mirror of
https://github.com/github/codeql.git
synced 2026-08-03 08:52:55 +02:00
408ba6218f
Flips the Python dataflow trunk from the legacy CFG (semmle/python/Flow.qll) and legacy ESSA SSA (semmle/python/essa/*) to the new shared CFG facade (semmle.python.controlflow.internal.Cfg) and the new SSA adapter (semmle.python.dataflow.new.internal.SsaImpl), both introduced additively in the preceding PRs in this stack. This is the trunk-flip equivalent of the original draft PR #21894 (kept around as documentation), rebased on top of the four preparatory PRs: P1: Remove AstNode.getAFlowNode() and rewrite callers (#21919). P2: Qualify Flow.qll's AST references with Py:: prefix (#21920). P3: Add new shared-CFG-backed control flow graph (#21921). P4: Add new shared-SSA-backed SSA adapter (#21923). The Python dataflow library (semmle/python/dataflow/new/) now imports the new CFG facade and SSA adapter. All CFG-typed predicates (ControlFlowNode, CallNode, BasicBlock, NameNode, AttrNode, ...) are qualified with the Cfg:: prefix; SSA references switch from EssaVariable/EssaDefinition to SsaImpl::Definition/SourceVariable. GuardNode is redesigned to use the new CFG's outcome-node model (isAfterTrue / isAfterFalse) instead of the legacy ConditionBlock + flipped indirection. Only BarrierGuard<...> is preserved as public API. Framework files (Bottle, FastApi, Django, Tornado, Pyramid, Stdlib, ...) are updated to take CFG nodes from the new facade. A handful of dataflow consistency tweaks for the new CFG: - Augmented-assignment targets are treated as both load and store. - 'from X import *' produces uncertain SSA writes for unknown names. - CFG nodes are canonicalised so dataflow does not see equivalent pre/post-order pairs as distinct nodes. Two AST tweaks for the new CFG: - AstNodeImpl: omit PEP 695 type-parameter names from FunctionDefExpr / ClassDefExpr children. - ImportResolution: drop the legacy essa import. Test churn (~175 files): reblessed library- and query-test .expected files reflect slightly different CFG granularity, different toString output, and a handful of true alert deltas in security queries. Verification: all 367 lib + src + consistency-queries compile clean. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
80 lines
1.6 KiB
Python
80 lines
1.6 KiB
Python
import sys; import os; sys.path.append(os.path.dirname(os.path.dirname((__file__))))
|
|
from taintlib import *
|
|
|
|
# This has no runtime impact, but allows autocomplete to work
|
|
from typing import TYPE_CHECKING
|
|
if TYPE_CHECKING:
|
|
from ..taintlib import *
|
|
|
|
|
|
# Actual tests
|
|
|
|
def emulated_authentication_check(arg):
|
|
if not arg == "safe":
|
|
raise Exception("user unauthenticated")
|
|
|
|
|
|
def test_custom_sanitizer_exception_raise():
|
|
s = TAINTED_STRING
|
|
|
|
try:
|
|
emulated_authentication_check(s)
|
|
ensure_not_tainted(s)
|
|
except:
|
|
ensure_tainted(s) # $ MISSING: tainted
|
|
raise
|
|
|
|
ensure_not_tainted(s)
|
|
|
|
|
|
def test_custom_sanitizer_exception_pass():
|
|
s = TAINTED_STRING
|
|
|
|
try:
|
|
emulated_authentication_check(s)
|
|
ensure_not_tainted(s)
|
|
except:
|
|
ensure_tainted(s) # $ MISSING: tainted
|
|
pass
|
|
|
|
ensure_tainted(s) # $ MISSING: tainted
|
|
|
|
|
|
def emulated_is_safe(arg):
|
|
# emulating something we won't be able to look at source code for
|
|
return eval("False")
|
|
|
|
|
|
def test_custom_sanitizer_guard():
|
|
s = TAINTED_STRING
|
|
|
|
if emulated_is_safe(s):
|
|
ensure_not_tainted(s)
|
|
else:
|
|
ensure_tainted(s) # $ tainted
|
|
|
|
ensure_tainted(s) # $ tainted
|
|
|
|
|
|
def emulated_escaping(arg):
|
|
return arg.replace("<", "?").replace(">", "?").replace("'", "?").replace("\"", "?")
|
|
|
|
|
|
def test_escape():
|
|
s = TAINTED_STRING
|
|
|
|
s2 = emulated_escaping(s)
|
|
ensure_not_tainted(s2)
|
|
ensure_tainted(s) # $ tainted
|
|
|
|
|
|
# Make tests runable
|
|
|
|
test_custom_sanitizer_exception_pass()
|
|
try:
|
|
test_custom_sanitizer_exception_raise()
|
|
except Exception:
|
|
pass
|
|
test_custom_sanitizer_guard()
|
|
test_escape()
|