Get rid of etags

Etags are meant for transient usage in browsers and are not meant for
any long term usage.
Fixes: #321

Signed-off-by: Hritik Vijay <hritikxx8@gmail.com>

Author: Hritik14

vulnerabilities/helpers.py

@@ -27,6 +27,7 @@
 from typing import List
 from typing import Optional
 from typing import Tuple
+from unittest.mock import MagicMock
 
 import requests
 import saneyaml
@@ -67,32 +68,8 @@ def fetch_yaml(url):
     return saneyaml.load(response.content)
 
 
-# FIXME: this is NOT how etags work .
-# We should instead send the proper HTTP header
-# https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/If-None-Match
-# and integrate this finely in the processing as this typically needs to use
-# streaming=True requests, and proper handling of the HTTP return code
-# In all cases this ends up being a single request, not a HEADD followed
-# by another real request
-def create_etag(data_src, url, etag_key):
-    """
-    Etags are like hashes of web responses. For a data source `data_src`,
-    we maintain (url, etag) mappings in the DB.  `create_etag`  creates
-    (`url`, etag) pair. If a (`url`, etag) already exists then the code
-    skips processing the response further to avoid duplicate work.
-
-    `etag_key` is the name of header which contains the etag for the url.
-    """
-    etag = requests.head(url).headers.get(etag_key)
-    if not etag:
-        return True
-
-    elif url in data_src.config.etags:
-        if data_src.config.etags[url] == etag:
-            return False
-
-    data_src.config.etags[url] = etag
-    return True
+# FIXME: Remove this entirely after complete importer-improver migration
+create_etag = MagicMock()
 
 
 def contains_alpha(string):

vulnerabilities/tests/test_helpers.py

@@ -20,43 +20,10 @@
 #  VulnerableCode is a free software tool from nexB Inc. and others.
 #  Visit https://github.com/nexB/vulnerablecode/ for support and download.
 
-import dataclasses
 from unittest import TestCase
 from unittest.mock import patch
 from unittest.mock import MagicMock
 
-from vulnerabilities.data_source import DataSource
-from vulnerabilities.helpers import create_etag
-
-
-@dataclasses.dataclass
-class DummyDataSourceConfiguration:
-    etags: dict
-
-
-class DummyDataSource(DataSource):
-    CONFIG_CLASS = DummyDataSourceConfiguration
-
 
 class TestHelpers(TestCase):
-    @classmethod
-    def setUpClass(cls):
-        data_source_cfg = {"etags": {}}
-        cls.data_source = DummyDataSource(config=data_source_cfg)
-
-    def test_create_etag(self):
-        assert self.data_source.config.etags == {}
-
-        mock_response = MagicMock()
-        mock_response.headers = {"ETag": "0x1234"}
-
-        with patch("vulnerabilities.helpers.requests.head", return_value=mock_response):
-            assert (
-                create_etag(data_src=self.data_source, url="https://example.org", etag_key="ETag")
-                is True
-            )
-            assert self.data_source.config.etags == {"https://example.org": "0x1234"}
-            assert (
-                create_etag(data_src=self.data_source, url="https://example.org", etag_key="ETag")
-                is False
-            )
+    ...