From 133e2efd8109e4945fa91d2d794e31ec6c2ab2ae Mon Sep 17 00:00:00 2001
From: kiblik <5609770+kiblik@users.noreply.github.com>
Date: Tue, 12 Nov 2024 15:34:13 +0100
Subject: [PATCH] feat(DD_DEDUPLICATION_ALGORITHM_PER_PARSER +
 DD_HASHCODE_FIELDS_PER_SCANNER): Add checker of values

---
 docs/content/en/usage/features.md         |  8 ++++----
 dojo/settings/.settings.dist.py.sha256sum |  2 +-
 dojo/settings/settings.dist.py            | 16 ++++++++++++++++
 3 files changed, 21 insertions(+), 5 deletions(-)

diff --git a/docs/content/en/usage/features.md b/docs/content/en/usage/features.md
index 5f99f34023f..7fad563b138 100644
--- a/docs/content/en/usage/features.md
+++ b/docs/content/en/usage/features.md
@@ -244,7 +244,7 @@ The environment variable will override the settings in `settings.dist.py`, repla
 
 The available algorithms are:
 
-DEDUPE_ALGO_UNIQUE_ID_FROM_TOOL
+DEDUPE_ALGO_UNIQUE_ID_FROM_TOOL (value for `DD_DEDUPLICATION_ALGORITHM_PER_PARSER`: `unique_id_from_tool`)
 :   The deduplication occurs based on
     finding.unique_id_from_tool which is a unique technical
     id existing in the source tool. Few scanners populate this
@@ -266,12 +266,12 @@ DEDUPE_ALGO_UNIQUE_ID_FROM_TOOL
             able to recognise that findings found in previous
             scans are actually the same as the new findings.
 
-DEDUPE_ALGO_HASH_CODE
+DEDUPE_ALGO_HASH_CODE (value for `DD_DEDUPLICATION_ALGORITHM_PER_PARSER`: `hash_code`)
 :   The deduplication occurs based on finding.hash_code. The
     hash_code itself is configurable for each scanner in
     parameter `HASHCODE_FIELDS_PER_SCANNER`.
 
-DEDUPE_ALGO_UNIQUE_ID_FROM_TOOL_OR_HASH_CODE
+DEDUPE_ALGO_UNIQUE_ID_FROM_TOOL_OR_HASH_CODE (value for `DD_DEDUPLICATION_ALGORITHM_PER_PARSER`: `unique_id_from_tool_or_hash_code`)
 :   A finding is a duplicate with another if they have the same
     unique_id_from_tool OR the same hash_code.
 
@@ -284,7 +284,7 @@ DEDUPE_ALGO_UNIQUE_ID_FROM_TOOL_OR_HASH_CODE
             cross-parser deduplication
 
 
-DEDUPE_ALGO_LEGACY
+DEDUPE_ALGO_LEGACY (value for `DD_DEDUPLICATION_ALGORITHM_PER_PARSER`: `legacy`)
 :   This is algorithm that was in place before the configuration
     per parser was made possible, and also the default one for
     backward compatibility reasons.
diff --git a/dojo/settings/.settings.dist.py.sha256sum b/dojo/settings/.settings.dist.py.sha256sum
index 59acc056a4b..ac4b313fa4c 100644
--- a/dojo/settings/.settings.dist.py.sha256sum
+++ b/dojo/settings/.settings.dist.py.sha256sum
@@ -1 +1 @@
-58e2f6cb0ed2c041fe2741d955b72cb7540bfb0923f489d6324717fcf00039da
+4ecb73239a728a885aef8a93747fad416d2fc68666aa8f6223a9993d67f705f1
diff --git a/dojo/settings/settings.dist.py b/dojo/settings/settings.dist.py
index 2571d99b0cf..6744b2fee61 100644
--- a/dojo/settings/settings.dist.py
+++ b/dojo/settings/settings.dist.py
@@ -1296,6 +1296,12 @@ def saml2_attrib_map_format(dict):
 if len(env("DD_HASHCODE_FIELDS_PER_SCANNER")) > 0:
     env_hashcode_fields_per_scanner = json.loads(env("DD_HASHCODE_FIELDS_PER_SCANNER"))
     for key, value in env_hashcode_fields_per_scanner.items():
+        if not isinstance(value, list):
+            msg = f"Fields definition '{value}' for hashcode calculation of '{key}' is not valid. It needs to be list of strings but it is {type(value)}."
+            raise TypeError(msg)
+        if not all(isinstance(field, str) for field in value):
+            msg = f"Fields for hashcode calculation for {key} are not valid. It needs to be list of strings. Some of fields are not string."
+            raise AttributeError(msg)
         if key in HASHCODE_FIELDS_PER_SCANNER:
             logger.info(f"Replacing {key} with value {value} (previously set to {HASHCODE_FIELDS_PER_SCANNER[key]}) from env var DD_HASHCODE_FIELDS_PER_SCANNER")
             HASHCODE_FIELDS_PER_SCANNER[key] = value
@@ -1377,6 +1383,13 @@ def saml2_attrib_map_format(dict):
 # Makes it possible to deduplicate on a technical id (same parser) and also on some functional fields (cross-parsers deduplication)
 DEDUPE_ALGO_UNIQUE_ID_FROM_TOOL_OR_HASH_CODE = "unique_id_from_tool_or_hash_code"
 
+DEDUPE_ALGOS = [
+    DEDUPE_ALGO_LEGACY,
+    DEDUPE_ALGO_UNIQUE_ID_FROM_TOOL,
+    DEDUPE_ALGO_HASH_CODE,
+    DEDUPE_ALGO_UNIQUE_ID_FROM_TOOL_OR_HASH_CODE,
+]
+
 # Allows to deduplicate with endpoints if endpoints is not included in the hashcode.
 # Possible values are: scheme, host, port, path, query, fragment, userinfo, and user. For a details description see https://hyperlink.readthedocs.io/en/latest/api.html#attributes.
 # Example:
@@ -1526,6 +1539,9 @@ def saml2_attrib_map_format(dict):
 if len(env("DD_DEDUPLICATION_ALGORITHM_PER_PARSER")) > 0:
     env_dedup_algorithm_per_parser = json.loads(env("DD_DEDUPLICATION_ALGORITHM_PER_PARSER"))
     for key, value in env_dedup_algorithm_per_parser.items():
+        if value not in DEDUPE_ALGOS:
+            msg = f"DEDUP algorithm '{value}' for '{key}' is not valid. Use one of following values: {', '.join(DEDUPE_ALGOS)}"
+            raise AttributeError(msg)
         if key in DEDUPLICATION_ALGORITHM_PER_PARSER:
             logger.info(f"Replacing {key} with value {value} (previously set to {DEDUPLICATION_ALGORITHM_PER_PARSER[key]}) from env var DD_DEDUPLICATION_ALGORITHM_PER_PARSER")
             DEDUPLICATION_ALGORITHM_PER_PARSER[key] = value