Add ability to read automationDetails.id if present

This commit is contained in:
Kristen Newbury
2023-05-17 15:23:19 -04:00
parent e2501b94a9
commit 9407e5b00f
5 changed files with 19 additions and 3 deletions

View File

@@ -9,7 +9,7 @@
# Sarif format information # Sarif format information
The tool operates on sarif generated by LGTM 1.27.0 (by default) or by the CodeQL CLI (enabled with the -f flag given a value of `CLI`). The tool operates on sarif generated by LGTM 1.27.0 (by default) or by the CodeQL CLI (enabled with the -f flag given a value of `CLI`). The supported sarif is [SARIF v2.1.0](https://docs.oasis-open.org/sarif/sarif/v2.1.0/csprd01/sarif-v2.1.0-csprd01.html).
The values that the -f flag accepts are: `LGTM` and `CLI`. The values that the -f flag accepts are: `LGTM` and `CLI`.

View File

@@ -79,10 +79,14 @@ def joins_for_projects(basetables, external_info):
""" """
b = basetables; e = external_info b = basetables; e = external_info
extra = ""
# if the sarif does have automationDetails
if "automationDetails" in b.project:
extra = b.project.automationDetails[0]
# if the sarif does have versionControlProvenance # if the sarif does have versionControlProvenance
if "repositoryUri" in b.project: if "repositoryUri" in b.project:
repoUri = b.project.repositoryUri[0] repoUri = b.project.repositoryUri[0]
e.project_id = hash.hash_unique(repoUri.encode()) e.project_id = hash.hash_unique((repoUri+extra).encode())
else: else:
repoUri = "unknown" repoUri = "unknown"

View File

@@ -250,6 +250,10 @@ def fillsig_dict(args, elem, context):
# Several rules overlap and need to be applied together, so this is (now) a # Several rules overlap and need to be applied together, so this is (now) a
# simple sequence tests. # simple sequence tests.
if 'results' in elem.keys() and not 'automationDetails' in elem.keys():
#want this to be blank if not present- ie no submodule info added/no sarif-category used
full_elem['automationDetails'] = {'id' : ""}
if {'locations', 'message', 'partialFingerprints', 'ruleId', if {'locations', 'message', 'partialFingerprints', 'ruleId',
'ruleIndex'}.issubset(elem.keys()): 'ruleIndex'}.issubset(elem.keys()):
# Ensure 'rule' is present # Ensure 'rule' is present

View File

@@ -30,6 +30,8 @@ struct_graph_CLI = (
('Array6920', ('array', (0, 'Struct5277'), (1, 'Struct9567'))), ('Array6920', ('array', (0, 'Struct5277'), (1, 'Struct9567'))),
('Struct1509', ('struct', ('semmle.formatSpecifier', 'String'), ('semmle.sourceLanguage', 'String'))), ('Struct1509', ('struct', ('semmle.formatSpecifier', 'String'), ('semmle.sourceLanguage', 'String'))),
('Struct2774', ('struct', ('text', 'String'))), ('Struct2774', ('struct', ('text', 'String'))),
#manually added for optional automationDetails
('Struct1111', ('struct', ('id', 'String'))),
( 'Struct6299', ( 'Struct6299',
( 'struct', ( 'struct',
('endColumn', 'Int'), ('endColumn', 'Int'),
@@ -146,6 +148,8 @@ struct_graph_CLI = (
( 'Struct9786', ( 'Struct9786',
( 'struct', ( 'struct',
('artifacts', 'Array6920'), ('artifacts', 'Array6920'),
#manually added for optional automationDetails
('automationDetails', 'Struct1111'),
('columnKind', 'String'), ('columnKind', 'String'),
('newlineSequences', 'Array7069'), ('newlineSequences', 'Array7069'),
('properties', 'Struct1509'), ('properties', 'Struct1509'),

View File

@@ -330,7 +330,11 @@ def joins_for_project_single(tgraph):
.rename(columns={"value_index": "value_index_1273"}) .rename(columns={"value_index": "value_index_1273"})
# #
.merge(sf(9786), how="left", left_on='id_or_value_at_index', right_on='struct_id', validate="1:m") .merge(sf(9786), how="left", left_on='id_or_value_at_index', right_on='struct_id', validate="1:m")
.drop(columns=['id_or_value_at_index', 'struct_id'])) .drop(columns=['id_or_value_at_index', 'struct_id'])
.merge(sf(1111), how="left", left_on='automationDetails', right_on='struct_id', validate="1:m")
.drop(columns=['automationDetails', 'struct_id'])
.rename(columns={"id": "automationDetails"}))
# #
#newlines there or not - handle #newlines there or not - handle
if 'newlineSequences' in project_df_temp1: if 'newlineSequences' in project_df_temp1: