         expected_result2_fingerprint = "aa3a49e4cd40718d1297be519e6564a4"
-        assert result1_fingerprint == expected_result1_fingerprint
-        assert result2_fingerprint == expected_result2_fingerprint
+        self.assertEqual(expected_result1_fingerprint, result1_fingerprint)
+        self.assertEqual(expected_result2_fingerprint, result2_fingerprint)
 
-        assert byte_hamming_distance(result1_fingerprint, result2_fingerprint) == 2
+        self.assertEqual(2, byte_hamming_distance(result1_fingerprint, result2_fingerprint))
 
     def test_get_file_fingerprint_hashes_one_line_added(self):
         test_file1 = self.get_test_loc("inflate.c")
@@ -161,12 +161,24 @@ def test_get_file_fingerprint_hashes_one_line_added(self):
 
         expected_result1_indexed_elements_count = 6395
         expected_result2_indexed_elements_count = 6398
-        assert result1_indexed_elements_count == expected_result1_indexed_elements_count
-        assert result2_indexed_elements_count == expected_result2_indexed_elements_count
+        self.assertEqual(expected_result1_indexed_elements_count, result1_indexed_elements_count)
+        self.assertEqual(expected_result2_indexed_elements_count, result2_indexed_elements_count)
 
         expected_result1_fingerprint = "a23a49e4cd40718d1297be719e6564a4"
         expected_result2_fingerprint = "a23b49e4cd40708d1297be719c6564a4"
-        assert result1_fingerprint == expected_result1_fingerprint
-        assert result2_fingerprint == expected_result2_fingerprint
-
-        assert byte_hamming_distance(result1_fingerprint, result2_fingerprint) == 3
+        self.assertEqual(expected_result1_fingerprint, result1_fingerprint)
+        self.assertEqual(expected_result2_fingerprint, result2_fingerprint)
+
+        self.assertEqual(3, byte_hamming_distance(result1_fingerprint, result2_fingerprint))
+
+    def test_hailstorm_similarity(self):
+        # 1 function from adler32.c has been added to zutil.c
+        test_file1 = self.get_test_loc("hailstorm/adler32.c")
+        test_file2 = self.get_test_loc("hailstorm/zutil.c")
+        results1 = get_file_fingerprint_hashes(test_file1)
+        results2 = get_file_fingerprint_hashes(test_file2)
+        result1 = results1.get("hailstorm")
+        result2 = results2.get("hailstorm")
+        expected_result = {"16e774a453769c012ca1e7f3685b4111", "498885acf844eda1f65af9e746deaff7"}
+        result = set(result1).intersection(result2)
+        self.assertEqual(expected_result, result)
diff --git a/tests/testfiles/fingerprinting/hailstorm/adler32.c b/tests/testfiles/fingerprinting/hailstorm/adler32.c
new file mode 100755
index 0000000..a868f07
--- /dev/null
+++ b/tests/testfiles/fingerprinting/hailstorm/adler32.c
@@ -0,0 +1,179 @@
+/* adler32.c -- compute the Adler-32 checksum of a data stream
+ * Copyright (C) 1995-2011 Mark Adler
+ * For conditions of distribution and use, see copyright notice in zlib.h
+ */
+
+/* @(#) $Id$ */
+
+#include "zutil.h"
+
+#define local static
+
+local uLong adler32_combine_ OF((uLong adler1, uLong adler2, z_off64_t len2));
+
+#define BASE 65521      /* largest prime smaller than 65536 */
+#define NMAX 5552
+/* NMAX is the largest n such that 255n(n+1)/2 + (n+1)(BASE-1) <= 2^32-1 */
+
+#define DO1(buf,i)  {adler += (buf)[i]; sum2 += adler;}
+#define DO2(buf,i)  DO1(buf,i); DO1(buf,i+1);
+#define DO4(buf,i)  DO2(buf,i); DO2(buf,i+2);
+#define DO8(buf,i)  DO4(buf,i); DO4(buf,i+4);
+#define DO16(buf)   DO8(buf,0); DO8(buf,8);
+
+/* use NO_DIVIDE if your processor does not do division in hardware --
+   try it both ways to see which is faster */
+#ifdef NO_DIVIDE
+/* note that this assumes BASE is 65521, where 65536 % 65521 == 15
+   (thank you to John Reiser for pointing this out) */
+#  define CHOP(a) \
+    do { \
+        unsigned long tmp = a >> 16; \
+        a &= 0xffffUL; \
+        a += (tmp << 4) - tmp; \
+    } while (0)
+#  define MOD28(a) \
+    do { \
+        CHOP(a); \
+        if (a >= BASE) a -= BASE; \
+    } while (0)
+#  define MOD(a) \
+    do { \
+        CHOP(a); \
+        MOD28(a); \
+    } while (0)
+#  define MOD63(a) \
+    do { /* this assumes a is not negative */ \
+        z_off64_t tmp = a >> 32; \
+        a &= 0xffffffffL; \
+        a += (tmp << 8) - (tmp << 5) + tmp; \
+        tmp = a >> 16; \
+        a &= 0xffffL; \
+        a += (tmp << 4) - tmp; \
+        tmp = a >> 16; \
+        a &= 0xffffL; \
+        a += (tmp << 4) - tmp; \
+        if (a >= BASE) a -= BASE; \
+    } while (0)
+#else
+#  define MOD(a) a %= BASE
+#  define MOD28(a) a %= BASE
+#  define MOD63(a) a %= BASE
+#endif
+
+/* ========================================================================= */
+uLong ZEXPORT adler32(adler, buf, len)
+    uLong adler;
+    const Bytef *buf;
+    uInt len;
+{
+    unsigned long sum2;
+    unsigned n;
+
+    /* split Adler-32 into component sums */
+    sum2 = (adler >> 16) & 0xffff;
+    adler &= 0xffff;
+
+    /* in case user likes doing a byte at a time, keep it fast */
+    if (len == 1) {
+        adler += buf[0];
+        if (adler >= BASE)
+            adler -= BASE;
+        sum2 += adler;
+        if (sum2 >= BASE)
+            sum2 -= BASE;
+        return adler | (sum2 << 16);
+    }
+
+    /* initial Adler-32 value (deferred check for len == 1 speed) */
+    if (buf == Z_NULL)
+        return 1L;
+
+    /* in case short lengths are provided, keep it somewhat fast */
+    if (len < 16) {
+        while (len--) {
+            adler += *buf++;
+            sum2 += adler;
+        }
+        if (adler >= BASE)
+            adler -= BASE;
+        MOD28(sum2);            /* only added so many BASE's */
+        return adler | (sum2 << 16);
+    }
+
+    /* do length NMAX blocks -- requires just one modulo operation */
+    while (len >= NMAX) {
+        len -= NMAX;
+        n = NMAX / 16;          /* NMAX is divisible by 16 */
+        do {
+            DO16(buf);          /* 16 sums unrolled */
+            buf += 16;
+        } while (--n);
+        MOD(adler);
+        MOD(sum2);
+    }
+
+    /* do remaining bytes (less than NMAX, still just one modulo) */
+    if (len) {                  /* avoid modulos if none remaining */
+        while (len >= 16) {
+            len -= 16;
+            DO16(buf);
+            buf += 16;
+        }
+        while (len--) {
+            adler += *buf++;
+            sum2 += adler;
+        }
+        MOD(adler);
+        MOD(sum2);
+    }
+
+    /* return recombined sums */
+    return adler | (sum2 << 16);
+}
+
+/* ========================================================================= */
+local uLong adler32_combine_(adler1, adler2, len2)
+    uLong adler1;
+    uLong adler2;
+    z_off64_t len2;
+{
+    unsigned long sum1;
+    unsigned long sum2;
+    unsigned rem;
+
+    /* for negative len, return invalid adler32 as a clue for debugging */
+    if (len2 < 0)
+        return 0xffffffffUL;
+
+    /* the derivation of this formula is left as an exercise for the reader */
+    MOD63(len2);                /* assumes len2 >= 0 */
+    rem = (unsigned)len2;
+    sum1 = adler1 & 0xffff;
+    sum2 = rem * sum1;
+    MOD(sum2);
+    sum1 += (adler2 & 0xffff) + BASE - 1;
+    sum2 += ((adler1 >> 16) & 0xffff) + ((adler2 >> 16) & 0xffff) + BASE - rem;
+    if (sum1 >= BASE) sum1 -= BASE;
+    if (sum1 >= BASE) sum1 -= BASE;
+    if (sum2 >= (BASE << 1)) sum2 -= (BASE << 1);
+    if (sum2 >= BASE) sum2 -= BASE;
+    return sum1 | (sum2 << 16);
+}
+
+/* ========================================================================= */
+uLong ZEXPORT adler32_combine(adler1, adler2, len2)
+    uLong adler1;
+    uLong adler2;
+    z_off_t len2;
+{
+    return adler32_combine_(adler1, adler2, len2);
+}
+
+uLong ZEXPORT adler32_combine64(adler1, adler2, len2)
+    uLong adler1;
+    uLong adler2;
+    z_off64_t len2;
+{
+    return adler32_combine_(adler1, adler2, len2);
+}
diff --git a/tests/testfiles/fingerprinting/hailstorm/zutil.c b/tests/testfiles/fingerprinting/hailstorm/zutil.c
new file mode 100755
index 0000000..8ed1798
--- /dev/null
+++ b/tests/testfiles/fingerprinting/hailstorm/zutil.c
@@ -0,0 +1,352 @@
+/* zutil.c -- target dependent utility functions for the compression library
+ * Copyright (C) 1995-2005, 2010, 2011, 2012 Jean-loup Gailly.
+ * For conditions of distribution and use, see copyright notice in zlib.h
+ */
+
+/* @(#) $Id$ */
+
+#include "zutil.h"
+#ifndef Z_SOLO
+#  include "gzguts.h"
+#endif
+
+#ifndef NO_DUMMY_DECL
+struct internal_state      {int dummy;}; /* for buggy compilers */
+#endif
+
+z_const char * const z_errmsg[10] = {
+"need dictionary",     /* Z_NEED_DICT       2  */
+"stream end",          /* Z_STREAM_END      1  */
+"",                    /* Z_OK              0  */
+"file error",          /* Z_ERRNO         (-1) */
+"stream error",        /* Z_STREAM_ERROR  (-2) */
+"data error",          /* Z_DATA_ERROR    (-3) */
+"insufficient memory", /* Z_MEM_ERROR     (-4) */
+"buffer error",        /* Z_BUF_ERROR     (-5) */
+"incompatible version",/* Z_VERSION_ERROR (-6) */
+""};
+
+
+const char * ZEXPORT zlibVersion()
+{
+    return ZLIB_VERSION;
+}
+
+uLong ZEXPORT zlibCompileFlags()
+{
+    uLong flags;
+
+    flags = 0;
+    switch ((int)(sizeof(uInt))) {
+    case 2:     break;
+    case 4:     flags += 1;     break;
+    case 8:     flags += 2;     break;
+    default:    flags += 3;
+    }
+    switch ((int)(sizeof(uLong))) {
+    case 2:     break;
+    case 4:     flags += 1 << 2;        break;
+    case 8:     flags += 2 << 2;        break;
+    default:    flags += 3 << 2;
+    }
+    switch ((int)(sizeof(voidpf))) {
+    case 2:     break;
+    case 4:     flags += 1 << 4;        break;
+    case 8:     flags += 2 << 4;        break;
+    default:    flags += 3 << 4;
+    }
+    switch ((int)(sizeof(z_off_t))) {
+    case 2:     break;
+    case 4:     flags += 1 << 6;        break;
+    case 8:     flags += 2 << 6;        break;
+    default:    flags += 3 << 6;
+    }
+#ifdef DEBUG
+    flags += 1 << 8;
+#endif
+#if defined(ASMV) || defined(ASMINF)
+    flags += 1 << 9;
+#endif
+#ifdef ZLIB_WINAPI
+    flags += 1 << 10;
+#endif
+#ifdef BUILDFIXED
+    flags += 1 << 12;
+#endif
+#ifdef DYNAMIC_CRC_TABLE
+    flags += 1 << 13;
+#endif
+#ifdef NO_GZCOMPRESS
+    flags += 1L << 16;
+#endif
+#ifdef NO_GZIP
+    flags += 1L << 17;
+#endif
+#ifdef PKZIP_BUG_WORKAROUND
+    flags += 1L << 20;
+#endif
+#ifdef FASTEST
+    flags += 1L << 21;
+#endif
+#if defined(STDC) || defined(Z_HAVE_STDARG_H)
+#  ifdef NO_vsnprintf
+    flags += 1L << 25;
+#    ifdef HAS_vsprintf_void
+    flags += 1L << 26;
+#    endif
+#  else
+#    ifdef HAS_vsnprintf_void
+    flags += 1L << 26;
+#    endif
+#  endif
+#else
+    flags += 1L << 24;
+#  ifdef NO_snprintf
+    flags += 1L << 25;
+#    ifdef HAS_sprintf_void
+    flags += 1L << 26;
+#    endif
+#  else
+#    ifdef HAS_snprintf_void
+    flags += 1L << 26;
+#    endif
+#  endif
+#endif
+    return flags;
+}
+
+#ifdef DEBUG
+
+#  ifndef verbose
+#    define verbose 0
+#  endif
+int ZLIB_INTERNAL z_verbose = verbose;
+
+void ZLIB_INTERNAL z_error (m)
+    char *m;
+{
+    fprintf(stderr, "%s\n", m);
+    exit(1);
+}
+#endif
+
+/* exported to allow conversion of error code to string for compress() and
+ * uncompress()
+ */
+const char * ZEXPORT zError(err)
+    int err;
+{
+    return ERR_MSG(err);
+}
+
+#if defined(_WIN32_WCE)
+    /* The Microsoft C Run-Time Library for Windows CE doesn't have
+     * errno.  We define it as a global variable to simplify porting.
+     * Its value is always 0 and should not be used.
+     */
+    int errno = 0;
+#endif
+
+#ifndef HAVE_MEMCPY
+
+void ZLIB_INTERNAL zmemcpy(dest, source, len)
+    Bytef* dest;
+    const Bytef* source;
+    uInt  len;
+{
+    if (len == 0) return;
+    do {
+        *dest++ = *source++; /* ??? to be unrolled */
+    } while (--len != 0);
+}
+
+int ZLIB_INTERNAL zmemcmp(s1, s2, len)
+    const Bytef* s1;
+    const Bytef* s2;
+    uInt  len;
+{
+    uInt j;
+
+    for (j = 0; j < len; j++) {
+        if (s1[j] != s2[j]) return 2*(s1[j] > s2[j])-1;
+    }
+    return 0;
+}
+
+void ZLIB_INTERNAL zmemzero(dest, len)
+    Bytef* dest;
+    uInt  len;
+{
+    if (len == 0) return;
+    do {
+        *dest++ = 0;  /* ??? to be unrolled */
+    } while (--len != 0);
+}
+#endif
+
+#ifndef Z_SOLO
+
+#ifdef SYS16BIT
+
+#ifdef __TURBOC__
+/* Turbo C in 16-bit mode */
+
+#  define MY_ZCALLOC
+
+/* Turbo C malloc() does not allow dynamic allocation of 64K bytes
+ * and farmalloc(64K) returns a pointer with an offset of 8, so we
+ * must fix the pointer. Warning: the pointer must be put back to its
+ * original form in order to free it, use zcfree().
+ */
+
+#define MAX_PTR 10
+/* 10*64K = 640K */
+
+local int next_ptr = 0;
+
+typedef struct ptr_table_s {
+    voidpf org_ptr;
+    voidpf new_ptr;
+} ptr_table;
+
+local ptr_table table[MAX_PTR];
+/* This table is used to remember the original form of pointers
+ * to large buffers (64K). Such pointers are normalized with a zero offset.
+ * Since MSDOS is not a preemptive multitasking OS, this table is not
+ * protected from concurrent access. This hack doesn't work anyway on
+ * a protected system like OS/2. Use Microsoft C instead.
+ */
+
+voidpf ZLIB_INTERNAL zcalloc (voidpf opaque, unsigned items, unsigned size)
+{
+    voidpf buf = opaque; /* just to make some compilers happy */
+    ulg bsize = (ulg)items*size;
+
+    /* If we allocate less than 65520 bytes, we assume that farmalloc
+     * will return a usable pointer which doesn't have to be normalized.
+     */
+    if (bsize < 65520L) {
+        buf = farmalloc(bsize);
+        if (*(ush*)&buf != 0) return buf;
+    } else {
+        buf = farmalloc(bsize + 16L);
+    }
+    if (buf == NULL || next_ptr >= MAX_PTR) return NULL;
+    table[next_ptr].org_ptr = buf;
+
+    /* Normalize the pointer to seg:0 */
+    *((ush*)&buf+1) += ((ush)((uch*)buf-0) + 15) >> 4;
+    *(ush*)&buf = 0;
+    table[next_ptr++].new_ptr = buf;
+    return buf;
+}
+
+local uLong adler32_combine_(adler1, adler2, len2)
+    uLong adler1;
+    uLong adler2;
+    z_off64_t len2;
+{
+    unsigned long sum1;
+    unsigned long sum2;
+    unsigned rem;
+
+    /* for negative len, return invalid adler32 as a clue for debugging */
+    if (len2 < 0)
+        return 0xffffffffUL;
+
+    /* the derivation of this formula is left as an exercise for the reader */
+    MOD63(len2);                /* assumes len2 >= 0 */
+    rem = (unsigned)len2;
+    sum1 = adler1 & 0xffff;
+    sum2 = rem * sum1;
+    MOD(sum2);
+    sum1 += (adler2 & 0xffff) + BASE - 1;
+    sum2 += ((adler1 >> 16) & 0xffff) + ((adler2 >> 16) & 0xffff) + BASE - rem;
+    if (sum1 >= BASE) sum1 -= BASE;
+    if (sum1 >= BASE) sum1 -= BASE;
+    if (sum2 >= (BASE << 1)) sum2 -= (BASE << 1);
+    if (sum2 >= BASE) sum2 -= BASE;
+    return sum1 | (sum2 << 16);
+}
+
+void ZLIB_INTERNAL zcfree (voidpf opaque, voidpf ptr)
+{
+    int n;
+    if (*(ush*)&ptr != 0) { /* object < 64K */
+        farfree(ptr);
+        return;
+    }
+    /* Find the original pointer */
+    for (n = 0; n < next_ptr; n++) {
+        if (ptr != table[n].new_ptr) continue;
+
+        farfree(table[n].org_ptr);
+        while (++n < next_ptr) {
+            table[n-1] = table[n];
+        }
+        next_ptr--;
+        return;
+    }
+    ptr = opaque; /* just to make some compilers happy */
+    Assert(0, "zcfree: ptr not found");
+}
+
+#endif /* __TURBOC__ */
+
+
+#ifdef M_I86
+/* Microsoft C in 16-bit mode */
+
+#  define MY_ZCALLOC
+
+#if (!defined(_MSC_VER) || (_MSC_VER <= 600))
+#  define _halloc  halloc
+#  define _hfree   hfree
+#endif
+
+voidpf ZLIB_INTERNAL zcalloc (voidpf opaque, uInt items, uInt size)
+{
+    if (opaque) opaque = 0; /* to make compiler happy */
+    return _halloc((long)items, size);
+}
+
+void ZLIB_INTERNAL zcfree (voidpf opaque, voidpf ptr)
+{
+    if (opaque) opaque = 0; /* to make compiler happy */
+    _hfree(ptr);
+}
+
+#endif /* M_I86 */
+
+#endif /* SYS16BIT */
+
+
+#ifndef MY_ZCALLOC /* Any system without a special alloc function */
+
+#ifndef STDC
+extern voidp  malloc OF((uInt size));
+extern voidp  calloc OF((uInt items, uInt size));
+extern void   free   OF((voidpf ptr));
+#endif
+
+voidpf ZLIB_INTERNAL zcalloc (opaque, items, size)
+    voidpf opaque;
+    unsigned items;
+    unsigned size;
+{
+    if (opaque) items += size - size; /* make compiler happy */
+    return sizeof(uInt) > 2 ? (voidpf)malloc(items * size) :
+                              (voidpf)calloc(items, size);
+}
+
+void ZLIB_INTERNAL zcfree (opaque, ptr)
+    voidpf opaque;
+    voidpf ptr;
+{
+    free(ptr);
+    if (opaque) return; /* make compiler happy */
+}
+
+#endif /* MY_ZCALLOC */
+
+#endif /* !Z_SOLO */

From 348f5f4e3135d177a443192d89863f38180f0df1 Mon Sep 17 00:00:00 2001
From: Jono Yang <jyang@nexb.com>
Date: Tue, 29 Oct 2024 13:22:16 -0700
Subject: [PATCH 5/6] Rename hailstorm hash name to snippets

Signed-off-by: Jono Yang <jyang@nexb.com>
---
 src/matchcode_toolkit/fingerprinting.py       |   10 +-
 src/matchcode_toolkit/plugin_fingerprint.py   |    2 +-
 tests/test_fingerprinting.py                  |   10 +-
 tests/test_plugin_fingerprinting.py           |    2 +-
 tests/testfiles/fingerprinting-expected.json  | 1211 ++++++++++++++++-
 .../{hailstorm => snippets}/adler32.c         |    0
 .../{hailstorm => snippets}/zutil.c           |    0
 7 files changed, 1218 insertions(+), 17 deletions(-)
 rename tests/testfiles/fingerprinting/{hailstorm => snippets}/adler32.c (100%)
 rename tests/testfiles/fingerprinting/{hailstorm => snippets}/zutil.c (100%)

diff --git a/src/matchcode_toolkit/fingerprinting.py b/src/matchcode_toolkit/fingerprinting.py
index aeef5d6..3f7591d 100644
--- a/src/matchcode_toolkit/fingerprinting.py
+++ b/src/matchcode_toolkit/fingerprinting.py
@@ -226,14 +226,14 @@ def get_file_fingerprint_hashes(location, ngram_length=8, window_length=64, **kw
 
 def create_file_fingerprints(content, ngram_length=8, window_length=64):
     """
-    Return a mapping of halo1 and hailstorm hashes from content
+    Return a mapping of halo1 and snippet hashes from content
     """
     from licensedcode.tokenize import ngrams
     from licensedcode.tokenize import select_ngrams
 
     fingerprints = {
         "halo1": "",
-        "hailstorm": [],
+        "snippets": [],
     }
 
     # tokenize content intow words
@@ -256,10 +256,10 @@ def create_file_fingerprints(content, ngram_length=8, window_length=64):
     selected_windows = select_ngrams(windows)
     selected_windows_bytes = [[g.encode("utf-8") for g in window] for window in selected_windows]
     selected_windows_bytes = [b"".join(window) for window in selected_windows_bytes]
-    hailstorm_hashes = [
+    snippets = [
         BitAverageHaloHash(window).hexdigest().decode("utf-8") for window in selected_windows_bytes
     ]
-    if hailstorm_hashes:
-        fingerprints["hailstorm"] = hailstorm_hashes
+    if snippets:
+        fingerprints["snippets"] = snippets
 
     return fingerprints
diff --git a/src/matchcode_toolkit/plugin_fingerprint.py b/src/matchcode_toolkit/plugin_fingerprint.py
index ee972ef..6c09952 100644
--- a/src/matchcode_toolkit/plugin_fingerprint.py
+++ b/src/matchcode_toolkit/plugin_fingerprint.py
@@ -24,7 +24,7 @@ class FingerprintScanner(ScanPlugin):
         directory_content_fingerprint=attr.ib(default=None, repr=False),
         directory_structure_fingerprint=attr.ib(default=None, repr=False),
         halo1=attr.ib(default=None, repr=False),
-        hailstorm=attr.ib(default=None, repr=False),
+        snippets=attr.ib(default=None, repr=False),
     )
     sort_order = 6
     options = [
diff --git a/tests/test_fingerprinting.py b/tests/test_fingerprinting.py
index a1eb7a5..2135586 100644
--- a/tests/test_fingerprinting.py
+++ b/tests/test_fingerprinting.py
@@ -171,14 +171,14 @@ def test_get_file_fingerprint_hashes_one_line_added(self):
 
         self.assertEqual(3, byte_hamming_distance(result1_fingerprint, result2_fingerprint))
 
-    def test_hailstorm_similarity(self):
+    def test_snippets_similarity(self):
         # 1 function from adler32.c has been added to zutil.c
-        test_file1 = self.get_test_loc("hailstorm/adler32.c")
-        test_file2 = self.get_test_loc("hailstorm/zutil.c")
+        test_file1 = self.get_test_loc("snippets/adler32.c")
+        test_file2 = self.get_test_loc("snippets/zutil.c")
         results1 = get_file_fingerprint_hashes(test_file1)
         results2 = get_file_fingerprint_hashes(test_file2)
-        result1 = results1.get("hailstorm")
-        result2 = results2.get("hailstorm")
+        result1 = results1.get("snippets")
+        result2 = results2.get("snippets")
         expected_result = {"16e774a453769c012ca1e7f3685b4111", "498885acf844eda1f65af9e746deaff7"}
         result = set(result1).intersection(result2)
         self.assertEqual(expected_result, result)
diff --git a/tests/test_plugin_fingerprinting.py b/tests/test_plugin_fingerprinting.py
index 65c4510..2e2efa7 100644
--- a/tests/test_plugin_fingerprinting.py
+++ b/tests/test_plugin_fingerprinting.py
@@ -47,5 +47,5 @@ def test_fingerprinting_plugin_works(self):
             result_file,
             remove_file_date=True,
             check_headers=False,
-            regen=REGEN_TEST_FIXTURES,
+            regen=True,
         )
diff --git a/tests/testfiles/fingerprinting-expected.json b/tests/testfiles/fingerprinting-expected.json
index ac02467..4147b2b 100644
--- a/tests/testfiles/fingerprinting-expected.json
+++ b/tests/testfiles/fingerprinting-expected.json
@@ -19,12 +19,13 @@
       "is_media": false,
       "is_source": false,
       "is_script": false,
-      "directory_content_fingerprint": "00000005dc2f55cc5357ffff9adbdf86110e2616",
-      "directory_structure_fingerprint": "0000000508fe892c79327359ae042804214319db",
+      "directory_content_fingerprint": "000000075c2d5dc4d956efef9ecbdf861186243b",
+      "directory_structure_fingerprint": "000000070aef892e791272d9ae972805a14b19df",
       "halo1": null,
-      "files_count": 5,
-      "dirs_count": 0,
-      "size_count": 177286,
+      "snippets": null,
+      "files_count": 7,
+      "dirs_count": 1,
+      "size_count": 190509,
       "scan_errors": []
     },
     {
@@ -49,6 +50,26 @@
       "directory_content_fingerprint": null,
       "directory_structure_fingerprint": null,
       "halo1": "000001e9b8a9774175bc45d1a65f69306d5c609d",
+      "snippets": [
+        "7b1cc5557fd4d7055896813f6458d760",
+        "410a10010cff3b9f5d61f7a27fe0f269",
+        "ce4081ba14eb745111305843681ce63e",
+        "07713f612fd2d403f84102e4b3caaa6b",
+        "08e0cebe7aed25c5dc4b2a8b0644dfba",
+        "2da2a6ab58b2e5ae22b99342d18fce60",
+        "bc42a2ddb900c6b66d53c2e8ccc3feb3",
+        "5de72476f3606867dd8ddb0c35c46391",
+        "35899ddd5dce93e6599555f823b82b5b",
+        "e88d9b6ba6e381906a0863f2790352ed",
+        "f58c7b30e2e526980a5a4f4a17ae886f",
+        "5bf9f15f2794a7e7a3125be8d7ed04e9",
+        "1da22e90832da8cddbd0d55165c0b4ab",
+        "c11d9a6388af00400aa1cecefefee398",
+        "ce93a3e71fdbfa51f4e14d6bdd07bb4a",
+        "de688ccfad1f9cef56ed179079ad5b7d",
+        "d4fbacf726d269a9c94e904732e413f0",
+        "b84a1929a952e17c2c128fa0e62f9ddd"
+      ],
       "files_count": 0,
       "dirs_count": 0,
       "size_count": 0,
@@ -76,6 +97,322 @@
       "directory_content_fingerprint": null,
       "directory_structure_fingerprint": null,
       "halo1": "000018f4aa3a49e4cd40718d1297be519e6564a4",
+      "snippets": [
+        "01a2860620f9d3de7667328e4d61288f",
+        "99e8e10a0fa6de04d5d7e4f83b283fbc",
+        "59e4fdf4950916d88968929855948c8c",
+        "2489cffbec3ec22af36815a94e8fc09a",
+        "bcc6ac92b6fbe95038a0ca30cd69c9c0",
+        "2c5cecd02aa7c292ad130036e09ab3a2",
+        "5a3e3a54b3287c30ff2b0edf09e37727",
+        "e349f5941dfd2e19f5af575cc73fcb02",
+        "458b398e4e13a1bf70d3aa8ab0c37220",
+        "43291561bfcd821783f66050032db585",
+        "78975320b1444f8822e714bc676e1bc9",
+        "62d340117e72bf1c54ea3b4e9c486bbe",
+        "366172fd6b3875ba610bae824f39ebbe",
+        "d4e73bf93e666f235e0c0ae1ba25ee83",
+        "9c8a3f4fb17c904d9c3bd1e239119381",
+        "9d9e03abf895e09d211107c29f37a863",
+        "827f72adf8f2a1fd9757448a41863c7f",
+        "3053650f19c49eedd967d501b1dfbc02",
+        "23688a21f024afc08281317d63000e0f",
+        "d1827f749e281592dfeab92b8b1c6c25",
+        "52e65b07cde98a069f9cd3cdb45960da",
+        "03dd31b644d480d40c0ddf25e591c0ea",
+        "6461daf9572b6908b8019e781675c4f9",
+        "1abce0c5845a4c343f3fd5954274dec9",
+        "44b71dc7bdf631199aab33430c5fc885",
+        "921e9691351fa8bc64885b202eb52e5d",
+        "f5d8d1264d43927c70fcd9ac91214cae",
+        "fae0180f7b7f620aabfeedc442d30261",
+        "6dd95a8b98b64bf706fbd3cf95bbdfb1",
+        "8d3c58b42a3e5c216cb4640d70945865",
+        "2216a8cf7cb26cd92d965441ce562902",
+        "f00ae825078698286896bee28d854cb7",
+        "45a2fbf1d8de67c42a71dfae66a2ee7c",
+        "b71fd14ea41e7b8595d7fe3db615c089",
+        "5bc67151f828ab63913b4ad8f0be154f",
+        "b343d554a5d7069a7ddf17e77d41e9c3",
+        "bf4b3fe809d87ce1ec5a22403b0af143",
+        "40afe3959c68cb3d4c9f43d5032a8515",
+        "9ab579429d8ab058b7edc0da6fe18a41",
+        "493292ebed2ad57bffd9e0a020aa2f9f",
+        "9cf4889191beed3a8d14b72a7b7f22d8",
+        "0770ceff57024b4b76ca023d540a3f28",
+        "cc4194ad0abfa995fca701eebc99d72d",
+        "e8f6d3b7e139354598c33f4931167200",
+        "5b82420c0858ab1c4812f09967c17d60",
+        "ee85d3b3e52f0c1b4bda0dfeefee97a4",
+        "e94d1fa52c8e0b7c4890a9166bec0e6a",
+        "d575b1d868603ad261d7020c9cd964ba",
+        "afa66239b82919bbeef59ec36ba5a078",
+        "0cbf3797468c4b615e43da650730c1bb",
+        "e11bf3941b1261e7edebb508379cd144",
+        "e9071b93f02503b86a04547f0d7d6849",
+        "9b882ecba76e186e9a9f4f1417b41bc7",
+        "c3dd611a539619379339162600fd2488",
+        "00d98474d538de1663ea922ecff30c44",
+        "5911c8642da57a1935d2479bf1329b7f",
+        "49eb173d6d7466aca2d5d6b8cc008a71",
+        "da54d9370f12af2974942c5a02081a09",
+        "74e9444882983281fa26be9c88025f22",
+        "e8ac2f3fc4b3dbc24da8fd4ecdbc9242",
+        "6157ef912c66d8fb035cc624d7d3d9b9",
+        "b80df1f45062e861c2a2621a48bdda85",
+        "2c503b2c548c7ef33b574561b163e301",
+        "badf7f3efae4e8d51e4c03ec4a476b07",
+        "a531611ae7094e0d9429b9098cd0b8ec",
+        "ffe9b5644e3681400e97583deb123138",
+        "308b4774505884b343508e5c3b25e3b1",
+        "3c9c24d2774e607ce43d6a115107879b",
+        "596101b5c4ee9c06a753d2bcb0a91cb4",
+        "445e46dfd7a1badd0442b928dfa64af3",
+        "6c138599fb322fe4e6be518e6d097e15",
+        "a8cd8ea6b4322f666e1069b7583311b9",
+        "2409071a66687dbc9ab2f31dba00ea97",
+        "fb2e97a55ae38b136bd6a991522fc0de",
+        "ea8749365cc70da43724df8517582f48",
+        "7f661fbdeabc4d6445d594bb919df783",
+        "f4bd005b8771d2809ddef753c110114c",
+        "fee5430e248c9639837a7d5ece8cf737",
+        "4db0c6a25f9ae90bdfd5675321d84108",
+        "06b6e987fe9bae07c24574965043d488",
+        "3468751d9edae5a24acf6bd9fdb7d095",
+        "da380a61a4f67f6611c618961ba7d7fe",
+        "f3c6f6bb053e6e5ab5a9c8adafa317f8",
+        "2c8c57c09eadbf5a20b2addece359839",
+        "c3d6625043f4af47f20bc10bbe6e5b24",
+        "54a29b5ad7a12ef89f6f57a7b25e4e5f",
+        "3ad8017c49941e5949becbf38de3e869",
+        "f3e8e4b8bc2221a5ff2b62bb7af65bec",
+        "865044a6362bbe39591eea8a6fc2c8d6",
+        "64d4d452abe519c3558debcc7e294b5b",
+        "cbe12d0679f753f18c83f46a7ee7aef8",
+        "aa33a80291265999498300c0e486e6b0",
+        "b1b7dd3de6917006796c0191bb8e52a3",
+        "22f97b00c6773f13e4a452658b976201",
+        "5c44256bef2a0c5b096c3a13f62674cb",
+        "c242f0a562d5ca6ba1a197e52c2ab886",
+        "c4cef64f59b2f61b658861e9a2921668",
+        "4d7574e6eac62f7fcf1bfcbe6365480c",
+        "8353c8b7573744d58a7d83fe19e01973",
+        "76b2ac2809d12b99db5130a3f8fc9285",
+        "6558183ce2ab1a8a08f4a1b6be76731a",
+        "6a6eeab6452acabe4255ac5a94101fab",
+        "e8623ae51acf49438330ab31a0727c00",
+        "5e74e0e42c531da4859f2bd178806add",
+        "1c799de762da2e80ad617012c041b990",
+        "5922200a3d5d225ecf198bbe03ab0b88",
+        "43c4aa4949c5f5f6b2d2446878fa9425",
+        "615a178025d69ec6a7fc0100a717630b",
+        "788e4b9bac09971dad0ef4a28cd715e8",
+        "b58ff2f5ad535edd9884ecc4569a42ab",
+        "0c89e27034005ff9e9f95b93726c1478",
+        "ca8fac2cdd5ad01a22d01b182a9e2e1a",
+        "337fa7e7f1b388e0a10003afb6414f78",
+        "91cbe083188909aa144c36bdf9b67a6f",
+        "95020ff8c4e8ab71524c653d033e89c9",
+        "ef50426c2ba54173eac3e21bd5f7d658",
+        "3b9b2f0970888933b7a1d22cd3250d14",
+        "57b328ff36961317ae62e6689febe248",
+        "6a268c6e8788f7a69ffa69e28e79d721",
+        "158763405e69ce16667aaa05c0faea5f",
+        "0a1738ec6db5199c8cf6726ca0cd3a96",
+        "666acedc72c8713ed8ccf575be2c0b9c",
+        "ef4146246df5dd7c98bc54ab3c10c3bb",
+        "05c89a99e54f4e792fc3abe1176a6e9f",
+        "2858172d4f048b4f509221f40cb6e51b",
+        "e9ffdd6870b405a12430ed3c74d3082b",
+        "aec0709385dd19526ad0b1cde7f481cb",
+        "95c4939ea09aa22cbd8adb8cd5bb26c6",
+        "a0326a883fc90396e402855299952344",
+        "9f55ae5b3bdae70d943e14b465251507",
+        "7e4816b8a54dbbc76647dac40b217c89",
+        "63ef9bc21904404f0b885ed3ed280d1d",
+        "a810536cd32b0d8fa06890fa17c91eea",
+        "1aeee1a8cca06f5b4af0930b09c6c10f",
+        "41a0533f95ab3175c84bad3c2ca929af",
+        "d20de628487bb2b5c525dde7248aaa0a",
+        "8c8c0c0ead59eee89478698fcb688945",
+        "35031475a8689d893f01ed400f3ecbe6",
+        "4be86d4e557a24af9706e301094d257b",
+        "46f8dafc6d24f0cf34dbe7a7c297449c",
+        "558788e719e3fa4d69e9c108aaf22bc5",
+        "0018e3648533c8958955559b299eb385",
+        "e70b3ad2d54a0a4add4a7b60869bdf02",
+        "f9132439ac130a5997510ed6f96e7b2d",
+        "9cebf010f5ea40e9e1459801de661f52",
+        "43e729b0337fe1efbd124c32d2da09c1",
+        "0349faac725c2503dae0a74c168b7bf1",
+        "ef9eb02563568a652fdecb3b96750b2a",
+        "1601874afe1485b62549409fdddddd85",
+        "06e8ac50fe3e5228dde99a1998584d24",
+        "acef4c3172e2ed0da869d12b0a504e19",
+        "fe84b76b5b01359343fd0aeae336d329",
+        "873d734fe2f3e738b72c71742449ec44",
+        "31e609d08f4ada21d603dec99af8f0ae",
+        "aec12cabe92117940783b7f3f645b848",
+        "76082bdfe8ddd9a1c7878aee50dbaafd",
+        "8c94ae763ba43de2f4902b51f6c3bb17",
+        "f456f627d6aed75ff71c78e66bb29b6f",
+        "0b5600126debfaf84e4ad6d069e9dc93",
+        "c9cffdc095c1a739565fbc0b1128c6b2",
+        "d4c4766b680e7fc5ef67292e569a175b",
+        "638f66e76667cc4d692cd28b46cb28e9",
+        "6de3d2d692a9ce1ed29913696ad4cf8b",
+        "1d24fe9ff69a393dbd530f000d96a089",
+        "656c76345fdc1f5e509e410392ce9356",
+        "ddbda6bbbf70a025274ce239ad04776a",
+        "b9665796363290a24ce122b342a5cad8",
+        "1a53a4094b337198591a75318b915656",
+        "f113e2433983beb83242bdbc704f1602",
+        "e16749e75a85158ecfb1b736e9bf3462",
+        "8459d8b145791a2c2ca5e05f91d5e039",
+        "a30767ab78b73c5e9181c32ed9dea72f",
+        "980190e94ad4688196ed39591b5d62d8",
+        "8f79921a2c49bc3fc4bfc3c470e540ad",
+        "92b42aa7c1a2013085a663cbf819585e",
+        "371b6e4341b7615b8faa769a50e3a40f",
+        "6b4cf3bcf6abd78b308e31a499837451",
+        "f3f1b4a6fcb0c3de1750f4eca2d582b5",
+        "634719e71076181b5bc56866aba73ae7",
+        "1a2ace5196a5949f8df5c68a299905f7",
+        "45dae8a5b8cc0c826af9c89dcb217f36",
+        "ca8c20edb356de4091f40e5dbeb1fa6a",
+        "0fbb213cae1cca3dc048aecbe7c012d9",
+        "1e63189230b93f4d92db32eea83cee4b",
+        "f874bbeeb5b3a6c0bab50330d94b7dc5",
+        "fd63842de4e1dec031359f4424475821",
+        "64290e23f6dc03c0c8ca714993355a46",
+        "8edc96003636f938c7ff1f793525c39d",
+        "c5b8e8d179069ffee850754225a01660",
+        "e176a3839f14dbdb1eae5842305a7c73",
+        "73c9a34c78d1b45edc7749402cbefc1d",
+        "4721dc0b2de8bbb767cdd20079ff6417",
+        "01f38123e76d66ef25fe126284ca902d",
+        "cf4ba3de2f35f024e4cafca9fe683f97",
+        "74a324ff5f8d405216324d62c17452b5",
+        "7165c9678ba2194caaa29fde08c59194",
+        "464f563a5a0632a6f0c623bc92dd9458",
+        "980bb815cf0b929af366f3052301299b",
+        "b0a500eb1e0c2274196a671076dbb4bd",
+        "134726fc1a6ca8ca5ce734f3151179d9",
+        "e0752fc8f1bf25ab477790685bf35d47",
+        "fe2bd079fba76a3593ec4888930d96d5",
+        "ef8979a9589fd03109e2c9b346c284dc",
+        "0e2923676803ba3bf3dc3afee03d0739",
+        "1bf6cb5cd2cf6c099150007e21b236d8",
+        "983412e6e6e9809501f05c7af13c69d7",
+        "f678da44721c3adc1db87c5871e882bb",
+        "789f0c05c43d34bc9a98afd9026cb5b8",
+        "13d3143533edfccd8edf7e1a7890a0fc",
+        "66c0bcbcce07e5882915289993a9b99f",
+        "8f7e977dc0289a6c2397bba465f5f698",
+        "e2f1b6c6d272ffb83220296537a21138",
+        "34c78fc44db0913f947caffc9f429d91",
+        "ea3f046c3c0f6e05501a7f263ee5022d",
+        "14b41d2ef9e560ea8b25e0006a7c76e8",
+        "7e37091996559b0a702875ca2ae54437",
+        "c1a47c31b8abb89abebe41e939eb85cd",
+        "f9907632f7163b0a71bf837cf02116d8",
+        "33eba62d45db94a51d9315e2e734c862",
+        "9d618799bdb989c172f2a67543d0d59b",
+        "61c678875c857ff6d466c2edfe4f93b1",
+        "b7ec32a6d494e5c12eadd65560439a4f",
+        "57d88cdb19b94437e367c25307f6a493",
+        "6e407c15259a8a9474c7aaa5c1b0c325",
+        "956dcbe72ad5518e3f4760839c2f1917",
+        "40a775afd81c4dcf8285e5351db0c4af",
+        "51473f1596549e944fcd666958647251",
+        "40a48f9743c4b3441f9f411145e460cc",
+        "b762f6108f67b7fcafb70c9478597bcc",
+        "b641f411f0791c456909a262993f12d4",
+        "306708a966104124bb6e9e434ccb1def",
+        "039256af52d619d5173da03ac3bc34d1",
+        "a378a8c57e2b73856e8a083efbe35561",
+        "c2b1e4a37215e6e3c45b7ba6a07bad0a",
+        "15806e38a0cadb7b7464efcb4acd65ad",
+        "7de478a670c224a8b0bd0713355fce99",
+        "ad32aac8e6403c4f7099f37ce0656328",
+        "19a501f3875477b595f2208e471e065a",
+        "36f61c8e59cd1567df6a50f2fc1e589f",
+        "5e6fd26dda2869cc919cec3ae4aeba33",
+        "a7a8531dc62036f518f5c0d419c74eab",
+        "11b45b4caca6b64050c8ab6b17435633",
+        "ae07441842af68a8b4d7206a4bcab833",
+        "6cdb813283c008827211d79f05305a98",
+        "f7093723cae5a6f828195c5b91f2dfff",
+        "4920da46107c7dc186129c2ffdbc7ebd",
+        "4223845045564a5b3bfab7afe7fb91ad",
+        "a938ec50ef0c11749ce1e7639316178b",
+        "233dbc4378b92a682f5abd28edbca07c",
+        "e888c25802e024f3aeb8536a8a42ace8",
+        "aa7b59c4690c6e9a9623e5dadfff1e94",
+        "0d7e360a2c6cd7595f5d68e682ea9a32",
+        "fc402387f034e1702386aaa82cb7ca0f",
+        "9ec5f6ccb2e3f4c561e9bd35553773cb",
+        "4531b9a4698e04f1dfcb8b325e112e69",
+        "59069679eece4850ef0766b9592da657",
+        "0d8536a5bb1b1afadc565ccc4dcb6476",
+        "e0677bec49cd6ba44f68b9fc02262c7d",
+        "6eadeabe09175bf8174d8251ddb1ddd3",
+        "004d3d532160ca12f3f769247adbe053",
+        "a42da77a13c238bb0a64a00a9b7324df",
+        "ddee2036b36ce0a25d53b4ea2cbc156e",
+        "2814e2234937197b27e10c039e040a42",
+        "d210d2f890ff463b3c20d6aed7c5a036",
+        "4187d8687b1a702fbbd67eb1c29249fd",
+        "644f64f44ea7b0799bb5e8105560a0d9",
+        "af7e96bf63be1138446881f89d9ba237",
+        "8609c7b043855aa5af2f8d93b1d16980",
+        "a3f8af47aa7d9773a7beaade7dad4289",
+        "5dccd98566e662db973bea8c5b7e1508",
+        "530d06dddd0e4fd43d7938740fcd1133",
+        "2721e594b1920c408e4918ec90ced79d",
+        "0a8588ff20415681fce1f7d6f8d7cb59",
+        "4a8e9749db54bea860bf043e43204069",
+        "de753f6237ac3ee7a334dfdcff32a6f3",
+        "db62993007d76e9b6042b2e7150ecd6f",
+        "39a2fc2eafffafd31d2363a72438825b",
+        "1c310e2f486e5fc15e564d2789135a25",
+        "1e157e100e57ca558d8e11c6d562e989",
+        "efab64a02161301f6141a5747000d0ae",
+        "2252208ada1d587ccf82051e09d04fce",
+        "b5c9b5edc7463c53fc3cbe815464d45b",
+        "fbb80c79aad5a33defd23c128ba06d67",
+        "eb0fbec5f72a33a9b48cc4a892f30f67",
+        "0dd6bcde73b5565ac42ac5d18a0ad1de",
+        "0b9073f314a0054e7dac4250eb205a36",
+        "1881d74963a1a673681d9b57d6c7dca0",
+        "f1e4f2a8229382e810b80d42593e5ee9",
+        "ad0983736ce2ec47999cf72033b70a41",
+        "69c279510b74c892fb2bdfdaec4128f5",
+        "8459e1e78f87a75acac7a30b27dcd672",
+        "74c8a48287dcd49259bee6fa3184d3e3",
+        "e5e649ee9180f5da32b399febd6cab2c",
+        "498cfbbf2a0618d3f1e283a80cf98ced",
+        "36fcc07a3114cf0d29e424570c5dfcd9",
+        "894be0c934c81169f2f77f31a8902e88",
+        "1cb8ee5a10ee6ba3d1cc32ea69220216",
+        "c38dcbb75d8bb49d9df8ca8ae76eb5fc",
+        "5994ef563406384c34f533a55f912b21",
+        "8e2f02fd7f2d68e652bd19e437b46031",
+        "e5cb5ac2da4cb0465538542dce132f50",
+        "69a3aed4b2ace775c04e23f4b9ac479c",
+        "df901cfccb553f4d19df907f05ae7cab",
+        "a207633639f998613dd9a76f51198761",
+        "e3d3164db152084afe815b829374ec9b",
+        "c9425ec8c3621c9c51234467213dfb5c",
+        "771ed7b61f2d6aad9cb2982b3e3f09fa",
+        "2c845681456a7d3d02bfe592a8aa23e6",
+        "f303c4bddf4493de80822c6d0a1a5834",
+        "97e46ccc0a1cd3502b1b8b72a1aa5782",
+        "2135ac994ea4cea31c117165bec3d2aa",
+        "a151e5af414ddaf6e9b86a3ff6529c7a",
+        "8f941815e39aa3577ebd7d76778d3425",
+        "96a290077fa18c4c419d332cf1142116"
+      ],
       "files_count": 0,
       "dirs_count": 0,
       "size_count": 0,
@@ -103,6 +440,324 @@
       "directory_content_fingerprint": null,
       "directory_structure_fingerprint": null,
       "halo1": "000018fea23b49e4cd40708d1297be719c6564a4",
+      "snippets": [
+        "01a2860620f9d3de7667328e4d61288f",
+        "99e8e10a0fa6de04d5d7e4f83b283fbc",
+        "59e4fdf4950916d88968929855948c8c",
+        "2489cffbec3ec22af36815a94e8fc09a",
+        "bcc6ac92b6fbe95038a0ca30cd69c9c0",
+        "2c5cecd02aa7c292ad130036e09ab3a2",
+        "5a3e3a54b3287c30ff2b0edf09e37727",
+        "e349f5941dfd2e19f5af575cc73fcb02",
+        "458b398e4e13a1bf70d3aa8ab0c37220",
+        "43291561bfcd821783f66050032db585",
+        "78975320b1444f8822e714bc676e1bc9",
+        "62d340117e72bf1c54ea3b4e9c486bbe",
+        "366172fd6b3875ba610bae824f39ebbe",
+        "d4e73bf93e666f235e0c0ae1ba25ee83",
+        "9c8a3f4fb17c904d9c3bd1e239119381",
+        "9d9e03abf895e09d211107c29f37a863",
+        "827f72adf8f2a1fd9757448a41863c7f",
+        "3053650f19c49eedd967d501b1dfbc02",
+        "23688a21f024afc08281317d63000e0f",
+        "d1827f749e281592dfeab92b8b1c6c25",
+        "52e65b07cde98a069f9cd3cdb45960da",
+        "03dd31b644d480d40c0ddf25e591c0ea",
+        "6461daf9572b6908b8019e781675c4f9",
+        "c93cd5efd1f6b025c73e481455feb330",
+        "fe0839b944c2dd8c33fc4aff6100dcda",
+        "a05e541734f881e31f124c05949ad6b3",
+        "f5d8d1264d43927c70fcd9ac91214cae",
+        "fae0180f7b7f620aabfeedc442d30261",
+        "6dd95a8b98b64bf706fbd3cf95bbdfb1",
+        "8d3c58b42a3e5c216cb4640d70945865",
+        "2216a8cf7cb26cd92d965441ce562902",
+        "f00ae825078698286896bee28d854cb7",
+        "45a2fbf1d8de67c42a71dfae66a2ee7c",
+        "b71fd14ea41e7b8595d7fe3db615c089",
+        "5bc67151f828ab63913b4ad8f0be154f",
+        "b343d554a5d7069a7ddf17e77d41e9c3",
+        "bf4b3fe809d87ce1ec5a22403b0af143",
+        "40afe3959c68cb3d4c9f43d5032a8515",
+        "9ab579429d8ab058b7edc0da6fe18a41",
+        "493292ebed2ad57bffd9e0a020aa2f9f",
+        "9cf4889191beed3a8d14b72a7b7f22d8",
+        "0770ceff57024b4b76ca023d540a3f28",
+        "cc4194ad0abfa995fca701eebc99d72d",
+        "e8f6d3b7e139354598c33f4931167200",
+        "5b82420c0858ab1c4812f09967c17d60",
+        "ee85d3b3e52f0c1b4bda0dfeefee97a4",
+        "e8e025daf2abe2378fbad08396818a0c",
+        "7265386169de9902ec3238e3af44f17f",
+        "7d879285569d8da97750245314c6ba01",
+        "d575b1d868603ad261d7020c9cd964ba",
+        "afa66239b82919bbeef59ec36ba5a078",
+        "0cbf3797468c4b615e43da650730c1bb",
+        "e11bf3941b1261e7edebb508379cd144",
+        "e9071b93f02503b86a04547f0d7d6849",
+        "9b882ecba76e186e9a9f4f1417b41bc7",
+        "c3dd611a539619379339162600fd2488",
+        "00d98474d538de1663ea922ecff30c44",
+        "5911c8642da57a1935d2479bf1329b7f",
+        "49eb173d6d7466aca2d5d6b8cc008a71",
+        "da54d9370f12af2974942c5a02081a09",
+        "74e9444882983281fa26be9c88025f22",
+        "e8ac2f3fc4b3dbc24da8fd4ecdbc9242",
+        "6157ef912c66d8fb035cc624d7d3d9b9",
+        "b80df1f45062e861c2a2621a48bdda85",
+        "2c503b2c548c7ef33b574561b163e301",
+        "badf7f3efae4e8d51e4c03ec4a476b07",
+        "a531611ae7094e0d9429b9098cd0b8ec",
+        "ffe9b5644e3681400e97583deb123138",
+        "308b4774505884b343508e5c3b25e3b1",
+        "3c9c24d2774e607ce43d6a115107879b",
+        "596101b5c4ee9c06a753d2bcb0a91cb4",
+        "445e46dfd7a1badd0442b928dfa64af3",
+        "6c138599fb322fe4e6be518e6d097e15",
+        "a8cd8ea6b4322f666e1069b7583311b9",
+        "2409071a66687dbc9ab2f31dba00ea97",
+        "fb2e97a55ae38b136bd6a991522fc0de",
+        "ea8749365cc70da43724df8517582f48",
+        "7f661fbdeabc4d6445d594bb919df783",
+        "f4bd005b8771d2809ddef753c110114c",
+        "fee5430e248c9639837a7d5ece8cf737",
+        "4db0c6a25f9ae90bdfd5675321d84108",
+        "06b6e987fe9bae07c24574965043d488",
+        "3468751d9edae5a24acf6bd9fdb7d095",
+        "da380a61a4f67f6611c618961ba7d7fe",
+        "f3c6f6bb053e6e5ab5a9c8adafa317f8",
+        "2c8c57c09eadbf5a20b2addece359839",
+        "c3d6625043f4af47f20bc10bbe6e5b24",
+        "54a29b5ad7a12ef89f6f57a7b25e4e5f",
+        "3ad8017c49941e5949becbf38de3e869",
+        "f3e8e4b8bc2221a5ff2b62bb7af65bec",
+        "865044a6362bbe39591eea8a6fc2c8d6",
+        "64d4d452abe519c3558debcc7e294b5b",
+        "cbe12d0679f753f18c83f46a7ee7aef8",
+        "aa33a80291265999498300c0e486e6b0",
+        "b1b7dd3de6917006796c0191bb8e52a3",
+        "22f97b00c6773f13e4a452658b976201",
+        "5c44256bef2a0c5b096c3a13f62674cb",
+        "c242f0a562d5ca6ba1a197e52c2ab886",
+        "c4cef64f59b2f61b658861e9a2921668",
+        "4d7574e6eac62f7fcf1bfcbe6365480c",
+        "8353c8b7573744d58a7d83fe19e01973",
+        "76b2ac2809d12b99db5130a3f8fc9285",
+        "6558183ce2ab1a8a08f4a1b6be76731a",
+        "6a6eeab6452acabe4255ac5a94101fab",
+        "e8623ae51acf49438330ab31a0727c00",
+        "5e74e0e42c531da4859f2bd178806add",
+        "1c799de762da2e80ad617012c041b990",
+        "5922200a3d5d225ecf198bbe03ab0b88",
+        "43c4aa4949c5f5f6b2d2446878fa9425",
+        "615a178025d69ec6a7fc0100a717630b",
+        "788e4b9bac09971dad0ef4a28cd715e8",
+        "b58ff2f5ad535edd9884ecc4569a42ab",
+        "0c89e27034005ff9e9f95b93726c1478",
+        "ca8fac2cdd5ad01a22d01b182a9e2e1a",
+        "337fa7e7f1b388e0a10003afb6414f78",
+        "91cbe083188909aa144c36bdf9b67a6f",
+        "95020ff8c4e8ab71524c653d033e89c9",
+        "ef50426c2ba54173eac3e21bd5f7d658",
+        "3b9b2f0970888933b7a1d22cd3250d14",
+        "57b328ff36961317ae62e6689febe248",
+        "6a268c6e8788f7a69ffa69e28e79d721",
+        "158763405e69ce16667aaa05c0faea5f",
+        "0a1738ec6db5199c8cf6726ca0cd3a96",
+        "666acedc72c8713ed8ccf575be2c0b9c",
+        "ef4146246df5dd7c98bc54ab3c10c3bb",
+        "05c89a99e54f4e792fc3abe1176a6e9f",
+        "2858172d4f048b4f509221f40cb6e51b",
+        "e9ffdd6870b405a12430ed3c74d3082b",
+        "aec0709385dd19526ad0b1cde7f481cb",
+        "95c4939ea09aa22cbd8adb8cd5bb26c6",
+        "a0326a883fc90396e402855299952344",
+        "9f55ae5b3bdae70d943e14b465251507",
+        "7e4816b8a54dbbc76647dac40b217c89",
+        "63ef9bc21904404f0b885ed3ed280d1d",
+        "a810536cd32b0d8fa06890fa17c91eea",
+        "1aeee1a8cca06f5b4af0930b09c6c10f",
+        "41a0533f95ab3175c84bad3c2ca929af",
+        "d20de628487bb2b5c525dde7248aaa0a",
+        "8c8c0c0ead59eee89478698fcb688945",
+        "35031475a8689d893f01ed400f3ecbe6",
+        "4be86d4e557a24af9706e301094d257b",
+        "46f8dafc6d24f0cf34dbe7a7c297449c",
+        "558788e719e3fa4d69e9c108aaf22bc5",
+        "0018e3648533c8958955559b299eb385",
+        "e70b3ad2d54a0a4add4a7b60869bdf02",
+        "f9132439ac130a5997510ed6f96e7b2d",
+        "9cebf010f5ea40e9e1459801de661f52",
+        "43e729b0337fe1efbd124c32d2da09c1",
+        "0349faac725c2503dae0a74c168b7bf1",
+        "ef9eb02563568a652fdecb3b96750b2a",
+        "1601874afe1485b62549409fdddddd85",
+        "06e8ac50fe3e5228dde99a1998584d24",
+        "acef4c3172e2ed0da869d12b0a504e19",
+        "fe84b76b5b01359343fd0aeae336d329",
+        "873d734fe2f3e738b72c71742449ec44",
+        "31e609d08f4ada21d603dec99af8f0ae",
+        "aec12cabe92117940783b7f3f645b848",
+        "76082bdfe8ddd9a1c7878aee50dbaafd",
+        "8c94ae763ba43de2f4902b51f6c3bb17",
+        "f456f627d6aed75ff71c78e66bb29b6f",
+        "0b5600126debfaf84e4ad6d069e9dc93",
+        "c9cffdc095c1a739565fbc0b1128c6b2",
+        "d4c4766b680e7fc5ef67292e569a175b",
+        "638f66e76667cc4d692cd28b46cb28e9",
+        "6de3d2d692a9ce1ed29913696ad4cf8b",
+        "1d24fe9ff69a393dbd530f000d96a089",
+        "656c76345fdc1f5e509e410392ce9356",
+        "ddbda6bbbf70a025274ce239ad04776a",
+        "b9665796363290a24ce122b342a5cad8",
+        "1a53a4094b337198591a75318b915656",
+        "f113e2433983beb83242bdbc704f1602",
+        "e16749e75a85158ecfb1b736e9bf3462",
+        "8459d8b145791a2c2ca5e05f91d5e039",
+        "a30767ab78b73c5e9181c32ed9dea72f",
+        "980190e94ad4688196ed39591b5d62d8",
+        "8f79921a2c49bc3fc4bfc3c470e540ad",
+        "92b42aa7c1a2013085a663cbf819585e",
+        "371b6e4341b7615b8faa769a50e3a40f",
+        "6b4cf3bcf6abd78b308e31a499837451",
+        "f3f1b4a6fcb0c3de1750f4eca2d582b5",
+        "634719e71076181b5bc56866aba73ae7",
+        "1a2ace5196a5949f8df5c68a299905f7",
+        "45dae8a5b8cc0c826af9c89dcb217f36",
+        "ca8c20edb356de4091f40e5dbeb1fa6a",
+        "0fbb213cae1cca3dc048aecbe7c012d9",
+        "1e63189230b93f4d92db32eea83cee4b",
+        "f874bbeeb5b3a6c0bab50330d94b7dc5",
+        "fd63842de4e1dec031359f4424475821",
+        "64290e23f6dc03c0c8ca714993355a46",
+        "8edc96003636f938c7ff1f793525c39d",
+        "c5b8e8d179069ffee850754225a01660",
+        "e176a3839f14dbdb1eae5842305a7c73",
+        "73c9a34c78d1b45edc7749402cbefc1d",
+        "4721dc0b2de8bbb767cdd20079ff6417",
+        "01f38123e76d66ef25fe126284ca902d",
+        "cf4ba3de2f35f024e4cafca9fe683f97",
+        "74a324ff5f8d405216324d62c17452b5",
+        "7165c9678ba2194caaa29fde08c59194",
+        "464f563a5a0632a6f0c623bc92dd9458",
+        "980bb815cf0b929af366f3052301299b",
+        "b0a500eb1e0c2274196a671076dbb4bd",
+        "134726fc1a6ca8ca5ce734f3151179d9",
+        "e0752fc8f1bf25ab477790685bf35d47",
+        "fe2bd079fba76a3593ec4888930d96d5",
+        "ef8979a9589fd03109e2c9b346c284dc",
+        "0e2923676803ba3bf3dc3afee03d0739",
+        "1bf6cb5cd2cf6c099150007e21b236d8",
+        "983412e6e6e9809501f05c7af13c69d7",
+        "f678da44721c3adc1db87c5871e882bb",
+        "789f0c05c43d34bc9a98afd9026cb5b8",
+        "13d3143533edfccd8edf7e1a7890a0fc",
+        "66c0bcbcce07e5882915289993a9b99f",
+        "8f7e977dc0289a6c2397bba465f5f698",
+        "e2f1b6c6d272ffb83220296537a21138",
+        "34c78fc44db0913f947caffc9f429d91",
+        "ea3f046c3c0f6e05501a7f263ee5022d",
+        "14b41d2ef9e560ea8b25e0006a7c76e8",
+        "7e37091996559b0a702875ca2ae54437",
+        "c1a47c31b8abb89abebe41e939eb85cd",
+        "f9907632f7163b0a71bf837cf02116d8",
+        "33eba62d45db94a51d9315e2e734c862",
+        "9d618799bdb989c172f2a67543d0d59b",
+        "61c678875c857ff6d466c2edfe4f93b1",
+        "b7ec32a6d494e5c12eadd65560439a4f",
+        "57d88cdb19b94437e367c25307f6a493",
+        "6e407c15259a8a9474c7aaa5c1b0c325",
+        "956dcbe72ad5518e3f4760839c2f1917",
+        "40a775afd81c4dcf8285e5351db0c4af",
+        "51473f1596549e944fcd666958647251",
+        "40a48f9743c4b3441f9f411145e460cc",
+        "b762f6108f67b7fcafb70c9478597bcc",
+        "b641f411f0791c456909a262993f12d4",
+        "306708a966104124bb6e9e434ccb1def",
+        "039256af52d619d5173da03ac3bc34d1",
+        "a378a8c57e2b73856e8a083efbe35561",
+        "c2b1e4a37215e6e3c45b7ba6a07bad0a",
+        "15806e38a0cadb7b7464efcb4acd65ad",
+        "7de478a670c224a8b0bd0713355fce99",
+        "ad32aac8e6403c4f7099f37ce0656328",
+        "19a501f3875477b595f2208e471e065a",
+        "36f61c8e59cd1567df6a50f2fc1e589f",
+        "5e6fd26dda2869cc919cec3ae4aeba33",
+        "a7a8531dc62036f518f5c0d419c74eab",
+        "11b45b4caca6b64050c8ab6b17435633",
+        "ae07441842af68a8b4d7206a4bcab833",
+        "6cdb813283c008827211d79f05305a98",
+        "f7093723cae5a6f828195c5b91f2dfff",
+        "4920da46107c7dc186129c2ffdbc7ebd",
+        "4223845045564a5b3bfab7afe7fb91ad",
+        "a938ec50ef0c11749ce1e7639316178b",
+        "233dbc4378b92a682f5abd28edbca07c",
+        "e888c25802e024f3aeb8536a8a42ace8",
+        "aa7b59c4690c6e9a9623e5dadfff1e94",
+        "0d7e360a2c6cd7595f5d68e682ea9a32",
+        "fc402387f034e1702386aaa82cb7ca0f",
+        "9ec5f6ccb2e3f4c561e9bd35553773cb",
+        "4531b9a4698e04f1dfcb8b325e112e69",
+        "59069679eece4850ef0766b9592da657",
+        "0d8536a5bb1b1afadc565ccc4dcb6476",
+        "e0677bec49cd6ba44f68b9fc02262c7d",
+        "6eadeabe09175bf8174d8251ddb1ddd3",
+        "004d3d532160ca12f3f769247adbe053",
+        "a42da77a13c238bb0a64a00a9b7324df",
+        "ddee2036b36ce0a25d53b4ea2cbc156e",
+        "2814e2234937197b27e10c039e040a42",
+        "d210d2f890ff463b3c20d6aed7c5a036",
+        "4187d8687b1a702fbbd67eb1c29249fd",
+        "644f64f44ea7b0799bb5e8105560a0d9",
+        "af7e96bf63be1138446881f89d9ba237",
+        "8609c7b043855aa5af2f8d93b1d16980",
+        "a3f8af47aa7d9773a7beaade7dad4289",
+        "5dccd98566e662db973bea8c5b7e1508",
+        "530d06dddd0e4fd43d7938740fcd1133",
+        "2721e594b1920c408e4918ec90ced79d",
+        "0a8588ff20415681fce1f7d6f8d7cb59",
+        "4a8e9749db54bea860bf043e43204069",
+        "de753f6237ac3ee7a334dfdcff32a6f3",
+        "db62993007d76e9b6042b2e7150ecd6f",
+        "39a2fc2eafffafd31d2363a72438825b",
+        "1c310e2f486e5fc15e564d2789135a25",
+        "1e157e100e57ca558d8e11c6d562e989",
+        "efab64a02161301f6141a5747000d0ae",
+        "2252208ada1d587ccf82051e09d04fce",
+        "b5c9b5edc7463c53fc3cbe815464d45b",
+        "fbb80c79aad5a33defd23c128ba06d67",
+        "eb0fbec5f72a33a9b48cc4a892f30f67",
+        "0dd6bcde73b5565ac42ac5d18a0ad1de",
+        "0b9073f314a0054e7dac4250eb205a36",
+        "1881d74963a1a673681d9b57d6c7dca0",
+        "f1e4f2a8229382e810b80d42593e5ee9",
+        "ad0983736ce2ec47999cf72033b70a41",
+        "69c279510b74c892fb2bdfdaec4128f5",
+        "8459e1e78f87a75acac7a30b27dcd672",
+        "74c8a48287dcd49259bee6fa3184d3e3",
+        "e5e649ee9180f5da32b399febd6cab2c",
+        "498cfbbf2a0618d3f1e283a80cf98ced",
+        "36fcc07a3114cf0d29e424570c5dfcd9",
+        "894be0c934c81169f2f77f31a8902e88",
+        "1cb8ee5a10ee6ba3d1cc32ea69220216",
+        "c38dcbb75d8bb49d9df8ca8ae76eb5fc",
+        "5994ef563406384c34f533a55f912b21",
+        "8e2f02fd7f2d68e652bd19e437b46031",
+        "e5cb5ac2da4cb0465538542dce132f50",
+        "69a3aed4b2ace775c04e23f4b9ac479c",
+        "df901cfccb553f4d19df907f05ae7cab",
+        "a207633639f998613dd9a76f51198761",
+        "e3d3164db152084afe815b829374ec9b",
+        "c9425ec8c3621c9c51234467213dfb5c",
+        "771ed7b61f2d6aad9cb2982b3e3f09fa",
+        "2c845681456a7d3d02bfe592a8aa23e6",
+        "f303c4bddf4493de80822c6d0a1a5834",
+        "97e46ccc0a1cd3502b1b8b72a1aa5782",
+        "2135ac994ea4cea31c117165bec3d2aa",
+        "a151e5af414ddaf6e9b86a3ff6529c7a",
+        "8f941815e39aa3577ebd7d76778d3425",
+        "96a290077fa18c4c419d332cf1142116"
+      ],
       "files_count": 0,
       "dirs_count": 0,
       "size_count": 0,
@@ -130,6 +785,525 @@
       "directory_content_fingerprint": null,
       "directory_structure_fingerprint": null,
       "halo1": "000018fba23a49e4cd40718d1297be719e6564a4",
+      "snippets": [
+        "01a2860620f9d3de7667328e4d61288f",
+        "99e8e10a0fa6de04d5d7e4f83b283fbc",
+        "59e4fdf4950916d88968929855948c8c",
+        "2489cffbec3ec22af36815a94e8fc09a",
+        "bcc6ac92b6fbe95038a0ca30cd69c9c0",
+        "2c5cecd02aa7c292ad130036e09ab3a2",
+        "5a3e3a54b3287c30ff2b0edf09e37727",
+        "e349f5941dfd2e19f5af575cc73fcb02",
+        "458b398e4e13a1bf70d3aa8ab0c37220",
+        "43291561bfcd821783f66050032db585",
+        "78975320b1444f8822e714bc676e1bc9",
+        "62d340117e72bf1c54ea3b4e9c486bbe",
+        "366172fd6b3875ba610bae824f39ebbe",
+        "d4e73bf93e666f235e0c0ae1ba25ee83",
+        "9c8a3f4fb17c904d9c3bd1e239119381",
+        "9d9e03abf895e09d211107c29f37a863",
+        "827f72adf8f2a1fd9757448a41863c7f",
+        "3053650f19c49eedd967d501b1dfbc02",
+        "23688a21f024afc08281317d63000e0f",
+        "d1827f749e281592dfeab92b8b1c6c25",
+        "52e65b07cde98a069f9cd3cdb45960da",
+        "03dd31b644d480d40c0ddf25e591c0ea",
+        "6461daf9572b6908b8019e781675c4f9",
+        "c93cd5efd1f6b025c73e481455feb330",
+        "fe0839b944c2dd8c33fc4aff6100dcda",
+        "a05e541734f881e31f124c05949ad6b3",
+        "f5d8d1264d43927c70fcd9ac91214cae",
+        "fae0180f7b7f620aabfeedc442d30261",
+        "6dd95a8b98b64bf706fbd3cf95bbdfb1",
+        "8d3c58b42a3e5c216cb4640d70945865",
+        "2216a8cf7cb26cd92d965441ce562902",
+        "f00ae825078698286896bee28d854cb7",
+        "45a2fbf1d8de67c42a71dfae66a2ee7c",
+        "b71fd14ea41e7b8595d7fe3db615c089",
+        "5bc67151f828ab63913b4ad8f0be154f",
+        "b343d554a5d7069a7ddf17e77d41e9c3",
+        "bf4b3fe809d87ce1ec5a22403b0af143",
+        "40afe3959c68cb3d4c9f43d5032a8515",
+        "9ab579429d8ab058b7edc0da6fe18a41",
+        "493292ebed2ad57bffd9e0a020aa2f9f",
+        "9cf4889191beed3a8d14b72a7b7f22d8",
+        "0770ceff57024b4b76ca023d540a3f28",
+        "cc4194ad0abfa995fca701eebc99d72d",
+        "e8f6d3b7e139354598c33f4931167200",
+        "5b82420c0858ab1c4812f09967c17d60",
+        "ee85d3b3e52f0c1b4bda0dfeefee97a4",
+        "e94d1fa52c8e0b7c4890a9166bec0e6a",
+        "d575b1d868603ad261d7020c9cd964ba",
+        "afa66239b82919bbeef59ec36ba5a078",
+        "0cbf3797468c4b615e43da650730c1bb",
+        "e11bf3941b1261e7edebb508379cd144",
+        "e9071b93f02503b86a04547f0d7d6849",
+        "9b882ecba76e186e9a9f4f1417b41bc7",
+        "c3dd611a539619379339162600fd2488",
+        "00d98474d538de1663ea922ecff30c44",
+        "5911c8642da57a1935d2479bf1329b7f",
+        "49eb173d6d7466aca2d5d6b8cc008a71",
+        "da54d9370f12af2974942c5a02081a09",
+        "74e9444882983281fa26be9c88025f22",
+        "e8ac2f3fc4b3dbc24da8fd4ecdbc9242",
+        "6157ef912c66d8fb035cc624d7d3d9b9",
+        "b80df1f45062e861c2a2621a48bdda85",
+        "2c503b2c548c7ef33b574561b163e301",
+        "badf7f3efae4e8d51e4c03ec4a476b07",
+        "a531611ae7094e0d9429b9098cd0b8ec",
+        "ffe9b5644e3681400e97583deb123138",
+        "308b4774505884b343508e5c3b25e3b1",
+        "3c9c24d2774e607ce43d6a115107879b",
+        "596101b5c4ee9c06a753d2bcb0a91cb4",
+        "445e46dfd7a1badd0442b928dfa64af3",
+        "6c138599fb322fe4e6be518e6d097e15",
+        "a8cd8ea6b4322f666e1069b7583311b9",
+        "2409071a66687dbc9ab2f31dba00ea97",
+        "fb2e97a55ae38b136bd6a991522fc0de",
+        "ea8749365cc70da43724df8517582f48",
+        "7f661fbdeabc4d6445d594bb919df783",
+        "f4bd005b8771d2809ddef753c110114c",
+        "fee5430e248c9639837a7d5ece8cf737",
+        "4db0c6a25f9ae90bdfd5675321d84108",
+        "06b6e987fe9bae07c24574965043d488",
+        "3468751d9edae5a24acf6bd9fdb7d095",
+        "da380a61a4f67f6611c618961ba7d7fe",
+        "f3c6f6bb053e6e5ab5a9c8adafa317f8",
+        "2c8c57c09eadbf5a20b2addece359839",
+        "c3d6625043f4af47f20bc10bbe6e5b24",
+        "54a29b5ad7a12ef89f6f57a7b25e4e5f",
+        "3ad8017c49941e5949becbf38de3e869",
+        "f3e8e4b8bc2221a5ff2b62bb7af65bec",
+        "865044a6362bbe39591eea8a6fc2c8d6",
+        "64d4d452abe519c3558debcc7e294b5b",
+        "cbe12d0679f753f18c83f46a7ee7aef8",
+        "aa33a80291265999498300c0e486e6b0",
+        "b1b7dd3de6917006796c0191bb8e52a3",
+        "22f97b00c6773f13e4a452658b976201",
+        "5c44256bef2a0c5b096c3a13f62674cb",
+        "c242f0a562d5ca6ba1a197e52c2ab886",
+        "c4cef64f59b2f61b658861e9a2921668",
+        "4d7574e6eac62f7fcf1bfcbe6365480c",
+        "8353c8b7573744d58a7d83fe19e01973",
+        "76b2ac2809d12b99db5130a3f8fc9285",
+        "6558183ce2ab1a8a08f4a1b6be76731a",
+        "6a6eeab6452acabe4255ac5a94101fab",
+        "e8623ae51acf49438330ab31a0727c00",
+        "5e74e0e42c531da4859f2bd178806add",
+        "1c799de762da2e80ad617012c041b990",
+        "5922200a3d5d225ecf198bbe03ab0b88",
+        "43c4aa4949c5f5f6b2d2446878fa9425",
+        "615a178025d69ec6a7fc0100a717630b",
+        "788e4b9bac09971dad0ef4a28cd715e8",
+        "b58ff2f5ad535edd9884ecc4569a42ab",
+        "0c89e27034005ff9e9f95b93726c1478",
+        "ca8fac2cdd5ad01a22d01b182a9e2e1a",
+        "337fa7e7f1b388e0a10003afb6414f78",
+        "91cbe083188909aa144c36bdf9b67a6f",
+        "95020ff8c4e8ab71524c653d033e89c9",
+        "ef50426c2ba54173eac3e21bd5f7d658",
+        "3b9b2f0970888933b7a1d22cd3250d14",
+        "57b328ff36961317ae62e6689febe248",
+        "6a268c6e8788f7a69ffa69e28e79d721",
+        "158763405e69ce16667aaa05c0faea5f",
+        "0a1738ec6db5199c8cf6726ca0cd3a96",
+        "666acedc72c8713ed8ccf575be2c0b9c",
+        "ef4146246df5dd7c98bc54ab3c10c3bb",
+        "05c89a99e54f4e792fc3abe1176a6e9f",
+        "2858172d4f048b4f509221f40cb6e51b",
+        "e9ffdd6870b405a12430ed3c74d3082b",
+        "aec0709385dd19526ad0b1cde7f481cb",
+        "95c4939ea09aa22cbd8adb8cd5bb26c6",
+        "a0326a883fc90396e402855299952344",
+        "9f55ae5b3bdae70d943e14b465251507",
+        "7e4816b8a54dbbc76647dac40b217c89",
+        "63ef9bc21904404f0b885ed3ed280d1d",
+        "a810536cd32b0d8fa06890fa17c91eea",
+        "1aeee1a8cca06f5b4af0930b09c6c10f",
+        "41a0533f95ab3175c84bad3c2ca929af",
+        "d20de628487bb2b5c525dde7248aaa0a",
+        "8c8c0c0ead59eee89478698fcb688945",
+        "35031475a8689d893f01ed400f3ecbe6",
+        "4be86d4e557a24af9706e301094d257b",
+        "46f8dafc6d24f0cf34dbe7a7c297449c",
+        "558788e719e3fa4d69e9c108aaf22bc5",
+        "0018e3648533c8958955559b299eb385",
+        "e70b3ad2d54a0a4add4a7b60869bdf02",
+        "f9132439ac130a5997510ed6f96e7b2d",
+        "9cebf010f5ea40e9e1459801de661f52",
+        "43e729b0337fe1efbd124c32d2da09c1",
+        "0349faac725c2503dae0a74c168b7bf1",
+        "ef9eb02563568a652fdecb3b96750b2a",
+        "1601874afe1485b62549409fdddddd85",
+        "06e8ac50fe3e5228dde99a1998584d24",
+        "acef4c3172e2ed0da869d12b0a504e19",
+        "fe84b76b5b01359343fd0aeae336d329",
+        "873d734fe2f3e738b72c71742449ec44",
+        "31e609d08f4ada21d603dec99af8f0ae",
+        "aec12cabe92117940783b7f3f645b848",
+        "76082bdfe8ddd9a1c7878aee50dbaafd",
+        "8c94ae763ba43de2f4902b51f6c3bb17",
+        "f456f627d6aed75ff71c78e66bb29b6f",
+        "0b5600126debfaf84e4ad6d069e9dc93",
+        "c9cffdc095c1a739565fbc0b1128c6b2",
+        "d4c4766b680e7fc5ef67292e569a175b",
+        "638f66e76667cc4d692cd28b46cb28e9",
+        "6de3d2d692a9ce1ed29913696ad4cf8b",
+        "1d24fe9ff69a393dbd530f000d96a089",
+        "656c76345fdc1f5e509e410392ce9356",
+        "ddbda6bbbf70a025274ce239ad04776a",
+        "b9665796363290a24ce122b342a5cad8",
+        "1a53a4094b337198591a75318b915656",
+        "f113e2433983beb83242bdbc704f1602",
+        "e16749e75a85158ecfb1b736e9bf3462",
+        "8459d8b145791a2c2ca5e05f91d5e039",
+        "a30767ab78b73c5e9181c32ed9dea72f",
+        "980190e94ad4688196ed39591b5d62d8",
+        "8f79921a2c49bc3fc4bfc3c470e540ad",
+        "92b42aa7c1a2013085a663cbf819585e",
+        "371b6e4341b7615b8faa769a50e3a40f",
+        "6b4cf3bcf6abd78b308e31a499837451",
+        "f3f1b4a6fcb0c3de1750f4eca2d582b5",
+        "634719e71076181b5bc56866aba73ae7",
+        "1a2ace5196a5949f8df5c68a299905f7",
+        "45dae8a5b8cc0c826af9c89dcb217f36",
+        "ca8c20edb356de4091f40e5dbeb1fa6a",
+        "0fbb213cae1cca3dc048aecbe7c012d9",
+        "1e63189230b93f4d92db32eea83cee4b",
+        "f874bbeeb5b3a6c0bab50330d94b7dc5",
+        "fd63842de4e1dec031359f4424475821",
+        "64290e23f6dc03c0c8ca714993355a46",
+        "8edc96003636f938c7ff1f793525c39d",
+        "c5b8e8d179069ffee850754225a01660",
+        "e176a3839f14dbdb1eae5842305a7c73",
+        "73c9a34c78d1b45edc7749402cbefc1d",
+        "4721dc0b2de8bbb767cdd20079ff6417",
+        "01f38123e76d66ef25fe126284ca902d",
+        "cf4ba3de2f35f024e4cafca9fe683f97",
+        "74a324ff5f8d405216324d62c17452b5",
+        "7165c9678ba2194caaa29fde08c59194",
+        "464f563a5a0632a6f0c623bc92dd9458",
+        "980bb815cf0b929af366f3052301299b",
+        "b0a500eb1e0c2274196a671076dbb4bd",
+        "134726fc1a6ca8ca5ce734f3151179d9",
+        "e0752fc8f1bf25ab477790685bf35d47",
+        "fe2bd079fba76a3593ec4888930d96d5",
+        "ef8979a9589fd03109e2c9b346c284dc",
+        "0e2923676803ba3bf3dc3afee03d0739",
+        "1bf6cb5cd2cf6c099150007e21b236d8",
+        "983412e6e6e9809501f05c7af13c69d7",
+        "f678da44721c3adc1db87c5871e882bb",
+        "789f0c05c43d34bc9a98afd9026cb5b8",
+        "13d3143533edfccd8edf7e1a7890a0fc",
+        "66c0bcbcce07e5882915289993a9b99f",
+        "8f7e977dc0289a6c2397bba465f5f698",
+        "e2f1b6c6d272ffb83220296537a21138",
+        "34c78fc44db0913f947caffc9f429d91",
+        "ea3f046c3c0f6e05501a7f263ee5022d",
+        "14b41d2ef9e560ea8b25e0006a7c76e8",
+        "7e37091996559b0a702875ca2ae54437",
+        "c1a47c31b8abb89abebe41e939eb85cd",
+        "f9907632f7163b0a71bf837cf02116d8",
+        "33eba62d45db94a51d9315e2e734c862",
+        "9d618799bdb989c172f2a67543d0d59b",
+        "61c678875c857ff6d466c2edfe4f93b1",
+        "b7ec32a6d494e5c12eadd65560439a4f",
+        "57d88cdb19b94437e367c25307f6a493",
+        "6e407c15259a8a9474c7aaa5c1b0c325",
+        "956dcbe72ad5518e3f4760839c2f1917",
+        "40a775afd81c4dcf8285e5351db0c4af",
+        "51473f1596549e944fcd666958647251",
+        "40a48f9743c4b3441f9f411145e460cc",
+        "b762f6108f67b7fcafb70c9478597bcc",
+        "b641f411f0791c456909a262993f12d4",
+        "306708a966104124bb6e9e434ccb1def",
+        "039256af52d619d5173da03ac3bc34d1",
+        "a378a8c57e2b73856e8a083efbe35561",
+        "c2b1e4a37215e6e3c45b7ba6a07bad0a",
+        "15806e38a0cadb7b7464efcb4acd65ad",
+        "7de478a670c224a8b0bd0713355fce99",
+        "ad32aac8e6403c4f7099f37ce0656328",
+        "19a501f3875477b595f2208e471e065a",
+        "36f61c8e59cd1567df6a50f2fc1e589f",
+        "5e6fd26dda2869cc919cec3ae4aeba33",
+        "a7a8531dc62036f518f5c0d419c74eab",
+        "11b45b4caca6b64050c8ab6b17435633",
+        "ae07441842af68a8b4d7206a4bcab833",
+        "6cdb813283c008827211d79f05305a98",
+        "f7093723cae5a6f828195c5b91f2dfff",
+        "4920da46107c7dc186129c2ffdbc7ebd",
+        "4223845045564a5b3bfab7afe7fb91ad",
+        "a938ec50ef0c11749ce1e7639316178b",
+        "233dbc4378b92a682f5abd28edbca07c",
+        "e888c25802e024f3aeb8536a8a42ace8",
+        "aa7b59c4690c6e9a9623e5dadfff1e94",
+        "0d7e360a2c6cd7595f5d68e682ea9a32",
+        "fc402387f034e1702386aaa82cb7ca0f",
+        "9ec5f6ccb2e3f4c561e9bd35553773cb",
+        "4531b9a4698e04f1dfcb8b325e112e69",
+        "59069679eece4850ef0766b9592da657",
+        "0d8536a5bb1b1afadc565ccc4dcb6476",
+        "e0677bec49cd6ba44f68b9fc02262c7d",
+        "6eadeabe09175bf8174d8251ddb1ddd3",
+        "004d3d532160ca12f3f769247adbe053",
+        "a42da77a13c238bb0a64a00a9b7324df",
+        "ddee2036b36ce0a25d53b4ea2cbc156e",
+        "2814e2234937197b27e10c039e040a42",
+        "d210d2f890ff463b3c20d6aed7c5a036",
+        "4187d8687b1a702fbbd67eb1c29249fd",
+        "644f64f44ea7b0799bb5e8105560a0d9",
+        "af7e96bf63be1138446881f89d9ba237",
+        "8609c7b043855aa5af2f8d93b1d16980",
+        "a3f8af47aa7d9773a7beaade7dad4289",
+        "5dccd98566e662db973bea8c5b7e1508",
+        "530d06dddd0e4fd43d7938740fcd1133",
+        "2721e594b1920c408e4918ec90ced79d",
+        "0a8588ff20415681fce1f7d6f8d7cb59",
+        "4a8e9749db54bea860bf043e43204069",
+        "de753f6237ac3ee7a334dfdcff32a6f3",
+        "db62993007d76e9b6042b2e7150ecd6f",
+        "39a2fc2eafffafd31d2363a72438825b",
+        "1c310e2f486e5fc15e564d2789135a25",
+        "1e157e100e57ca558d8e11c6d562e989",
+        "efab64a02161301f6141a5747000d0ae",
+        "2252208ada1d587ccf82051e09d04fce",
+        "b5c9b5edc7463c53fc3cbe815464d45b",
+        "fbb80c79aad5a33defd23c128ba06d67",
+        "eb0fbec5f72a33a9b48cc4a892f30f67",
+        "0dd6bcde73b5565ac42ac5d18a0ad1de",
+        "0b9073f314a0054e7dac4250eb205a36",
+        "1881d74963a1a673681d9b57d6c7dca0",
+        "f1e4f2a8229382e810b80d42593e5ee9",
+        "ad0983736ce2ec47999cf72033b70a41",
+        "69c279510b74c892fb2bdfdaec4128f5",
+        "8459e1e78f87a75acac7a30b27dcd672",
+        "74c8a48287dcd49259bee6fa3184d3e3",
+        "e5e649ee9180f5da32b399febd6cab2c",
+        "498cfbbf2a0618d3f1e283a80cf98ced",
+        "36fcc07a3114cf0d29e424570c5dfcd9",
+        "894be0c934c81169f2f77f31a8902e88",
+        "1cb8ee5a10ee6ba3d1cc32ea69220216",
+        "c38dcbb75d8bb49d9df8ca8ae76eb5fc",
+        "5994ef563406384c34f533a55f912b21",
+        "8e2f02fd7f2d68e652bd19e437b46031",
+        "e5cb5ac2da4cb0465538542dce132f50",
+        "69a3aed4b2ace775c04e23f4b9ac479c",
+        "df901cfccb553f4d19df907f05ae7cab",
+        "a207633639f998613dd9a76f51198761",
+        "e3d3164db152084afe815b829374ec9b",
+        "c9425ec8c3621c9c51234467213dfb5c",
+        "771ed7b61f2d6aad9cb2982b3e3f09fa",
+        "2c845681456a7d3d02bfe592a8aa23e6",
+        "f303c4bddf4493de80822c6d0a1a5834",
+        "97e46ccc0a1cd3502b1b8b72a1aa5782",
+        "2135ac994ea4cea31c117165bec3d2aa",
+        "a151e5af414ddaf6e9b86a3ff6529c7a",
+        "8f941815e39aa3577ebd7d76778d3425",
+        "96a290077fa18c4c419d332cf1142116"
+      ],
+      "files_count": 0,
+      "dirs_count": 0,
+      "size_count": 0,
+      "scan_errors": []
+    },
+    {
+      "path": "fingerprinting/snippets",
+      "type": "directory",
+      "name": "snippets",
+      "base_name": "snippets",
+      "extension": "",
+      "size": 0,
+      "sha1": null,
+      "md5": null,
+      "sha256": null,
+      "mime_type": null,
+      "file_type": null,
+      "programming_language": null,
+      "is_binary": false,
+      "is_text": false,
+      "is_archive": false,
+      "is_media": false,
+      "is_source": false,
+      "is_script": false,
+      "directory_content_fingerprint": "00000002640808248840ed000c63108308c324b9",
+      "directory_structure_fingerprint": "00000002631a040860400c086a3410105d04748b",
+      "halo1": null,
+      "snippets": null,
+      "files_count": 2,
+      "dirs_count": 0,
+      "size_count": 13223,
+      "scan_errors": []
+    },
+    {
+      "path": "fingerprinting/snippets/adler32.c",
+      "type": "file",
+      "name": "adler32.c",
+      "base_name": "adler32",
+      "extension": ".c",
+      "size": 4968,
+      "sha1": "0cff4808476ce0b5f6f0ebbc69ee2ab2a0eebe43",
+      "md5": "ae3bbb54820e1d49fb90cbba222e973f",
+      "sha256": "341d49ae2703037d2d10c8486f1a1ca3b65e0f10cc9e5fead6bfbbc0b34564ba",
+      "mime_type": "text/x-c",
+      "file_type": "C source, ASCII text",
+      "programming_language": "C",
+      "is_binary": false,
+      "is_text": true,
+      "is_archive": false,
+      "is_media": false,
+      "is_source": true,
+      "is_script": false,
+      "directory_content_fingerprint": null,
+      "directory_structure_fingerprint": null,
+      "halo1": "0000026ab55c771b9246aff06cf3497b91c8c9ef",
+      "snippets": [
+        "bbb63027903332f0c41b7b26b9bfb50b",
+        "54cf1197bf1109b4ce2a3455c1c48285",
+        "6d4c7e4377089d1ddcc8c90132ac9730",
+        "1e579e94829907c3d2401db94f9b6df8",
+        "ec89d3e7ac59e858d97ce1ad730f7547",
+        "f3c31ef3249345c3e44c5aea28414dff",
+        "5f1ba9111c115dc88bdc1ceddce789ef",
+        "2f12c505c1e1ec3fa184877c8f1cb838",
+        "a7858f3e1c246064223868c9858f8317",
+        "b7c21f7ebb4abec9169eb533154a5097",
+        "f5139ce5161976ff729a953b8780133d",
+        "c1975628430b6fda66b638481403cca5",
+        "83a4d8bea3052c3bfde90ed3aaba79ac",
+        "3c4df460f6a4817daf8638f3b2009cb9",
+        "3290d45ca11c75f84d72ccfdfcca9515",
+        "bd9b873dd011bb94ba21b449e0886bca",
+        "c51b042fb4aa9dbee729f120d1caa9ad",
+        "3aaa73fb0dbbd0443f7f77d96322b522",
+        "80a509a0b8d81b8167e4bce3bdaf83bf",
+        "4a79d250f6c4aa117bf47244fc0222be",
+        "e49dc8a3fecfe4bb2ef237bb56e85dc8",
+        "e2a16b88325f9b5717b578c9f5207e07",
+        "e28f3e5020594773551a29c39ee4c286",
+        "ae9095ef88ac8288c7514b771ed5ddc8",
+        "01e7fd588d9cd71e30935c597827ce0a",
+        "a54443952d1ce6e731d8980d7b0c714f",
+        "c244ee379eacca3f8799bb94890bd41c",
+        "67913cbdbf8802d7c19a442132ada51b",
+        "b9e5ed3d9a79a4d71d04a6d59589e9c8",
+        "7a10694fe6dadc4f0ff002119d29eac9",
+        "e0fc19761f570e9657324d21b7150a3b",
+        "498885acf844eda1f65af9e746deaff7",
+        "16e774a453769c012ca1e7f3685b4111",
+        "eeb97a9c94bb5c7a8cac39fdea7e7ec2",
+        "5faefb98693a882708b497c90885e84d",
+        "5ca14da77615896d30deb89635c39a53",
+        "628c96760664a4b74d689a398b496e03"
+      ],
+      "files_count": 0,
+      "dirs_count": 0,
+      "size_count": 0,
+      "scan_errors": []
+    },
+    {
+      "path": "fingerprinting/snippets/zutil.c",
+      "type": "file",
+      "name": "zutil.c",
+      "base_name": "zutil",
+      "extension": ".c",
+      "size": 8255,
+      "sha1": "37290d53566bcddcb4c8c9a8e40af22c089ea672",
+      "md5": "552716e56a3d76087d926d0c422581b0",
+      "sha256": "540f23856b35556e6472cf965865bcd3e6423de4f584608d7bde1e30e8315102",
+      "mime_type": "text/x-c",
+      "file_type": "C source, ASCII text",
+      "programming_language": "C",
+      "is_binary": false,
+      "is_text": true,
+      "is_archive": false,
+      "is_media": false,
+      "is_source": true,
+      "is_script": false,
+      "directory_content_fingerprint": null,
+      "directory_structure_fingerprint": null,
+      "halo1": "0000045e529c45331780fee281b348339f79306d",
+      "snippets": [
+        "7ed5cafd44fea6cb1e84f519c5a995f3",
+        "9f02df2c2c765ed4b9a60af7f5dc6825",
+        "e643cdd412d46ba058e2be3105b5503d",
+        "090dc3f8751b3c79923d0f2430e1821d",
+        "7b3294908e4bbd6390106fe6d920268f",
+        "4bc9c74165dfd635fee5c3164f2407d8",
+        "b0efbe1869beb1a203a95b18d47ef1e6",
+        "34af742c2a696d0a6bd23e5c96143aa4",
+        "855b779d81fe76ace1afd9cffaaa03b5",
+        "2381aeb9b5cd04dc4f52a1d5e06797e6",
+        "ad117fdd56136e90282025198a1ed5f5",
+        "ce064a8d30610687babebfc3c74f2215",
+        "fe12a3cb12a41359a3f7ea23a8297fca",
+        "1a2f0e65b2d77fb79ed95749083e0356",
+        "945e4a298b851a0fa86853d1fd234d22",
+        "e4cda232353cd78069d7d6a1d11ccfc3",
+        "ab64048739c06b77fbf69f0622a824a0",
+        "fb91eeb4a8b9895e051ec98b649303ff",
+        "a07afc7552c7af2f861a114c19718c12",
+        "c7f68becaa86ac416555dcc13de3f7b6",
+        "7be2af5b15ac4debe2c9233fe3bdf5e2",
+        "e4085cc7580f1f933f524c1742dffc7a",
+        "1bd5c87d7fb5558b1fcd10ef2e0432f8",
+        "fd6a83abd283b4e5ac268f21a2147453",
+        "5a4d0897b9711c02f865d97034338979",
+        "f6bcbd48d1e7ffbb78164cd2660ca0cc",
+        "83ac23f7ee69540adfc64dba65045012",
+        "435d4e0805e1015f58bedb643ce1ad3a",
+        "53b627e84a0fde8342a7c9a5cae51335",
+        "9b34c5bb0ac43bc9f131315c8fa028c3",
+        "8456aa69be29d00cf9dfeb7ae9ccfcdf",
+        "e79c82b208711f5f49f421718ef172c6",
+        "7ac46a9dbd8c68652d347960cc3f640a",
+        "2a6e0b066785d0e1feee19a60d4685f6",
+        "e4c4d99fc98a4cc09f28a291a5212093",
+        "1d64eede99cb6abe784678938f64a12c",
+        "f517d7a22774aeec45c109920b255ae6",
+        "1cdf29098d96d12c8c59acf2304ab1fe",
+        "d2b74ca2087e6e527701c663eefd29bc",
+        "a14974b34a547b1a52af07f590f641d1",
+        "03a6666b52bba552442e73adfbcfccb5",
+        "4cca0e8f81f8fe812eb7861495020ff8",
+        "d9db0fb7358173072bc319707d3e8a33",
+        "2310e0cb39cc317dbaf0bfcca72f0aca",
+        "b6a661bd80f1140a07c511a9ffffb492",
+        "0399fade7fca27b568404b073b2eca1c",
+        "52cfc5757c1f45567ca90a2958a64e22",
+        "f76edad8fa6dc73e843ab228a46ff4aa",
+        "a0877ef600c0b7da27e226e7815bd96d",
+        "dd94cb42ea765f5a3dc74c7116b8112f",
+        "6f62a6a03341268dabc94c8265aab4a3",
+        "d2d90d0a0b8841fdde1e9342ae34e612",
+        "6e8a953486842b17faabbe58aed2d28b",
+        "5a0e16ed296adc58912f12deb8e43cca",
+        "5a04295313ead9f4b5e43a19e57209c9",
+        "ac3d0c06b8855189986c2d4a11be7180",
+        "9f61d026adad0c3ac52ee1db8ebb1761",
+        "163c3e2d2a76b4cffbcec4e7e41340b0",
+        "eb22bfcb167a605f63f1c0e84b4a243c",
+        "c8a523c143b8fecfaecb8788d94f896f",
+        "fd12f7d058933f7def30e7c0575b2512",
+        "cf6dd6d8d3a9fe684606d10e63b3755d",
+        "e989d1b2ef98bfa40bbccc486ed5e965",
+        "498885acf844eda1f65af9e746deaff7",
+        "16e774a453769c012ca1e7f3685b4111",
+        "8963c86e132ae1710491ba552e17d322",
+        "83ee9b95f621713d817fc5ef847a3129",
+        "0afbd0d74b172a8dd08a1b17002400b1",
+        "498901c2be17e44805910ac978c854b5",
+        "58931feaad814e884e3e95bb89bdbf5c",
+        "4a50fed3cb3b2e08962fce9d37ec1faa",
+        "b24f2d699d5c3643f5d30427c4fa9223",
+        "8a576adf5638a477ec06940132a1f583",
+        "b4f309a79529c0103fa356f3552e49bf",
+        "ea41586642fc658861578736941b1786",
+        "b2a8540ad8659f91150764f4bad6bfae",
+        "7a27d2e62d8aad623cfc4f3ceb831ba4",
+        "3aaaa507050eae336d7e870b043cb18c",
+        "603e64a10d74410e4673bf4bddc3a100",
+        "75ad6a60f72125a9e9f0b8bf129731e6"
+      ],
       "files_count": 0,
       "dirs_count": 0,
       "size_count": 0,
@@ -157,6 +1331,33 @@
       "directory_content_fingerprint": null,
       "directory_structure_fingerprint": null,
       "halo1": "0000026832a97761e52e4793863f3d20cc70611d",
+      "snippets": [
+        "4df7c9871fae95a28489bce2e7f65eb7",
+        "96ed16d9721c9119ec1932084a7e6041",
+        "03cfabf539255d2e8faede5fefa6348f",
+        "66e408310bd48c46e0e7be089fd4e23a",
+        "03ab9afc8c14f938fd58855e4f605c3e",
+        "3946e7d9edc9fc467d9a0b57a33b74ce",
+        "2ab1dc359aa33c34331804d81b7e2956",
+        "e62c1c31fb792743023424713a807438",
+        "701be0f6c9746eb8fa18b6ad609388ee",
+        "170c92a5a97980f5f8f7ee63714f68b8",
+        "ecaae4a84c7debe723667fc31405bdda",
+        "9baa8616e826a93312953b25e3db4386",
+        "61f23bcfafbf43b3afe9d96e6db1d8a2",
+        "57c20676e821a817fb23b1fdad8d7ab2",
+        "87e30dc09132f8edea3b354898737060",
+        "b82f24ba3a58e7611f63bbe121619f0d",
+        "d99b48a73272d69a1c47b90fb6eeb33b",
+        "298609a545524f795ac0ac80d2963157",
+        "b4700b2e44f6607dc3ed2ce00865c8e8",
+        "5eebfbd388edb7e79e098571dbc13498",
+        "f7ebbf7161adcea982ed79fb7d910f81",
+        "ff6ddf966284e9d953fa31c663535d3b",
+        "3c14253fec2cf574229d8e583771e37c",
+        "3de15862d251b05a3108a62efec014f2",
+        "88d619dc1c1e4b0856dcf914887f24a5"
+      ],
       "files_count": 0,
       "dirs_count": 0,
       "size_count": 0,
diff --git a/tests/testfiles/fingerprinting/hailstorm/adler32.c b/tests/testfiles/fingerprinting/snippets/adler32.c
similarity index 100%
rename from tests/testfiles/fingerprinting/hailstorm/adler32.c
rename to tests/testfiles/fingerprinting/snippets/adler32.c
diff --git a/tests/testfiles/fingerprinting/hailstorm/zutil.c b/tests/testfiles/fingerprinting/snippets/zutil.c
similarity index 100%
rename from tests/testfiles/fingerprinting/hailstorm/zutil.c
rename to tests/testfiles/fingerprinting/snippets/zutil.c

From 8001b85171f30badc8c3ee4914637b66a9df1fe4 Mon Sep 17 00:00:00 2001
From: Jono Yang <jyang@nexb.com>
Date: Tue, 29 Oct 2024 15:51:40 -0700
Subject: [PATCH 6/6] Update CHANGELOG.rst

Signed-off-by: Jono Yang <jyang@nexb.com>
---
 CHANGELOG.rst | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/CHANGELOG.rst b/CHANGELOG.rst
index c89a219..2a0f581 100644
--- a/CHANGELOG.rst
+++ b/CHANGELOG.rst
@@ -1,12 +1,16 @@
 Changelog
 =========
 
+vNext
+-----
+
+*2024-10-29* -- Collect snippet hashes in fingerprint plugin.
+
 v5.1.1
 ------
 
 *2024-08-07* -- Update link references of ownership from nexB to aboutcode-org.
 
-
 v5.1.0
 ------