Python: add new shared-CFG-backed control flow graph

Preparatory refactor for the shared-CFG dataflow migration. Adds the
new Python CFG library additively, without changing any production
behaviour.

Library additions:

- semmle.python.controlflow.internal.AstNodeImpl — mediates between
  the Python AST and the shared codeql.controlflow.ControlFlowGraph
  signature. Wraps Python's Stmt/Expr/Scope/Pattern and adds two
  synthetic kinds of node (BlockStmt for body slots, intermediate
  nodes for multi-operand boolean expressions).

- semmle.python.controlflow.internal.Cfg — public facade
  re-exposing the same API surface as semmle/python/Flow.qll
  (ControlFlowNode, CallNode, BasicBlock, NameNode, DefinitionNode,
  CompareNode, ...), backed by the shared CFG.

- lib/printCfgNew.ql — debug/visualisation query for the new CFG.

- consistency-queries/CfgConsistency.ql — consistency query running
  the shared CFG's standard checks against Python.

Shared library:

- shared.controlflow.ControlFlowGraph — adds two defaulted
  getWhileElse / getForeachElse predicates to AstSig so Python can
  model while-else / for-else (no behavioural change for other
  languages).

Test additions:

- ControlFlow/bindings/* — annotation-driven SSA-binding tests for
  the new CFG (annassign, compound, comprehension, decorated,
  except_handler, imports, match_pattern, parameters, simple,
  type_params, walrus_starred, with_stmt, dead_under_no_raise).

- ControlFlow/store-load/* — basic store/load coverage.

- ControlFlow/evaluation-order/NewCfg*.ql — mirrors of the existing
  OldCfg evaluation-order self-validation suite, run against the
  new CFG via NewCfgImpl.qll.

- Minor extensions to existing test_if.py / test_boolean.py +
  cosmetic .expected churn on a handful of OldCfg tests.

No dataflow, SSA, or production query is migrated yet — that lands in
follow-up PRs. The new CFG library has zero callers in lib/ and src/.

Verified by:
- All lib + src + consistency-queries compile clean (367 queries).
- All 56 ControlFlow library-tests pass.
- All 474 dataflow + PointsTo library-tests + consistency tests pass.
- syntax_error/CONSISTENCY/CfgConsistency passes.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

.github/workflows/go-version-update.yml

@@ -1,208 +0,0 @@
-name: Update Go version
-
-on:
-  workflow_dispatch:
-  schedule:
-    - cron: "0 3 * * 1"  # Run weekly on Mondays at 3 AM UTC (1 = Monday)
-
-permissions:
-  contents: write
-  pull-requests: write
-
-jobs:
-  update-go-version:
-    name: Check and update Go version
-    if: github.repository == 'github/codeql'
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v5
-        with:
-          fetch-depth: 0
-
-      - name: Set up Git
-        run: |
-          git config user.name "github-actions[bot]"
-          git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
-
-      - name: Fetch latest Go version
-        id: fetch-version
-        run: |
-          LATEST_GO_VERSION=$(curl -s https://go.dev/dl/?mode=json | jq -r '.[0].version')
-          
-          if [ -z "$LATEST_GO_VERSION" ] || [ "$LATEST_GO_VERSION" = "null" ]; then
-            echo "Error: Failed to fetch latest Go version from go.dev"
-            exit 1
-          fi
-          
-          echo "Latest Go version from go.dev: $LATEST_GO_VERSION"
-          echo "version=$LATEST_GO_VERSION" >> $GITHUB_OUTPUT
-          
-          # Extract version numbers (e.g., go1.26.0 -> 1.26.0)
-          LATEST_VERSION_NUM=$(echo $LATEST_GO_VERSION | sed 's/^go//')
-          echo "version_num=$LATEST_VERSION_NUM" >> $GITHUB_OUTPUT
-          
-          # Extract major.minor version (e.g., 1.26.0 -> 1.26)
-          LATEST_MAJOR_MINOR=$(echo $LATEST_VERSION_NUM | sed -E 's/^([0-9]+\.[0-9]+).*/\1/')
-          echo "major_minor=$LATEST_MAJOR_MINOR" >> $GITHUB_OUTPUT
-
-      - name: Check current Go version
-        id: current-version
-        run: |
-          CURRENT_VERSION=$(sed -n 's/.*go_sdk\.download(version = \"\([^\"]*\)\".*/\1/p' MODULE.bazel)
-          
-          if [ -z "$CURRENT_VERSION" ]; then
-            echo "Error: Could not extract Go version from MODULE.bazel"
-            exit 1
-          fi
-          
-          echo "Current Go version in MODULE.bazel: $CURRENT_VERSION"
-          echo "version=$CURRENT_VERSION" >> $GITHUB_OUTPUT
-          
-          # Extract major.minor version
-          CURRENT_MAJOR_MINOR=$(echo $CURRENT_VERSION | sed -E 's/^([0-9]+\.[0-9]+).*/\1/')
-          echo "major_minor=$CURRENT_MAJOR_MINOR" >> $GITHUB_OUTPUT
-
-      - name: Compare versions
-        id: compare
-        run: |
-          LATEST="${{ steps.fetch-version.outputs.version_num }}"
-          CURRENT="${{ steps.current-version.outputs.version }}"
-          
-          echo "Latest: $LATEST"
-          echo "Current: $CURRENT"
-          
-          if [ "$LATEST" = "$CURRENT" ]; then
-            echo "Go version is up to date"
-            echo "needs_update=false" >> $GITHUB_OUTPUT
-          else
-            echo "Go version needs update from $CURRENT to $LATEST"
-            echo "needs_update=true" >> $GITHUB_OUTPUT
-          fi
-
-      - name: Update Go version in files
-        if: steps.compare.outputs.needs_update == 'true'
-        run: |
-          LATEST_VERSION_NUM="${{ steps.fetch-version.outputs.version_num }}"
-          LATEST_MAJOR_MINOR="${{ steps.fetch-version.outputs.major_minor }}"
-          CURRENT_VERSION="${{ steps.current-version.outputs.version }}"
-          CURRENT_MAJOR_MINOR="${{ steps.current-version.outputs.major_minor }}"
-          
-          echo "Updating from $CURRENT_VERSION to $LATEST_VERSION_NUM"
-          
-          # Escape dots in current version strings for use in sed patterns
-          CURRENT_VERSION_ESCAPED=$(echo "$CURRENT_VERSION" | sed 's/\./\\./g')
-          CURRENT_MAJOR_MINOR_ESCAPED=$(echo "$CURRENT_MAJOR_MINOR" | sed 's/\./\\./g')
-          
-          # Update MODULE.bazel
-          sed -i "s/go_sdk\.download(version = \"$CURRENT_VERSION_ESCAPED\")/go_sdk.download(version = \"$LATEST_VERSION_NUM\")/" MODULE.bazel
-          if ! grep -q "go_sdk.download(version = \"$LATEST_VERSION_NUM\")" MODULE.bazel; then
-            echo "Error: Failed to update MODULE.bazel"
-            exit 1
-          fi
-          
-          # Update go/extractor/go.mod
-          if ! sed -i "s/^go $CURRENT_MAJOR_MINOR_ESCAPED\$/go $LATEST_MAJOR_MINOR/" go/extractor/go.mod; then
-            echo "Warning: Failed to update go directive in go.mod"
-          fi
-          if ! sed -i "s/^toolchain go$CURRENT_VERSION_ESCAPED\$/toolchain go$LATEST_VERSION_NUM/" go/extractor/go.mod; then
-            echo "Warning: Failed to update toolchain in go.mod"
-          fi
-          
-          # Update go/extractor/autobuilder/build-environment.go
-          if ! sed -i "s/var maxGoVersion = util\.NewSemVer(\"$CURRENT_MAJOR_MINOR_ESCAPED\")/var maxGoVersion = util.NewSemVer(\"$LATEST_MAJOR_MINOR\")/" go/extractor/autobuilder/build-environment.go; then
-            echo "Warning: Failed to update build-environment.go"
-          fi
-          
-          # Update go/actions/test/action.yml
-          if ! sed -i "s/default: \"~$CURRENT_VERSION_ESCAPED\"/default: \"~$LATEST_VERSION_NUM\"/" go/actions/test/action.yml; then
-            echo "Warning: Failed to update action.yml"
-          fi
-          
-          # Show what changed
-          git diff
-
-      - name: Check for changes
-        id: check-changes
-        if: steps.compare.outputs.needs_update == 'true'
-        run: |
-          if git diff --quiet; then
-            echo "No changes detected"
-            echo "has_changes=false" >> $GITHUB_OUTPUT
-          else
-            echo "Changes detected"
-            echo "has_changes=true" >> $GITHUB_OUTPUT
-          fi
-
-      - name: Check for existing PR
-        if: steps.check-changes.outputs.has_changes == 'true'
-        id: check-pr
-        env:
-          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: |
-          BRANCH_NAME="workflow/go-version-update"
-          PR_NUMBER=$(gh pr list --head "$BRANCH_NAME" --state open --json number --jq '.[0].number')
-          
-          if [ -n "$PR_NUMBER" ]; then
-            echo "Existing PR found: #$PR_NUMBER"
-            echo "pr_exists=true" >> $GITHUB_OUTPUT
-            echo "pr_number=$PR_NUMBER" >> $GITHUB_OUTPUT
-          else
-            echo "No existing PR found"
-            echo "pr_exists=false" >> $GITHUB_OUTPUT
-          fi
-
-      - name: Commit and push changes
-        if: steps.check-changes.outputs.has_changes == 'true'
-        run: |
-          BRANCH_NAME="workflow/go-version-update"
-          LATEST_VERSION_NUM="${{ steps.fetch-version.outputs.version_num }}"
-          LATEST_MAJOR_MINOR="${{ steps.fetch-version.outputs.major_minor }}"
-          
-          # Create or switch to branch
-          git checkout -B "$BRANCH_NAME"
-          
-          # Stage and commit changes
-          git add MODULE.bazel go/extractor/go.mod go/extractor/autobuilder/build-environment.go go/actions/test/action.yml
-          git commit -m "Go: Update to $LATEST_VERSION_NUM"
-          
-          # Push changes
-          git push --force-with-lease origin "$BRANCH_NAME"
-
-      - name: Create or update PR
-        if: steps.check-changes.outputs.has_changes == 'true'
-        env:
-          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: |
-          BRANCH_NAME="workflow/go-version-update"
-          LATEST_VERSION_NUM="${{ steps.fetch-version.outputs.version_num }}"
-          CURRENT_VERSION="${{ steps.current-version.outputs.version }}"
-          
-          PR_TITLE="Go: Update to $LATEST_VERSION_NUM"
-          
-          PR_BODY=$(cat <<EOF
-          This PR updates Go from $CURRENT_VERSION to $LATEST_VERSION_NUM.
-
-          Updated files:
-          - \`MODULE.bazel\` - go_sdk.download version
-          - \`go/extractor/go.mod\` - go directive and toolchain
-          - \`go/extractor/autobuilder/build-environment.go\` - maxGoVersion (only if MAJOR.MINOR changes)
-          - \`go/actions/test/action.yml\` - default go-test-version
-
-          This PR was automatically created by the [Go version update workflow](https://github.com/${{ github.repository }}/blob/main/.github/workflows/go-version-update.yml).
-          EOF
-          )
-          
-          if [ "${{ steps.check-pr.outputs.pr_exists }}" = "true" ]; then
-            echo "Updating existing PR #${{ steps.check-pr.outputs.pr_number }}"
-            gh pr edit "${{ steps.check-pr.outputs.pr_number }}" --title "$PR_TITLE" --body "$PR_BODY"
-          else
-            echo "Creating new PR"
-            gh pr create \
-              --title "$PR_TITLE" \
-              --body "$PR_BODY" \
-              --base main \
-              --head "$BRANCH_NAME" \
-              --label "Go"
-          fi

MODULE.bazel

@@ -273,7 +273,7 @@ use_repo(
 )
 
 go_sdk = use_extension("@rules_go//go:extensions.bzl", "go_sdk")
-go_sdk.download(version = "1.26.4")
+go_sdk.download(version = "1.26.0")
 
 go_deps = use_extension("@gazelle//:extensions.bzl", "go_deps")
 go_deps.from_file(go_mod = "//go/extractor:go.mod")

config/identical-files.json

@@ -11,6 +11,10 @@
     "java/ql/lib/semmle/code/java/dataflow/internal/rangeanalysis/SignAnalysisCommon.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/rangeanalysis/SignAnalysisCommon.qll"
   ],
+  "Bound Java/C#": [
+    "java/ql/lib/semmle/code/java/dataflow/Bound.qll",
+    "csharp/ql/lib/semmle/code/csharp/dataflow/Bound.qll"
+  ],
   "ModulusAnalysis Java/C#": [
     "java/ql/lib/semmle/code/java/dataflow/ModulusAnalysis.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/ModulusAnalysis.qll"

csharp/ql/lib/qlpack.yml

@@ -9,7 +9,6 @@ dependencies:
   codeql/controlflow: ${workspace}
   codeql/dataflow: ${workspace}
   codeql/mad: ${workspace}
-  codeql/rangeanalysis: ${workspace}
   codeql/ssa: ${workspace}
   codeql/threat-models: ${workspace}
   codeql/tutorial: ${workspace}

csharp/ql/lib/semmle/code/csharp/dataflow/Bound.qll

@@ -4,31 +4,67 @@
 overlay[local?]
 module;
 
-private import csharp as CS
+private import internal.rangeanalysis.BoundSpecific
-private import semmle.code.csharp.dataflow.SSA::Ssa
-private import semmle.code.csharp.dataflow.internal.rangeanalysis.ConstantUtils as CU
-private import semmle.code.csharp.dataflow.internal.rangeanalysis.RangeUtils as RU
-private import semmle.code.csharp.dataflow.internal.rangeanalysis.SsaUtils as SU
-private import codeql.rangeanalysis.Bound as SharedBound
 
-/** Provides C#-specific definitions for bounds. */
+private newtype TBound =
-private module BoundDefs implements SharedBound::BoundDefinitions<CS::Location> {
+  TBoundZero() or
-  class Type = CS::Type;
+  TBoundSsa(SsaVariable v) { v.getSourceVariable().getType() instanceof IntegralType } or
-
+  TBoundExpr(Expr e) {
-  class SsaVariable = SU::SsaVariable;
+    interestingExprBound(e) and
-
+    not exists(SsaVariable v | e = v.getAUse())
-  class SsaSourceVariable = SourceVariable;
-
-  class Expr = CS::ControlFlowNodes::ExprNode;
-
-  class IntegralType = CS::IntegralType;
-
-  class ConstantIntegerExpr = CU::ConstantIntegerExpr;
-
-  /** Holds if `e` is a bound expression and it is not an SSA variable read. */
-  predicate interestingExprBound(Expr e) { CU::systemArrayLengthAccess(e.getExpr()) }
   }
 
-module BoundImpl = SharedBound::Bound<CS::Location, BoundDefs>;
+/**
+ * A bound that may be inferred for an expression plus/minus an integer delta.
+ */
+abstract class Bound extends TBound {
+  /** Gets a textual representation of this bound. */
+  abstract string toString();
 
-import BoundImpl
+  /** Gets an expression that equals this bound plus `delta`. */
+  abstract Expr getExpr(int delta);
+
+  /** Gets an expression that equals this bound. */
+  Expr getExpr() { result = this.getExpr(0) }
+
+  /** Gets the location of this bound. */
+  abstract Location getLocation();
+}
+
+/**
+ * The bound that corresponds to the integer 0. This is used to represent all
+ * integer bounds as bounds are always accompanied by an added integer delta.
+ */
+class ZeroBound extends Bound, TBoundZero {
+  override string toString() { result = "0" }
+
+  override Expr getExpr(int delta) { result.(ConstantIntegerExpr).getIntValue() = delta }
+
+  override Location getLocation() { result.hasLocationInfo("", 0, 0, 0, 0) }
+}
+
+/**
+ * A bound corresponding to the value of an SSA variable.
+ */
+class SsaBound extends Bound, TBoundSsa {
+  /** Gets the SSA variable that equals this bound. */
+  SsaVariable getSsa() { this = TBoundSsa(result) }
+
+  override string toString() { result = this.getSsa().toString() }
+
+  override Expr getExpr(int delta) { result = this.getSsa().getAUse() and delta = 0 }
+
+  override Location getLocation() { result = this.getSsa().getLocation() }
+}
+
+/**
+ * A bound that corresponds to the value of a specific expression that might be
+ * interesting, but isn't otherwise represented by the value of an SSA variable.
+ */
+class ExprBound extends Bound, TBoundExpr {
+  override string toString() { result = this.getExpr().toString() }
+
+  override Expr getExpr(int delta) { this = TBoundExpr(result) and delta = 0 }
+
+  override Location getLocation() { result = this.getExpr().getLocation() }
+}

csharp/ql/lib/semmle/code/csharp/dataflow/internal/rangeanalysis/BoundSpecific.qll

@@ -0,0 +1,22 @@
+/**
+ * Provides C#-specific definitions for bounds.
+ */
+
+private import csharp as CS
+private import semmle.code.csharp.dataflow.SSA::Ssa as Ssa
+private import semmle.code.csharp.dataflow.internal.rangeanalysis.ConstantUtils as CU
+private import semmle.code.csharp.dataflow.internal.rangeanalysis.RangeUtils as RU
+private import semmle.code.csharp.dataflow.internal.rangeanalysis.SsaUtils as SU
+
+class SsaVariable = SU::SsaVariable;
+
+class Expr = CS::ControlFlowNodes::ExprNode;
+
+class Location = CS::Location;
+
+class IntegralType = CS::IntegralType;
+
+class ConstantIntegerExpr = CU::ConstantIntegerExpr;
+
+/** Holds if `e` is a bound expression and it is not an SSA variable read. */
+predicate interestingExprBound(Expr e) { CU::systemArrayLengthAccess(e.getExpr()) }

docs/codeql/codeql-overview/codeql-changelog/codeql-cli-2.25.6.rst

@@ -1,139 +0,0 @@
-.. _codeql-cli-2.25.6:
-
-==========================
-CodeQL 2.25.6 (2026-06-04)
-==========================
-
-.. contents:: Contents
-   :depth: 2
-   :local:
-   :backlinks: none
-
-This is an overview of changes in the CodeQL CLI and relevant CodeQL query and library packs. For additional updates on changes to the CodeQL code scanning experience, check out the `code scanning section on the GitHub blog <https://github.blog/tag/code-scanning/>`__, `relevant GitHub Changelog updates <https://github.blog/changelog/label/application-security/>`__, `changes in the CodeQL extension for Visual Studio Code <https://marketplace.visualstudio.com/items/GitHub.vscode-codeql/changelog>`__, and the `CodeQL Action changelog <https://github.com/github/codeql-action/blob/main/CHANGELOG.md>`__.
-
-Security Coverage
------------------
-
-CodeQL 2.25.6 runs a total of 496 security queries when configured with the Default suite (covering 169 CWE). The Extended suite enables an additional 131 queries (covering 32 more CWE).
-
-CodeQL CLI
-----------
-
-Improvements
-~~~~~~~~~~~~
-
-*   When the :code:`git` executable is available, CodeQL can now obtain configuration and queries from SHA-256 Git repositories, and infer Git metadata about them.
-
-Miscellaneous
-~~~~~~~~~~~~~
-
-*   The build of Eclipse Temurin OpenJDK that is used to run the CodeQL CLI has been updated to version 21.0.11.
-
-Query Packs
------------
-
-Bug Fixes
-~~~~~~~~~
-
-GitHub Actions
-""""""""""""""
-
-*   Adjusted (minor) help file descriptions for queries: :code:`actions/untrusted-checkout/critical`, :code:`actions/untrusted-checkout/high`, :code:`actions/untrusted-checkout/medium`. Clarified wording on a minor point, added one more listed resource and added one more recommendation for things to check.
-
-Major Analysis Improvements
-~~~~~~~~~~~~~~~~~~~~~~~~~~~
-
-GitHub Actions
-""""""""""""""
-
-*   Adjusted :code:`actions/untrusted-checkout/critical` to align more with other untrusted resource queries, where the alert location is the location where the artifact is obtained from (the checkout point). This aligns with the other 2 related queries. This will cause the same alerts to re-open for closed alerts of this query.
-
-Minor Analysis Improvements
-~~~~~~~~~~~~~~~~~~~~~~~~~~~
-
-GitHub Actions
-""""""""""""""
-
-*   Altered the alert message for clarity for queries: :code:`actions/untrusted-checkout/critical`, :code:`actions/untrusted-checkout/high`.
-*   The :code:`actions/unpinned-tag` query now recognizes 64-character SHA-256 commit hashes as properly pinned references, in addition to 40-character SHA-1 hashes.
-
-Query Metadata Changes
-~~~~~~~~~~~~~~~~~~~~~~
-
-GitHub Actions
-""""""""""""""
-
-*   Reversed adjustment of the name of :code:`actions/untrusted-checkout/high`, but kept the portion of the previous change for the word "trusted" to "privileged". Added a missing "a" to phrasing in :code:`actions/untrusted-checkout/high` and :code:`actions/untrusted-checkout/medium`.
-
-Language Libraries
-------------------
-
-Major Analysis Improvements
-~~~~~~~~~~~~~~~~~~~~~~~~~~~
-
-Swift
-"""""
-
-*   Upgraded to allow analysis of Swift 6.3.2.
-
-Minor Analysis Improvements
-~~~~~~~~~~~~~~~~~~~~~~~~~~~
-
-C/C++
-"""""
-
-*   Added flow source models for :code:`scanf_s` and related functions.
-*   Added a :code:`Call` column to :code:`LocalFlowSourceFunction::hasLocalFlowSource` and :code:`RemoteFlowSourceFunction::hasRemoteFlowSource`. The old predicates without a :code:`Call` column continue to be supported.
-
-C#
-""
-
-*   Full support for C# 14 / .NET 10. All new language features are now supported by the extractor. The QL library and data flow analysis now support the new C# 14 language constructs and include generated Models as Data (MaD) models for the .NET 10 runtime.
-*   C# 14: Added support for user-defined instance increment/decrement operators.
-
-Java/Kotlin
-"""""""""""
-
-*   Added LLM-generated source and sink models for :code:`org.apache.avro`.
-
-JavaScript/TypeScript
-"""""""""""""""""""""
-
-*   The sensitive data heuristics used to identify code that handles passwords and private data have been improved. Most of the changes permit more variations of established patterns, thereby finding more sensitive data. Queries that use the sensitive data library (for example :code:`js/clear-text-logging`) may find more correct results and fewer false positive results after these changes.
-
-Python
-""""""
-
-*   The sensitive data heuristics used to identify code that handles passwords and private data have been improved. Most of the changes permit more variations of established patterns, thereby finding more sensitive data. Queries that use the sensitive data library (for example :code:`py/clear-text-logging-sensitive-data`) may find more correct results and fewer false positive results after these changes.
-
-Swift
-"""""
-
-*   The sensitive data heuristics used to identify code that handles passwords and private data have been improved. Most of the changes permit more variations of established patterns, thereby finding more sensitive data. Queries that use the sensitive data library (for example :code:`swift/cleartext-logging`) may find more correct results and fewer false positive results after these changes.
-
-GitHub Actions
-""""""""""""""
-
-*   The GitHub Actions analysis now recognizes more Bash regex checks that restrict a value to alphanumeric characters, including regexes like :code:`^[0-9a-zA-Z]{40}([0-9a-zA-Z]{24})?$` which check for a SHA-1 or SHA-256 hash. This may reduce false positive results where command output is validated with grouped or optional alphanumeric patterns before being used.
-
-Rust
-""""
-
-*   The sensitive data heuristics used to identify code that handles passwords and private data have been improved. Most of the changes permit more variations of established patterns, thereby finding more sensitive data. Queries that use the sensitive data library (for example :code:`rust/cleartext-logging`) may find more correct results and fewer false positive results after these changes.
-
-Deprecated APIs
-~~~~~~~~~~~~~~~
-
-C/C++
-"""""
-
-*   The :code:`UsingAliasTypedefType` class has been deprecated. Use :code:`TypeAliasType` instead.
-
-New Features
-~~~~~~~~~~~~
-
-C/C++
-"""""
-
-*   Added a :code:`getOriginalTemplate` predicate to :code:`TemplateClass`, :code:`TemplateFunction`, :code:`TemplateVariable`, and :code:`AliasTemplateType`, which yields the class member template the template was generated from. The predicates only have results for templates that are members of class template instantiations.
-*   Added :code:`AliasTemplateType` and :code:`AliasTemplateInstantiationType` classes, representing C++ alias templates and their instantiations.

docs/codeql/codeql-overview/codeql-changelog/index.rst

@@ -11,7 +11,6 @@ A list of queries for each suite and language `is available here <https://docs.g
 .. toctree::
    :maxdepth: 1
 
-   codeql-cli-2.25.6
    codeql-cli-2.25.5
    codeql-cli-2.25.4
    codeql-cli-2.25.3

go/actions/test/action.yml

@@ -4,7 +4,7 @@ inputs:
   go-test-version:
     description: Which Go version to use for running the tests
     required: false
-    default: "~1.26.4"
+    default: "~1.26.0"
   run-code-checks:
     description: Whether to run formatting, code and qhelp generation checks
     required: false

go/extractor/go.mod

@@ -2,14 +2,14 @@ module github.com/github/codeql-go/extractor
 
 go 1.26
 
-toolchain go1.26.4
+toolchain go1.26.0
 
 // when updating this, run
 //    bazel run @rules_go//go -- mod tidy
 // when adding or removing dependencies, run
 //    bazel mod tidy
 require (
-	golang.org/x/mod v0.37.0
+	golang.org/x/mod v0.36.0
 	golang.org/x/tools v0.45.0
 )
 

go/extractor/go.sum

@@ -6,8 +6,8 @@ github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZb
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu7U=
 github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U=
-golang.org/x/mod v0.37.0 h1:vF1DjpVEshcIqoEaauuHebaLk1O1forxjxBaVn884JQ=
+golang.org/x/mod v0.36.0 h1:JJjpVx6myfUsUdAzZuOSTTmRE0PfZeNWzzvKrP7amb4=
-golang.org/x/mod v0.37.0/go.mod h1:m8S8VeM9r4dzDwjrKO0a1sZP3YjeMamRRlD+fmR2Q/0=
+golang.org/x/mod v0.36.0/go.mod h1:moc6ELqsWcOw5Ef3xVprK5ul/MvtVvkIXLziUOICjUQ=
 golang.org/x/sync v0.20.0 h1:e0PTpb7pjO8GAtTs2dQ6jYa5BWYlMuX047Dco/pItO4=
 golang.org/x/sync v0.20.0/go.mod h1:9xrNwdLfx4jkKbNva9FpL6vEN7evnE43NNNJQ2LF3+0=
 golang.org/x/tools v0.45.0 h1:18qN3FAooORvApf5XjCXgsuayZOEtXf6JK18I3+ONa8=

go/ql/test/library-tests/semmle/go/dataflow/ExternalValueFlow/completetest.ql

@@ -9,9 +9,9 @@ import semmle.go.dataflow.internal.FlowSummaryImpl as FlowSummaryImpl
 import utils.test.InlineFlowTest
 
 module Config implements DataFlow::ConfigSig {
-  predicate isSource(DataFlow::Node source) { sourceNode(source, "qltest") }
+  predicate isSource(DataFlow::Node src) { sourceNode(src, "qltest") }
 
-  predicate isSink(DataFlow::Node sink) { sinkNode(sink, "qltest") }
+  predicate isSink(DataFlow::Node src) { sinkNode(src, "qltest") }
 }
 
 import ValueFlowTest<Config>

go/ql/test/library-tests/semmle/go/dataflow/VarArgs/CONSISTENCY/DataFlowConsistency.expected

@@ -1,2 +0,0 @@
-reverseRead
-| main.go:23:3:23:5 | out | Origin of readStep is missing a PostUpdateNode. |

go/ql/test/library-tests/semmle/go/dataflow/VarArgs/main.go

@@ -4,7 +4,7 @@ func source() string {
 	return "untrusted data"
 }
 
-func sink(any) {
+func sink(string) {
 }
 
 type A struct {
@@ -19,10 +19,6 @@ func functionWithVarArgsParameter(s ...string) string {
 	return s[1]
 }
 
-func functionWithVarArgsOutParameter(in string, out ...*string) {
-	*out[0] = in
-}
-
 func functionWithSliceOfStructsParameter(s []A) string {
 	return s[1].f
 }
@@ -42,12 +38,6 @@ func main() {
 	sink(functionWithVarArgsParameter(sSlice...)) // $ hasValueFlow="call to functionWithVarArgsParameter"
 	sink(functionWithVarArgsParameter(s0, s1))    // $ hasValueFlow="call to functionWithVarArgsParameter"
 
-	var out1 *string
-	var out2 *string
-	functionWithVarArgsOutParameter(source(), out1, out2)
-	sink(out1) // $ MISSING: hasValueFlow="out1"
-	sink(out2) // $ MISSING: hasValueFlow="out2"
-
 	sliceOfStructs := []A{{f: source()}}
 	sink(sliceOfStructs[0].f) // $ hasValueFlow="selection of f"
 

go/ql/test/library-tests/semmle/go/dataflow/VarArgsWithExternalFlow/Flows.expected

@@ -1,2 +0,0 @@
-invalidModelRow
-testFailures

go/ql/test/library-tests/semmle/go/dataflow/VarArgsWithExternalFlow/Flows.ext.yml

@@ -1,21 +0,0 @@
-extensions:
-  - addsTo:
-      pack: codeql/go-all
-      extensible: summaryModel
-    data:
-      - ["github.com/nonexistent/test", "", False, "FunctionWithParameter", "", "", "Argument[0]", "ReturnValue", "value", "manual"]
-      - ["github.com/nonexistent/test", "", False, "FunctionWithSliceParameter", "", "", "Argument[0].ArrayElement", "ReturnValue", "value", "manual"]
-      - ["github.com/nonexistent/test", "", False, "FunctionWithVarArgsParameter", "", "", "Argument[0].ArrayElement", "ReturnValue", "value", "manual"]
-      - ["github.com/nonexistent/test", "", False, "FunctionWithVarArgsOutParameter", "", "", "Argument[0]", "Argument[1].ArrayElement", "value", "manual"]
-      - ["github.com/nonexistent/test", "", False, "FunctionWithSliceOfStructsParameter", "", "", "Argument[0].ArrayElement.Field[github.com/nonexistent/test.A.Field]", "ReturnValue", "value", "manual"]
-      - ["github.com/nonexistent/test", "", False, "FunctionWithVarArgsOfStructsParameter", "", "", "Argument[0].ArrayElement.Field[github.com/nonexistent/test.A.Field]", "ReturnValue", "value", "manual"]
-  - addsTo:
-      pack: codeql/go-all
-      extensible: sourceModel
-    data:
-      - ["github.com/nonexistent/test", "", False, "VariadicSource", "", "", "Argument[0]", "qltest", "manual"]
-  - addsTo:
-      pack: codeql/go-all
-      extensible: sinkModel
-    data:
-      - ["github.com/nonexistent/test", "", False, "VariadicSink", "", "", "Argument[0]", "qltest", "manual"]

go/ql/test/library-tests/semmle/go/dataflow/VarArgsWithExternalFlow/Flows.ql

@@ -1,22 +0,0 @@
-import go
-import semmle.go.dataflow.ExternalFlow
-import ModelValidation
-import utils.test.InlineFlowTest
-
-module Config implements DataFlow::ConfigSig {
-  predicate isSource(DataFlow::Node source) {
-    sourceNode(source, "qltest")
-    or
-    exists(Function fn | fn.hasQualifiedName(_, ["source", "taint"]) |
-      source = fn.getACall().getResult()
-    )
-  }
-
-  predicate isSink(DataFlow::Node sink) {
-    sinkNode(sink, "qltest")
-    or
-    exists(Function fn | fn.hasQualifiedName(_, "sink") | sink = fn.getACall().getAnArgument())
-  }
-}
-
-import FlowTest<Config, Config>

go/ql/test/library-tests/semmle/go/dataflow/VarArgsWithExternalFlow/go.mod

@@ -1,5 +0,0 @@
-module semmle.go.Packages
-
-go 1.25
-
-require github.com/nonexistent/test v0.0.0-20200203000000-0000000000000

go/ql/test/library-tests/semmle/go/dataflow/VarArgsWithExternalFlow/main.go

@@ -1,56 +0,0 @@
-package main
-
-import (
-	"github.com/nonexistent/test"
-)
-
-func source() string {
-	return "untrusted data"
-}
-
-func sink(any) {
-}
-
-func main() {
-	s := source()
-	sink(test.FunctionWithParameter(s)) // $ hasValueFlow="call to FunctionWithParameter"
-
-	stringSlice := []string{source()}
-	sink(stringSlice[0]) // $ hasValueFlow="index expression"
-
-	s0 := ""
-	s1 := source()
-	sSlice := []string{s0, s1}
-	sink(test.FunctionWithParameter(sSlice[1]))        // $ hasValueFlow="call to FunctionWithParameter"
-	sink(test.FunctionWithSliceParameter(sSlice))      // $ hasValueFlow="call to FunctionWithSliceParameter"
-	sink(test.FunctionWithVarArgsParameter(sSlice...)) // $ hasValueFlow="call to FunctionWithVarArgsParameter"
-	sink(test.FunctionWithVarArgsParameter(s0, s1))    // $ hasValueFlow="call to FunctionWithVarArgsParameter"
-
-	var out1 *string
-	var out2 *string
-	test.FunctionWithVarArgsOutParameter(source(), out1, out2)
-	sink(out1) // $ MISSING: hasValueFlow="out1"
-	sink(out2) // $ MISSING: hasValueFlow="out2"
-
-	sliceOfStructs := []test.A{{Field: source()}}
-	sink(sliceOfStructs[0].Field) // $ hasValueFlow="selection of Field"
-
-	a0 := test.A{Field: ""}
-	a1 := test.A{Field: source()}
-	aSlice := []test.A{a0, a1}
-	sink(test.FunctionWithSliceOfStructsParameter(aSlice))      // $ hasValueFlow="call to FunctionWithSliceOfStructsParameter"
-	sink(test.FunctionWithVarArgsOfStructsParameter(aSlice...)) // $ hasValueFlow="call to FunctionWithVarArgsOfStructsParameter"
-	sink(test.FunctionWithVarArgsOfStructsParameter(a0, a1))    // $ hasValueFlow="call to FunctionWithVarArgsOfStructsParameter"
-
-	var variadicSource string
-	test.VariadicSource(&variadicSource)
-	sink(variadicSource)  // $ MISSING: hasTaintFlow="variadicSource"
-	sink(&variadicSource) // $ MISSING: hasTaintFlow="&..."
-
-	var variadicSourcePtr *string
-	test.VariadicSource(variadicSourcePtr)
-	sink(variadicSourcePtr)  // $ MISSING: hasTaintFlow="variadicSourcePtr"
-	sink(*variadicSourcePtr) // $ MISSING: hasTaintFlow="star expression"
-
-	test.VariadicSink(source()) // $ hasTaintFlow="[]type{args}"
-}

go/ql/test/library-tests/semmle/go/dataflow/VarArgsWithExternalFlow/vendor/github.com/nonexistent/test/stub.go

@@ -1,32 +0,0 @@
-package test
-
-type A struct {
-	Field string
-}
-
-func FunctionWithParameter(s string) string {
-	return ""
-}
-
-func FunctionWithSliceParameter(s []string) string {
-	return ""
-}
-
-func FunctionWithVarArgsParameter(s ...string) string {
-	return ""
-}
-
-func FunctionWithVarArgsOutParameter(in string, out ...*string) {
-}
-
-func FunctionWithSliceOfStructsParameter(s []A) string {
-	return ""
-}
-
-func FunctionWithVarArgsOfStructsParameter(s ...A) string {
-	return ""
-}
-
-func VariadicSource(s ...*string) {}
-
-func VariadicSink(s ...string) {}

go/ql/test/library-tests/semmle/go/dataflow/VarArgsWithExternalFlow/vendor/modules.txt

@@ -1,3 +0,0 @@
-# github.com/nonexistent/test v0.0.0-20200203000000-0000000000000
-## explicit
-github.com/nonexistent/test

go/ql/test/library-tests/semmle/go/dataflow/VarArgsWithFunctionModels/Flows.ql

@@ -20,9 +20,6 @@ class SummaryModelTest extends DataFlow::FunctionModel {
     this.hasQualifiedName("github.com/nonexistent/test", "FunctionWithVarArgsParameter") and
     (inp.isParameter(_) and outp.isResult())
     or
-    this.hasQualifiedName("github.com/nonexistent/test", "FunctionWithVarArgsOutParameter") and
-    (inp.isParameter(0) and outp.isParameter(any(int i | i >= 1)))
-    or
     this.hasQualifiedName("github.com/nonexistent/test", "FunctionWithSliceOfStructsParameter") and
     (inp.isParameter(0) and outp.isResult())
     or

go/ql/test/library-tests/semmle/go/dataflow/VarArgsWithFunctionModels/go.mod

@@ -1,5 +1,5 @@
 module semmle.go.Packages
 
-go 1.25
+go 1.17
 
 require github.com/nonexistent/test v0.0.0-20200203000000-0000000000000

go/ql/test/library-tests/semmle/go/dataflow/VarArgsWithFunctionModels/main.go

@@ -8,7 +8,7 @@ func source() string {
 	return "untrusted data"
 }
 
-func sink(any) {
+func sink(string) {
 }
 
 func main() {
@@ -24,14 +24,7 @@ func main() {
 	sink(test.FunctionWithParameter(sSlice[1]))        // $ hasValueFlow="call to FunctionWithParameter"
 	sink(test.FunctionWithSliceParameter(sSlice))      // $ hasTaintFlow="call to FunctionWithSliceParameter" MISSING: hasValueFlow="call to FunctionWithSliceParameter"
 	sink(test.FunctionWithVarArgsParameter(sSlice...)) // $ hasTaintFlow="call to FunctionWithVarArgsParameter" MISSING: hasValueFlow="call to FunctionWithVarArgsParameter"
-	randomFunctionWithMoreThanOneParameter(1, 2, 3, 4, 5) // This is needed to make the next line pass, because we need to have seen a call to a function with at least 2 parameters for ParameterInput to exist with index 1.
+	sink(test.FunctionWithVarArgsParameter(s0, s1))    // $ MISSING: hasValueFlow="call to FunctionWithVarArgsParameter"
-	sink(test.FunctionWithVarArgsParameter(s0, s1))       // $ hasValueFlow="call to FunctionWithVarArgsParameter"
-
-	var out1 *string
-	var out2 *string
-	test.FunctionWithVarArgsOutParameter(source(), out1, out2)
-	sink(out1) // $ hasValueFlow="out1"
-	sink(out2) // $ hasValueFlow="out2"
 
 	sliceOfStructs := []test.A{{Field: source()}}
 	sink(sliceOfStructs[0].Field) // $ hasValueFlow="selection of Field"
@@ -44,6 +37,3 @@ func main() {
 	sink(test.FunctionWithVarArgsOfStructsParameter(aSlice...)) // $ MISSING: hasValueFlow="call to FunctionWithVarArgsOfStructsParameter"
 	sink(test.FunctionWithVarArgsOfStructsParameter(a0, a1))    // $ MISSING: hasValueFlow="call to FunctionWithVarArgsOfStructsParameter"
 }
-
-func randomFunctionWithMoreThanOneParameter(i1, i2, i3, i4, i5 int) {
-}

go/ql/test/library-tests/semmle/go/dataflow/VarArgsWithFunctionModels/vendor/github.com/nonexistent/test/stub.go

@@ -16,9 +16,6 @@ func FunctionWithVarArgsParameter(s ...string) string {
 	return ""
 }
 
-func FunctionWithVarArgsOutParameter(in string, out ...*string) {
-}
-
 func FunctionWithSliceOfStructsParameter(s []A) string {
 	return ""
 }

java/documentation/library-coverage/coverage.csv

@@ -194,7 +194,7 @@ org.apache.hc.core5.http,73,2,45,,,,,,,,,,,,,1,,,,,,,,,,,,,,,,,,,,,72,,,,,,,,,,,
 org.apache.hc.core5.net,,,18,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,18,
 org.apache.hc.core5.util,,,24,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,18,6
 org.apache.hive.hcatalog.templeton,1,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,1,,,,,,,,,,,,,,,,
-org.apache.http,53,3,117,,,,,,,,,,,,,2,,,,,,,,,,,,,,,,,,,,,51,,,,,,,,,,,,,,,,3,108,9
+org.apache.http,48,3,95,,,,,,,,,,,,,2,,,,,,,,,,,,,,,,,,,,,46,,,,,,,,,,,,,,,,3,86,9
 org.apache.ibatis.jdbc,6,,57,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,6,,,,,,,,,,,,,,,57,
 org.apache.ibatis.mapping,,,1,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,1,
 org.apache.log4j,11,,,,,,,,,,,,,,,,,,,,,,11,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,

java/documentation/library-coverage/coverage.rst

@@ -13,7 +13,7 @@ Java framework & library support
    `Apache Commons IO <https://commons.apache.org/proper/commons-io/>`_,``org.apache.commons.io``,,570,124,105,,,,,15
    `Apache Commons Lang <https://commons.apache.org/proper/commons-lang/>`_,``org.apache.commons.lang3``,,425,7,,,,,,
    `Apache Commons Text <https://commons.apache.org/proper/commons-text/>`_,``org.apache.commons.text``,,272,,,,,,,
-   `Apache HttpComponents <https://hc.apache.org/>`_,"``org.apache.hc.core5.*``, ``org.apache.http``",5,205,127,,3,,,,124
+   `Apache HttpComponents <https://hc.apache.org/>`_,"``org.apache.hc.core5.*``, ``org.apache.http``",5,183,122,,3,,,,119
    `Apache Log4j 2 <https://logging.apache.org/log4j/2.0/>`_,``org.apache.logging.log4j``,,8,359,,,,,,
    `Apache Struts <https://struts.apache.org/>`_,"``org.apache.struts2``, ``org.apache.struts.beanvalidation.validation.interceptor``",,3877,14,,,,,,
    `Apache Velocity <https://velocity.apache.org/>`_,"``org.apache.velocity.app``, ``org.apache.velocity.runtime``",,,8,,,,,,
@@ -41,5 +41,5 @@ Java framework & library support
    `Thymeleaf <https://www.thymeleaf.org/>`_,``org.thymeleaf``,,2,2,,,,,,
    `jOOQ <https://www.jooq.org/>`_,``org.jooq``,,,1,,,1,,,
    Others,"``actions.osgi``, ``antlr``, ``ch.ethz.ssh2``, ``cn.hutool.core.codec``, ``com.alibaba.com.caucho.hessian.io``, ``com.alibaba.druid.sql``, ``com.alibaba.fastjson2``, ``com.amazonaws.auth``, ``com.auth0.jwt.algorithms``, ``com.azure.identity``, ``com.caucho.burlap.io``, ``com.caucho.hessian.io``, ``com.cedarsoftware.util.io``, ``com.esotericsoftware.kryo.io``, ``com.esotericsoftware.kryo5.io``, ``com.esotericsoftware.yamlbeans``, ``com.hubspot.jinjava``, ``com.jcraft.jsch``, ``com.microsoft.sqlserver.jdbc``, ``com.mitchellbosecke.pebble``, ``com.opensymphony.xwork2``, ``com.sshtools.j2ssh.authentication``, ``com.sun.crypto.provider``, ``com.sun.jndi.ldap``, ``com.sun.net.httpserver``, ``com.sun.net.ssl``, ``com.sun.rowset``, ``com.sun.security.auth.module``, ``com.sun.security.ntlm``, ``com.sun.security.sasl.digest``, ``com.thoughtworks.xstream``, ``com.trilead.ssh2``, ``com.unboundid.ldap.sdk``, ``com.zaxxer.hikari``, ``flexjson``, ``hudson``, ``io.jsonwebtoken``, ``io.undertow.server.handlers.resource``, ``javafx.scene.web``, ``jenkins``, ``jodd.json``, ``liquibase.database.jvm``, ``liquibase.statement.core``, ``net.lingala.zip4j``, ``net.schmizz.sshj``, ``net.sf.json``, ``net.sf.saxon.s9api``, ``ognl``, ``org.acegisecurity``, ``org.antlr.runtime``, ``org.apache.avro``, ``org.apache.commons.codec``, ``org.apache.commons.compress.archivers.tar``, ``org.apache.commons.exec``, ``org.apache.commons.fileupload``, ``org.apache.commons.httpclient.util``, ``org.apache.commons.jelly``, ``org.apache.commons.jexl2``, ``org.apache.commons.jexl3``, ``org.apache.commons.lang``, ``org.apache.commons.logging``, ``org.apache.commons.net``, ``org.apache.commons.ognl``, ``org.apache.cxf.catalog``, ``org.apache.cxf.common.classloader``, ``org.apache.cxf.common.jaxb``, ``org.apache.cxf.common.logging``, ``org.apache.cxf.configuration.jsse``, ``org.apache.cxf.helpers``, ``org.apache.cxf.resource``, ``org.apache.cxf.staxutils``, ``org.apache.cxf.tools.corba.utils``, ``org.apache.cxf.tools.util``, ``org.apache.cxf.transform``, ``org.apache.directory.ldap.client.api``, ``org.apache.hadoop.fs``, ``org.apache.hadoop.hive.metastore``, ``org.apache.hadoop.hive.ql.exec``, ``org.apache.hadoop.hive.ql.metadata``, ``org.apache.hc.client5.http.async.methods``, ``org.apache.hc.client5.http.classic.methods``, ``org.apache.hc.client5.http.fluent``, ``org.apache.hive.hcatalog.templeton``, ``org.apache.ibatis.jdbc``, ``org.apache.ibatis.mapping``, ``org.apache.log4j``, ``org.apache.shiro.authc``, ``org.apache.shiro.codec``, ``org.apache.shiro.jndi``, ``org.apache.shiro.mgt``, ``org.apache.sshd.client.session``, ``org.apache.tools.ant``, ``org.apache.tools.zip``, ``org.codehaus.cargo.container.installer``, ``org.dom4j``, ``org.exolab.castor.xml``, ``org.fusesource.leveldbjni``, ``org.geogebra.web.full.main``, ``org.gradle.api.file``, ``org.ho.yaml``, ``org.influxdb``, ``org.jabsorb``, ``org.jboss.vfs``, ``org.jdbi.v3.core``, ``org.jenkins.ui.icon``, ``org.jenkins.ui.symbol``, ``org.keycloak.models.map.storage``, ``org.kohsuke.stapler``, ``org.lastaflute.web``, ``org.mvel2``, ``org.openjdk.jmh.runner.options``, ``org.owasp.esapi``, ``org.pac4j.jwt.config.encryption``, ``org.pac4j.jwt.config.signature``, ``org.scijava.log``, ``org.xml.sax``, ``org.xmlpull.v1``, ``play.libs.ws``, ``play.mvc``, ``ratpack.core.form``, ``ratpack.core.handling``, ``ratpack.core.http``, ``ratpack.exec``, ``ratpack.form``, ``ratpack.func``, ``ratpack.handling``, ``ratpack.http``, ``ratpack.util``, ``software.amazon.awssdk.transfer.s3.model``, ``sun.jvmstat.perfdata.monitor.protocol.local``, ``sun.jvmstat.perfdata.monitor.protocol.rmi``, ``sun.misc``, ``sun.net.ftp``, ``sun.net.www.protocol.http``, ``sun.security.acl``, ``sun.security.jgss.krb5``, ``sun.security.krb5``, ``sun.security.pkcs``, ``sun.security.pkcs11``, ``sun.security.provider``, ``sun.security.ssl``, ``sun.security.x509``, ``sun.tools.jconsole``",127,6034,775,148,6,14,18,,186
-   Totals,,382,26403,2707,421,16,137,33,1,415
+   Totals,,382,26381,2702,421,16,137,33,1,410
 

java/ql/lib/change-notes/2026-05-07-apache-httpclient-ssrf-sinks.md

@@ -1,4 +0,0 @@
----
-category: minorAnalysis
----
-* Improved modeling of Apache HttpClient `execute` method sinks for `java/ssrf` and `java/non-https-url`.

java/ql/lib/ext/org.apache.http.client.methods.model.yml

@@ -11,7 +11,7 @@ extensions:
       - ["org.apache.http.client.methods", "HttpPost", False, "HttpPost", "", "", "Argument[0]", "request-forgery", "manual"]
       - ["org.apache.http.client.methods", "HttpPut", False, "HttpPut", "", "", "Argument[0]", "request-forgery", "manual"]
       - ["org.apache.http.client.methods", "HttpRequestBase", True, "setURI", "", "", "Argument[0]", "request-forgery", "manual"]
-      - ["org.apache.http.client.methods", "HttpRequestWrapper", True, "setURI", "(URI)", "", "Argument[0]", "request-forgery", "ai-manual"]
+      - ["org.apache.http.client.methods", "HttpRequestWrapper", True, "setURI", "(URI)", "", "Argument[0]", "request-forgery", "hq-manual"]
       - ["org.apache.http.client.methods", "HttpTrace", False, "HttpTrace", "", "", "Argument[0]", "request-forgery", "manual"]
       - ["org.apache.http.client.methods", "RequestBuilder", False, "delete", "", "", "Argument[0]", "request-forgery", "manual"]
       - ["org.apache.http.client.methods", "RequestBuilder", False, "get", "", "", "Argument[0]", "request-forgery", "manual"]
@@ -22,29 +22,3 @@ extensions:
       - ["org.apache.http.client.methods", "RequestBuilder", False, "put", "", "", "Argument[0]", "request-forgery", "manual"]
       - ["org.apache.http.client.methods", "RequestBuilder", False, "setUri", "", "", "Argument[0]", "request-forgery", "manual"]
       - ["org.apache.http.client.methods", "RequestBuilder", False, "trace", "", "", "Argument[0]", "request-forgery", "manual"]
-  - addsTo:
-      pack: codeql/java-all
-      extensible: summaryModel
-    data:
-      - ["org.apache.http.client.methods", "RequestBuilder", True, "build", "()", "", "Argument[this]", "ReturnValue", "taint", "ai-manual"]
-      - ["org.apache.http.client.methods", "RequestBuilder", True, "delete", "(String)", "", "Argument[0]", "ReturnValue", "taint", "ai-manual"]
-      - ["org.apache.http.client.methods", "RequestBuilder", True, "delete", "(URI)", "", "Argument[0]", "ReturnValue", "taint", "ai-manual"]
-      - ["org.apache.http.client.methods", "RequestBuilder", True, "get", "(String)", "", "Argument[0]", "ReturnValue", "taint", "ai-manual"]
-      - ["org.apache.http.client.methods", "RequestBuilder", True, "get", "(URI)", "", "Argument[0]", "ReturnValue", "taint", "ai-manual"]
-      - ["org.apache.http.client.methods", "RequestBuilder", True, "getUri", "()", "", "Argument[this]", "ReturnValue", "taint", "ai-manual"]
-      - ["org.apache.http.client.methods", "RequestBuilder", True, "head", "(String)", "", "Argument[0]", "ReturnValue", "taint", "ai-manual"]
-      - ["org.apache.http.client.methods", "RequestBuilder", True, "head", "(URI)", "", "Argument[0]", "ReturnValue", "taint", "ai-manual"]
-      - ["org.apache.http.client.methods", "RequestBuilder", True, "options", "(String)", "", "Argument[0]", "ReturnValue", "taint", "ai-manual"]
-      - ["org.apache.http.client.methods", "RequestBuilder", True, "options", "(URI)", "", "Argument[0]", "ReturnValue", "taint", "ai-manual"]
-      - ["org.apache.http.client.methods", "RequestBuilder", True, "patch", "(String)", "", "Argument[0]", "ReturnValue", "taint", "ai-manual"]
-      - ["org.apache.http.client.methods", "RequestBuilder", True, "patch", "(URI)", "", "Argument[0]", "ReturnValue", "taint", "ai-manual"]
-      - ["org.apache.http.client.methods", "RequestBuilder", True, "post", "(String)", "", "Argument[0]", "ReturnValue", "taint", "ai-manual"]
-      - ["org.apache.http.client.methods", "RequestBuilder", True, "post", "(URI)", "", "Argument[0]", "ReturnValue", "taint", "ai-manual"]
-      - ["org.apache.http.client.methods", "RequestBuilder", True, "put", "(String)", "", "Argument[0]", "ReturnValue", "taint", "ai-manual"]
-      - ["org.apache.http.client.methods", "RequestBuilder", True, "put", "(URI)", "", "Argument[0]", "ReturnValue", "taint", "ai-manual"]
-      - ["org.apache.http.client.methods", "RequestBuilder", True, "setUri", "(String)", "", "Argument[0]", "Argument[this]", "taint", "ai-manual"]
-      - ["org.apache.http.client.methods", "RequestBuilder", True, "setUri", "(String)", "", "Argument[0]", "ReturnValue", "taint", "ai-manual"]
-      - ["org.apache.http.client.methods", "RequestBuilder", True, "setUri", "(URI)", "", "Argument[0]", "Argument[this]", "taint", "ai-manual"]
-      - ["org.apache.http.client.methods", "RequestBuilder", True, "setUri", "(URI)", "", "Argument[0]", "ReturnValue", "taint", "ai-manual"]
-      - ["org.apache.http.client.methods", "RequestBuilder", True, "trace", "(String)", "", "Argument[0]", "ReturnValue", "taint", "ai-manual"]
-      - ["org.apache.http.client.methods", "RequestBuilder", True, "trace", "(URI)", "", "Argument[0]", "ReturnValue", "taint", "ai-manual"]

java/ql/lib/ext/org.apache.http.client.model.yml

@@ -3,11 +3,6 @@ extensions:
       pack: codeql/java-all
       extensible: sinkModel
     data:
-      - ["org.apache.http.client", "HttpClient", True, "execute", "(HttpHost,HttpRequest)", "", "Argument[0]", "request-forgery", "ai-manual"]
-      - ["org.apache.http.client", "HttpClient", True, "execute", "(HttpHost,HttpRequest,HttpContext)", "", "Argument[0]", "request-forgery", "ai-manual"]
-      - ["org.apache.http.client", "HttpClient", True, "execute", "(HttpHost,HttpRequest,ResponseHandler)", "", "Argument[0]", "request-forgery", "ai-manual"]
-      - ["org.apache.http.client", "HttpClient", True, "execute", "(HttpHost,HttpRequest,ResponseHandler,HttpContext)", "", "Argument[0]", "request-forgery", "ai-manual"]
-      - ["org.apache.http.client", "HttpClient", True, "execute", "(HttpUriRequest)", "", "Argument[0]", "request-forgery", "ai-manual"]
       - ["org.apache.http.client", "HttpClient", True, "execute", "(HttpUriRequest,HttpContext)", "", "Argument[0]", "request-forgery", "ai-manual"]
-      - ["org.apache.http.client", "HttpClient", True, "execute", "(HttpUriRequest,ResponseHandler)", "", "Argument[0]", "request-forgery", "ai-manual"]
       - ["org.apache.http.client", "HttpClient", True, "execute", "(HttpUriRequest,ResponseHandler,HttpContext)", "", "Argument[0]", "request-forgery", "ai-manual"]
+      - ["org.apache.http.client", "HttpClient", True, "execute", "(HttpUriRequest)", "", "Argument[0]", "request-forgery", "ai-manual"]

java/ql/lib/semmle/code/java/dataflow/Bound.qll

@@ -4,33 +4,67 @@
 overlay[local?]
 module;
 
-private import java as J
+private import internal.rangeanalysis.BoundSpecific
-private import semmle.code.java.dataflow.SSA
-private import semmle.code.java.dataflow.RangeUtils as RU
-private import codeql.rangeanalysis.Bound as SharedBound
 
-private module BoundDefs implements SharedBound::BoundDefinitions<J::Location> {
+private newtype TBound =
-  class SsaVariable extends Ssa::SsaDefinition {
+  TBoundZero() or
-    /** Gets a use of this variable. */
+  TBoundSsa(SsaVariable v) { v.getSourceVariable().getType() instanceof IntegralType } or
-    Expr getAUse() { result = super.getARead() }
+  TBoundExpr(Expr e) {
+    interestingExprBound(e) and
+    not exists(SsaVariable v | e = v.getAUse())
   }
 
-  class SsaSourceVariable = Ssa::SourceVariable;
+/**
+ * A bound that may be inferred for an expression plus/minus an integer delta.
+ */
+abstract class Bound extends TBound {
+  /** Gets a textual representation of this bound. */
+  abstract string toString();
 
-  class Type = J::Type;
+  /** Gets an expression that equals this bound plus `delta`. */
+  abstract Expr getExpr(int delta);
 
-  class Expr = J::Expr;
+  /** Gets an expression that equals this bound. */
+  Expr getExpr() { result = this.getExpr(0) }
 
-  class IntegralType = J::IntegralType;
+  /** Gets the location of this bound. */
-
+  abstract Location getLocation();
-  class ConstantIntegerExpr = RU::ConstantIntegerExpr;
-
-  /** Holds if `e` is a bound expression and it is not an SSA variable read. */
-  predicate interestingExprBound(Expr e) {
-    e.(J::FieldRead).getField() instanceof J::ArrayLengthField
-  }
 }
 
-module BoundImpl = SharedBound::Bound<J::Location, BoundDefs>;
+/**
+ * The bound that corresponds to the integer 0. This is used to represent all
+ * integer bounds as bounds are always accompanied by an added integer delta.
+ */
+class ZeroBound extends Bound, TBoundZero {
+  override string toString() { result = "0" }
 
-import BoundImpl
+  override Expr getExpr(int delta) { result.(ConstantIntegerExpr).getIntValue() = delta }
+
+  override Location getLocation() { result.hasLocationInfo("", 0, 0, 0, 0) }
+}
+
+/**
+ * A bound corresponding to the value of an SSA variable.
+ */
+class SsaBound extends Bound, TBoundSsa {
+  /** Gets the SSA variable that equals this bound. */
+  SsaVariable getSsa() { this = TBoundSsa(result) }
+
+  override string toString() { result = this.getSsa().toString() }
+
+  override Expr getExpr(int delta) { result = this.getSsa().getAUse() and delta = 0 }
+
+  override Location getLocation() { result = this.getSsa().getLocation() }
+}
+
+/**
+ * A bound that corresponds to the value of a specific expression that might be
+ * interesting, but isn't otherwise represented by the value of an SSA variable.
+ */
+class ExprBound extends Bound, TBoundExpr {
+  override string toString() { result = this.getExpr().toString() }
+
+  override Expr getExpr(int delta) { this = TBoundExpr(result) and delta = 0 }
+
+  override Location getLocation() { result = this.getExpr().getLocation() }
+}

java/ql/lib/semmle/code/java/dataflow/internal/rangeanalysis/BoundSpecific.qll

@@ -0,0 +1,27 @@
+/**
+ * Provides Java-specific definitions for bounds.
+ */
+overlay[local?]
+module;
+
+private import java as J
+private import semmle.code.java.dataflow.SSA as Ssa
+private import semmle.code.java.dataflow.RangeUtils as RU
+
+class SsaVariable extends Ssa::SsaDefinition {
+  /** Gets a use of this variable. */
+  Expr getAUse() { result = super.getARead() }
+}
+
+class Expr = J::Expr;
+
+class Location = J::Location;
+
+class IntegralType = J::IntegralType;
+
+class ConstantIntegerExpr = RU::ConstantIntegerExpr;
+
+/** Holds if `e` is a bound expression and it is not an SSA variable read. */
+predicate interestingExprBound(Expr e) {
+  e.(J::FieldRead).getField() instanceof J::ArrayLengthField
+}

java/ql/test/query-tests/security/CWE-918/ApacheHttpClientExecuteSSRF.java

@@ -1,45 +0,0 @@
-import java.io.IOException;
-
-import org.apache.http.HttpHost;
-import org.apache.http.HttpRequest;
-import org.apache.http.client.HttpClient;
-import org.apache.http.client.ResponseHandler;
-import org.apache.http.client.methods.HttpUriRequest;
-import org.apache.http.client.methods.RequestBuilder;
-import org.apache.http.impl.client.HttpClients;
-import org.apache.http.message.BasicHttpRequest;
-import org.apache.http.protocol.HttpContext;
-import javax.servlet.ServletException;
-import javax.servlet.http.HttpServlet;
-import javax.servlet.http.HttpServletRequest;
-import javax.servlet.http.HttpServletResponse;
-
-public class ApacheHttpClientExecuteSSRF extends HttpServlet {
-
-    protected void doGet(HttpServletRequest request, HttpServletResponse response)
-            throws ServletException, IOException {
-        try {
-
-            String source = request.getParameter("host"); // $ Source
-
-            HttpHost host = new HttpHost(source);
-            HttpRequest req = new BasicHttpRequest("GET", "/");
-            HttpUriRequest uriReq = RequestBuilder.get(source).build(); // $ Alert
-            HttpContext context = null;
-            HttpClient client = HttpClients.createDefault();
-            ResponseHandler<Object> handler = null;
-
-            client.execute(host, req); // $ Alert
-            client.execute(host, req, context); // $ Alert
-            client.execute(host, req, handler); // $ Alert
-            client.execute(host, req, handler, context); // $ Alert
-            client.execute(uriReq); // $ Alert
-            client.execute(uriReq, context); // $ Alert
-            client.execute(uriReq, handler); // $ Alert
-            client.execute(uriReq, handler, context); // $ Alert
-
-        } catch (Exception e) {
-            // TODO: handle exception
-        }
-    }
-}

java/ql/test/query-tests/security/CWE-918/options

@@ -1 +1 @@
-//semmle-extractor-options: --javac-args -source 11 -target 11 -cp ${testdir}/../../../stubs/javax-validation-constraints:${testdir}/../../../stubs/springframework-5.8.x:${testdir}/../../../stubs/javax-ws-rs-api-2.1.1:${testdir}/../../../stubs/javax-ws-rs-api-3.0.0:${testdir}/../../../stubs/apache-http-4.4.13/:${testdir}/../../../stubs/apache-http-client-4.4.13:${testdir}/../../../stubs/projectreactor-3.4.3/:${testdir}/../../../stubs/postgresql-42.3.3/:${testdir}/../../../stubs/HikariCP-3.4.5/:${testdir}/../../../stubs/spring-jdbc-5.3.8/:${testdir}/../../../stubs/jdbi3-core-3.27.2/:${testdir}/../../../stubs/cargo:${testdir}/../../../stubs/javafx-web:${testdir}/../../../stubs/apache-commons-jelly-1.0.1:${testdir}/../../../stubs/dom4j-2.1.1:${testdir}/../../../stubs/jaxen-1.2.0:${testdir}/../../../stubs/stapler-1.263:${testdir}/../../../stubs/javax-servlet-2.5:${testdir}/../../../stubs/apache-commons-fileupload-1.4:${testdir}/../../../stubs/saxon-xqj-9.x:${testdir}/../../../stubs/apache-commons-beanutils:${testdir}/../../../stubs/apache-commons-lang:${testdir}/../../../stubs/apache-http-5:${testdir}/../../../stubs/playframework-2.6.x:${testdir}/../../../stubs/jaxws-api-2.0:${testdir}/../../../stubs/apache-cxf
+//semmle-extractor-options: --javac-args -source 11 -target 11 -cp ${testdir}/../../../stubs/javax-validation-constraints:${testdir}/../../../stubs/springframework-5.8.x:${testdir}/../../../stubs/javax-ws-rs-api-2.1.1:${testdir}/../../../stubs/javax-ws-rs-api-3.0.0:${testdir}/../../../stubs/apache-http-4.4.13/:${testdir}/../../../stubs/projectreactor-3.4.3/:${testdir}/../../../stubs/postgresql-42.3.3/:${testdir}/../../../stubs/HikariCP-3.4.5/:${testdir}/../../../stubs/spring-jdbc-5.3.8/:${testdir}/../../../stubs/jdbi3-core-3.27.2/:${testdir}/../../../stubs/cargo:${testdir}/../../../stubs/javafx-web:${testdir}/../../../stubs/apache-commons-jelly-1.0.1:${testdir}/../../../stubs/dom4j-2.1.1:${testdir}/../../../stubs/jaxen-1.2.0:${testdir}/../../../stubs/stapler-1.263:${testdir}/../../../stubs/javax-servlet-2.5:${testdir}/../../../stubs/apache-commons-fileupload-1.4:${testdir}/../../../stubs/saxon-xqj-9.x:${testdir}/../../../stubs/apache-commons-beanutils:${testdir}/../../../stubs/apache-commons-lang:${testdir}/../../../stubs/apache-http-5:${testdir}/../../../stubs/playframework-2.6.x:${testdir}/../../../stubs/jaxws-api-2.0:${testdir}/../../../stubs/apache-cxf

java/ql/test/stubs/apache-http-client-4.4.13/org/apache/http/client/HttpClient.java

@@ -1,23 +0,0 @@
-// Generated automatically from org.apache.http.client.HttpClient for testing purposes
-
-package org.apache.http.client;
-
-import java.io.IOException;
-import org.apache.http.HttpHost;
-import org.apache.http.HttpRequest;
-import org.apache.http.HttpResponse;
-import org.apache.http.client.methods.HttpUriRequest;
-import org.apache.http.protocol.HttpContext;
-
-public interface HttpClient {
-    HttpResponse execute(HttpHost target, HttpRequest request) throws IOException;
-    HttpResponse execute(HttpHost target, HttpRequest request, HttpContext context) throws IOException;
-    <T> T execute(HttpHost target, HttpRequest request, ResponseHandler<? extends T> responseHandler) throws IOException;
-    <T> T execute(HttpHost target, HttpRequest request, ResponseHandler<? extends T> responseHandler, HttpContext context)
-            throws IOException;
-    HttpResponse execute(HttpUriRequest request) throws IOException;
-    HttpResponse execute(HttpUriRequest request, HttpContext context) throws IOException;
-    <T> T execute(HttpUriRequest request, ResponseHandler<? extends T> responseHandler) throws IOException;
-    <T> T execute(HttpUriRequest request, ResponseHandler<? extends T> responseHandler, HttpContext context)
-            throws IOException;
-}

java/ql/test/stubs/apache-http-client-4.4.13/org/apache/http/client/ResponseHandler.java

@@ -1,9 +0,0 @@
-// Generated automatically from org.apache.http.client.ResponseHandler for testing purposes
-
-package org.apache.http.client;
-
-import org.apache.http.HttpResponse;
-
-public interface ResponseHandler<T> {
-    T handleResponse(HttpResponse response);
-}

java/ql/test/stubs/apache-http-client-4.4.13/org/apache/http/impl/client/CloseableHttpClient.java

@@ -1,7 +0,0 @@
-package org.apache.http.impl.client;
-
-import org.apache.http.client.HttpClient;
-
-public abstract class CloseableHttpClient implements HttpClient {
-
-}

java/ql/test/stubs/apache-http-client-4.4.13/org/apache/http/impl/client/HttpClients.java

@@ -1,10 +0,0 @@
-// Generated automatically from org.apache.http.client.HttpClient for testing purposes
-
-package org.apache.http.impl.client;
-
-import java.io.IOException;
-import org.apache.http.impl.client.CloseableHttpClient;
-
-public final class HttpClients {
-        public static CloseableHttpClient createDefault() { return null; }
-}

javascript/ql/integration-tests/query-suite/not_included_in_qls.expected

@@ -63,7 +63,6 @@ ql/javascript/ql/src/experimental/Security/CWE-347/decodeJwtWithoutVerificationL
 ql/javascript/ql/src/experimental/Security/CWE-444/InsecureHttpParser.ql
 ql/javascript/ql/src/experimental/Security/CWE-522-DecompressionBombs/DecompressionBombs.ql
 ql/javascript/ql/src/experimental/Security/CWE-918/SSRF.ql
-ql/javascript/ql/src/experimental/Security/CWE-918/SsrfIpv6TransitionIncompleteGuard.ql
 ql/javascript/ql/src/experimental/StandardLibrary/MultipleArgumentsToSetConstructor.ql
 ql/javascript/ql/src/experimental/heuristics/ql/src/Security/CWE-020/UntrustedDataToExternalAPI.ql
 ql/javascript/ql/src/experimental/heuristics/ql/src/Security/CWE-078/CommandInjection.ql

javascript/ql/src/change-notes/2026-06-06-ssrf-ipv6-transition-incomplete-guard.md

@@ -1,4 +0,0 @@
----
-category: newQuery
----
-* Added a new experimental query, `javascript/ssrf-ipv6-transition-incomplete-guard`, to detect SSRF host-validation guards that reject private IPv4 ranges but fail to unwrap IPv6-transition forms (IPv4-mapped `::ffff:`, NAT64 `64:ff9b::`, 6to4 `2002::`), allowing the guard to be bypassed by wrapping an internal IPv4 address in a transition literal.

javascript/ql/src/experimental/Security/CWE-918/SsrfIpv6TransitionIncompleteGuard.qhelp

@@ -1,59 +0,0 @@
-<!DOCTYPE qhelp PUBLIC
-  "-//Semmle//qhelp//EN"
-  "qhelp.dtd">
-<qhelp>
-
-<overview>
-    <p>
-        Server-side request forgery (SSRF) guards frequently reject requests to internal
-        addresses by checking the request host against a denylist of private, loopback and
-        cloud-metadata IPv4 ranges. When such a guard inspects only the dotted-quad IPv4 form
-        and never unwraps IPv6-transition representations, it can be bypassed: the host
-        validator classifies the address as public, but the operating system routes the
-        connection to the embedded internal IPv4 endpoint.
-    </p>
-    <p>
-        The affected forms include IPv4-mapped IPv6 (<code>::ffff:169.254.169.254</code>),
-        NAT64 (<code>64:ff9b::a9fe:a9fe</code>) and 6to4 (<code>2002::</code>). A URL such as
-        <code>http://[::ffff:169.254.169.254]/</code> passes a dotted-quad denylist unchanged
-        while still reaching the internal address.
-    </p>
-</overview>
-
-<recommendation>
-    <p>
-        Normalize the host before validating it: parse the address with a transition-aware
-        library and unwrap IPv4-mapped, NAT64 and 6to4 forms to their embedded IPv4 address,
-        then apply the private-range check to the normalized value. Libraries such as
-        <code>ipaddr.js</code> classify these forms correctly via their range API, and
-        SSRF-protection libraries such as <code>request-filtering-agent</code> apply the check
-        after DNS resolution. Validate the resolved address rather than the textual host.
-    </p>
-</recommendation>
-
-<example>
-    <p>
-        The following guard rejects private IPv4 ranges using the <code>private-ip</code>
-        package, which inspects the textual IPv4 form only. An attacker supplies
-        <code>::ffff:169.254.169.254</code>, which the guard classifies as public, but the
-        request still reaches the internal metadata endpoint.
-    </p>
-
-    <sample src="examples/SsrfIpv6TransitionIncompleteGuardBad.js"/>
-
-    <p>
-        The following guard parses the host with a transition-aware classifier, so the
-        embedded internal IPv4 address is detected regardless of the transition form used.
-    </p>
-
-    <sample src="examples/SsrfIpv6TransitionIncompleteGuardGood.js"/>
-</example>
-
-<references>
-
-<li>OWASP: <a href="https://owasp.org/www-community/attacks/Server_Side_Request_Forgery">Server-Side Request Forgery</a>.</li>
-<li>Common Weakness Enumeration: <a href="https://cwe.mitre.org/data/definitions/918.html">CWE-918</a>.</li>
-<li>Common Weakness Enumeration: <a href="https://cwe.mitre.org/data/definitions/1389.html">CWE-1389</a>.</li>
-
-</references>
-</qhelp>

javascript/ql/src/experimental/Security/CWE-918/SsrfIpv6TransitionIncompleteGuard.ql

@@ -1,129 +0,0 @@
-/**
- * @name SSRF host guard does not reject IPv6-transition forms
- * @description An SSRF host guard that rejects private or loopback IPv4 ranges but never
- *              unwraps IPv6-transition forms (IPv4-mapped `::ffff:`, NAT64 `64:ff9b::`,
- *              6to4 `2002::`) can be bypassed by wrapping an internal IPv4 address in a
- *              transition literal, allowing requests to reach internal endpoints.
- * @kind problem
- * @problem.severity warning
- * @id javascript/ssrf-ipv6-transition-incomplete-guard
- * @tags security
- *       experimental
- *       external/cwe/cwe-918
- *       external/cwe/cwe-1389
- */
-
-import javascript
-
-/**
- * Holds if `f` imports a dotted-quad-oriented private-IP guard package whose
- * classification is performed on the textual IPv4 form and therefore returns
- * `false` for an internal address wrapped in an IPv6-transition literal.
- */
-predicate importsHandRolledIpGuard(File f) {
-  exists(DataFlow::SourceNode mod |
-    mod.getFile() = f and
-    mod = DataFlow::moduleImport(["private-ip", "is-ip", "ip", "ip-range-check"])
-  )
-}
-
-/**
- * Holds if `f` contains a call to an `isPrivate`-style host classifier, the
- * common name for a hand-rolled SSRF guard.
- */
-predicate hasIsPrivateCall(File f) {
-  exists(DataFlow::CallNode c |
-    c.getFile() = f and
-    c.getCalleeName().regexpMatch("(?i)^is_?private(ip|address|host)?$")
-  )
-  or
-  exists(DataFlow::MethodCallNode m |
-    m.getFile() = f and
-    m.getMethodName().regexpMatch("(?i)^is_?private(ip|address|host)?$")
-  )
-}
-
-/**
- * Holds if `f` contains a hand-written RFC 1918, loopback or cloud-metadata IPv4
- * literal used as a denylist entry.
- */
-predicate hasRfc1918Literal(File f) {
-  exists(StringLiteral s |
-    s.getFile() = f and
-    s.getValue()
-        .regexpMatch("(?i).*(127\\.0\\.0\\.1|169\\.254\\.169\\.254|10\\.|192\\.168|172\\.1[6-9]|::1|fc00|fd00|metadata\\.google).*")
-  )
-}
-
-/** Holds if `f` carries any hand-rolled, dotted-quad-oriented SSRF guard signal. */
-predicate hasUnsafeGuardSignal(File f) {
-  importsHandRolledIpGuard(f) or
-  hasIsPrivateCall(f) or
-  hasRfc1918Literal(f)
-}
-
-/** Holds if `func` has a name that reads as an SSRF host or URL validator. */
-predicate isSsrfValidatorFunction(Function func) {
-  func.getName()
-      .regexpMatch("(?i).*(validate|check|guard|reject|deny|block|allow|is_?safe|sanitiz)e?_?.*(url|host|ip|address|target|endpoint|webhook|origin).*")
-  or
-  func.getName()
-      .regexpMatch("(?i).*(is_?)?(private|internal|loopback|reserved|external)_?(ip|address|host|url).*")
-  or
-  func.getName().regexpMatch("(?i).*(ssrf|metadata).*")
-}
-
-/**
- * Holds if `f` imports a maturity-hardened, transition-aware address classifier
- * or SSRF-protection library that does unwrap IPv6-transition forms.
- */
-predicate importsSafeClassifier(File f) {
-  exists(DataFlow::SourceNode mod |
-    mod.getFile() = f and
-    mod =
-      DataFlow::moduleImport([
-          "ipaddr.js", "ssrf-req-filter", "request-filtering-agent", "ssrf-agent", "netmask",
-          "ip-cidr", "cidr-matcher", "blocked-at"
-        ])
-  )
-}
-
-/**
- * Holds if `f` already performs an explicit IPv6-transition unwrap or
- * canonicalization, so the guard does see the embedded IPv4 address.
- */
-predicate hasTransitionUnwrap(File f) {
-  exists(StringLiteral s |
-    s.getFile() = f and
-    (
-      s.getValue().matches("%64:ff9b%") or
-      s.getValue().matches("%::ffff%") or
-      s.getValue().matches("%2002:%") or
-      s.getValue().matches("%2001:%")
-    )
-  )
-  or
-  exists(Identifier id |
-    id.getFile() = f and
-    id.getName()
-        .regexpMatch("(?i).*(ipv4mapped|v4mapped|mappedipv4|ipv4inipv6|embeddedipv4|unwrap.*ip|toipv4|canonicaliz|isipv4compat).*")
-  )
-  or
-  exists(DataFlow::MethodCallNode m | m.getFile() = f and m.getMethodName() = ["range", "kind"])
-}
-
-/** Holds if `f` is treated as safe (transition-aware), suppressing the alert. */
-predicate isSafe(File f) { importsSafeClassifier(f) or hasTransitionUnwrap(f) }
-
-from Function guard, File f
-where
-  guard.getFile() = f and
-  isSsrfValidatorFunction(guard) and
-  hasUnsafeGuardSignal(f) and
-  not isSafe(f) and
-  not f.getRelativePath()
-      .regexpMatch("(?i).*/(tests?|specs?|examples?|__tests__|e2e|node_modules)/.*")
-select guard,
-  "This SSRF host guard rejects private IPv4 ranges but never unwraps IPv6-transition forms " +
-    "(IPv4-mapped '::ffff:', NAT64 '64:ff9b::', 6to4 '2002::'); an attacker can wrap an internal " +
-    "IPv4 address in a transition literal to bypass it and reach internal endpoints."

javascript/ql/src/experimental/Security/CWE-918/examples/SsrfIpv6TransitionIncompleteGuardBad.js

@@ -1,14 +0,0 @@
-const isPrivate = require('private-ip');
-const fetch = require('node-fetch');
-
-// BAD: `private-ip` classifies the textual IPv4 form only, so it returns false
-// for `::ffff:169.254.169.254`. The guard treats the wrapped internal address as
-// public, but the request still reaches the metadata endpoint.
-async function validateUrlHost(host) {
-  if (isPrivate(host)) {
-    throw new Error('blocked private host');
-  }
-  return fetch('http://' + host + '/');
-}
-
-module.exports = { validateUrlHost };

javascript/ql/src/experimental/Security/CWE-918/examples/SsrfIpv6TransitionIncompleteGuardGood.js

@@ -1,16 +0,0 @@
-const ipaddr = require('ipaddr.js');
-const fetch = require('node-fetch');
-
-// GOOD: ipaddr.js parses the host and classifies it with `.range()`, which is
-// transition-aware. `::ffff:169.254.169.254` parses as an IPv4-mapped address and
-// is reported in the `linkLocal` range, so the guard is complete.
-async function validateTargetHost(host) {
-  const addr = ipaddr.parse(host);
-  const range = addr.range();
-  if (range === 'private' || range === 'loopback' || range === 'linkLocal') {
-    throw new Error('blocked internal host');
-  }
-  return fetch('http://' + host + '/');
-}
-
-module.exports = { validateTargetHost };

javascript/ql/test/experimental/Security/CWE-918/SsrfIpv6TransitionIncompleteGuard/SsrfIpv6TransitionIncompleteGuard.expected

@@ -1,2 +0,0 @@
-| bad-private-ip-pkg.js:6:1:11:1 | async f ... '/');\\n} | This SSRF host guard rejects private IPv4 ranges but never unwraps IPv6-transition forms (IPv4-mapped '::ffff:', NAT64 '64:ff9b::', 6to4 '2002::'); an attacker can wrap an internal IPv4 address in a transition literal to bypass it and reach internal endpoints. |
-| bad-rfc1918-regex.js:5:1:16:1 | functio ... '/');\\n} | This SSRF host guard rejects private IPv4 ranges but never unwraps IPv6-transition forms (IPv4-mapped '::ffff:', NAT64 '64:ff9b::', 6to4 '2002::'); an attacker can wrap an internal IPv4 address in a transition literal to bypass it and reach internal endpoints. |

javascript/ql/test/experimental/Security/CWE-918/SsrfIpv6TransitionIncompleteGuard/SsrfIpv6TransitionIncompleteGuard.qlref

@@ -1 +0,0 @@
-experimental/Security/CWE-918/SsrfIpv6TransitionIncompleteGuard.ql

javascript/ql/test/experimental/Security/CWE-918/SsrfIpv6TransitionIncompleteGuard/bad-private-ip-pkg.js

@@ -1,13 +0,0 @@
-const isPrivate = require('private-ip');
-const fetch = require('node-fetch');
-
-// BAD: `private-ip` classifies the textual IPv4 form only. It returns false for
-// `::ffff:169.254.169.254`, so a transition-wrapped internal address slips past.
-async function validateUrlHost(host) { // NOT OK
-  if (isPrivate(host)) {
-    throw new Error('blocked private host');
-  }
-  return fetch('http://' + host + '/');
-}
-
-module.exports = { validateUrlHost };

javascript/ql/test/experimental/Security/CWE-918/SsrfIpv6TransitionIncompleteGuard/bad-rfc1918-regex.js

@@ -1,18 +0,0 @@
-const http = require('http');
-
-// BAD: a hand-written RFC 1918 / loopback / metadata denylist matched against the
-// host string. The embedded IPv4 inside `::ffff:10.0.0.1` is never seen.
-function checkTargetHost(host) { // NOT OK
-  if (
-    host === '127.0.0.1' ||
-    host === '169.254.169.254' ||
-    host.startsWith('10.') ||
-    host.startsWith('192.168') ||
-    host.startsWith('172.16')
-  ) {
-    throw new Error('blocked internal host');
-  }
-  return http.get('http://' + host + '/');
-}
-
-module.exports = { checkTargetHost };

javascript/ql/test/experimental/Security/CWE-918/SsrfIpv6TransitionIncompleteGuard/good-explicit-unwrap.js

@@ -1,32 +0,0 @@
-const http = require('http');
-
-const IPV4_MAPPED_PREFIX = '::ffff:';
-
-// OK: this guard uses a hand-rolled denylist, but it first unwraps the
-// IPv6-transition form, so the embedded IPv4 is normalized before the check.
-function unwrapMapped(host) {
-  // strip an IPv4-mapped `::ffff:` prefix down to the embedded dotted quad
-  if (host.toLowerCase().startsWith(IPV4_MAPPED_PREFIX)) {
-    return host.slice(IPV4_MAPPED_PREFIX.length);
-  }
-  return host;
-}
-
-function isPrivateAddress(host) { // OK
-  const h = unwrapMapped(host);
-  return (
-    h === '127.0.0.1' ||
-    h === '169.254.169.254' ||
-    h.startsWith('10.') ||
-    h.startsWith('192.168')
-  );
-}
-
-function validateHost(host) { // OK
-  if (isPrivateAddress(host)) {
-    throw new Error('blocked internal host');
-  }
-  return http.get('http://' + host + '/');
-}
-
-module.exports = { validateHost };

javascript/ql/test/experimental/Security/CWE-918/SsrfIpv6TransitionIncompleteGuard/good-ipaddr.js

@@ -1,16 +0,0 @@
-const ipaddr = require('ipaddr.js');
-const fetch = require('node-fetch');
-
-// OK: ipaddr.js parses the address and classifies it with `.range()`, which is
-// transition-aware. `::ffff:10.0.0.1` parses as an IPv4-mapped address and is
-// reported in the `private` range, so the guard is complete.
-async function validateTargetHost(host) { // OK
-  const addr = ipaddr.parse(host);
-  const range = addr.range();
-  if (range === 'private' || range === 'loopback' || range === 'linkLocal') {
-    throw new Error('blocked internal host');
-  }
-  return fetch('http://' + host + '/');
-}
-
-module.exports = { validateTargetHost };

javascript/resources/codeql-extractor.yml

@@ -21,19 +21,13 @@ file_coverage_languages:
     scc_languages:
       - TypeScript
       - TypeScript Typings
-  - name: vue
-    display_name: Vue.js component
-    scc_languages:
-      - Vue
 github_api_languages:
   - JavaScript
   - TypeScript
-  - Vue
 scc_languages:
   - JavaScript
   - TypeScript
   - TypeScript Typings
-  - Vue
 file_types:
   - name: javascript
     display_name: JavaScript

python/ql/consistency-queries/CfgConsistency.ql

@@ -0,0 +1,2 @@
+import semmle.python.controlflow.internal.AstNodeImpl
+import ControlFlow::Consistency

python/ql/consistency-queries/DataFlowConsistency.ql

@@ -36,8 +36,6 @@ private module Input implements InputSig<Location, PythonDataFlow> {
     // parameter, but dataflow-consistency queries should _not_ complain about there not
     // being a post-update node for the synthetic `**kwargs` parameter.
     n instanceof SynthDictSplatParameterNode
-    or
-    Private::Conversions::readStep(n, _, _)
   }
 
   predicate uniqueParameterNodePositionExclude(DataFlowCallable c, ParameterPosition pos, Node p) {

python/ql/lib/LegacyPointsTo.qll

@@ -213,9 +213,11 @@ class ExprWithPointsTo extends Expr {
    * Gets what this expression might "refer-to" in the given `context`.
    */
   predicate refersTo(Context context, Object obj, ClassObject cls, AstNode origin) {
-    this.getAFlowNode()
+    exists(ControlFlowNode this_, ControlFlowNode origin_ |
-        .(ControlFlowNodeWithPointsTo)
+      this_.getNode() = this and origin_.getNode() = origin
-        .refersTo(context, obj, cls, origin.getAFlowNode())
+    |
+      this_.(ControlFlowNodeWithPointsTo).refersTo(context, obj, cls, origin_)
+    )
   }
 
   /**
@@ -226,7 +228,11 @@ class ExprWithPointsTo extends Expr {
    */
   pragma[nomagic]
   predicate refersTo(Object obj, AstNode origin) {
-    this.getAFlowNode().(ControlFlowNodeWithPointsTo).refersTo(obj, origin.getAFlowNode())
+    exists(ControlFlowNode this_, ControlFlowNode origin_ |
+      this_.getNode() = this and origin_.getNode() = origin
+    |
+      this_.(ControlFlowNodeWithPointsTo).refersTo(obj, origin_)
+    )
   }
 
   /**
@@ -240,16 +246,22 @@ class ExprWithPointsTo extends Expr {
    * in the given `context`.
    */
   predicate pointsTo(Context context, Value value, AstNode origin) {
-    this.getAFlowNode()
+    exists(ControlFlowNode this_, ControlFlowNode origin_ |
-        .(ControlFlowNodeWithPointsTo)
+      this_.getNode() = this and origin_.getNode() = origin
-        .pointsTo(context, value, origin.getAFlowNode())
+    |
+      this_.(ControlFlowNodeWithPointsTo).pointsTo(context, value, origin_)
+    )
   }
 
   /**
    * Holds if this expression might "point-to" to `value` which is from `origin`.
    */
   predicate pointsTo(Value value, AstNode origin) {
-    this.getAFlowNode().(ControlFlowNodeWithPointsTo).pointsTo(value, origin.getAFlowNode())
+    exists(ControlFlowNode this_, ControlFlowNode origin_ |
+      this_.getNode() = this and origin_.getNode() = origin
+    |
+      this_.(ControlFlowNodeWithPointsTo).pointsTo(value, origin_)
+    )
   }
 
   /**
@@ -475,7 +487,10 @@ class FunctionMetricsWithPointsTo extends FunctionMetrics {
     not non_coupling_method(result) and
     exists(Call call | call.getScope() = this |
       exists(FunctionObject callee | callee.getFunction() = result |
-        call.getAFlowNode().getFunction().(ControlFlowNodeWithPointsTo).refersTo(callee)
+        exists(CallNode call_ |
+          call_.getNode() = call and
+          call_.getFunction().(ControlFlowNodeWithPointsTo).refersTo(callee)
+        )
       )
       or
       exists(Attribute a | call.getFunc() = a |

python/ql/lib/analysis/DefinitionTracking.qll

@@ -64,7 +64,7 @@ private predicate jump_to_defn(ControlFlowNode use, Definition defn) {
 private predicate preferred_jump_to_defn(Expr use, Definition def) {
   not use instanceof ClassExpr and
   not use instanceof FunctionExpr and
-  jump_to_defn(use.getAFlowNode(), def)
+  exists(ControlFlowNode useNode | useNode.getNode() = use | jump_to_defn(useNode, def))
 }
 
 private predicate unique_jump_to_defn(Expr use, Definition def) {
@@ -452,7 +452,7 @@ private predicate self_parameter_jump_to_defn_attribute(
  * This exists primarily for testing use `getPreferredDefinition()` instead.
  */
 Definition getADefinition(Expr use) {
-  jump_to_defn(use.getAFlowNode(), result) and
+  exists(ControlFlowNode useNode | useNode.getNode() = use | jump_to_defn(useNode, result)) and
   not use instanceof Call and
   not use.isArtificial() and
   // Not the use itself

python/ql/lib/change-notes/2026-05-19-add-shared-cfg.md

@@ -0,0 +1,4 @@
+---
+category: minorAnalysis
+---
+* A new Python control flow graph implementation has been added under `semmle.python.controlflow.internal.Cfg` (backed by `AstNodeImpl.qll`), built on the shared `codeql.controlflow.ControlFlowGraph` library. It is not yet used by the dataflow library or any production query; the legacy CFG in `semmle/python/Flow.qll` remains the default. The new library is exposed for tests and for upcoming migrations.

python/ql/lib/change-notes/2026-05-19-deprecate-getAFlowNode.md

@@ -0,0 +1,5 @@
+---
+category: deprecated
+---
+* The `AstNode.getAFlowNode()` predicate has been deprecated. Use `ControlFlowNode.getNode()` from the other direction instead: replace `e.getAFlowNode() = n` with `n.getNode() = e`. This is a preparatory step towards migrating the dataflow library off the legacy CFG; it has no semantic effect.
+

python/ql/lib/change-notes/2026-05-28-remove-imprecise-containter-steps.md

@@ -1,4 +0,0 @@
----
-category: minorAnalysis
----
-* Python taint tracking is now more precise for values flowing through container contents, such as list, set, tuple, and dictionary elements. This may remove some false positive alerts.

python/ql/lib/change-notes/2026-06-01-deprecate-getAReturnValueFlowNode.md

@@ -0,0 +1,4 @@
+---
+category: deprecated
+---
+* The `Function.getAReturnValueFlowNode()` predicate has been deprecated. Bind a `Return` node explicitly instead — `exists(Return ret | ret.getScope() = f and n.getNode() = ret.getValue())`. This is a preparatory step towards migrating the dataflow library off the legacy CFG; it has no semantic effect.

python/ql/lib/printCfgNew.ql

@@ -0,0 +1,45 @@
+/**
+ * @name Print CFG (New)
+ * @description Produces a representation of a file's Control Flow Graph
+ *              using the new shared control flow library.
+ *              This query is used by the VS Code extension.
+ * @id python/print-cfg
+ * @kind graph
+ * @tags ide-contextual-queries/print-cfg
+ */
+
+private import python as Py
+import semmle.python.controlflow.internal.AstNodeImpl
+
+external string selectedSourceFile();
+
+private predicate selectedSourceFileAlias = selectedSourceFile/0;
+
+external int selectedSourceLine();
+
+private predicate selectedSourceLineAlias = selectedSourceLine/0;
+
+external int selectedSourceColumn();
+
+private predicate selectedSourceColumnAlias = selectedSourceColumn/0;
+
+module ViewCfgQueryInput implements ControlFlow::ViewCfgQueryInputSig<Py::File> {
+  predicate selectedSourceFile = selectedSourceFileAlias/0;
+
+  predicate selectedSourceLine = selectedSourceLineAlias/0;
+
+  predicate selectedSourceColumn = selectedSourceColumnAlias/0;
+
+  predicate cfgScopeSpan(
+    Ast::Callable callable, Py::File file, int startLine, int startColumn, int endLine,
+    int endColumn
+  ) {
+    exists(Py::Scope scope |
+      scope = callable.asScope() and
+      file = scope.getLocation().getFile() and
+      scope.getLocation().hasLocationInfo(_, startLine, startColumn, endLine, endColumn)
+    )
+  }
+}
+
+import ControlFlow::ViewCfgQuery<Py::File, ViewCfgQueryInput>

python/ql/lib/semmle/python/AstExtended.qll

@@ -16,21 +16,26 @@ abstract class AstNode extends AstNode_ {
   /** Gets the scope that this node occurs in */
   abstract Scope getScope();
 
-  /**
-   * Gets a flow node corresponding directly to this node.
-   * NOTE: For some statements and other purely syntactic elements,
-   * there may not be a `ControlFlowNode`
-   */
-  cached
-  ControlFlowNode getAFlowNode() {
-    Stages::AST::ref() and
-    py_flow_bb_node(result, this, _, _)
-  }
-
   /** Gets the location for this AST node */
   cached
   Location getLocation() { none() }
 
+  /**
+   * DEPRECATED: use `ControlFlowNode.getNode()` from the other direction instead;
+   * that is, replace `e.getAFlowNode() = n` with `n.getNode() = e`. This API is
+   * being removed to untangle the AST and CFG hierarchies in preparation for
+   * migrating the dataflow library off the legacy CFG.
+   *
+   * Gets a flow node corresponding directly to this node.
+   * NOTE: For some statements and other purely syntactic elements,
+   * there may not be a `ControlFlowNode`.
+   */
+  cached
+  deprecated ControlFlowNode getAFlowNode() {
+    Stages::AST::ref() and
+    py_flow_bb_node(result, this, _, _)
+  }
+
   /**
    * Whether this syntactic element is artificial, that is it is generated
    * by the compiler and is not present in the source

python/ql/lib/semmle/python/Exprs.qll

@@ -28,7 +28,9 @@ class Expr extends Expr_, AstNode {
   /** Whether this expression may have a side effect (as determined purely from its syntax) */
   predicate hasSideEffects() {
     /* If an exception raised by this expression handled, count that as a side effect */
-    this.getAFlowNode().getASuccessor().getNode() instanceof ExceptStmt
+    exists(ControlFlowNode n | n.getNode() = this |
+      n.getASuccessor().getNode() instanceof ExceptStmt
+    )
     or
     this.getASubExpression().hasSideEffects()
   }
@@ -68,8 +70,6 @@ class Attribute extends Attribute_ {
   /* syntax: Expr.name */
   override Expr getASubExpression() { result = this.getObject() }
 
-  override AttrNode getAFlowNode() { result = super.getAFlowNode() }
-
   /** Gets the name of this attribute. That is the `name` in `obj.name` */
   string getName() { result = Attribute_.super.getAttr() }
 
@@ -96,8 +96,6 @@ class Subscript extends Subscript_ {
   }
 
   Expr getObject() { result = Subscript_.super.getValue() }
-
-  override SubscriptNode getAFlowNode() { result = super.getAFlowNode() }
 }
 
 /** A call expression, such as `func(...)` */
@@ -113,8 +111,6 @@ class Call extends Call_ {
 
   override string toString() { result = this.getFunc().toString() + "()" }
 
-  override CallNode getAFlowNode() { result = super.getAFlowNode() }
-
   /** Gets a tuple (*) argument of this call. */
   Expr getStarargs() { result = this.getAPositionalArg().(Starred).getValue() }
 
@@ -200,8 +196,6 @@ class IfExp extends IfExp_ {
   override Expr getASubExpression() {
     result = this.getTest() or result = this.getBody() or result = this.getOrelse()
   }
-
-  override IfExprNode getAFlowNode() { result = super.getAFlowNode() }
 }
 
 /** A starred expression, such as the `*rest` in the assignment `first, *rest = seq` */
@@ -410,8 +404,6 @@ class PlaceHolder extends PlaceHolder_ {
   override Expr getASubExpression() { none() }
 
   override string toString() { result = "$" + this.getId() }
-
-  override NameNode getAFlowNode() { result = super.getAFlowNode() }
 }
 
 /** A tuple expression such as `( 1, 3, 5, 7, 9 )` */
@@ -478,8 +470,6 @@ class Name extends Name_ {
 
   override string toString() { result = this.getId() }
 
-  override NameNode getAFlowNode() { result = super.getAFlowNode() }
-
   override predicate isArtificial() {
     /* Artificial variable names in comprehensions all start with "." */
     this.getId().charAt(0) = "."
@@ -585,8 +575,6 @@ abstract class NameConstant extends Name, ImmutableLiteral {
 
   override predicate isConstant() { any() }
 
-  override NameConstantNode getAFlowNode() { result = Name.super.getAFlowNode() }
-
   override predicate isArtificial() { none() }
 }
 

python/ql/lib/semmle/python/Flow.qll

@@ -1,7 +1,7 @@
 overlay[local]
 module;
 
-import python
+import python as Py
 private import semmle.python.internal.CachedStages
 private import codeql.controlflow.BasicBlock as BB
 
@@ -17,7 +17,7 @@ private import codeql.controlflow.BasicBlock as BB
  */
 
 private predicate augstore(ControlFlowNode load, ControlFlowNode store) {
-  exists(Expr load_store | exists(AugAssign aa | aa.getTarget() = load_store) |
+  exists(Py::Expr load_store | exists(Py::AugAssign aa | aa.getTarget() = load_store) |
     toAst(load) = load_store and
     toAst(store) = load_store and
     load.strictlyDominates(store)
@@ -25,7 +25,7 @@ private predicate augstore(ControlFlowNode load, ControlFlowNode store) {
 }
 
 /** A non-dispatched getNode() to avoid negative recursion issues */
-private AstNode toAst(ControlFlowNode n) { py_flow_bb_node(n, result, _, _) }
+private Py::AstNode toAst(ControlFlowNode n) { py_flow_bb_node(n, result, _, _) }
 
 /**
  * A control flow node. Control flow nodes have a many-to-one relation with syntactic nodes,
@@ -35,19 +35,19 @@ private AstNode toAst(ControlFlowNode n) { py_flow_bb_node(n, result, _, _) }
 class ControlFlowNode extends @py_flow_node {
   /** Whether this control flow node is a load (including those in augmented assignments) */
   predicate isLoad() {
-    exists(Expr e | e = toAst(this) | py_expr_contexts(_, 3, e) and not augstore(_, this))
+    exists(Py::Expr e | e = toAst(this) | py_expr_contexts(_, 3, e) and not augstore(_, this))
   }
 
   /** Whether this control flow node is a store (including those in augmented assignments) */
   predicate isStore() {
-    exists(Expr e | e = toAst(this) | py_expr_contexts(_, 5, e) or augstore(_, this))
+    exists(Py::Expr e | e = toAst(this) | py_expr_contexts(_, 5, e) or augstore(_, this))
   }
 
   /** Whether this control flow node is a delete */
-  predicate isDelete() { exists(Expr e | e = toAst(this) | py_expr_contexts(_, 2, e)) }
+  predicate isDelete() { exists(Py::Expr e | e = toAst(this) | py_expr_contexts(_, 2, e)) }
 
   /** Whether this control flow node is a parameter */
-  predicate isParameter() { exists(Expr e | e = toAst(this) | py_expr_contexts(_, 4, e)) }
+  predicate isParameter() { exists(Py::Expr e | e = toAst(this) | py_expr_contexts(_, 4, e)) }
 
   /** Whether this control flow node is a store in an augmented assignment */
   predicate isAugStore() { augstore(_, this) }
@@ -57,61 +57,61 @@ class ControlFlowNode extends @py_flow_node {
 
   /** Whether this flow node corresponds to a literal */
   predicate isLiteral() {
-    toAst(this) instanceof Bytes
+    toAst(this) instanceof Py::Bytes
     or
-    toAst(this) instanceof Dict
+    toAst(this) instanceof Py::Dict
     or
-    toAst(this) instanceof DictComp
+    toAst(this) instanceof Py::DictComp
     or
-    toAst(this) instanceof Set
+    toAst(this) instanceof Py::Set
     or
-    toAst(this) instanceof SetComp
+    toAst(this) instanceof Py::SetComp
     or
-    toAst(this) instanceof Ellipsis
+    toAst(this) instanceof Py::Ellipsis
     or
-    toAst(this) instanceof GeneratorExp
+    toAst(this) instanceof Py::GeneratorExp
     or
-    toAst(this) instanceof Lambda
+    toAst(this) instanceof Py::Lambda
     or
-    toAst(this) instanceof ListComp
+    toAst(this) instanceof Py::ListComp
     or
-    toAst(this) instanceof List
+    toAst(this) instanceof Py::List
     or
-    toAst(this) instanceof Num
+    toAst(this) instanceof Py::Num
     or
-    toAst(this) instanceof Tuple
+    toAst(this) instanceof Py::Tuple
     or
-    toAst(this) instanceof Unicode
+    toAst(this) instanceof Py::Unicode
     or
-    toAst(this) instanceof NameConstant
+    toAst(this) instanceof Py::NameConstant
   }
 
   /** Whether this flow node corresponds to an attribute expression */
-  predicate isAttribute() { toAst(this) instanceof Attribute }
+  predicate isAttribute() { toAst(this) instanceof Py::Attribute }
 
   /** Whether this flow node corresponds to an subscript expression */
-  predicate isSubscript() { toAst(this) instanceof Subscript }
+  predicate isSubscript() { toAst(this) instanceof Py::Subscript }
 
   /** Whether this flow node corresponds to an import member */
-  predicate isImportMember() { toAst(this) instanceof ImportMember }
+  predicate isImportMember() { toAst(this) instanceof Py::ImportMember }
 
   /** Whether this flow node corresponds to a call */
-  predicate isCall() { toAst(this) instanceof Call }
+  predicate isCall() { toAst(this) instanceof Py::Call }
 
   /** Whether this flow node is the first in a module */
-  predicate isModuleEntry() { this.isEntryNode() and toAst(this) instanceof Module }
+  predicate isModuleEntry() { this.isEntryNode() and toAst(this) instanceof Py::Module }
 
   /** Whether this flow node corresponds to an import */
-  predicate isImport() { toAst(this) instanceof ImportExpr }
+  predicate isImport() { toAst(this) instanceof Py::ImportExpr }
 
   /** Whether this flow node corresponds to a conditional expression */
-  predicate isIfExp() { toAst(this) instanceof IfExp }
+  predicate isIfExp() { toAst(this) instanceof Py::IfExp }
 
   /** Whether this flow node corresponds to a function definition expression */
-  predicate isFunction() { toAst(this) instanceof FunctionExpr }
+  predicate isFunction() { toAst(this) instanceof Py::FunctionExpr }
 
   /** Whether this flow node corresponds to a class definition expression */
-  predicate isClass() { toAst(this) instanceof ClassExpr }
+  predicate isClass() { toAst(this) instanceof Py::ClassExpr }
 
   /** Gets a predecessor of this flow node */
   ControlFlowNode getAPredecessor() { this = result.getASuccessor() }
@@ -123,25 +123,25 @@ class ControlFlowNode extends @py_flow_node {
   ControlFlowNode getImmediateDominator() { py_idoms(this, result) }
 
   /** Gets the syntactic element corresponding to this flow node */
-  AstNode getNode() { py_flow_bb_node(this, result, _, _) }
+  Py::AstNode getNode() { py_flow_bb_node(this, result, _, _) }
 
   /** Gets a textual representation of this element. */
   cached
   string toString() {
     Stages::AST::ref() and
     // Since modules can have ambigous names, entry nodes can too, if we do not collate them.
-    exists(Scope s | s.getEntryNode() = this |
+    exists(Py::Scope s | s.getEntryNode() = this |
       result = "Entry node for " + concat( | | s.toString(), ",")
     )
     or
-    exists(Scope s | s.getANormalExit() = this | result = "Exit node for " + s.toString())
+    exists(Py::Scope s | s.getANormalExit() = this | result = "Exit node for " + s.toString())
     or
-    not exists(Scope s | s.getEntryNode() = this or s.getANormalExit() = this) and
+    not exists(Py::Scope s | s.getEntryNode() = this or s.getANormalExit() = this) and
     result = "ControlFlowNode for " + this.getNode().toString()
   }
 
   /** Gets the location of this ControlFlowNode */
-  Location getLocation() { result = this.getNode().getLocation() }
+  Py::Location getLocation() { result = this.getNode().getLocation() }
 
   /** Whether this flow node is the first in its scope */
   predicate isEntryNode() { py_scope_flow(this, _, -1) }
@@ -151,9 +151,9 @@ class ControlFlowNode extends @py_flow_node {
 
   /** Gets the scope containing this flow node */
   cached
-  Scope getScope() {
+  Py::Scope getScope() {
     Stages::AST::ref() and
-    if this.getNode() instanceof Scope
+    if this.getNode() instanceof Py::Scope
     then
       /* Entry or exit node */
       result = this.getNode()
@@ -161,7 +161,7 @@ class ControlFlowNode extends @py_flow_node {
   }
 
   /** Gets the enclosing module */
-  Module getEnclosingModule() { result = this.getScope().getEnclosingModule() }
+  Py::Module getEnclosingModule() { result = this.getScope().getEnclosingModule() }
 
   /** Gets a successor for this node if the relevant condition is True. */
   ControlFlowNode getATrueSuccessor() {
@@ -188,7 +188,7 @@ class ControlFlowNode extends @py_flow_node {
   }
 
   /** Whether the scope may be exited as a result of this node raising an exception */
-  predicate isExceptionalExit(Scope s) { py_scope_flow(this, s, 1) }
+  predicate isExceptionalExit(Py::Scope s) { py_scope_flow(this, s, 1) }
 
   /** Whether this node is a normal (non-exceptional) exit */
   predicate isNormalExit() { py_scope_flow(this, _, 0) or py_scope_flow(this, _, 2) }
@@ -236,7 +236,7 @@ class ControlFlowNode extends @py_flow_node {
   /* join-ordering helper for `getAChild() */
   pragma[noinline]
   private ControlFlowNode getExprChild(BasicBlock dom) {
-    this.getNode().(Expr).getAChildNode() = result.getNode() and
+    this.getNode().(Py::Expr).getAChildNode() = result.getNode() and
     result.getBasicBlock().dominates(dom) and
     not this instanceof UnaryExprNode
   }
@@ -249,16 +249,16 @@ class ControlFlowNode extends @py_flow_node {
  */
 
 private class AnyNode extends ControlFlowNode {
-  override AstNode getNode() { result = super.getNode() }
+  override Py::AstNode getNode() { result = super.getNode() }
 }
 
 /** A control flow node corresponding to a call expression, such as `func(...)` */
 class CallNode extends ControlFlowNode {
-  CallNode() { toAst(this) instanceof Call }
+  CallNode() { toAst(this) instanceof Py::Call }
 
   /** Gets the flow node corresponding to the function expression for the call corresponding to this flow node */
   ControlFlowNode getFunction() {
-    exists(Call c |
+    exists(Py::Call c |
       this.getNode() = c and
       c.getFunc() = result.getNode() and
       result.getBasicBlock().dominates(this.getBasicBlock())
@@ -267,7 +267,7 @@ class CallNode extends ControlFlowNode {
 
   /** Gets the flow node corresponding to the n'th positional argument of the call corresponding to this flow node */
   ControlFlowNode getArg(int n) {
-    exists(Call c |
+    exists(Py::Call c |
       this.getNode() = c and
       c.getArg(n) = result.getNode() and
       result.getBasicBlock().dominates(this.getBasicBlock())
@@ -276,7 +276,7 @@ class CallNode extends ControlFlowNode {
 
   /** Gets the flow node corresponding to the named argument of the call corresponding to this flow node */
   ControlFlowNode getArgByName(string name) {
-    exists(Call c, Keyword k |
+    exists(Py::Call c, Py::Keyword k |
       this.getNode() = c and
       k = c.getANamedArg() and
       k.getValue() = result.getNode() and
@@ -292,7 +292,7 @@ class CallNode extends ControlFlowNode {
     result = this.getArgByName(_)
   }
 
-  override Call getNode() { result = super.getNode() }
+  override Py::Call getNode() { result = super.getNode() }
 
   predicate isDecoratorCall() {
     this.isClassDecoratorCall()
@@ -301,11 +301,11 @@ class CallNode extends ControlFlowNode {
   }
 
   predicate isClassDecoratorCall() {
-    exists(ClassExpr cls | this.getNode() = cls.getADecoratorCall())
+    exists(Py::ClassExpr cls | this.getNode() = cls.getADecoratorCall())
   }
 
   predicate isFunctionDecoratorCall() {
-    exists(FunctionExpr func | this.getNode() = func.getADecoratorCall())
+    exists(Py::FunctionExpr func | this.getNode() = func.getADecoratorCall())
   }
 
   /** Gets the first tuple (*) argument of this call, if any. */
@@ -323,11 +323,11 @@ class CallNode extends ControlFlowNode {
 
 /** A control flow corresponding to an attribute expression, such as `value.attr` */
 class AttrNode extends ControlFlowNode {
-  AttrNode() { toAst(this) instanceof Attribute }
+  AttrNode() { toAst(this) instanceof Py::Attribute }
 
   /** Gets the flow node corresponding to the object of the attribute expression corresponding to this flow node */
   ControlFlowNode getObject() {
-    exists(Attribute a |
+    exists(Py::Attribute a |
       this.getNode() = a and
       a.getObject() = result.getNode() and
       result.getBasicBlock().dominates(this.getBasicBlock())
@@ -339,7 +339,7 @@ class AttrNode extends ControlFlowNode {
    * with the matching name
    */
   ControlFlowNode getObject(string name) {
-    exists(Attribute a |
+    exists(Py::Attribute a |
       this.getNode() = a and
       a.getObject() = result.getNode() and
       a.getName() = name and
@@ -348,57 +348,57 @@ class AttrNode extends ControlFlowNode {
   }
 
   /** Gets the attribute name of the attribute expression corresponding to this flow node */
-  string getName() { exists(Attribute a | this.getNode() = a and a.getName() = result) }
+  string getName() { exists(Py::Attribute a | this.getNode() = a and a.getName() = result) }
 
-  override Attribute getNode() { result = super.getNode() }
+  override Py::Attribute getNode() { result = super.getNode() }
 }
 
 /** A control flow node corresponding to a `from ... import ...` expression */
 class ImportMemberNode extends ControlFlowNode {
-  ImportMemberNode() { toAst(this) instanceof ImportMember }
+  ImportMemberNode() { toAst(this) instanceof Py::ImportMember }
 
   /**
    * Gets the flow node corresponding to the module in the import-member expression corresponding to this flow node,
    * with the matching name
    */
   ControlFlowNode getModule(string name) {
-    exists(ImportMember i | this.getNode() = i and i.getModule() = result.getNode() |
+    exists(Py::ImportMember i | this.getNode() = i and i.getModule() = result.getNode() |
       i.getName() = name and
       result.getBasicBlock().dominates(this.getBasicBlock())
     )
   }
 
-  override ImportMember getNode() { result = super.getNode() }
+  override Py::ImportMember getNode() { result = super.getNode() }
 }
 
 /** A control flow node corresponding to an artificial expression representing an import */
 class ImportExprNode extends ControlFlowNode {
-  ImportExprNode() { toAst(this) instanceof ImportExpr }
+  ImportExprNode() { toAst(this) instanceof Py::ImportExpr }
 
-  override ImportExpr getNode() { result = super.getNode() }
+  override Py::ImportExpr getNode() { result = super.getNode() }
 }
 
 /** A control flow node corresponding to a `from ... import *` statement */
 class ImportStarNode extends ControlFlowNode {
-  ImportStarNode() { toAst(this) instanceof ImportStar }
+  ImportStarNode() { toAst(this) instanceof Py::ImportStar }
 
   /** Gets the flow node corresponding to the module in the import-star corresponding to this flow node */
   ControlFlowNode getModule() {
-    exists(ImportStar i | this.getNode() = i and i.getModuleExpr() = result.getNode() |
+    exists(Py::ImportStar i | this.getNode() = i and i.getModuleExpr() = result.getNode() |
       result.getBasicBlock().dominates(this.getBasicBlock())
     )
   }
 
-  override ImportStar getNode() { result = super.getNode() }
+  override Py::ImportStar getNode() { result = super.getNode() }
 }
 
 /** A control flow node corresponding to a subscript expression, such as `value[slice]` */
 class SubscriptNode extends ControlFlowNode {
-  SubscriptNode() { toAst(this) instanceof Subscript }
+  SubscriptNode() { toAst(this) instanceof Py::Subscript }
 
   /** flow node corresponding to the value of the sequence in a subscript operation */
   ControlFlowNode getObject() {
-    exists(Subscript s |
+    exists(Py::Subscript s |
       this.getNode() = s and
       s.getObject() = result.getNode() and
       result.getBasicBlock().dominates(this.getBasicBlock())
@@ -407,23 +407,23 @@ class SubscriptNode extends ControlFlowNode {
 
   /** flow node corresponding to the index in a subscript operation */
   ControlFlowNode getIndex() {
-    exists(Subscript s |
+    exists(Py::Subscript s |
       this.getNode() = s and
       s.getIndex() = result.getNode() and
       result.getBasicBlock().dominates(this.getBasicBlock())
     )
   }
 
-  override Subscript getNode() { result = super.getNode() }
+  override Py::Subscript getNode() { result = super.getNode() }
 }
 
 /** A control flow node corresponding to a comparison operation, such as `x<y` */
 class CompareNode extends ControlFlowNode {
-  CompareNode() { toAst(this) instanceof Compare }
+  CompareNode() { toAst(this) instanceof Py::Compare }
 
   /** Whether left and right are a pair of operands for this comparison */
-  predicate operands(ControlFlowNode left, Cmpop op, ControlFlowNode right) {
+  predicate operands(ControlFlowNode left, Py::Cmpop op, ControlFlowNode right) {
-    exists(Compare c, Expr eleft, Expr eright |
+    exists(Py::Compare c, Py::Expr eleft, Py::Expr eright |
       this.getNode() = c and left.getNode() = eleft and right.getNode() = eright
     |
       eleft = c.getLeft() and eright = c.getComparator(0) and op = c.getOp(0)
@@ -436,26 +436,26 @@ class CompareNode extends ControlFlowNode {
     right.getBasicBlock().dominates(this.getBasicBlock())
   }
 
-  override Compare getNode() { result = super.getNode() }
+  override Py::Compare getNode() { result = super.getNode() }
 }
 
 /** A control flow node corresponding to a conditional expression such as, `body if test else orelse` */
 class IfExprNode extends ControlFlowNode {
-  IfExprNode() { toAst(this) instanceof IfExp }
+  IfExprNode() { toAst(this) instanceof Py::IfExp }
 
   /** flow node corresponding to one of the operands of an if-expression */
   ControlFlowNode getAnOperand() { result = this.getAPredecessor() }
 
-  override IfExp getNode() { result = super.getNode() }
+  override Py::IfExp getNode() { result = super.getNode() }
 }
 
 /** A control flow node corresponding to an assignment expression such as `lhs := rhs`. */
 class AssignmentExprNode extends ControlFlowNode {
-  AssignmentExprNode() { toAst(this) instanceof AssignExpr }
+  AssignmentExprNode() { toAst(this) instanceof Py::AssignExpr }
 
   /** Gets the flow node corresponding to the left-hand side of the assignment expression */
   ControlFlowNode getTarget() {
-    exists(AssignExpr a |
+    exists(Py::AssignExpr a |
       this.getNode() = a and
       a.getTarget() = result.getNode() and
       result.getBasicBlock().dominates(this.getBasicBlock())
@@ -464,27 +464,27 @@ class AssignmentExprNode extends ControlFlowNode {
 
   /** Gets the flow node corresponding to the right-hand side of the assignment expression */
   ControlFlowNode getValue() {
-    exists(AssignExpr a |
+    exists(Py::AssignExpr a |
       this.getNode() = a and
       a.getValue() = result.getNode() and
       result.getBasicBlock().dominates(this.getBasicBlock())
     )
   }
 
-  override AssignExpr getNode() { result = super.getNode() }
+  override Py::AssignExpr getNode() { result = super.getNode() }
 }
 
 /** A control flow node corresponding to a binary expression, such as `x + y` */
 class BinaryExprNode extends ControlFlowNode {
-  BinaryExprNode() { toAst(this) instanceof BinaryExpr }
+  BinaryExprNode() { toAst(this) instanceof Py::BinaryExpr }
 
   /** flow node corresponding to one of the operands of a binary expression */
   ControlFlowNode getAnOperand() { result = this.getLeft() or result = this.getRight() }
 
-  override BinaryExpr getNode() { result = super.getNode() }
+  override Py::BinaryExpr getNode() { result = super.getNode() }
 
   ControlFlowNode getLeft() {
-    exists(BinaryExpr b |
+    exists(Py::BinaryExpr b |
       this.getNode() = b and
       result.getNode() = b.getLeft() and
       result.getBasicBlock().dominates(this.getBasicBlock())
@@ -492,7 +492,7 @@ class BinaryExprNode extends ControlFlowNode {
   }
 
   ControlFlowNode getRight() {
-    exists(BinaryExpr b |
+    exists(Py::BinaryExpr b |
       this.getNode() = b and
       result.getNode() = b.getRight() and
       result.getBasicBlock().dominates(this.getBasicBlock())
@@ -500,11 +500,11 @@ class BinaryExprNode extends ControlFlowNode {
   }
 
   /** Gets the operator of this binary expression node. */
-  Operator getOp() { result = this.getNode().getOp() }
+  Py::Operator getOp() { result = this.getNode().getOp() }
 
   /** Whether left and right are a pair of operands for this binary expression */
-  predicate operands(ControlFlowNode left, Operator op, ControlFlowNode right) {
+  predicate operands(ControlFlowNode left, Py::Operator op, ControlFlowNode right) {
-    exists(BinaryExpr b, Expr eleft, Expr eright |
+    exists(Py::BinaryExpr b, Py::Expr eleft, Py::Expr eright |
       this.getNode() = b and left.getNode() = eleft and right.getNode() = eright
     |
       eleft = b.getLeft() and eright = b.getRight() and op = b.getOp()
@@ -516,20 +516,20 @@ class BinaryExprNode extends ControlFlowNode {
 
 /** A control flow node corresponding to a boolean shortcut (and/or) operation */
 class BoolExprNode extends ControlFlowNode {
-  BoolExprNode() { toAst(this) instanceof BoolExpr }
+  BoolExprNode() { toAst(this) instanceof Py::BoolExpr }
 
   /** flow node corresponding to one of the operands of a boolean expression */
   ControlFlowNode getAnOperand() {
-    exists(BoolExpr b | this.getNode() = b and result.getNode() = b.getAValue()) and
+    exists(Py::BoolExpr b | this.getNode() = b and result.getNode() = b.getAValue()) and
     this.getBasicBlock().dominates(result.getBasicBlock())
   }
 
-  override BoolExpr getNode() { result = super.getNode() }
+  override Py::BoolExpr getNode() { result = super.getNode() }
 }
 
 /** A control flow node corresponding to a unary expression: (`+x`), (`-x`) or (`~x`) */
 class UnaryExprNode extends ControlFlowNode {
-  UnaryExprNode() { toAst(this) instanceof UnaryExpr }
+  UnaryExprNode() { toAst(this) instanceof Py::UnaryExpr }
 
   /**
    * Gets flow node corresponding to the operand of a unary expression.
@@ -540,7 +540,7 @@ class UnaryExprNode extends ControlFlowNode {
    */
   ControlFlowNode getOperand() { result = this.getAPredecessor() }
 
-  override UnaryExpr getNode() { result = super.getNode() }
+  override Py::UnaryExpr getNode() { result = super.getNode() }
 
   override ControlFlowNode getAChild() { result = this.getAPredecessor() }
 }
@@ -555,27 +555,27 @@ class DefinitionNode extends ControlFlowNode {
   cached
   DefinitionNode() {
     Stages::AST::ref() and
-    exists(Assign a | a.getATarget().getAFlowNode() = this)
+    exists(Py::Assign a | this.getNode() = a.getATarget())
     or
-    exists(AssignExpr a | a.getTarget().getAFlowNode() = this)
+    exists(Py::AssignExpr a | this.getNode() = a.getTarget())
     or
-    exists(AnnAssign a | a.getTarget().getAFlowNode() = this and exists(a.getValue()))
+    exists(Py::AnnAssign a | this.getNode() = a.getTarget() and exists(a.getValue()))
     or
-    exists(Alias a | a.getAsname().getAFlowNode() = this)
+    exists(Py::Alias a | this.getNode() = a.getAsname())
     or
     augstore(_, this)
     or
     // `x, y = 1, 2` where LHS is a combination of list or tuples
-    exists(Assign a | list_or_tuple_nested_element(a.getATarget()).getAFlowNode() = this)
+    exists(Py::Assign a | this.getNode() = list_or_tuple_nested_element(a.getATarget()))
     or
-    exists(For for | for.getTarget().getAFlowNode() = this)
+    exists(Py::For for | this.getNode() = for.getTarget())
     or
-    exists(Parameter param | this = param.asName().getAFlowNode() and exists(param.getDefault()))
+    exists(Py::Parameter param | this.getNode() = param.asName() and exists(param.getDefault()))
   }
 
   /** flow node corresponding to the value assigned for the definition corresponding to this flow node */
   ControlFlowNode getValue() {
-    result = assigned_value(this.getNode()).getAFlowNode() and
+    result.getNode() = assigned_value(this.getNode()) and
     (
       result.getBasicBlock().dominates(this.getBasicBlock())
       or
@@ -584,16 +584,16 @@ class DefinitionNode extends ControlFlowNode {
       // since the default value for a parameter is evaluated in the same basic block as
       // the function definition, but the parameter belongs to the basic block of the function,
       // there is no dominance relationship between the two.
-      exists(Parameter param | this = param.asName().getAFlowNode())
+      exists(Py::Parameter param | this.getNode() = param.asName())
     )
   }
 }
 
-private Expr list_or_tuple_nested_element(Expr list_or_tuple) {
+private Py::Expr list_or_tuple_nested_element(Py::Expr list_or_tuple) {
-  exists(Expr elt |
+  exists(Py::Expr elt |
-    elt = list_or_tuple.(Tuple).getAnElt()
+    elt = list_or_tuple.(Py::Tuple).getAnElt()
     or
-    elt = list_or_tuple.(List).getAnElt()
+    elt = list_or_tuple.(Py::List).getAnElt()
   |
     result = elt
     or
@@ -603,12 +603,12 @@ private Expr list_or_tuple_nested_element(Expr list_or_tuple) {
 
 /**
  * A control flow node corresponding to a deletion statement, such as `del x`.
- * There can be multiple `DeletionNode`s for each `Delete` such that each
+ * There can be multiple `DeletionNode`s for each `Py::Delete` such that each
  * target has own `DeletionNode`. The CFG for `del a, x.y` looks like:
  * `NameNode('a') -> DeletionNode -> NameNode('b') -> AttrNode('y') -> DeletionNode`.
  */
 class DeletionNode extends ControlFlowNode {
-  DeletionNode() { toAst(this) instanceof Delete }
+  DeletionNode() { toAst(this) instanceof Py::Delete }
 
   /** Gets the unique target of this deletion node. */
   ControlFlowNode getTarget() { result.getASuccessor() = this }
@@ -617,9 +617,9 @@ class DeletionNode extends ControlFlowNode {
 /** A control flow node corresponding to a sequence (tuple or list) literal */
 abstract class SequenceNode extends ControlFlowNode {
   SequenceNode() {
-    toAst(this) instanceof Tuple
+    toAst(this) instanceof Py::Tuple
     or
-    toAst(this) instanceof List
+    toAst(this) instanceof Py::List
   }
 
   /** Gets the control flow node for an element of this sequence */
@@ -632,11 +632,11 @@ abstract class SequenceNode extends ControlFlowNode {
 
 /** A control flow node corresponding to a tuple expression such as `( 1, 3, 5, 7, 9 )` */
 class TupleNode extends SequenceNode {
-  TupleNode() { toAst(this) instanceof Tuple }
+  TupleNode() { toAst(this) instanceof Py::Tuple }
 
   override ControlFlowNode getElement(int n) {
     Stages::AST::ref() and
-    exists(Tuple t | this.getNode() = t and result.getNode() = t.getElt(n)) and
+    exists(Py::Tuple t | this.getNode() = t and result.getNode() = t.getElt(n)) and
     (
       result.getBasicBlock().dominates(this.getBasicBlock())
       or
@@ -647,10 +647,10 @@ class TupleNode extends SequenceNode {
 
 /** A control flow node corresponding to a list expression, such as `[ 1, 3, 5, 7, 9 ]` */
 class ListNode extends SequenceNode {
-  ListNode() { toAst(this) instanceof List }
+  ListNode() { toAst(this) instanceof Py::List }
 
   override ControlFlowNode getElement(int n) {
-    exists(List l | this.getNode() = l and result.getNode() = l.getElt(n)) and
+    exists(Py::List l | this.getNode() = l and result.getNode() = l.getElt(n)) and
     (
       result.getBasicBlock().dominates(this.getBasicBlock())
       or
@@ -661,10 +661,10 @@ class ListNode extends SequenceNode {
 
 /** A control flow node corresponding to a set expression, such as `{ 1, 3, 5, 7, 9 }` */
 class SetNode extends ControlFlowNode {
-  SetNode() { toAst(this) instanceof Set }
+  SetNode() { toAst(this) instanceof Py::Set }
 
   ControlFlowNode getAnElement() {
-    exists(Set s | this.getNode() = s and result.getNode() = s.getElt(_)) and
+    exists(Py::Set s | this.getNode() = s and result.getNode() = s.getElt(_)) and
     (
       result.getBasicBlock().dominates(this.getBasicBlock())
       or
@@ -675,20 +675,20 @@ class SetNode extends ControlFlowNode {
 
 /** A control flow node corresponding to a dictionary literal, such as `{ 'a': 1, 'b': 2 }` */
 class DictNode extends ControlFlowNode {
-  DictNode() { toAst(this) instanceof Dict }
+  DictNode() { toAst(this) instanceof Py::Dict }
 
   /**
    * Gets a key of this dictionary literal node, for those items that have keys
    * E.g, in {'a':1, **b} this returns only 'a'
    */
   ControlFlowNode getAKey() {
-    exists(Dict d | this.getNode() = d and result.getNode() = d.getAKey()) and
+    exists(Py::Dict d | this.getNode() = d and result.getNode() = d.getAKey()) and
     result.getBasicBlock().dominates(this.getBasicBlock())
   }
 
   /** Gets a value of this dictionary literal node */
   ControlFlowNode getAValue() {
-    exists(Dict d | this.getNode() = d and result.getNode() = d.getAValue()) and
+    exists(Py::Dict d | this.getNode() = d and result.getNode() = d.getAValue()) and
     result.getBasicBlock().dominates(this.getBasicBlock())
   }
 }
@@ -712,21 +712,23 @@ class IterableNode extends ControlFlowNode {
   }
 }
 
-private AstNode assigned_value(Expr lhs) {
+private Py::AstNode assigned_value(Py::Expr lhs) {
   /* lhs = result */
-  exists(Assign a | a.getATarget() = lhs and result = a.getValue())
+  exists(Py::Assign a | a.getATarget() = lhs and result = a.getValue())
   or
   /* lhs := result */
-  exists(AssignExpr a | a.getTarget() = lhs and result = a.getValue())
+  exists(Py::AssignExpr a | a.getTarget() = lhs and result = a.getValue())
   or
   /* lhs : annotation = result */
-  exists(AnnAssign a | a.getTarget() = lhs and result = a.getValue())
+  exists(Py::AnnAssign a | a.getTarget() = lhs and result = a.getValue())
   or
   /* import result as lhs */
-  exists(Alias a | a.getAsname() = lhs and result = a.getValue())
+  exists(Py::Alias a | a.getAsname() = lhs and result = a.getValue())
   or
   /* lhs += x  =>  result = (lhs + x) */
-  exists(AugAssign a, BinaryExpr b | b = a.getOperation() and result = b and lhs = b.getLeft())
+  exists(Py::AugAssign a, Py::BinaryExpr b |
+    b = a.getOperation() and result = b and lhs = b.getLeft()
+  )
   or
   /*
    * ..., lhs, ... = ..., result, ...
@@ -734,31 +736,31 @@ private AstNode assigned_value(Expr lhs) {
    * ..., (..., lhs, ...), ... = ..., (..., result, ...), ...
    */
 
-  exists(Assign a | nested_sequence_assign(a.getATarget(), a.getValue(), lhs, result))
+  exists(Py::Assign a | nested_sequence_assign(a.getATarget(), a.getValue(), lhs, result))
   or
   /* for lhs in seq: => `result` is the `for` node, representing the `iter(next(seq))` operation. */
-  result.(For).getTarget() = lhs
+  result.(Py::For).getTarget() = lhs
   or
-  exists(Parameter param | lhs = param.asName() and result = param.getDefault())
+  exists(Py::Parameter param | lhs = param.asName() and result = param.getDefault())
 }
 
 predicate nested_sequence_assign(
-  Expr left_parent, Expr right_parent, Expr left_result, Expr right_result
+  Py::Expr left_parent, Py::Expr right_parent, Py::Expr left_result, Py::Expr right_result
 ) {
-  exists(Assign a |
+  exists(Py::Assign a |
     a.getATarget().getASubExpression*() = left_parent and
     a.getValue().getASubExpression*() = right_parent
   ) and
-  exists(int i, Expr left_elem, Expr right_elem |
+  exists(int i, Py::Expr left_elem, Py::Expr right_elem |
     (
-      left_elem = left_parent.(Tuple).getElt(i)
+      left_elem = left_parent.(Py::Tuple).getElt(i)
       or
-      left_elem = left_parent.(List).getElt(i)
+      left_elem = left_parent.(Py::List).getElt(i)
     ) and
     (
-      right_elem = right_parent.(Tuple).getElt(i)
+      right_elem = right_parent.(Py::Tuple).getElt(i)
       or
-      right_elem = right_parent.(List).getElt(i)
+      right_elem = right_parent.(Py::List).getElt(i)
     )
   |
     left_result = left_elem and right_result = right_elem
@@ -769,9 +771,9 @@ predicate nested_sequence_assign(
 
 /** A flow node for a `for` statement. */
 class ForNode extends ControlFlowNode {
-  ForNode() { toAst(this) instanceof For }
+  ForNode() { toAst(this) instanceof Py::For }
 
-  override For getNode() { result = super.getNode() }
+  override Py::For getNode() { result = super.getNode() }
 
   /** Holds if this `for` statement causes iteration over `sequence` storing each step of the iteration in `target` */
   predicate iterates(ControlFlowNode target, ControlFlowNode sequence) {
@@ -782,7 +784,7 @@ class ForNode extends ControlFlowNode {
 
   /** Gets the sequence node for this `for` statement. */
   ControlFlowNode getSequence() {
-    exists(For for |
+    exists(Py::For for |
       toAst(this) = for and
       for.getIter() = result.getNode()
     |
@@ -792,7 +794,7 @@ class ForNode extends ControlFlowNode {
 
   /** A possible `target` for this `for` statement, not accounting for loop unrolling */
   private ControlFlowNode possibleTarget() {
-    exists(For for |
+    exists(Py::For for |
       toAst(this) = for and
       for.getTarget() = result.getNode() and
       this.getBasicBlock().dominates(result.getBasicBlock())
@@ -809,11 +811,11 @@ class ForNode extends ControlFlowNode {
 
 /** A flow node for a `raise` statement */
 class RaiseStmtNode extends ControlFlowNode {
-  RaiseStmtNode() { toAst(this) instanceof Raise }
+  RaiseStmtNode() { toAst(this) instanceof Py::Raise }
 
   /** Gets the control flow node for the exception raised by this raise statement */
   ControlFlowNode getException() {
-    exists(Raise r |
+    exists(Py::Raise r |
       r = toAst(this) and
       r.getException() = toAst(result) and
       result.getBasicBlock().dominates(this.getBasicBlock())
@@ -827,36 +829,36 @@ class RaiseStmtNode extends ControlFlowNode {
  */
 class NameNode extends ControlFlowNode {
   NameNode() {
-    exists(Name n | py_flow_bb_node(this, n, _, _))
+    exists(Py::Name n | py_flow_bb_node(this, n, _, _))
     or
-    exists(PlaceHolder p | py_flow_bb_node(this, p, _, _))
+    exists(Py::PlaceHolder p | py_flow_bb_node(this, p, _, _))
   }
 
   /** Whether this flow node defines the variable `v`. */
-  predicate defines(Variable v) {
+  predicate defines(Py::Variable v) {
-    exists(Name d | this.getNode() = d and d.defines(v)) and
+    exists(Py::Name d | this.getNode() = d and d.defines(v)) and
     not this.isLoad()
   }
 
   /** Whether this flow node deletes the variable `v`. */
-  predicate deletes(Variable v) { exists(Name d | this.getNode() = d and d.deletes(v)) }
+  predicate deletes(Py::Variable v) { exists(Py::Name d | this.getNode() = d and d.deletes(v)) }
 
   /** Whether this flow node uses the variable `v`. */
-  predicate uses(Variable v) {
+  predicate uses(Py::Variable v) {
     this.isLoad() and
-    exists(Name u | this.getNode() = u and u.uses(v))
+    exists(Py::Name u | this.getNode() = u and u.uses(v))
     or
-    exists(PlaceHolder u |
+    exists(Py::PlaceHolder u |
-      this.getNode() = u and u.getVariable() = v and u.getCtx() instanceof Load
+      this.getNode() = u and u.getVariable() = v and u.getCtx() instanceof Py::Load
     )
     or
     Scopes::use_of_global_variable(this, v.getScope(), v.getId())
   }
 
   string getId() {
-    result = this.getNode().(Name).getId()
+    result = this.getNode().(Py::Name).getId()
     or
-    result = this.getNode().(PlaceHolder).getId()
+    result = this.getNode().(Py::PlaceHolder).getId()
   }
 
   /** Whether this is a use of a local variable. */
@@ -868,82 +870,84 @@ class NameNode extends ControlFlowNode {
   /** Whether this is a use of a global (including builtin) variable. */
   predicate isGlobal() { Scopes::use_of_global_variable(this, _, _) }
 
-  predicate isSelf() { exists(SsaVariable selfvar | selfvar.isSelf() and selfvar.getAUse() = this) }
+  predicate isSelf() {
+    exists(Py::SsaVariable selfvar | selfvar.isSelf() and selfvar.getAUse() = this)
+  }
 }
 
 /** A control flow node corresponding to a named constant, one of `None`, `True` or `False`. */
 class NameConstantNode extends NameNode {
-  NameConstantNode() { exists(NameConstant n | py_flow_bb_node(this, n, _, _)) }
+  NameConstantNode() { exists(Py::NameConstant n | py_flow_bb_node(this, n, _, _)) }
   /*
    * We ought to override uses as well, but that has
    * a serious performance impact.
-   *    deprecated predicate uses(Variable v) { none() }
+   *    deprecated predicate uses(Py::Variable v) { none() }
    */
 
   }
 
 /** A control flow node corresponding to a starred expression, `*a`. */
 class StarredNode extends ControlFlowNode {
-  StarredNode() { toAst(this) instanceof Starred }
+  StarredNode() { toAst(this) instanceof Py::Starred }
 
-  ControlFlowNode getValue() { toAst(result) = toAst(this).(Starred).getValue() }
+  ControlFlowNode getValue() { toAst(result) = toAst(this).(Py::Starred).getValue() }
 }
 
 /** The ControlFlowNode for an 'except' statement. */
 class ExceptFlowNode extends ControlFlowNode {
-  ExceptFlowNode() { this.getNode() instanceof ExceptStmt }
+  ExceptFlowNode() { this.getNode() instanceof Py::ExceptStmt }
 
   /**
    * Gets the type handled by this exception handler.
-   * `ExceptionType` in `except ExceptionType as e:`
+   * `Py::ExceptionType` in `except Py::ExceptionType as e:`
    */
   ControlFlowNode getType() {
-    exists(ExceptStmt ex |
+    exists(Py::ExceptStmt ex |
       this.getBasicBlock().dominates(result.getBasicBlock()) and
       ex = this.getNode() and
-      result = ex.getType().getAFlowNode()
+      result.getNode() = ex.getType()
     )
   }
 
   /**
    * Gets the name assigned to the handled exception, if any.
-   * `e` in `except ExceptionType as e:`
+   * `e` in `except Py::ExceptionType as e:`
    */
   ControlFlowNode getName() {
-    exists(ExceptStmt ex |
+    exists(Py::ExceptStmt ex |
       this.getBasicBlock().dominates(result.getBasicBlock()) and
       ex = this.getNode() and
-      result = ex.getName().getAFlowNode()
+      result.getNode() = ex.getName()
     )
   }
 }
 
 /** The ControlFlowNode for an 'except*' statement. */
 class ExceptGroupFlowNode extends ControlFlowNode {
-  ExceptGroupFlowNode() { this.getNode() instanceof ExceptGroupStmt }
+  ExceptGroupFlowNode() { this.getNode() instanceof Py::ExceptGroupStmt }
 
   /**
    * Gets the type handled by this exception handler.
-   * `ExceptionType` in `except* ExceptionType as e:`
+   * `Py::ExceptionType` in `except* Py::ExceptionType as e:`
    */
   ControlFlowNode getType() {
     this.getBasicBlock().dominates(result.getBasicBlock()) and
-    result = this.getNode().(ExceptGroupStmt).getType().getAFlowNode()
+    result.getNode() = this.getNode().(Py::ExceptGroupStmt).getType()
   }
 
   /**
    * Gets the name assigned to the handled exception, if any.
-   * `e` in `except* ExceptionType as e:`
+   * `e` in `except* Py::ExceptionType as e:`
    */
   ControlFlowNode getName() {
     this.getBasicBlock().dominates(result.getBasicBlock()) and
-    result = this.getNode().(ExceptGroupStmt).getName().getAFlowNode()
+    result.getNode() = this.getNode().(Py::ExceptGroupStmt).getName()
   }
 }
 
 private module Scopes {
   private predicate fast_local(NameNode n) {
-    exists(FastLocalVariable v |
+    exists(Py::FastLocalVariable v |
       n.uses(v) and
       v.getScope() = n.getScope()
     )
@@ -952,15 +956,15 @@ private module Scopes {
   predicate local(NameNode n) {
     fast_local(n)
     or
-    exists(SsaVariable var |
+    exists(Py::SsaVariable var |
       var.getAUse() = n and
-      n.getScope() instanceof Class and
+      n.getScope() instanceof Py::Class and
       exists(var.getDefinition())
     )
   }
 
   predicate non_local(NameNode n) {
-    exists(FastLocalVariable flv |
+    exists(Py::FastLocalVariable flv |
       flv.getALoad() = n.getNode() and
       not flv.getScope() = n.getScope()
     )
@@ -968,20 +972,20 @@ private module Scopes {
 
   // magic is fine, but we get questionable join-ordering of it
   pragma[nomagic]
-  predicate use_of_global_variable(NameNode n, Module scope, string name) {
+  predicate use_of_global_variable(NameNode n, Py::Module scope, string name) {
     n.isLoad() and
     not non_local(n) and
-    not exists(SsaVariable var | var.getAUse() = n |
+    not exists(Py::SsaVariable var | var.getAUse() = n |
-      var.getVariable() instanceof FastLocalVariable
+      var.getVariable() instanceof Py::FastLocalVariable
       or
-      n.getScope() instanceof Class and
+      n.getScope() instanceof Py::Class and
       not maybe_undefined(var)
     ) and
     name = n.getId() and
     scope = n.getEnclosingModule()
   }
 
-  private predicate maybe_undefined(SsaVariable var) {
+  private predicate maybe_undefined(Py::SsaVariable var) {
     not exists(var.getDefinition()) and not py_ssa_phi(var, _)
     or
     var.getDefinition().isDelete()
@@ -1058,13 +1062,13 @@ class BasicBlock extends @py_flow_node {
   private predicate oneNodeBlock() { this.firstNode() = this.getLastNode() }
 
   private predicate startLocationInfo(string file, int line, int col) {
-    if this.firstNode().getNode() instanceof Scope
+    if this.firstNode().getNode() instanceof Py::Scope
     then this.firstNode().getASuccessor().getLocation().hasLocationInfo(file, line, col, _, _)
     else this.firstNode().getLocation().hasLocationInfo(file, line, col, _, _)
   }
 
   private predicate endLocationInfo(int endl, int endc) {
-    if this.getLastNode().getNode() instanceof Scope and not this.oneNodeBlock()
+    if this.getLastNode().getNode() instanceof Py::Scope and not this.oneNodeBlock()
     then this.getLastNode().getAPredecessor().getLocation().hasLocationInfo(_, _, _, endl, endc)
     else this.getLastNode().getLocation().hasLocationInfo(_, _, _, endl, endc)
   }
@@ -1081,7 +1085,7 @@ class BasicBlock extends @py_flow_node {
 
   /** Whether flow from this basic block reaches a normal exit from its scope */
   predicate reachesExit() {
-    exists(Scope s | s.getANormalExit().getBasicBlock() = this)
+    exists(Py::Scope s | s.getANormalExit().getBasicBlock() = this)
     or
     this.getASuccessor().reachesExit()
   }
@@ -1122,7 +1126,7 @@ class BasicBlock extends @py_flow_node {
 
   /** Gets the scope of this block */
   pragma[nomagic]
-  Scope getScope() {
+  Py::Scope getScope() {
     exists(ControlFlowNode n | n.getBasicBlock() = this |
       /* Take care not to use an entry or exit node as that node's scope will be the outer scope */
       not py_scope_flow(n, _, -1) and
@@ -1145,17 +1149,17 @@ class BasicBlock extends @py_flow_node {
   predicate reaches(BasicBlock other) { this = other or this.strictlyReaches(other) }
 
   /**
-   * Gets the `ConditionBlock`, if any, that controls this block and
+   * Gets the `Py::ConditionBlock`, if any, that controls this block and
-   * does not control any other `ConditionBlock`s that control this block.
+   * does not control any other `Py::ConditionBlock`s that control this block.
-   * That is the `ConditionBlock` that is closest dominator.
+   * That is the `Py::ConditionBlock` that is closest dominator.
    */
-  ConditionBlock getImmediatelyControllingBlock() {
+  Py::ConditionBlock getImmediatelyControllingBlock() {
     result = this.nonControllingImmediateDominator*().getImmediateDominator()
   }
 
   private BasicBlock nonControllingImmediateDominator() {
     result = this.getImmediateDominator() and
-    not result.(ConditionBlock).controls(this, _)
+    not result.(Py::ConditionBlock).controls(this, _)
   }
 
   /**
@@ -1175,7 +1179,7 @@ private class ControlFlowNodeAlias = ControlFlowNode;
 
 final private class FinalBasicBlock = BasicBlock;
 
-module Cfg implements BB::CfgSig<Location> {
+module Cfg implements BB::CfgSig<Py::Location> {
   private import codeql.controlflow.SuccessorType
 
   class ControlFlowNode = ControlFlowNodeAlias;
@@ -1186,7 +1190,7 @@ module Cfg implements BB::CfgSig<Location> {
     // Using the location of the first node is simple
     // and we just need a way to identify the basic block
     // during debugging, so this will be serviceable.
-    Location getLocation() { result = super.getNode(0).getLocation() }
+    Py::Location getLocation() { result = super.getNode(0).getLocation() }
 
     int length() { result = count(int i | exists(this.getNode(i))) }
 

python/ql/lib/semmle/python/Function.qll

@@ -153,8 +153,16 @@ class Function extends Function_, Scope, AstNode {
 
   override predicate contains(AstNode inner) { Scope.super.contains(inner) }
 
-  /** Gets a control flow node for a return value of this function */
+  /**
-  ControlFlowNode getAReturnValueFlowNode() {
+   * DEPRECATED: bind a `Return` node explicitly instead, e.g.
+   * `exists(Return ret | ret.getScope() = this and n.getNode() = ret.getValue())`.
+   * This API is being phased out together with `AstNode.getAFlowNode()` to
+   * untangle the AST and CFG hierarchies in preparation for migrating the
+   * dataflow library off the legacy CFG.
+   *
+   * Gets a control flow node for a return value of this function.
+   */
+  deprecated ControlFlowNode getAReturnValueFlowNode() {
     exists(Return ret |
       ret.getScope() = this and
       ret.getValue() = result.getNode()

python/ql/lib/semmle/python/Import.qll

@@ -162,8 +162,6 @@ class ImportMember extends ImportMember_ {
   string getImportedModuleName() {
     result = this.getModule().(ImportExpr).getImportedModuleName() + "." + this.getName()
   }
-
-  override ImportMemberNode getAFlowNode() { result = super.getAFlowNode() }
 }
 
 /** An import statement */

python/ql/lib/semmle/python/SelfAttribute.qll

@@ -46,20 +46,23 @@ class SelfAttributeRead extends SelfAttribute {
   }
 
   predicate guardedByHasattr() {
-    exists(Variable var, ControlFlowNode n |
+    exists(Variable var, ControlFlowNode n, ControlFlowNode this_, ControlFlowNode obj_ |
-      var.getAUse() = this.getObject().getAFlowNode() and
+      this_.getNode() = this and obj_.getNode() = this.getObject()
+    |
+      var.getAUse() = obj_ and
       hasattr(n, var.getAUse(), this.getName()) and
-      n.strictlyDominates(this.getAFlowNode())
+      n.strictlyDominates(this_)
     )
   }
 
   pragma[noinline]
   predicate locallyDefined() {
-    exists(SelfAttributeStore store |
+    exists(SelfAttributeStore store, ControlFlowNode store_, ControlFlowNode this_ |
-      this.getName() = store.getName() and
+      store_.getNode() = store and this_.getNode() = this
-      this.getScope() = store.getScope()
     |
-      store.getAFlowNode().strictlyDominates(this.getAFlowNode())
+      this.getName() = store.getName() and
+      this.getScope() = store.getScope() and
+      store_.strictlyDominates(this_)
     )
   }
 }

python/ql/lib/semmle/python/dataflow/new/BarrierGuards.qll

@@ -5,24 +5,30 @@ private import semmle.python.dataflow.new.DataFlow
 
 private predicate constCompare(DataFlow::GuardNode g, ControlFlowNode node, boolean branch) {
   exists(CompareNode cn | cn = g |
-    exists(ImmutableLiteral const, Cmpop op |
+    exists(ImmutableLiteral const, Cmpop op, ControlFlowNode c |
+      c.getNode() = const and
+      (
         op = any(Eq eq) and branch = true
         or
         op = any(NotEq ne) and branch = false
+      )
     |
-      cn.operands(const.getAFlowNode(), op, node)
+      cn.operands(c, op, node)
       or
-      cn.operands(node, op, const.getAFlowNode())
+      cn.operands(node, op, c)
     )
     or
-    exists(NameConstant const, Cmpop op |
+    exists(NameConstant const, Cmpop op, ControlFlowNode c |
+      c.getNode() = const and
+      (
         op = any(Is is_) and branch = true
         or
         op = any(IsNot isn) and branch = false
+      )
     |
-      cn.operands(const.getAFlowNode(), op, node)
+      cn.operands(c, op, node)
       or
-      cn.operands(node, op, const.getAFlowNode())
+      cn.operands(node, op, c)
     )
     or
     exists(IterableNode const_iterable, Cmpop op |

python/ql/lib/semmle/python/dataflow/new/internal/Attributes.qll

@@ -228,7 +228,7 @@ private class ClassDefinitionAsAttrWrite extends AttrWrite, CfgNode {
 
   override Node getValue() { result.asCfgNode() = node.getValue() }
 
-  override Node getObject() { result.asCfgNode() = cls.getAFlowNode() }
+  override Node getObject() { result.asCfgNode().getNode() = cls }
 
   override ExprNode getAttributeNameExpr() { none() }
 

python/ql/lib/semmle/python/dataflow/new/internal/DataFlowDispatch.qll

@@ -1913,8 +1913,8 @@ abstract class ReturnNode extends Node {
 class ExtractedReturnNode extends ReturnNode, CfgNode {
   // See `TaintTrackingImplementation::returnFlowStep`
   ExtractedReturnNode() {
-    node = any(Return ret).getValue().getAFlowNode() or
+    node.getNode() = any(Return ret).getValue() or
-    node = any(Yield yield).getAFlowNode()
+    node.getNode() = any(Yield yield)
   }
 
   override ReturnKind getKind() { any() }
@@ -1932,7 +1932,7 @@ class ExtractedReturnNode extends ReturnNode, CfgNode {
 class YieldNodeInContextManagerFunction extends ReturnNode, CfgNode {
   YieldNodeInContextManagerFunction() {
     hasContextmanagerDecorator(node.getScope()) and
-    node = any(Yield yield).getValue().getAFlowNode()
+    node.getNode() = any(Yield yield).getValue()
   }
 
   override ReturnKind getKind() { any() }

python/ql/lib/semmle/python/dataflow/new/internal/DataFlowPrivate.qll

@@ -185,8 +185,8 @@ private predicate synthDictSplatArgumentNodeStoreStep(
  */
 predicate yieldStoreStep(Node nodeFrom, Content c, Node nodeTo) {
   exists(Yield yield |
-    nodeTo.asCfgNode() = yield.getAFlowNode() and
+    nodeTo.asCfgNode().getNode() = yield and
-    nodeFrom.asCfgNode() = yield.getValue().getAFlowNode() and
+    nodeFrom.asCfgNode().getNode() = yield.getValue() and
     // TODO: Consider if this will also need to transfer dictionary content
     // once dictionary comprehensions are supported.
     c instanceof ListElementContent
@@ -753,7 +753,7 @@ predicate jumpStepNotSharedWithTypeTracker(Node nodeFrom, Node nodeTo) {
  * As of 2024-04-02 the type-tracking library only supports precise content, so there is
  * no reason to include steps for list content right now.
  */
-predicate storeStepCommon(Node nodeFrom, Content c, Node nodeTo) {
+predicate storeStepCommon(Node nodeFrom, ContentSet c, Node nodeTo) {
   tupleStoreStep(nodeFrom, c, nodeTo)
   or
   dictStoreStep(nodeFrom, c, nodeTo)
@@ -767,8 +767,7 @@ predicate storeStepCommon(Node nodeFrom, Content c, Node nodeTo) {
  * Holds if data can flow from `nodeFrom` to `nodeTo` via an assignment to
  * content `c`.
  */
-predicate storeStep(Node nodeFrom, ContentSet cs, Node nodeTo) {
+predicate storeStep(Node nodeFrom, ContentSet c, Node nodeTo) {
-  exists(Content c | cs = singleton(c) |
   storeStepCommon(nodeFrom, c, nodeTo)
   or
   listStoreStep(nodeFrom, c, nodeTo)
@@ -781,6 +780,9 @@ predicate storeStep(Node nodeFrom, ContentSet cs, Node nodeTo) {
   or
   any(Orm::AdditionalOrmSteps es).storeStep(nodeFrom, c, nodeTo)
   or
+  FlowSummaryImpl::Private::Steps::summaryStoreStep(nodeFrom.(FlowSummaryNode).getSummaryNode(), c,
+    nodeTo.(FlowSummaryNode).getSummaryNode())
+  or
   synthStarArgsElementParameterNodeStoreStep(nodeFrom, c, nodeTo)
   or
   synthDictSplatArgumentNodeStoreStep(nodeFrom, c, nodeTo)
@@ -788,10 +790,6 @@ predicate storeStep(Node nodeFrom, ContentSet cs, Node nodeTo) {
   yieldStoreStep(nodeFrom, c, nodeTo)
   or
   VariableCapture::storeStep(nodeFrom, c, nodeTo)
-  )
-  or
-  FlowSummaryImpl::Private::Steps::summaryStoreStep(nodeFrom.(FlowSummaryNode).getSummaryNode(), cs,
-    nodeTo.(FlowSummaryNode).getSummaryNode())
 }
 
 /**
@@ -987,7 +985,7 @@ predicate attributeStoreStep(Node nodeFrom, AttributeContent c, Node nodeTo) {
 /**
  * Subset of `readStep` that should be shared with type-tracking.
  */
-predicate readStepCommon(Node nodeFrom, Content c, Node nodeTo) {
+predicate readStepCommon(Node nodeFrom, ContentSet c, Node nodeTo) {
   subscriptReadStep(nodeFrom, c, nodeTo)
   or
   iterableUnpackingReadStep(nodeFrom, c, nodeTo)
@@ -996,8 +994,7 @@ predicate readStepCommon(Node nodeFrom, Content c, Node nodeTo) {
 /**
  * Holds if data can flow from `nodeFrom` to `nodeTo` via a read of content `c`.
  */
-predicate readStep(Node nodeFrom, ContentSet cs, Node nodeTo) {
+predicate readStep(Node nodeFrom, ContentSet c, Node nodeTo) {
-  exists(Content c | cs = singleton(c) |
   readStepCommon(nodeFrom, c, nodeTo)
   or
   matchReadStep(nodeFrom, c, nodeTo)
@@ -1006,15 +1003,12 @@ predicate readStep(Node nodeFrom, ContentSet cs, Node nodeTo) {
   or
   attributeReadStep(nodeFrom, c, nodeTo)
   or
+  FlowSummaryImpl::Private::Steps::summaryReadStep(nodeFrom.(FlowSummaryNode).getSummaryNode(), c,
+    nodeTo.(FlowSummaryNode).getSummaryNode())
+  or
   synthDictSplatParameterNodeReadStep(nodeFrom, c, nodeTo)
   or
   VariableCapture::readStep(nodeFrom, c, nodeTo)
-  )
-  or
-  FlowSummaryImpl::Private::Steps::summaryReadStep(nodeFrom.(FlowSummaryNode).getSummaryNode(), cs,
-    nodeTo.(FlowSummaryNode).getSummaryNode())
-  or
-  Conversions::readStep(nodeFrom, cs, nodeTo)
 }
 
 /** Data flows from a sequence to a subscript of the sequence. */
@@ -1070,68 +1064,23 @@ predicate attributeReadStep(Node nodeFrom, AttributeContent c, AttrRead nodeTo)
   nodeTo.accesses(nodeFrom, c.getAttribute())
 }
 
-module Conversions {
-  private import semmle.python.Concepts
-
-  predicate decoderReadStep(Node nodeFrom, ContentSet c, Node nodeTo) {
-    exists(Decoding decoding |
-      nodeFrom = decoding.getAnInput() and
-      nodeTo = decoding.getOutput()
-    ) and
-    c.isAnyTupleOrDictionaryElement()
-  }
-
-  predicate encoderReadStep(Node nodeFrom, ContentSet c, Node nodeTo) {
-    exists(Encoding encoding |
-      nodeFrom = encoding.getAnInput() and
-      nodeTo = encoding.getOutput()
-    ) and
-    c.isAnyTupleOrDictionaryElement()
-  }
-
-  predicate formatReadStep(Node nodeFrom, ContentSet c, Node nodeTo) {
-    // % formatting
-    exists(BinaryExprNode fmt | fmt = nodeTo.asCfgNode() |
-      fmt.getOp() instanceof Mod and
-      fmt.getRight() = nodeFrom.asCfgNode()
-    ) and
-    c.isAnyTupleElement()
-    or
-    // format_map
-    // see https://docs.python.org/3/library/stdtypes.html#str.format_map
-    nodeTo.(MethodCallNode).calls(_, "format_map") and
-    nodeTo.(MethodCallNode).getArg(0) = nodeFrom and
-    c.isAnyDictionaryElement()
-  }
-
-  predicate readStep(Node nodeFrom, ContentSet c, Node nodeTo) {
-    decoderReadStep(nodeFrom, c, nodeTo)
-    or
-    encoderReadStep(nodeFrom, c, nodeTo)
-    or
-    formatReadStep(nodeFrom, c, nodeTo)
-  }
-}
-
 /**
  * Holds if values stored inside content `c` are cleared at node `n`. For example,
  * any value stored inside `f` is cleared at the pre-update node associated with `x`
  * in `x.f = newValue`.
  */
-predicate clearsContent(Node n, ContentSet cs) {
+predicate clearsContent(Node n, ContentSet c) {
-  exists(Content c | cs = singleton(c) |
   matchClearStep(n, c)
   or
   attributeClearStep(n, c)
   or
   dictClearStep(n, c)
   or
+  FlowSummaryImpl::Private::Steps::summaryClearsContent(n.(FlowSummaryNode).getSummaryNode(), c)
+  or
   dictSplatParameterNodeClearStep(n, c)
   or
   VariableCapture::clearsContent(n, c)
-  )
-  or
-  FlowSummaryImpl::Private::Steps::summaryClearsContent(n.(FlowSummaryNode).getSummaryNode(), cs)
 }
 
 /**
@@ -1249,65 +1198,12 @@ predicate allowParameterReturnInSelf(ParameterNode p) {
   )
 }
 
-bindingset[s]
-private string getFirstChar(string s) {
-  result =
-    min(int i, string c |
-      c = s.charAt(i) and c != "_"
-      or
-      c = "" and i = s.length()
-    |
-      c order by i
-    )
-}
-
-private string getAttributeContentFirstChar(AttributeContent ac) {
-  result = getFirstChar(ac.getAttribute())
-}
-
-private string getDictionaryElementContentKeyFirstChar(DictionaryElementContent dec) {
-  result = getFirstChar(dec.getKey())
-}
-
-private newtype TContentApprox =
-  TListElementContentApprox() or
-  TSetElementContentApprox() or
-  TTupleElementContentApprox() or
-  TDictionaryElementContentApprox(string first) {
-    first = "" // for `TDictionaryElementAnyContent`
-    or
-    first = getDictionaryElementContentKeyFirstChar(_)
-  } or
-  TAttributeContentApprox(string first) { first = getAttributeContentFirstChar(_) } or
-  TCapturedVariableContentApprox()
-
 /** An approximated `Content`. */
-class ContentApprox extends TContentApprox {
+class ContentApprox = Unit;
-  /** Gets a textual representation of this element. */
-  string toString() { result = "" }
-}
 
 /** Gets an approximated value for content `c`. */
-ContentApprox getContentApprox(Content c) {
+pragma[inline]
-  c = TListElementContent() and
+ContentApprox getContentApprox(Content c) { any() }
-  result = TListElementContentApprox()
-  or
-  c = TSetElementContent() and
-  result = TSetElementContentApprox()
-  or
-  c = TTupleElementContent(_) and
-  result = TTupleElementContentApprox()
-  or
-  result = TDictionaryElementContentApprox(getDictionaryElementContentKeyFirstChar(c))
-  or
-  c = TDictionaryElementAnyContent() and
-  result = TDictionaryElementContentApprox("")
-  or
-  result = TAttributeContentApprox(getAttributeContentFirstChar(c))
-  or
-  c = TCapturedVariableContent(_) and
-  result = TCapturedVariableContentApprox()
-}
 
 /** Helper for `.getEnclosingCallable`. */
 DataFlowCallable getCallableScope(Scope s) {

python/ql/lib/semmle/python/dataflow/new/internal/DataFlowPublic.qll

@@ -485,7 +485,7 @@ class ModuleVariableNode extends Node, TModuleVariableNode {
 
   /** Gets a node that reads this variable, excluding reads that happen through `from ... import *`. */
   Node getALocalRead() {
-    result.asCfgNode() = var.getALoad().getAFlowNode() and
+    result.asCfgNode().getNode() = var.getALoad() and
     not result.getScope() = mod
   }
 
@@ -898,78 +898,19 @@ class CapturedVariableContent extends Content, TCapturedVariableContent {
   override string getMaDRepresentation() { none() }
 }
 
-/**
- * An entity that represents a set of `Content`s.
- *
- * Most `ContentSet`s are singletons (i.e. they consist of a single `Content`),
- * but `AnyDictionaryElement` and `AnyTupleElement` act as wildcards on the
- * read side: a read at such a `ContentSet` matches any specific dictionary
- * key / tuple index store, as well as (for dictionaries) the
- * "unknown-bucket" Content `DictionaryElementAnyContent`.
- *
- * Keeping these as wildcard `ContentSet`s (rather than enumerating one
- * `ContentSet` per key/index) keeps the dataflow `readSetEx` relation small
- * when implicit reads are used (e.g. at sinks via `defaultImplicitTaintRead`).
- */
-private newtype TContentSet =
-  TSingletonContent(Content c) or
-  TAnyTupleElement() or
-  TAnyDictionaryElement() or
-  TAnyTupleOrDictionaryElement()
-
 /**
  * An entity that represents a set of `Content`s.
  *
  * The set may be interpreted differently depending on whether it is
  * stored into (`getAStoreContent`) or read from (`getAReadContent`).
  */
-class ContentSet extends TContentSet {
+class ContentSet instanceof Content {
-  /** Holds if this content set is the singleton `{c}`. */
-  predicate isSingleton(Content c) { this = TSingletonContent(c) }
-
-  /** Holds if this content set is the wildcard for all tuple elements. */
-  predicate isAnyTupleElement() { this = TAnyTupleElement() }
-
-  /** Holds if this content set is the wildcard for all dictionary elements. */
-  predicate isAnyDictionaryElement() { this = TAnyDictionaryElement() }
-
-  /** Holds if this content set is the wildcard for all tuple elements or dictionary elements. */
-  predicate isAnyTupleOrDictionaryElement() { this = TAnyTupleOrDictionaryElement() }
-
   /** Gets a content that may be stored into when storing into this set. */
-  Content getAStoreContent() { this = TSingletonContent(result) }
+  Content getAStoreContent() { result = this }
 
   /** Gets a content that may be read from when reading from this set. */
-  Content getAReadContent() {
+  Content getAReadContent() { result = this }
-    this = TSingletonContent(result)
-    or
-    // Wildcard expansion: a read at "any tuple element" matches a store at any
-    // specific tuple index. (Stores always target a specific index, so we don't
-    // need a `TupleElementAnyContent` Content kind here.)
-    this = TAnyTupleElement() and result instanceof TupleElementContent
-    or
-    this = TAnyDictionaryElement() and
-    (result instanceof DictionaryElementContent or result instanceof DictionaryElementAnyContent)
-    or
-    this = TAnyTupleOrDictionaryElement() and
-    (
-      result instanceof TupleElementContent or
-      result instanceof DictionaryElementContent or
-      result instanceof DictionaryElementAnyContent
-    )
-  }
 
   /** Gets a textual representation of this content set. */
-  string toString() {
+  string toString() { result = super.toString() }
-    exists(Content c | this = TSingletonContent(c) | result = c.toString())
-    or
-    this = TAnyTupleElement() and result = "Any tuple element"
-    or
-    this = TAnyDictionaryElement() and result = "Any dictionary element"
-    or
-    this = TAnyTupleOrDictionaryElement() and result = "Any tuple or dictionary element"
 }
-}
-
-/** Gets the singleton `ContentSet` wrapping the `Content` `c`. */
-ContentSet singleton(Content c) { result = TSingletonContent(c) }

python/ql/lib/semmle/python/dataflow/new/internal/FlowSummaryImpl.qll

@@ -66,29 +66,21 @@ module Input implements InputSig<Location, DataFlowImplSpecific::PythonDataFlow>
   }
 
   string encodeContent(ContentSet cs, string arg) {
-    exists(Content c | cs.isSingleton(c) |
+    cs = TListElementContent() and result = "ListElement" and arg = ""
-      c = TListElementContent() and result = "ListElement" and arg = ""
     or
-      c = TSetElementContent() and result = "SetElement" and arg = ""
+    cs = TSetElementContent() and result = "SetElement" and arg = ""
     or
     exists(int index |
-        c = TTupleElementContent(index) and result = "TupleElement" and arg = index.toString()
+      cs = TTupleElementContent(index) and result = "TupleElement" and arg = index.toString()
     )
     or
     exists(string key |
-        c = TDictionaryElementContent(key) and result = "DictionaryElement" and arg = key
+      cs = TDictionaryElementContent(key) and result = "DictionaryElement" and arg = key
     )
     or
-      c = TDictionaryElementAnyContent() and result = "DictionaryElementAny" and arg = ""
+    cs = TDictionaryElementAnyContent() and result = "DictionaryElementAny" and arg = ""
     or
-      exists(string attr | c = TAttributeContent(attr) and result = "Attribute" and arg = attr)
+    exists(string attr | cs = TAttributeContent(attr) and result = "Attribute" and arg = attr)
-    )
-    or
-    cs.isAnyTupleElement() and result = "AnyTupleElement" and arg = ""
-    or
-    cs.isAnyDictionaryElement() and result = "AnyDictionaryElement" and arg = ""
-    or
-    cs.isAnyTupleOrDictionaryElement() and result = "AnyTupleOrDictionaryElement" and arg = ""
   }
 
   bindingset[token]
@@ -147,29 +139,27 @@ module Private {
     predicate withContent = SC::withContent/1;
 
     /** Gets a summary component that represents a list element. */
-    SummaryComponent listElement() { result = content(singleton(any(ListElementContent c))) }
+    SummaryComponent listElement() { result = content(any(ListElementContent c)) }
 
     /** Gets a summary component that represents a set element. */
-    SummaryComponent setElement() { result = content(singleton(any(SetElementContent c))) }
+    SummaryComponent setElement() { result = content(any(SetElementContent c)) }
 
     /** Gets a summary component that represents a tuple element. */
     SummaryComponent tupleElement(int index) {
-      exists(TupleElementContent c | c.getIndex() = index and result = content(singleton(c)))
+      exists(TupleElementContent c | c.getIndex() = index and result = content(c))
     }
 
     /** Gets a summary component that represents a dictionary element. */
     SummaryComponent dictionaryElement(string key) {
-      exists(DictionaryElementContent c | c.getKey() = key and result = content(singleton(c)))
+      exists(DictionaryElementContent c | c.getKey() = key and result = content(c))
     }
 
     /** Gets a summary component that represents a dictionary element at any key. */
-    SummaryComponent dictionaryElementAny() {
+    SummaryComponent dictionaryElementAny() { result = content(any(DictionaryElementAnyContent c)) }
-      result = content(singleton(any(DictionaryElementAnyContent c)))
-    }
 
     /** Gets a summary component that represents an attribute element. */
     SummaryComponent attribute(string attr) {
-      exists(AttributeContent c | c.getAttribute() = attr and result = content(singleton(c)))
+      exists(AttributeContent c | c.getAttribute() = attr and result = content(c))
     }
 
     /** Gets a summary component that represents the return value of a call. */

python/ql/lib/semmle/python/dataflow/new/internal/ImportResolution.qll

@@ -9,7 +9,19 @@ private import semmle.python.dataflow.new.DataFlow
 private import semmle.python.dataflow.new.internal.ImportStar
 private import semmle.python.dataflow.new.TypeTracking
 private import semmle.python.dataflow.new.internal.DataFlowPrivate
-private import semmle.python.essa.SsaDefinitions
+
+/**
+ * Holds if `init` is a package's `__init__.py` and `var` is a global variable in
+ * `init` whose name matches a submodule of the package.
+ *
+ * Inlined from `SsaSource::init_module_submodule_defn` to avoid pulling
+ * `semmle.python.essa.SsaDefinitions` into the new dataflow stack.
+ */
+private predicate initModuleSubmoduleDefn(GlobalVariable var, Module init) {
+  init.isPackageInit() and
+  exists(init.getPackage().getSubModule(var.getId())) and
+  var.getScope() = init
+}
 
 /**
  * Python modules and the way imports are resolved are... complicated. Here's a crash course in how
@@ -326,7 +338,7 @@ module ImportResolution {
     // imported yet.
     exists(string submodule, Module package, EssaVariable var |
       submodule = var.getName() and
-      SsaSource::init_module_submodule_defn(var.getSourceVariable(), package.getEntryNode()) and
+      initModuleSubmoduleDefn(var.getSourceVariable(), package) and
       m = getModuleFromName(package.getPackageName() + "." + submodule) and
       result.asCfgNode() = var.getDefinition().(EssaNodeDefinition).getDefiningNode()
     )

python/ql/lib/semmle/python/dataflow/new/internal/TaintTrackingPrivate.qll

@@ -11,34 +11,12 @@ private import semmle.python.ApiGraphs
  */
 predicate defaultTaintSanitizer(DataFlow::Node node) { none() }
 
-/**
- * Holds if default taint tracking should read content `contentSet` implicitly and
- * propagate taint from a container to reads of that content.
- */
-private predicate defaultTaintReadContent(DataFlow::ContentSet contentSet) {
-  // Tuple and dictionary content is precise, so use wildcard content sets to avoid
-  // blowing up the size of `Stage1::readSetEx` (otherwise this predicate would
-  // expand to one row per (node, distinct key or index) and the framework's
-  // read-set relation grows quadratically). `ContentSet.getAReadContent` expands
-  // these wildcards back to the specific contents when matching against stores.
-  contentSet.isAnyTupleOrDictionaryElement()
-  or
-  // List and set element content is already imprecise, so no wildcard expansion is
-  // needed.
-  contentSet.getAStoreContent() instanceof DataFlow::ListElementContent
-  or
-  contentSet.getAStoreContent() instanceof DataFlow::SetElementContent
-}
-
 /**
  * Holds if default `TaintTracking::Configuration`s should allow implicit reads
  * of `c` at sinks and inputs to additional taint steps.
  */
 bindingset[node]
-predicate defaultImplicitTaintRead(DataFlow::Node node, DataFlow::ContentSet c) {
+predicate defaultImplicitTaintRead(DataFlow::Node node, DataFlow::ContentSet c) { none() }
-  exists(node) and
-  defaultTaintReadContent(c)
-}
 
 private module Cached {
   /**
@@ -150,6 +128,11 @@ predicate stringManipulation(DataFlow::CfgNode nodeFrom, DataFlow::CfgNode nodeT
     nodeFrom.getNode() = object and
     method_name in ["partition", "rpartition", "rsplit", "split", "splitlines"]
     or
+    // Iterable[str] -> str
+    // TODO: check if these should be handled differently in regards to content
+    method_name = "join" and
+    nodeFrom.getNode() = call.getArg(0)
+    or
     // Mapping[str, Any] -> str
     method_name = "format_map" and
     nodeFrom.getNode() = call.getArg(0)
@@ -178,21 +161,32 @@ predicate stringManipulation(DataFlow::CfgNode nodeFrom, DataFlow::CfgNode nodeT
 }
 
 /**
- * Holds if taint can flow from `nodeFrom` to `nodeTo` with a step related to reading
+ * Holds if taint can flow from `nodeFrom` to `nodeTo` with a step related to containers
- * content from containers (lists/sets/dictionaries/tuples): subscripts, iteration,
+ * (lists/sets/dictionaries): literals, constructor invocation, methods. Note that this
- * constructor invocation, methods.
+ * is currently very imprecise, as an example, since we model `dict.get`, we treat any
+ * `<tainted object>.get(<arg>)` will be tainted, whether it's true or not.
  */
 predicate containerStep(DataFlow::Node nodeFrom, DataFlow::Node nodeTo) {
-  exists(DataFlow::ContentSet contentSet |
+  // construction by literal
-    DataFlowPrivate::readStep(nodeFrom, contentSet, nodeTo) and
+  //
-    exists(DataFlow::Content c | c = contentSet.getAReadContent() |
+  // TODO: once we have proper flow-summary modeling, we might not need this step any
-      c instanceof DataFlow::TupleElementContent or
+  // longer -- but there needs to be a matching read-step for the store-step, and we
-      c instanceof DataFlow::DictionaryElementContent or
+  // don't provide that right now.
-      c instanceof DataFlow::DictionaryElementAnyContent or
+  DataFlowPrivate::listStoreStep(nodeFrom, _, nodeTo)
-      c instanceof DataFlow::ListElementContent or
+  or
-      c instanceof DataFlow::SetElementContent
+  DataFlowPrivate::setStoreStep(nodeFrom, _, nodeTo)
-    )
+  or
-  )
+  DataFlowPrivate::tupleStoreStep(nodeFrom, _, nodeTo)
+  or
+  DataFlowPrivate::dictStoreStep(nodeFrom, _, nodeTo)
+  or
+  // comprehension, so there is taint-flow from `x` in `[x for x in xs]` to the
+  // resulting list of the list-comprehension.
+  //
+  // TODO: once we have proper flow-summary modeling, we might not need this step any
+  // longer -- but there needs to be a matching read-step for the store-step, and we
+  // don't provide that right now.
+  DataFlowPrivate::yieldStoreStep(nodeFrom, _, nodeTo)
 }
 
 /**

python/ql/lib/semmle/python/dataflow/new/internal/TypeTrackingImpl.qll

@@ -94,8 +94,10 @@ private module SummaryTypeTrackerInput implements SummaryTypeTracker::Input {
   Node returnOf(Node callable, SummaryComponent return) {
     return = FlowSummaryImpl::Private::SummaryComponent::return() and
     // `result` should be the return value of a callable expression (lambda or function) referenced by `callable`
-    result.asCfgNode() =
+    exists(Return ret |
-      callable.getALocalSource().asExpr().(CallableExpr).getInnerScope().getAReturnValueFlowNode()
+      ret.getScope() = callable.getALocalSource().asExpr().(CallableExpr).getInnerScope() and
+      result.asCfgNode().getNode() = ret.getValue()
+    )
   }
 
   // Relating callables to nodes
@@ -241,7 +243,7 @@ module TypeTrackingInput implements Shared::TypeTrackingInput<Location> {
     // is only fed set/list content)
     not nodeFrom instanceof DataFlowPublic::IterableElementNode
     or
-    TypeTrackerSummaryFlow::basicStoreStep(nodeFrom, nodeTo, DataFlowPublic::singleton(content))
+    TypeTrackerSummaryFlow::basicStoreStep(nodeFrom, nodeTo, content)
   }
 
   /**
@@ -272,15 +274,14 @@ module TypeTrackingInput implements Shared::TypeTrackingInput<Location> {
       nodeFrom.asCfgNode() instanceof SequenceNode
     )
     or
-    TypeTrackerSummaryFlow::basicLoadStep(nodeFrom, nodeTo, DataFlowPublic::singleton(content))
+    TypeTrackerSummaryFlow::basicLoadStep(nodeFrom, nodeTo, content)
   }
 
   /**
    * Holds if the `loadContent` of `nodeFrom` is stored in the `storeContent` of `nodeTo`.
    */
   predicate loadStoreStep(Node nodeFrom, Node nodeTo, Content loadContent, Content storeContent) {
-    TypeTrackerSummaryFlow::basicLoadStoreStep(nodeFrom, nodeTo,
+    TypeTrackerSummaryFlow::basicLoadStoreStep(nodeFrom, nodeTo, loadContent, storeContent)
-      DataFlowPublic::singleton(loadContent), DataFlowPublic::singleton(storeContent))
   }
 
   /**

python/ql/lib/semmle/python/dataflow/new/internal/VariableCapture.qll

@@ -61,7 +61,7 @@ private module CaptureInput implements Shared::InputSig<Location, Cfg::BasicBloc
   class VariableWrite extends ControlFlowNode {
     CapturedVariable v;
 
-    VariableWrite() { this = v.getAStore().getAFlowNode().(DefinitionNode).getValue() }
+    VariableWrite() { exists(DefinitionNode d | d.getNode() = v.getAStore() | this = d.getValue()) }
 
     CapturedVariable getVariable() { result = v }
 
@@ -71,7 +71,7 @@ private module CaptureInput implements Shared::InputSig<Location, Cfg::BasicBloc
   class VariableRead extends Expr {
     CapturedVariable v;
 
-    VariableRead() { this = v.getALoad().getAFlowNode() }
+    VariableRead() { this.getNode() = v.getALoad() }
 
     CapturedVariable getVariable() { result = v }
   }

python/ql/lib/semmle/python/dataflow/old/Implementation.qll

@@ -448,8 +448,7 @@ class TaintTrackingImplementation extends string instanceof TaintTracking::Confi
       context = TNoParam() and
       src = TTaintTrackingNode_(retval, TNoParam(), path, kind, this) and
       node.asCfgNode() = call and
-      retval.asCfgNode() =
+      retval.asCfgNode().getNode() = any(Return ret | ret.getScope() = pyfunc.getScope()).getValue()
-        any(Return ret | ret.getScope() = pyfunc.getScope()).getValue().getAFlowNode()
     ) and
     edgeLabel = "return"
   }
@@ -471,8 +470,7 @@ class TaintTrackingImplementation extends string instanceof TaintTracking::Confi
       this.callContexts(call, src, pyfunc, context, callee) and
       retnode = TTaintTrackingNode_(retval, callee, path, kind, this) and
       node.asCfgNode() = call and
-      retval.asCfgNode() =
+      retval.asCfgNode().getNode() = any(Return ret | ret.getScope() = pyfunc.getScope()).getValue()
-        any(Return ret | ret.getScope() = pyfunc.getScope()).getValue().getAFlowNode()
     ) and
     edgeLabel = "call"
   }
@@ -716,8 +714,10 @@ private class EssaTaintTracking extends string instanceof TaintTracking::Configu
       src = TTaintTrackingNode_(srcnode, context, path, srckind, this) and
       path.noAttribute()
     |
-      assign.getValue().getAFlowNode() = srcnode.asCfgNode() and
+      srcnode.asCfgNode().getNode() = assign.getValue() and
-      depth = iterable_unpacking_descent(assign.getATarget().getAFlowNode(), defn.getDefiningNode()) and
+      exists(SequenceNode left_parent | left_parent.getNode() = assign.getATarget() |
+        depth = iterable_unpacking_descent(left_parent, defn.getDefiningNode())
+      ) and
       kind = taint_at_depth(srckind, depth)
     )
   }
@@ -964,7 +964,7 @@ private TaintKind taint_at_depth(SequenceKind parent_kind, int depth) {
  * - with `left_defn` = `*y`, `left_parent` = `((x, *y), ...)`, result = 1
  */
 int iterable_unpacking_descent(SequenceNode left_parent, ControlFlowNode left_defn) {
-  exists(Assign a | a.getATarget().getASubExpression*().getAFlowNode() = left_parent) and
+  exists(Assign a | left_parent.getNode() = a.getATarget().getASubExpression*()) and
   left_parent.getAnElement() = left_defn and
   // Handle `a, *b = some_iterable`
   if left_defn instanceof StarredNode then result = 0 else result = 1

python/ql/lib/semmle/python/essa/SsaDefinitions.qll

@@ -56,7 +56,7 @@ module SsaSource {
   predicate with_definition(Variable v, ControlFlowNode defn) {
     exists(With with, Name var |
       with.getOptionalVars() = var and
-      var.getAFlowNode() = defn
+      defn.getNode() = var
     |
       var = v.getAStore()
     )
@@ -67,7 +67,7 @@ module SsaSource {
   predicate pattern_capture_definition(Variable v, ControlFlowNode defn) {
     exists(MatchCapturePattern capture, Name var |
       capture.getVariable() = var and
-      var.getAFlowNode() = defn
+      defn.getNode() = var
     |
       var = v.getAStore()
     )
@@ -78,7 +78,7 @@ module SsaSource {
   predicate pattern_alias_definition(Variable v, ControlFlowNode defn) {
     exists(MatchAsPattern pattern, Name var |
       pattern.getAlias() = var and
-      var.getAFlowNode() = defn
+      defn.getNode() = var
     |
       var = v.getAStore()
     )

python/ql/lib/semmle/python/frameworks/Bottle.qll

@@ -59,7 +59,7 @@ module Bottle {
 
         override Parameter getARoutedParameter() { none() }
 
-        override Function getARequestHandler() { result.getADecorator().getAFlowNode() = node }
+        override Function getARequestHandler() { node.getNode() = result.getADecorator() }
       }
     }
 
@@ -73,7 +73,10 @@ module Bottle {
       /** A response returned by a view callable. */
       class BottleReturnResponse extends Http::Server::HttpResponse::Range {
         BottleReturnResponse() {
-          this.asCfgNode() = any(View::ViewCallable vc).getAReturnValueFlowNode()
+          exists(Return ret |
+            ret.getScope() = any(View::ViewCallable vc) and
+            this.asCfgNode().getNode() = ret.getValue()
+          )
         }
 
         override DataFlow::Node getBody() { result = this }

python/ql/lib/semmle/python/frameworks/Django.qll

@@ -2872,7 +2872,10 @@ module PrivateDjango {
     DataFlow::CfgNode
   {
     DjangoRedirectViewGetRedirectUrlReturn() {
-      node = any(GetRedirectUrlFunction f).getAReturnValueFlowNode()
+      exists(Return ret |
+        ret.getScope() = any(GetRedirectUrlFunction f) and
+        node.getNode() = ret.getValue()
+      )
     }
 
     override DataFlow::Node getRedirectLocation() { result = this }

python/ql/lib/semmle/python/frameworks/FastApi.qll

@@ -129,7 +129,7 @@ module FastApi {
       result in [this.getArg(0), this.getArgByName("path")]
     }
 
-    override Function getARequestHandler() { result.getADecorator().getAFlowNode() = node }
+    override Function getARequestHandler() { node.getNode() = result.getADecorator() }
 
     override string getFramework() { result = "FastAPI" }
 
@@ -309,7 +309,10 @@ module FastApi {
       FastApiRouteSetup routeSetup;
 
       FastApiRequestHandlerReturn() {
-        node = routeSetup.getARequestHandler().getAReturnValueFlowNode()
+        exists(Return ret |
+          ret.getScope() = routeSetup.getARequestHandler() and
+          node.getNode() = ret.getValue()
+        )
       }
 
       override DataFlow::Node getBody() { result = this }

python/ql/lib/semmle/python/frameworks/Flask.qll

@@ -371,7 +371,7 @@ module Flask {
       result in [this.getArg(0), this.getArgByName("rule")]
     }
 
-    override Function getARequestHandler() { result.getADecorator().getAFlowNode() = node }
+    override Function getARequestHandler() { node.getNode() = result.getADecorator() }
   }
 
   /**
@@ -536,7 +536,7 @@ module Flask {
     FlaskRouteHandlerReturn() {
       exists(Function routeHandler |
         routeHandler = any(FlaskRouteSetup rs).getARequestHandler() and
-        node = routeHandler.getAReturnValueFlowNode() and
+        exists(Return ret | ret.getScope() = routeHandler and node.getNode() = ret.getValue()) and
         not this instanceof Flask::Response::InstanceSource
       )
     }

python/ql/lib/semmle/python/frameworks/FlaskAdmin.qll

@@ -38,7 +38,7 @@ private module FlaskAdmin {
       result in [this.getArg(0), this.getArgByName("url")]
     }
 
-    override Function getARequestHandler() { result.getADecorator().getAFlowNode() = node }
+    override Function getARequestHandler() { node.getNode() = result.getADecorator() }
   }
 
   /**
@@ -71,7 +71,7 @@ private module FlaskAdmin {
 
     override Function getARequestHandler() {
       exists(Flask::FlaskViewClass cls |
-        cls.getADecorator().getAFlowNode() = node and
+        node.getNode() = cls.getADecorator() and
         result = cls.getARequestHandler()
       )
     }

python/ql/lib/semmle/python/frameworks/Pyramid.qll

@@ -166,7 +166,10 @@ module Pyramid {
     /** A response returned by a view callable. */
     private class PyramidReturnResponse extends Http::Server::HttpResponse::Range {
       PyramidReturnResponse() {
-        this.asCfgNode() = any(View::ViewCallable vc).getAReturnValueFlowNode() and
+        exists(Return ret |
+          ret.getScope() = any(View::ViewCallable vc) and
+          this.asCfgNode().getNode() = ret.getValue()
+        ) and
         not this = instance()
       }
 

python/ql/lib/semmle/python/frameworks/Stdlib.qll

@@ -2254,8 +2254,9 @@ module StdlibPrivate {
       DataFlow::CfgNode
     {
       WsgirefSimpleServerApplicationReturn() {
-        exists(WsgirefSimpleServerApplication requestHandler |
+        exists(WsgirefSimpleServerApplication requestHandler, Return ret |
-          node = requestHandler.getAReturnValueFlowNode()
+          ret.getScope() = requestHandler and
+          node.getNode() = ret.getValue()
         )
       }
 
@@ -4244,7 +4245,6 @@ module StdlibPrivate {
         )
         // TODO: Once we have DictKeyContent, we need to transform that into ListElementContent
       ) and
-      // Element content is mutated into list element content
       output = "ReturnValue.ListElement" and
       preservesValue = true
       or
@@ -4271,9 +4271,11 @@ module StdlibPrivate {
         preservesValue = true
       )
       or
-      input = "Argument[0].ListElement" and
+      // TODO: We need to also translate iterable content such as list element
+      //       but we currently lack TupleElementAny
+      input = "Argument[0]" and
       output = "ReturnValue" and
-      preservesValue = true
+      preservesValue = false
     }
   }
 
@@ -4968,26 +4970,6 @@ module StdlibPrivate {
     }
   }
 
-  /** A flow summary for `str.join`. */
-  class StrJoinSummary extends SummarizedCallable::Range {
-    StrJoinSummary() { this = "str.join" }
-
-    override DataFlow::CallCfgNode getACall() { result.(DataFlow::MethodCallNode).calls(_, "join") }
-
-    override DataFlow::ArgumentNode getACallback() {
-      result.(DataFlow::AttrRead).getAttributeName() = "join"
-    }
-
-    override predicate propagatesFlow(string input, string output, boolean preservesValue) {
-      (
-        // For code like `" ".join([name])`
-        input = "Argument[0,iterable:].ListElement" and
-        preservesValue = true
-      ) and
-      output = "ReturnValue"
-    }
-  }
-
   // ---------------------------------------------------------------------------
   // asyncio
   // ---------------------------------------------------------------------------

python/ql/lib/semmle/python/frameworks/Twisted.qll

@@ -182,7 +182,10 @@ private module Twisted {
     DataFlow::CfgNode
   {
     TwistedResourceRenderMethodReturn() {
-      this.asCfgNode() = any(TwistedResourceRenderMethod meth).getAReturnValueFlowNode()
+      exists(Return ret |
+        ret.getScope() = any(TwistedResourceRenderMethod meth) and
+        this.asCfgNode().getNode() = ret.getValue()
+      )
     }
 
     override DataFlow::Node getBody() { result = this }

python/ql/lib/semmle/python/frameworks/lxml.model.yml

@@ -1,6 +0,0 @@
-extensions:
-  - addsTo:
-      pack: codeql/python-all
-      extensible: summaryModel
-    data:
-      - ['lxml', 'Member[etree].Member[fromstringlist]', 'Argument[0,strings:].ListElement', 'ReturnValue', 'taint']

python/ql/lib/semmle/python/frameworks/xml.model.yml

@@ -1,6 +0,0 @@
-extensions:
-  - addsTo:
-      pack: codeql/python-all
-      extensible: summaryModel
-    data:
-      - ['xml', 'Member[etree].Member[fromstringlist]', 'Argument[0,strings:].ListElement', 'ReturnValue', 'taint']

python/ql/lib/semmle/python/internal/CachedStages.qll

@@ -77,7 +77,7 @@ module Stages {
       or
       exists(any(AstExtended::AstNode n).getParentNode())
       or
-      exists(any(AstExtended::AstNode n).getAFlowNode())
+      exists(PyFlow::ControlFlowNode cfg, AstExtended::AstNode n | cfg.getNode() = n)
       or
       exists(any(PyFlow::BasicBlock b).getImmediateDominator())
       or

python/ql/lib/semmle/python/objects/Callables.qll

@@ -56,8 +56,9 @@ abstract class CallableObjectInternal extends ObjectInternal {
 /** A Python function. */
 class PythonFunctionObjectInternal extends CallableObjectInternal, TPythonFunctionObject {
   override Function getScope() {
-    exists(CallableExpr expr |
+    exists(CallableExpr expr, ControlFlowNode exprCfg |
-      this = TPythonFunctionObject(expr.getAFlowNode()) and
+      exprCfg.getNode() = expr and
+      this = TPythonFunctionObject(exprCfg) and
       result = expr.getInnerScope()
     )
   }
@@ -80,11 +81,12 @@ class PythonFunctionObjectInternal extends CallableObjectInternal, TPythonFuncti
 
   pragma[nomagic]
   override predicate callResult(PointsToContext callee, ObjectInternal obj, CfgOrigin origin) {
-    exists(Function func, ControlFlowNode rval, ControlFlowNode forigin |
+    exists(Function func, Return ret, ControlFlowNode rval, ControlFlowNode forigin |
       func = this.getScope() and
       callee.appliesToScope(func)
     |
-      rval = func.getAReturnValueFlowNode() and
+      ret.getScope() = func and
+      rval.getNode() = ret.getValue() and
       PointsToInternal::pointsTo(rval, callee, obj, forigin) and
       origin = CfgOrigin::fromCfgNode(forigin)
     )
@@ -160,10 +162,11 @@ class PythonFunctionObjectInternal extends CallableObjectInternal, TPythonFuncti
 }
 
 private BasicBlock blockReturningNone(Function func) {
-  exists(Return ret |
+  exists(Return ret, ControlFlowNode ret_ |
     not exists(ret.getValue()) and
     ret.getScope() = func and
-    result = ret.getAFlowNode().getBasicBlock()
+    ret_.getNode() = ret and
+    result = ret_.getBasicBlock()
   )
 }
 

python/ql/lib/semmle/python/objects/Classes.qll

@@ -113,8 +113,9 @@ abstract class ClassObjectInternal extends ObjectInternal {
 class PythonClassObjectInternal extends ClassObjectInternal, TPythonClassObject {
   /** Gets the scope for this Python class */
   Class getScope() {
-    exists(ClassExpr expr |
+    exists(ClassExpr expr, ControlFlowNode exprCfg |
-      this = TPythonClassObject(expr.getAFlowNode()) and
+      exprCfg.getNode() = expr and
+      this = TPythonClassObject(exprCfg) and
       result = expr.getInnerScope()
     )
   }

python/ql/lib/semmle/python/objects/ObjectAPI.qll

@@ -745,7 +745,12 @@ class PythonFunctionValue extends FunctionValue {
   override int maxParameters() { result = this.getScope().getMaxPositionalArguments() }
 
   /** Gets a control flow node corresponding to a return statement in this function */
-  ControlFlowNode getAReturnedNode() { result = this.getScope().getAReturnValueFlowNode() }
+  ControlFlowNode getAReturnedNode() {
+    exists(Return ret |
+      ret.getScope() = this.getScope() and
+      result.getNode() = ret.getValue()
+    )
+  }
 
   override ClassValue getARaisedType() { scope_raises(result, this.getScope()) }
 

python/ql/lib/semmle/python/objects/TObject.qll

@@ -387,7 +387,7 @@ private PythonClassObjectInternal abcMetaClassObject() {
 private predicate neither_class_nor_static_method(Function f) {
   not exists(f.getADecorator())
   or
-  exists(ControlFlowNode deco | deco = f.getADecorator().getAFlowNode() |
+  exists(ControlFlowNode deco | deco.getNode() = f.getADecorator() |
     exists(ObjectInternal o | PointsToInternal::pointsTo(deco, _, o, _) |
       o != ObjectInternal::staticMethod() and
       o != ObjectInternal::classMethod()

python/ql/lib/semmle/python/pointsto/PointsTo.qll

@@ -711,7 +711,7 @@ private module InterModulePointsTo {
     ControlFlowNode f, PointsToContext context, ObjectInternal value, ControlFlowNode origin
   ) {
     exists(string name, ImportExpr i |
-      i.getAFlowNode() = f and
+      f.getNode() = i and
       i.getImportedModuleName() = name and
       PointsToInternal::module_imported_as(value, name) and
       origin = f and
@@ -2118,8 +2118,9 @@ module Types {
     result.getBuiltin() = cls.getBuiltin().getBaseClass() and n = 0
     or
     exists(Class pycls | pycls = cls.(PythonClassObjectInternal).getScope() |
-      exists(ObjectInternal base |
+      exists(ObjectInternal base, ControlFlowNode baseNode |
-        PointsToInternal::pointsTo(pycls.getBase(n).getAFlowNode(), _, base, _)
+        baseNode.getNode() = pycls.getBase(n) and
+        PointsToInternal::pointsTo(baseNode, _, base, _)
       |
         result = base and base != ObjectInternal::unknown()
         or
@@ -2223,7 +2224,10 @@ module Types {
   }
 
   private ControlFlowNode decorator_call_callee(PythonClassObjectInternal cls) {
-    result = cls.getScope().getADecorator().getAFlowNode().(CallNode).getFunction()
+    exists(CallNode deco |
+      deco.getNode() = cls.getScope().getADecorator() and
+      result = deco.getFunction()
+    )
   }
 
   private boolean has_six_add_metaclass(PythonClassObjectInternal cls) {
@@ -2262,7 +2266,7 @@ module Types {
   }
 
   private EssaVariable metaclass_var(Class cls) {
-    result.getASourceUse() = cls.getMetaClass().getAFlowNode()
+    result.getASourceUse().getNode() = cls.getMetaClass()
     or
     major_version() = 2 and
     not exists(cls.getMetaClass()) and

python/ql/lib/semmle/python/types/ClassObject.qll

@@ -181,7 +181,7 @@ class ClassObject extends Object {
     )
   }
 
-  ControlFlowNode declaredMetaClass() { result = this.getPyClass().getMetaClass().getAFlowNode() }
+  ControlFlowNode declaredMetaClass() { result.getNode() = this.getPyClass().getMetaClass() }
 
   /** Has type inference failed to compute the full class hierarchy for this class for the reason given. */
   predicate failedInference(string reason) { Types::failedInference(this.theClass(), reason) }
@@ -195,8 +195,9 @@ class ClassObject extends Object {
    * It is guaranteed that getProbableSingletonInstance() returns at most one Object for each ClassObject.
    */
   Object getProbableSingletonInstance() {
-    exists(ControlFlowNodeWithPointsTo use, Expr origin |
+    exists(ControlFlowNodeWithPointsTo use, Expr origin, ControlFlowNode origin_ |
-      use.refersTo(result, this, origin.getAFlowNode())
+      origin_.getNode() = origin and
+      use.refersTo(result, this, origin_)
     |
       this.hasStaticallyUniqueInstance() and
       /* Ensure that original expression will be executed only one. */

python/ql/lib/semmle/python/types/Exceptions.qll

@@ -427,7 +427,7 @@ class ExceptFlowNodeWithPointsTo extends ExceptFlowNode {
 }
 
 private ControlFlowNodeWithPointsTo element_from_tuple_objectapi(Object tuple) {
-  exists(Tuple t | t = tuple.getOrigin() and result = t.getAnElt().getAFlowNode())
+  exists(Tuple t | t = tuple.getOrigin() and result.getNode() = t.getAnElt())
 }
 
 /**