Merge branch 'main' into feat/revisit-vulns

3 files changed, 15 insertions, 8 deletions

diff --git a/sec_certs/config/settings-schema.json b/sec_certs/config/settings-schema.json
index c4871096..7e40a0ac 100644
--- a/sec_certs/config/settings-schema.json
+++ b/sec_certs/config/settings-schema.json
@@ -137,6 +137,9 @@
         "cc_maintenances_latest_snapshot": {
             "$ref": "#/definitions/settings_url_entry"
         },
+        "pp_latest_snapshot": {
+            "$ref": "#/definitions/settings_url_entry"
+        },
         "ignore_first_page": {
             "$ref": "#/definitions/settings_boolean_entry"
         },
@@ -170,6 +173,7 @@
         "cpe_n_max_matches",
         "cc_latest_snapshot",
         "cc_maintenances_latest_snapshot",
+        "pp_latest_snapshot",
         "ignore_first_page",
         "cert_threshold",
         "fips_latest_snapshot",
diff --git a/sec_certs/config/settings.yaml b/sec_certs/config/settings.yaml
index 2325955b..c6d54242 100644
--- a/sec_certs/config/settings.yaml
+++ b/sec_certs/config/settings.yaml
@@ -22,11 +22,14 @@ cpe_n_max_matches:
   description: Maximum number of candidate CPE items that may be related to given certificate, >0
   value: 100
 cc_latest_snapshot:
-  description: Url from where to fetch the latest snapshot of fully processed CC dataset
+  description: URL from where to fetch the latest snapshot of fully processed CC dataset
   value: https://seccerts.org/cc/dataset.json
 cc_maintenances_latest_snapshot:
-  description: Url from where to fetch the latest snapshot of CC maintenance updates
+  description: URL from where to fetch the latest snapshot of CC maintenance updates
   value: https://seccerts.org/cc/maintenance_updates.json
+pp_latest_snapshot:
+  description: URL from where to fetch the latest snapshot of the PP dataset
+  value: https://seccerts.org/static/pp.json
 ignore_first_page:
   description: During keyword search, first page usually contains addresses - ignore it.
   value: true
@@ -34,7 +37,7 @@ cert_threshold:
   description: Used with --higher-precision-results. Determines the amount of mismatched algorithms to be considered faulty.
   value: 5
 fips_latest_snapshot:
-  description: Url for the latest snapshot of FIPS dataset
+  description: URL for the latest snapshot of FIPS dataset
   value: https://seccerts.org/fips/dataset.json
 minimal_token_length:
   description: Minimal length of a string that will be considered as a token during keyword extraction in CVE matching
diff --git a/sec_certs/dataset/protection_profile.py b/sec_certs/dataset/protection_profile.py
index c71f98b5..58ea2044 100644
--- a/sec_certs/dataset/protection_profile.py
+++ b/sec_certs/dataset/protection_profile.py
@@ -3,9 +3,10 @@ import logging
 import tempfile
 from dataclasses import dataclass
 from pathlib import Path
-from typing import ClassVar, Dict, Optional, Tuple, Union
+from typing import Dict, Optional, Tuple, Union
 
 import sec_certs.utils.helpers as helpers
+from sec_certs.config.configuration import config
 from sec_certs.sample.protection_profile import ProtectionProfile
 
 logger = logging.getLogger(__name__)
@@ -13,8 +14,6 @@ logger = logging.getLogger(__name__)
 
 @dataclass
 class ProtectionProfileDataset:
-    static_dataset_url: ClassVar[str] = "https://ajanovsky.cz/pp_data_complete_processed.json"
-
     pps: Dict[Tuple[str, Optional[str]], ProtectionProfile]
 
     def __iter__(self):
@@ -48,12 +47,13 @@ class ProtectionProfileDataset:
 
     @classmethod
     def from_web(cls, store_dataset_path: Optional[Path] = None):
-        logger.info(f"Downloading static PP dataset from: {cls.static_dataset_url}")
+
+        logger.info(f"Downloading static PP dataset from: {config.pp_latest_snapshot}")
         if not store_dataset_path:
             tmp = tempfile.TemporaryDirectory()
             store_dataset_path = Path(tmp.name) / "pp_dataset.json"
 
-        helpers.download_file(cls.static_dataset_url, store_dataset_path)
+        helpers.download_file(config.pp_latest_snapshot, store_dataset_path)
         obj = cls.from_json(store_dataset_path)
 
         if not store_dataset_path: