Files
codeql/python/ql/test/library-tests/dataflow/summaries/TestSummaries.qll
yoff 408ba6218f Python: switch dataflow library to new (shared) CFG + SSA
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>
2026-06-22 13:46:43 +00:00

248 lines
7.8 KiB
Plaintext

overlay[local?]
module;
private import python
private import semmle.python.controlflow.internal.Cfg as Cfg
private import semmle.python.dataflow.new.FlowSummary
private import semmle.python.ApiGraphs
/**
* This module ensures that the `callStep` predicate in
* our type tracker implelemtation does not refer to the
* `getACall` predicate on `SummarizedCallable`.
*/
module RecursionGuard {
private import semmle.python.dataflow.new.internal.TypeTrackingImpl::TypeTrackingInput as TT
private class RecursionGuard extends SummarizedCallable::Range {
RecursionGuard() { this = "RecursionGuard" }
override DataFlow::CallCfgNode getACall() {
result.getFunction().asCfgNode().(Cfg::NameNode).getId() = this and
(TT::callStep(_, _) implies any())
}
override predicate propagatesFlow(string input, string output, boolean preservesValue) {
none()
}
override DataFlow::ArgumentNode getACallback() { result.asExpr().(Name).getId() = this }
}
}
private class SummarizedCallableIdentity extends SummarizedCallable::Range {
SummarizedCallableIdentity() { this = "identity" }
override DataFlow::CallCfgNode getACall() {
result.getFunction().asCfgNode().(Cfg::NameNode).getId() = this
}
override DataFlow::ArgumentNode getACallback() { result.asExpr().(Name).getId() = this }
override predicate propagatesFlow(string input, string output, boolean preservesValue) {
input = "Argument[0]" and
output = "ReturnValue" and
preservesValue = true
}
}
// For lambda flow to work, implement lambdaCall and lambdaCreation
private class SummarizedCallableApplyLambda extends SummarizedCallable::Range {
SummarizedCallableApplyLambda() { this = "apply_lambda" }
override DataFlow::CallCfgNode getACall() {
result.getFunction().asCfgNode().(Cfg::NameNode).getId() = this
}
override DataFlow::ArgumentNode getACallback() { result.asExpr().(Name).getId() = this }
override predicate propagatesFlow(string input, string output, boolean preservesValue) {
input = "Argument[1]" and
output = "Argument[0].Parameter[0]" and
preservesValue = true
or
input = "Argument[0].ReturnValue" and
output = "ReturnValue" and
preservesValue = true
}
}
private class SummarizedCallableReversed extends SummarizedCallable::Range {
SummarizedCallableReversed() { this = "list_reversed" }
override DataFlow::CallCfgNode getACall() {
result.getFunction().asCfgNode().(Cfg::NameNode).getId() = this
}
override DataFlow::ArgumentNode getACallback() { result.asExpr().(Name).getId() = this }
override predicate propagatesFlow(string input, string output, boolean preservesValue) {
input = "Argument[0].ListElement" and
output = "ReturnValue.ListElement" and
preservesValue = true
}
}
private class SummarizedCallableMap extends SummarizedCallable::Range {
SummarizedCallableMap() { this = "list_map" }
override DataFlow::CallCfgNode getACall() {
result.getFunction().asCfgNode().(Cfg::NameNode).getId() = this
}
override DataFlow::ArgumentNode getACallback() { result.asExpr().(Name).getId() = this }
override predicate propagatesFlow(string input, string output, boolean preservesValue) {
input = "Argument[1].ListElement" and
output = "Argument[0].Parameter[0]" and
preservesValue = true
or
input = "Argument[0].ReturnValue" and
output = "ReturnValue.ListElement" and
preservesValue = true
}
}
private class SummarizedCallableAppend extends SummarizedCallable::Range {
SummarizedCallableAppend() { this = "append_to_list" }
override DataFlow::CallCfgNode getACall() {
result.getFunction().asCfgNode().(Cfg::NameNode).getId() = this
}
override DataFlow::ArgumentNode getACallback() { result.asExpr().(Name).getId() = this }
override predicate propagatesFlow(string input, string output, boolean preservesValue) {
input = "Argument[0]" and
output = "ReturnValue" and
preservesValue = false
or
input = "Argument[1]" and
output = "ReturnValue.ListElement" and
preservesValue = true
}
}
private class SummarizedCallableJsonLoads extends SummarizedCallable::Range {
SummarizedCallableJsonLoads() { this = "json.loads" }
override DataFlow::CallCfgNode getACall() {
result = API::moduleImport("json").getMember("loads").getACall()
}
override DataFlow::ArgumentNode getACallback() {
result = API::moduleImport("json").getMember("loads").getAValueReachableFromSource()
}
override predicate propagatesFlow(string input, string output, boolean preservesValue) {
input = "Argument[0]" and
output = "ReturnValue.ListElement" and
preservesValue = true
}
}
// Repeated summaries
private class SummarizedCallableWithSubpath extends SummarizedCallable::Range {
SummarizedCallableWithSubpath() { this = "extracted_package.functions.with_subpath" }
override DataFlow::CallCfgNode getACall() {
result =
API::moduleImport("extracted_package")
.getMember("functions")
.getMember("with_subpath")
.getACall()
}
override DataFlow::ArgumentNode getACallback() {
result =
API::moduleImport("extracted_package")
.getMember("functions")
.getMember("with_subpath")
.getAValueReachableFromSource()
}
override predicate propagatesFlow(string input, string output, boolean preservesValue) {
input = "Argument[0]" and
output = "ReturnValue" and
preservesValue = false
}
}
private class SummarizedCallableWithSubpathAgain extends SummarizedCallable::Range {
SummarizedCallableWithSubpathAgain() { this = "extracted_package.functions.with_subpathII" }
override DataFlow::CallCfgNode getACall() {
result =
API::moduleImport("extracted_package")
.getMember("functions")
.getMember("with_subpath")
.getACall()
}
override DataFlow::ArgumentNode getACallback() {
result =
API::moduleImport("extracted_package")
.getMember("functions")
.getMember("with_subpath")
.getAValueReachableFromSource()
}
override predicate propagatesFlow(string input, string output, boolean preservesValue) {
input = "Argument[0]" and
output = "ReturnValue.Attribute[pattern]" and
preservesValue = true
}
}
private class SummarizedCallableWithoutSubpath extends SummarizedCallable::Range {
SummarizedCallableWithoutSubpath() { this = "extracted_package.functions.without_subpath" }
override DataFlow::CallCfgNode getACall() {
result =
API::moduleImport("extracted_package")
.getMember("functions")
.getMember("without_subpath")
.getACall()
}
override DataFlow::ArgumentNode getACallback() {
result =
API::moduleImport("extracted_package")
.getMember("functions")
.getMember("without_subpath")
.getAValueReachableFromSource()
}
override predicate propagatesFlow(string input, string output, boolean preservesValue) {
input = "Argument[0]" and
output = "ReturnValue" and
preservesValue = false
}
}
private class SummarizedCallableWithoutSubpathAgain extends SummarizedCallable::Range {
SummarizedCallableWithoutSubpathAgain() { this = "extracted_package.functions.without_subpathII" }
override DataFlow::CallCfgNode getACall() {
result =
API::moduleImport("extracted_package")
.getMember("functions")
.getMember("without_subpath")
.getACall()
}
override DataFlow::ArgumentNode getACallback() {
result =
API::moduleImport("extracted_package")
.getMember("functions")
.getMember("without_subpath")
.getAValueReachableFromSource()
}
override predicate propagatesFlow(string input, string output, boolean preservesValue) {
input = "Argument[0]" and
output = "ReturnValue.Attribute[pattern]" and
preservesValue = true
}
}