hohn/sarif-cli
1
0
Fork 0
mirror of https://github.com/hohn/sarif-cli.git synced 2025-12-16 09:13:04 +01:00
Code Issues Packages Projects Releases Wiki Activity

fix: set id and scan_id type to uint64 to suppress float conversion

Browse Source
This commit is contained in:
Michael Hohn
2022-06-01 13:00:37 -07:00
committed by =Michael Hohn
parent 0fc6eb3cce
commit 82a8e7a6dc
1 changed files with 40 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

70
sarif_cli/scan_tables.py
View File

@@ -53,34 +53,37 @@ def joins_for_results(basetables, external_info):
def _results_from_kind_problem(basetables, external_info):
b = basetables; e = external_info
flakegen = snowflake_id.Snowflake(2)
res = pd.DataFrame(data={
'id': [flakegen.next() for _ in range(len(b.kind_problem))],
'scan_id' : e.scan_id,
'query_id' : e.ql_query_id,
'result_type' : "kind_problem",
'codeFlow_id' : 0, # link to codeflows (kind_pathproblem only, NULL here)
'message': b.kind_problem.message_text,
'message_object' : pd.NA,
'location': b.kind_problem.location_uri,
# for kind_problem, use the same location for source and sink
'source_startLine' : b.kind_problem.location_startLine,
'source_startCol' : b.kind_problem.location_startColumn,
'source_endLine' : b.kind_problem.location_endLine,
'source_endCol' : b.kind_problem.location_endColumn,
'sink_startLine' : b.kind_problem.location_startLine,
'sink_startCol' : b.kind_problem.location_startColumn,
'sink_endLine' : b.kind_problem.location_endLine,
'sink_endCol' : b.kind_problem.location_endColumn,
'source_object' : pd.NA, # TODO: find high-level info from query name or tags?
'sink_object' : pd.NA,
})
return res
res = pd.DataFrame(
data={
'id': [flakegen.next() for _ in range(len(b.kind_problem))],
'scan_id' : e.scan_id,
'query_id' : e.ql_query_id,
'result_type' : "kind_problem",
'codeFlow_id' : 0, # link to codeflows (kind_pathproblem only, NULL here)
'message': b.kind_problem.message_text,
'message_object' : pd.NA,
'location': b.kind_problem.location_uri,
# for kind_problem, use the same location for source and sink
'source_startLine' : b.kind_problem.location_startLine,
'source_startCol' : b.kind_problem.location_startColumn,
'source_endLine' : b.kind_problem.location_endLine,
'source_endCol' : b.kind_problem.location_endColumn,
'sink_startLine' : b.kind_problem.location_startLine,
'sink_startCol' : b.kind_problem.location_startColumn,
'sink_endLine' : b.kind_problem.location_endLine,
'sink_endCol' : b.kind_problem.location_endColumn,
'source_object' : pd.NA, # TODO: find high-level info from query name or tags?
'sink_object' : pd.NA,
})
# Force column type(s) to avoid floats in output.
res1 = res.astype({ 'id' : 'uint64', 'scan_id': 'uint64'}).reset_index(drop=True)
return res1
def _results_from_kind_pathproblem(basetables, external_info):
@@ -168,7 +171,14 @@ def _results_from_kind_pathproblem(basetables, external_info):
source_sink_coll.append(res)
results0 = pd.DataFrame(data=source_sink_coll).drop_duplicates().reset_index(drop=True)
# Now add the snowflake ids
# Add the snowflake ids
results0['id'] = [flakegen.next() for _ in range(len(results0))]
return results0
# The 'scan_id' column is needed for astype
if len(results0) == 0:
results0['scan_id'] = []
# Force column type(s) to avoid floats in output.
results1 = results0.astype({ 'id' : 'uint64', 'scan_id': 'uint64'}).reset_index(drop=True)
return results1