Java: Add expanded arguments

.bazelrc

@@ -1,9 +1,3 @@
-common --enable_platform_specific_config
-
-build --repo_env=CC=clang --repo_env=CXX=clang++
-
-build:linux --cxxopt=-std=c++20
-build:macos --cxxopt=-std=c++20 --cpu=darwin_x86_64
-build:windows --cxxopt=/std:c++20 --cxxopt=/Zc:preprocessor
+build --repo_env=CC=clang --repo_env=CXX=clang++ --cxxopt="-std=c++17"
 
 try-import %workspace%/local.bazelrc

.bazelversion

@@ -1 +1 @@
-6.3.1
+5.0.0

.devcontainer/devcontainer.json

@@ -1,6 +1,6 @@
 {
   "extensions": [
-    "rust-lang.rust-analyzer",
+    "rust-lang.rust",
     "bungcip.better-toml",
     "github.vscode-codeql",
     "hbenl.vscode-test-explorer",

.github/labeler.yml

@@ -11,7 +11,7 @@ Go:
   - change-notes/**/*go.*
 
 Java:
-  - any: [ 'java/**/*', '!java/kotlin-extractor/**/*', '!java/ql/test/kotlin/**/*' ]
+  - any: [ 'java/**/*', '!java/kotlin-extractor/**/*', '!java/kotlin-explorer/**/*', '!java/ql/test/kotlin/**/*' ]
   - change-notes/**/*java.*
 
 JS:
@@ -20,6 +20,7 @@ JS:
 
 Kotlin:
   - java/kotlin-extractor/**/*
+  - java/kotlin-explorer/**/*
   - java/ql/test/kotlin/**/*
 
 Python:
@@ -45,7 +46,11 @@ documentation:
 
 # Since these are all shared files that need to be synced, just pick _one_ copy of each.
 "DataFlow Library":
-  - "shared/dataflow/**/*"
+  - "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImpl.qll"
+  - "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImplCommon.qll"
+  - "java/ql/lib/semmle/code/java/dataflow/internal/tainttracking1/TaintTrackingImpl.qll"
+  - "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImplConsistency.qll"
+  - "java/ql/lib/semmle/code/java/dataflow/internal/FlowSummaryImpl.qll"
 
 "ATM":
   - javascript/ql/experimental/adaptivethreatmodeling/**/*

.github/workflows/atm-check-query-suite.yml

@@ -0,0 +1,102 @@
+name: "ATM - Check query suite"
+
+env:
+  QUERY_PACK: javascript/ql/experimental/adaptivethreatmodeling/src
+  QUERY_SUITE: codeql-suites/javascript-atm-code-scanning.qls
+
+on:
+  pull_request:
+    paths:
+      - ".github/workflows/atm-check-query-suite.yml"
+      - "javascript/ql/experimental/adaptivethreatmodeling/**"
+  workflow_dispatch:
+
+jobs:
+  atm-check-query-suite:
+    runs-on: ubuntu-latest-xl
+
+    steps:
+      - uses: actions/checkout@v3
+
+      - name: Setup CodeQL
+        uses: ./.github/actions/fetch-codeql
+        with:
+          channel: release
+
+      - name: Cache compilation cache
+        id: query-cache
+        uses: ./.github/actions/cache-query-compilation
+        with: 
+          key: atm-suite
+
+      - name: Install ATM model
+        run: |
+          set -exu
+
+          # Install dependencies of ATM query pack, i.e. the ATM model
+          codeql pack install "${QUERY_PACK}"
+
+          # Retrieve model checksum
+          model_checksum=$(codeql resolve extensions "${QUERY_PACK}/${QUERY_SUITE}" | jq -r '.models[0].checksum')
+
+          # Trust the model so that we can use it in the ATM boosted queries
+          mkdir -p "$HOME/.config/codeql"
+          echo "--insecurely-execute-ml-model-checksums ${model_checksum}" >> "$HOME/.config/codeql/config"
+
+      - name: Create test DB
+        run: |
+          DB_PATH="${RUNNER_TEMP}/db"
+          echo "DB_PATH=${DB_PATH}" >> "${GITHUB_ENV}"
+
+          codeql database create "${DB_PATH}" --source-root config/atm --language javascript 
+
+      - name: Run ATM query suite
+        run: |
+          SARIF_PATH="${RUNNER_TEMP}/sarif.json"
+          echo "SARIF_PATH=${SARIF_PATH}" >> "${GITHUB_ENV}"
+
+          codeql database analyze \
+            --threads=0 \
+            --ram 50000 \
+            --format sarif-latest \
+            --output "${SARIF_PATH}" \
+            --sarif-group-rules-by-pack \
+            -vv \
+            --compilation-cache "${{ steps.query-cache.outputs.cache-dir }}" \
+            -- \
+            "${DB_PATH}" \
+            "${QUERY_PACK}/${QUERY_SUITE}"
+
+      - name: Upload SARIF
+        uses: actions/upload-artifact@v3
+        with:
+          name: javascript-ml-powered-queries.sarif
+          path: "${{ env.SARIF_PATH }}"
+          retention-days: 5
+
+      - name: Check results
+        run: |
+          # We should run at least the ML-powered queries in `expected_rules`.
+          expected_rules="js/ml-powered/nosql-injection js/ml-powered/path-injection js/ml-powered/sql-injection js/ml-powered/xss"
+
+          for rule in ${expected_rules}; do
+            found_rule=$(jq --arg rule "${rule}" '[.runs[0].tool.extensions[].rules | select(. != null) |
+              flatten | .[].id] | any(. == $rule)' "${SARIF_PATH}")
+            if [[ "${found_rule}" != "true" ]]; then
+              echo "Expected SARIF output to contain rule '${rule}', but found no such rule."
+              exit 1
+            else
+              echo "Found rule '${rule}'."
+            fi
+          done
+
+          # We should have at least one alert from an ML-powered query.
+          num_alerts=$(jq '[.runs[0].results[] |
+            select(.properties.score != null and (.rule.id | startswith("js/ml-powered/")))] | length' \
+            "${SARIF_PATH}")
+          if [[ "${num_alerts}" -eq 0 ]]; then
+            echo "Expected to find at least one alert from an ML-powered query but found ${num_alerts}."
+            exit 1
+          else
+            echo "Found ${num_alerts} alerts from ML-powered queries.";
+          fi

.github/workflows/atm-model-integration-tests.yml

@@ -0,0 +1,12 @@
+name: ATM Model Integration Tests
+
+on:
+  workflow_dispatch:
+
+jobs:
+  hello-world:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: foo
+        run: echo "Hello world"

.github/workflows/check-change-note.yml

@@ -8,9 +8,9 @@ on:
       - "*/ql/src/**/*.qll"
       - "*/ql/lib/**/*.ql"
       - "*/ql/lib/**/*.qll"
-      - "*/ql/lib/**/*.yml"
       - "!**/experimental/**"
       - "!ql/**"
+      - "!swift/**"
       - ".github/workflows/check-change-note.yml"
 
 jobs:
@@ -26,9 +26,9 @@ jobs:
         run: |
           gh api 'repos/${{github.repository}}/pulls/${{github.event.number}}/files' --paginate --jq 'any(.[].filename ; test("/change-notes/.*[.]md$"))' |
           grep true -c
-      - name: Fail if the change note filename doesn't match the expected format. The file name must be of the form 'YYYY-MM-DD.md', 'YYYY-MM-DD-{title}.md', where '{title}' is arbitrary text, or released/x.y.z.md for released change-notes
+      - name: Fail if the change note filename doesn't match the expected format. The file name must be of the form 'YYYY-MM-DD.md' or 'YYYY-MM-DD-{title}.md', where '{title}' is arbitrary text.
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         run: |
-          gh api 'repos/${{github.repository}}/pulls/${{github.event.number}}/files' --paginate --jq '[.[].filename | select(test("/change-notes/.*[.]md$"))] | all(test("/change-notes/[0-9]{4}-[0-9]{2}-[0-9]{2}.*[.]md$") or test("/change-notes/released/[0-9]*[.][0-9]*[.][0-9]*[.]md$"))' |
+          gh api 'repos/${{github.repository}}/pulls/${{github.event.number}}/files' --paginate --jq '[.[].filename | select(test("/change-notes/.*[.]md$"))] | all(test("/change-notes/[0-9]{4}-[0-9]{2}-[0-9]{2}.*[.]md$"))' |
           grep true -c

.github/workflows/check-implicit-this.yml

@@ -1,29 +0,0 @@
-name: "Check implicit this warnings"
-
-on:
-  workflow_dispatch:
-  pull_request:
-    paths:
-      - "**qlpack.yml"
-    branches:
-      - main
-      - "rc/*"
-
-jobs:
-  check:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-      - name: Check that implicit this warnings is enabled for all packs
-        shell: bash
-        run: |
-          EXIT_CODE=0
-          packs="$(find . -iname 'qlpack.yml')"
-          for pack_file in ${packs}; do
-            option="$(yq '.warnOnImplicitThis' ${pack_file})"
-            if [ "${option}" != "true" ]; then
-              echo "::error file=${pack_file}::warnOnImplicitThis property must be set to 'true' for pack ${pack_file}"
-              EXIT_CODE=1
-            fi
-          done
-          exit "${EXIT_CODE}"

.github/workflows/check-qldoc.yml

@@ -15,7 +15,7 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
         with:
           fetch-depth: 2
 

.github/workflows/check-query-ids.yml

@@ -16,6 +16,6 @@ jobs:
     name: Check query IDs
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - name: Check for duplicate query IDs
         run: python3 misc/scripts/check-query-ids.py

.github/workflows/close-stale.yml

@@ -12,7 +12,7 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/stale@v8
+    - uses: actions/stale@v7
       with:
         repo-token: ${{ secrets.GITHUB_TOKEN }}
         stale-issue-message: 'This issue is stale because it has been open 14 days with no activity. Comment or remove the `Stale` label in order to avoid having this issue closed in 7 days.'

.github/workflows/codeql-analysis.yml

@@ -33,7 +33,7 @@ jobs:
         dotnet-version: 7.0.102
 
     - name: Checkout repository
-      uses: actions/checkout@v4
+      uses: actions/checkout@v3
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL

.github/workflows/compile-queries.yml

@@ -13,7 +13,7 @@ jobs:
     runs-on: ubuntu-latest-xl
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - name: Setup CodeQL
         uses: ./.github/actions/fetch-codeql
         with:

.github/workflows/csharp-qltest.yml

@@ -29,7 +29,7 @@ jobs:
   qlupgrade:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - uses: ./.github/actions/fetch-codeql
       - name: Check DB upgrade scripts
         run: |
@@ -52,7 +52,8 @@ jobs:
       matrix:
         slice: ["1/2", "2/2"]
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
+      - uses: ./.github/actions/fetch-codeql
       - uses: ./csharp/actions/create-extractor-pack
       - name: Cache compilation cache
         id: query-cache
@@ -61,41 +62,25 @@ jobs:
           key: csharp-qltest-${{ matrix.slice }}
       - name: Run QL tests
         run: |
-          codeql test run --threads=0 --ram 50000 --slice ${{ matrix.slice }} --search-path extractor-pack --check-databases --check-undefined-labels --check-repeated-labels --check-redefined-labels --consistency-queries ql/consistency-queries ql/test --compilation-cache "${{ steps.query-cache.outputs.cache-dir }}"
+          CODEQL_PATH=$(gh codeql version --format=json | jq -r .unpackedLocation)
+          # The legacy ASP extractor is not in this repo, so take the one from the nightly build
+          mv "$CODEQL_PATH/csharp/tools/extractor-asp.jar" "${{ github.workspace }}/csharp/extractor-pack/tools"
+          # Safe guard against using the bundled extractor
+          rm -rf "$CODEQL_PATH/csharp"
+          codeql test run --threads=0 --ram 50000 --slice ${{ matrix.slice }} --search-path "${{ github.workspace }}/csharp/extractor-pack" --check-databases --check-undefined-labels --check-repeated-labels --check-redefined-labels --consistency-queries ql/consistency-queries ql/test --compilation-cache "${{ steps.query-cache.outputs.cache-dir }}"
         env:
           GITHUB_TOKEN: ${{ github.token }}
   unit-tests:
-    strategy:
-      matrix:
-        os: [ubuntu-latest, windows-2019]
-    runs-on: ${{ matrix.os }}
+    runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - name: Setup dotnet
         uses: actions/setup-dotnet@v3
         with:
           dotnet-version: 7.0.102
       - name: Extractor unit tests
         run: |
-          dotnet test -p:RuntimeFrameworkVersion=7.0.2 extractor/Semmle.Util.Tests
-          dotnet test -p:RuntimeFrameworkVersion=7.0.2 extractor/Semmle.Extraction.Tests
-          dotnet test -p:RuntimeFrameworkVersion=7.0.2 autobuilder/Semmle.Autobuild.CSharp.Tests
+          dotnet test -p:RuntimeFrameworkVersion=7.0.2 "${{ github.workspace }}/csharp/extractor/Semmle.Util.Tests"
+          dotnet test -p:RuntimeFrameworkVersion=7.0.2 "${{ github.workspace }}/csharp/extractor/Semmle.Extraction.Tests"
+          dotnet test -p:RuntimeFrameworkVersion=7.0.2 "${{ github.workspace }}/csharp/autobuilder/Semmle.Autobuild.CSharp.Tests"
           dotnet test -p:RuntimeFrameworkVersion=7.0.2 "${{ github.workspace }}/cpp/autobuilder/Semmle.Autobuild.Cpp.Tests"
-        shell: bash
-  stubgentest:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-      - uses: ./csharp/actions/create-extractor-pack
-      - name: Run stub generator tests
-        run: |
-          # Generate (Asp)NetCore stubs
-          STUBS_PATH=stubs_output
-          python3 ql/src/Stubs/make_stubs_nuget.py webapp Swashbuckle.AspNetCore.Swagger latest "$STUBS_PATH"
-          rm -rf ql/test/resources/stubs/_frameworks
-          # Update existing stubs in the repo with the freshly generated ones
-          mv "$STUBS_PATH/output/stubs/_frameworks" ql/test/resources/stubs/
-          git status
-          codeql test run --threads=0 --search-path extractor-pack --check-databases --check-undefined-labels --check-repeated-labels --check-redefined-labels --consistency-queries ql/consistency-queries -- ql/test/library-tests/dataflow/flowsources/aspremote
-        env:
-          GITHUB_TOKEN: ${{ github.token }}

.github/workflows/csv-coverage-metrics.yml

@@ -19,7 +19,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
       - name: Setup CodeQL
         uses: ./.github/actions/fetch-codeql
       - name: Create empty database
@@ -47,7 +47,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
       - name: Setup CodeQL
         uses: ./.github/actions/fetch-codeql
       - name: Create empty database

.github/workflows/csv-coverage-pr-artifacts.yml

@@ -10,7 +10,6 @@ on:
       - "*/ql/src/**/*.qll"
       - "*/ql/lib/**/*.ql"
       - "*/ql/lib/**/*.qll"
-      - "*/ql/lib/ext/**/*.yml"
       - "misc/scripts/library-coverage/*.py"
       # input data files
       - "*/documentation/library-coverage/cwe-sink.csv"
@@ -31,11 +30,11 @@ jobs:
           GITHUB_CONTEXT: ${{ toJSON(github.event) }}
         run: echo "$GITHUB_CONTEXT"
       - name: Clone self (github/codeql) - MERGE
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
         with:
           path: merge
       - name: Clone self (github/codeql) - BASE
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
         with:
           fetch-depth: 2
           path: base

.github/workflows/csv-coverage-pr-comment.yml

@@ -20,7 +20,7 @@ jobs:
         GITHUB_CONTEXT: ${{ toJSON(github.event) }}
       run: echo "$GITHUB_CONTEXT"
     - name: Clone self (github/codeql)
-      uses: actions/checkout@v4
+      uses: actions/checkout@v3
     - name: Set up Python 3.8
       uses: actions/setup-python@v4
       with:

.github/workflows/csv-coverage-timeseries.yml

@@ -9,11 +9,11 @@ jobs:
 
     steps:
       - name: Clone self (github/codeql)
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
         with:
           path: script
       - name: Clone self (github/codeql) for analysis
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
         with:
           path: codeqlModels
           fetch-depth: 0

.github/workflows/csv-coverage-update.yml

@@ -17,7 +17,7 @@ jobs:
           GITHUB_CONTEXT: ${{ toJSON(github.event) }}
         run: echo "$GITHUB_CONTEXT"
       - name: Clone self (github/codeql)
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
         with:
           path: ql
           fetch-depth: 0

.github/workflows/csv-coverage.yml

@@ -13,11 +13,11 @@ jobs:
 
     steps:
       - name: Clone self (github/codeql)
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
         with:
           path: script
       - name: Clone self (github/codeql) for analysis
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
         with:
           path: codeqlModels
           ref: ${{ github.event.inputs.qlModelShaOverride || github.ref }}

.github/workflows/fast-forward.yml

@@ -1,50 +0,0 @@
-# Fast-forwards the branch specified in BRANCH_NAME
-# to the github.ref/sha that this workflow is run on.
-# Used as part of the release process, to ensure
-# external query writers can always access a branch of github/codeql
-# that is compatible with the latest stable release.
-name: Fast-forward tracking branch for selected CodeQL version
-on:
-  workflow_dispatch:
-
-jobs:
-  fast-forward:
-    name: Fast-forward tracking branch for selected CodeQL version
-    runs-on: ubuntu-latest
-    if: github.repository == 'github/codeql'
-    permissions:
-      contents: write
-    env:
-      BRANCH_NAME: 'lgtm.com'
-    steps:
-      - name: Validate chosen branch
-        if: ${{ !startsWith(github.ref_name, 'codeql-cli-') }}
-        shell: bash
-        run: |
-          echo "::error ::The $BRANCH_NAME tracking branch should only be fast-forwarded to the tip of a codeql-cli-* branch, got $GITHUB_REF_NAME instead."
-          exit 1
-
-      - name: Checkout
-        uses: actions/checkout@v4
-
-      - name: Git config
-        shell: bash
-        run: |
-          git config user.name "github-actions[bot]"
-          git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
-
-      - name: Fetch
-        shell: bash
-        run: |
-          set -x
-          echo "Fetching $BRANCH_NAME"
-          # Explicitly unshallow and fetch to ensure the remote ref is available.
-          git fetch --unshallow origin "$BRANCH_NAME"
-          git checkout -b "$BRANCH_NAME" "origin/$BRANCH_NAME"
-
-      - name: Fast-forward
-        shell: bash
-        run: |
-          echo "Fast-forwarding $BRANCH_NAME to ${GITHUB_REF}@${GITHUB_SHA}"
-          git merge --ff-only "$GITHUB_SHA"
-          git push origin "$BRANCH_NAME"

.github/workflows/go-tests-other-os.yml

@@ -7,21 +7,19 @@ on:
       - .github/workflows/go-tests-other-os.yml
       - .github/actions/**
       - codeql-workspace.yml
-env:
-  GO_VERSION: '~1.21.0'
 jobs:
   test-mac:
     name: Test MacOS
     runs-on: macos-latest
     steps:
-      - name: Set up Go ${{ env.GO_VERSION }}
+      - name: Set up Go 1.20
         uses: actions/setup-go@v4
         with:
-          go-version: ${{ env.GO_VERSION }}
+          go-version: 1.20.0
         id: go
 
       - name: Check out code
-        uses: actions/checkout@v4
+        uses: actions/checkout@v2
 
       - name: Set up CodeQL CLI
         uses: ./.github/actions/fetch-codeql
@@ -49,14 +47,14 @@ jobs:
     name: Test Windows
     runs-on: windows-latest-xl
     steps:
-      - name: Set up Go ${{ env.GO_VERSION }}
+      - name: Set up Go 1.20
         uses: actions/setup-go@v4
         with:
-          go-version: ${{ env.GO_VERSION }}
+          go-version: 1.20.0
         id: go
 
       - name: Check out code
-        uses: actions/checkout@v4
+        uses: actions/checkout@v2
 
       - name: Set up CodeQL CLI
         uses: ./.github/actions/fetch-codeql

.github/workflows/go-tests.yml

@@ -15,21 +15,19 @@ on:
       - .github/workflows/go-tests.yml
       - .github/actions/**
       - codeql-workspace.yml
-env:
-  GO_VERSION: '~1.21.0'
 jobs:
   test-linux:
     name: Test Linux (Ubuntu)
     runs-on: ubuntu-latest-xl
     steps:
-      - name: Set up Go ${{ env.GO_VERSION }}
+      - name: Set up Go 1.20
         uses: actions/setup-go@v4
         with:
-          go-version: ${{ env.GO_VERSION }}
+          go-version: 1.20.0
         id: go
 
       - name: Check out code
-        uses: actions/checkout@v4
+        uses: actions/checkout@v2
 
       - name: Set up CodeQL CLI
         uses: ./.github/actions/fetch-codeql

.github/workflows/js-ml-tests.yml

@@ -0,0 +1,65 @@
+name: JS ML-powered queries tests
+
+on:
+  push:
+    paths:
+      - "javascript/ql/experimental/adaptivethreatmodeling/**"
+      - .github/workflows/js-ml-tests.yml
+      - .github/actions/fetch-codeql/action.yml
+      - codeql-workspace.yml
+    branches:
+      - main
+      - "rc/*"
+  pull_request:
+    paths:
+      - "javascript/ql/experimental/adaptivethreatmodeling/**"
+      - .github/workflows/js-ml-tests.yml
+      - .github/actions/fetch-codeql/action.yml
+      - codeql-workspace.yml
+  workflow_dispatch:
+
+defaults:
+  run:
+    working-directory: javascript/ql/experimental/adaptivethreatmodeling
+
+jobs:
+  qltest:
+    name: Test QL
+    runs-on: ubuntu-latest-xl
+    steps:
+      - uses: actions/checkout@v3
+
+      - uses: ./.github/actions/fetch-codeql
+
+      - name: Install pack dependencies
+        run: |
+          for pack in modelbuilding src test; do
+            codeql pack install --mode verify -- "${pack}"
+          done
+      
+      - name: Cache compilation cache
+        id: query-cache
+        uses: ./.github/actions/cache-query-compilation
+        with: 
+          key: js-ml-test
+
+      - name: Check QL compilation
+        run: |
+          codeql query compile \
+            --check-only \
+            --ram 50000 \
+            --additional-packs "${{ github.workspace }}" \
+            --threads=0 \
+            --compilation-cache "${{ steps.query-cache.outputs.cache-dir }}" \
+            -- \
+            lib modelbuilding src
+
+      - name: Run QL tests
+        run: |
+          codeql test run \
+            --threads=0 \
+            --ram 50000 \
+            --additional-packs "${{ github.workspace }}" \
+            --compilation-cache "${{ steps.query-cache.outputs.cache-dir }}" \
+            -- \
+            test

.github/workflows/mad_modelDiff.yml

@@ -27,12 +27,12 @@ jobs:
         slug: ${{fromJson(github.event.inputs.projects || '["apache/commons-codec", "apache/commons-io", "apache/commons-beanutils", "apache/commons-logging", "apache/commons-fileupload", "apache/commons-lang", "apache/commons-validator", "apache/commons-csv", "apache/dubbo"]' )}}
     steps:
       - name: Clone github/codeql from PR
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
         if: github.event.pull_request
         with:
           path: codeql-pr
       - name: Clone github/codeql from main
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
         with:
           path: codeql-main
           ref: main

.github/workflows/mad_regenerate-models.yml

@@ -27,11 +27,11 @@ jobs:
             ref: "placeholder"
     steps:
       - name: Clone self (github/codeql)
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
       - name: Setup CodeQL binaries
         uses: ./.github/actions/fetch-codeql
       - name: Clone repositories
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
         with:
           path: repos/${{ matrix.ref }}
           ref: ${{ matrix.ref }}

.github/workflows/qhelp-pr-preview.yml

@@ -43,7 +43,7 @@ jobs:
           if-no-files-found: error
           retention-days: 1
 
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
         with:
           fetch-depth: 2
           persist-credentials: false

.github/workflows/ql-for-ql-build.yml

@@ -14,7 +14,7 @@ jobs:
     runs-on: ubuntu-latest-xl
     steps:
       ### Build the queries ###
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
         with:
           fetch-depth: 0
       - name: Find codeql
@@ -32,7 +32,7 @@ jobs:
           path: |
             ql/extractor-pack/
             ql/target/release/buramu
-          key: ${{ runner.os }}-${{ steps.os_version.outputs.version }}-extractor-${{ hashFiles('ql/**/Cargo.lock') }}-${{ hashFiles('shared/tree-sitter-extractor') }}-${{ hashFiles('ql/**/*.rs') }}
+          key: ${{ runner.os }}-${{ steps.os_version.outputs.version }}-extractor-${{ hashFiles('ql/**/Cargo.lock') }}-${{ hashFiles('ql/**/*.rs') }}
       - name: Cache cargo
         if: steps.cache-extractor.outputs.cache-hit != 'true'
         uses: actions/cache@v3

.github/workflows/ql-for-ql-dataset_measure.yml

@@ -21,7 +21,7 @@ jobs:
           - github/codeql
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
 
       - name: Find codeql
         id: find-codeql
@@ -42,7 +42,7 @@ jobs:
         env:
           CODEQL: ${{ steps.find-codeql.outputs.codeql-path }}
       - name: Checkout ${{ matrix.repo }}
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
         with:
           repository: ${{ matrix.repo }}
           path: ${{ github.workspace }}/repo
@@ -71,7 +71,7 @@ jobs:
     runs-on: ubuntu-latest
     needs: measure
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - uses: actions/download-artifact@v3
         with:
           name: measurements

.github/workflows/ql-for-ql-tests.yml

@@ -21,7 +21,7 @@ jobs:
   qltest:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - name: Find codeql
         id: find-codeql
         uses: github/codeql-action/init@v2
@@ -61,7 +61,7 @@ jobs:
     needs: [qltest]
     runs-on: ${{ matrix.os }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - name: Install GNU tar 
         if: runner.os == 'macOS'
         run: |

.github/workflows/query-list.yml

@@ -20,7 +20,7 @@ jobs:
 
     steps:
     - name: Clone self (github/codeql)
-      uses: actions/checkout@v4
+      uses: actions/checkout@v3
       with:
         path: codeql 
     - name: Set up Python 3.8

.github/workflows/ruby-build.yml

@@ -42,15 +42,12 @@ jobs:
     runs-on: ${{ matrix.os }}
 
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - name: Install GNU tar
         if: runner.os == 'macOS'
         run: |
           brew install gnu-tar
           echo "/usr/local/opt/gnu-tar/libexec/gnubin" >> $GITHUB_PATH
-      - name: Install cargo-cross
-        if: runner.os == 'Linux'
-        run: cargo install cross --version 0.2.5
       - uses: ./.github/actions/os-version
         id: os_version
       - name: Cache entire extractor
@@ -58,10 +55,12 @@ jobs:
         id: cache-extractor
         with:
           path: |
-            ruby/extractor/target/release/codeql-extractor-ruby
-            ruby/extractor/target/release/codeql-extractor-ruby.exe
+            ruby/extractor/target/release/autobuilder
+            ruby/extractor/target/release/autobuilder.exe
+            ruby/extractor/target/release/extractor
+            ruby/extractor/target/release/extractor.exe
             ruby/extractor/ql/lib/codeql/ruby/ast/internal/TreeSitter.qll
-          key: ${{ runner.os }}-${{ steps.os_version.outputs.version }}-ruby-extractor-${{ hashFiles('ruby/extractor/rust-toolchain.toml', 'ruby/extractor/Cargo.lock') }}-${{ hashFiles('shared/tree-sitter-extractor') }}-${{ hashFiles('ruby/extractor/**/*.rs') }}
+          key: ${{ runner.os }}-${{ steps.os_version.outputs.version }}-ruby-extractor-${{ hashFiles('ruby/extractor/rust-toolchain.toml', 'ruby/extractor/Cargo.lock') }}--${{ hashFiles('ruby/extractor/**/*.rs') }}
       - uses: actions/cache@v3
         if: steps.cache-extractor.outputs.cache-hit != 'true'
         with:
@@ -79,20 +78,12 @@ jobs:
       - name: Run tests
         if: steps.cache-extractor.outputs.cache-hit != 'true'
         run: cd extractor && cargo test --verbose
-      # On linux, build the extractor via cross in a centos7 container.
-      # This ensures we don't depend on glibc > 2.17.
-      - name: Release build (linux)
-        if: steps.cache-extractor.outputs.cache-hit != 'true' && runner.os == 'Linux'
-        run: |
-          cd extractor
-          cross build --release
-          mv target/x86_64-unknown-linux-gnu/release/codeql-extractor-ruby target/release/
-      - name: Release build (windows and macos)
-        if: steps.cache-extractor.outputs.cache-hit != 'true' && runner.os != 'Linux'
+      - name: Release build
+        if: steps.cache-extractor.outputs.cache-hit != 'true'
         run: cd extractor && cargo build --release
       - name: Generate dbscheme
         if: ${{ matrix.os == 'ubuntu-latest' && steps.cache-extractor.outputs.cache-hit != 'true'}}
-        run: extractor/target/release/codeql-extractor-ruby generate --dbscheme ql/lib/ruby.dbscheme --library ql/lib/codeql/ruby/ast/internal/TreeSitter.qll
+        run: extractor/target/release/generator --dbscheme ql/lib/ruby.dbscheme --library ql/lib/codeql/ruby/ast/internal/TreeSitter.qll
       - uses: actions/upload-artifact@v3
         if: ${{ matrix.os == 'ubuntu-latest' }}
         with:
@@ -107,13 +98,15 @@ jobs:
         with:
           name: extractor-${{ matrix.os }}
           path: |
-            ruby/extractor/target/release/codeql-extractor-ruby
-            ruby/extractor/target/release/codeql-extractor-ruby.exe
+            ruby/extractor/target/release/autobuilder
+            ruby/extractor/target/release/autobuilder.exe
+            ruby/extractor/target/release/extractor
+            ruby/extractor/target/release/extractor.exe
           retention-days: 1
   compile-queries:
     runs-on: ubuntu-latest-xl
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - name: Fetch CodeQL
         uses: ./.github/actions/fetch-codeql
       - name: Cache compilation cache
@@ -145,7 +138,7 @@ jobs:
     runs-on: ubuntu-latest
     needs: [build, compile-queries]
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - uses: actions/download-artifact@v3
         with:
           name: ruby.dbscheme
@@ -166,10 +159,13 @@ jobs:
           mkdir -p ruby
           cp -r codeql-extractor.yml tools ql/lib/ruby.dbscheme.stats ruby/
           mkdir -p ruby/tools/{linux64,osx64,win64}
-          cp linux64/codeql-extractor-ruby ruby/tools/linux64/extractor
-          cp osx64/codeql-extractor-ruby ruby/tools/osx64/extractor
-          cp win64/codeql-extractor-ruby.exe ruby/tools/win64/extractor.exe
-          chmod +x ruby/tools/{linux64,osx64}/extractor
+          cp linux64/autobuilder ruby/tools/linux64/autobuilder
+          cp osx64/autobuilder ruby/tools/osx64/autobuilder
+          cp win64/autobuilder.exe ruby/tools/win64/autobuilder.exe
+          cp linux64/extractor ruby/tools/linux64/extractor
+          cp osx64/extractor ruby/tools/osx64/extractor
+          cp win64/extractor.exe ruby/tools/win64/extractor.exe
+          chmod +x ruby/tools/{linux64,osx64}/{autobuilder,extractor}
           zip -rq codeql-ruby.zip ruby
       - uses: actions/upload-artifact@v3
         with:
@@ -206,7 +202,7 @@ jobs:
     runs-on: ${{ matrix.os }}
     needs: [package]
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - name: Fetch CodeQL
         uses: ./.github/actions/fetch-codeql
 
@@ -231,54 +227,3 @@ jobs:
         shell: bash
         run: |
           codeql database analyze --search-path "${{ runner.temp }}/ruby-bundle" --format=sarifv2.1.0 --output=out.sarif ../database ruby-code-scanning.qls
-
-  # This is a copy of the 'test' job that runs in a centos7 container.
-  # This tests that the extractor works correctly on systems with an old glibc.
-  test-centos7:
-    defaults:
-      run:
-        working-directory: ${{ github.workspace }}
-    strategy:
-      fail-fast: false
-    runs-on: ubuntu-latest
-    container:
-      image: centos:centos7
-      env:
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-    needs: [package]
-    steps:
-      - name: Install gh cli
-        run: |
-          yum-config-manager --add-repo https://cli.github.com/packages/rpm/gh-cli.repo
-          # fetch-codeql requires unzip and jq
-          # jq is available in epel-release (https://docs.fedoraproject.org/en-US/epel/)
-          yum install -y gh unzip epel-release
-          yum install -y jq
-      - uses: actions/checkout@v3
-      - name: Fetch CodeQL
-        uses: ./.github/actions/fetch-codeql
-
-      # Due to a bug in Actions, we can't use runner.temp in the run blocks here.
-      # https://github.com/actions/runner/issues/2185
-
-      - name: Download Ruby bundle
-        uses: actions/download-artifact@v3
-        with:
-          name: codeql-ruby-bundle
-          path: ${{ runner.temp }}
-      - name: Unzip Ruby bundle
-        shell: bash
-        run: unzip -q -d "$RUNNER_TEMP"/ruby-bundle "$RUNNER_TEMP"/codeql-ruby-bundle.zip
-
-      - name: Run QL test
-        shell: bash
-        run: |
-          codeql test run --search-path "$RUNNER_TEMP"/ruby-bundle --additional-packs "$RUNNER_TEMP"/ruby-bundle ruby/ql/test/library-tests/ast/constants/
-      - name: Create database
-        shell: bash
-        run: |
-          codeql database create --search-path "$RUNNER_TEMP"/ruby-bundle --language ruby --source-root ruby/ql/test/library-tests/ast/constants/ ../database
-      - name: Analyze database
-        shell: bash
-        run: |
-          codeql database analyze --search-path "$RUNNER_TEMP"/ruby-bundle --format=sarifv2.1.0 --output=out.sarif ../database ruby-code-scanning.qls

.github/workflows/ruby-dataset-measure.yml

@@ -27,14 +27,14 @@ jobs:
         repo: [rails/rails, discourse/discourse, spree/spree, ruby/ruby]
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
 
       - uses: ./.github/actions/fetch-codeql
 
       - uses: ./ruby/actions/create-extractor-pack
 
       - name: Checkout ${{ matrix.repo }}
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
         with:
           repository: ${{ matrix.repo }}
           path: ${{ github.workspace }}/repo
@@ -59,7 +59,7 @@ jobs:
     runs-on: ubuntu-latest
     needs: measure
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - uses: actions/download-artifact@v3
         with:
           name: measurements

.github/workflows/ruby-qltest.yml

@@ -4,7 +4,6 @@ on:
   push:
     paths:
       - "ruby/**"
-      - "shared/**"
       - .github/workflows/ruby-build.yml
       - .github/actions/fetch-codeql/action.yml
       - codeql-workspace.yml
@@ -14,7 +13,6 @@ on:
   pull_request:
     paths:
       - "ruby/**"
-      - "shared/**"
       - .github/workflows/ruby-qltest.yml
       - .github/actions/fetch-codeql/action.yml
       - codeql-workspace.yml
@@ -33,7 +31,7 @@ jobs:
   qlupgrade:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - uses: ./.github/actions/fetch-codeql
       - name: Check DB upgrade scripts
         run: |
@@ -54,7 +52,7 @@ jobs:
     strategy:
       fail-fast: false
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - uses: ./.github/actions/fetch-codeql
       - uses: ./ruby/actions/create-extractor-pack
       - name: Cache compilation cache

.github/workflows/swift.yml

@@ -16,7 +16,6 @@ on:
     branches:
       - main
       - rc/*
-      - codeql-cli-*
   push:
     paths:
       - "swift/**"
@@ -31,7 +30,6 @@ on:
     branches:
       - main
       - rc/*
-      - codeql-cli-*
 
 jobs:
   # not using a matrix as you cannot depend on a specific job in a matrix, and we want to start linux checks
@@ -39,31 +37,31 @@ jobs:
   build-and-test-macos:
     runs-on: macos-12-xl
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - uses: ./swift/actions/build-and-test
   build-and-test-linux:
     runs-on: ubuntu-latest-xl
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - uses: ./swift/actions/build-and-test
   qltests-linux:
     needs: build-and-test-linux
     runs-on: ubuntu-latest-xl
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - uses: ./swift/actions/run-ql-tests
   qltests-macos:
     if : ${{ github.event_name == 'pull_request' }}
     needs: build-and-test-macos
     runs-on: macos-12-xl
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - uses: ./swift/actions/run-ql-tests
   integration-tests-linux:
     needs: build-and-test-linux
     runs-on: ubuntu-latest-xl
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - uses: ./swift/actions/run-integration-tests
   integration-tests-macos:
     if : ${{ github.event_name == 'pull_request' }}
@@ -71,13 +69,13 @@ jobs:
     runs-on: macos-12-xl
     timeout-minutes: 60
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - uses: ./swift/actions/run-integration-tests
   codegen:
     if : ${{ github.event_name == 'pull_request' }}
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - uses: bazelbuild/setup-bazelisk@v2
       - uses: actions/setup-python@v4
         with:
@@ -102,6 +100,6 @@ jobs:
     if : ${{ github.event_name == 'pull_request' }}
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - uses: ./.github/actions/fetch-codeql
       - uses: ./swift/actions/database-upgrade-scripts

.github/workflows/sync-files.yml

@@ -14,9 +14,7 @@ jobs:
   sync:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v3
       - name: Check synchronized files
         run: python config/sync-files.py
-      - name: Check dbscheme fragments
-        run: python config/sync-dbscheme-fragments.py
 

.github/workflows/tree-sitter-extractor-test.yml

@@ -1,46 +0,0 @@
-name: Test tree-sitter-extractor
-
-on:
-  push:
-    paths:
-      - "shared/tree-sitter-extractor/**"
-      - .github/workflows/tree-sitter-extractor-test.yml
-    branches:
-      - main
-      - "rc/*"
-  pull_request:
-    paths:
-      - "shared/tree-sitter-extractor/**"
-      - .github/workflows/tree-sitter-extractor-test.yml
-    branches:
-      - main
-      - "rc/*"
-
-env:
-  CARGO_TERM_COLOR: always
-
-defaults:
-  run:
-    working-directory: shared/tree-sitter-extractor
-
-jobs:
-  test:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-      - name: Check formatting
-        run: cargo fmt --all -- --check
-      - name: Run tests
-        run: cargo test --verbose
-  fmt:
-    runs-on: ubuntu-latest  
-    steps:
-      - uses: actions/checkout@v4
-      - name: Check formatting
-        run: cargo fmt --check
-  clippy:
-    runs-on: ubuntu-latest  
-    steps:
-      - uses: actions/checkout@v4
-      - name: Run clippy
-        run: cargo clippy -- --no-deps -D warnings -A clippy::new_without_default -A clippy::too_many_arguments

.github/workflows/validate-change-notes.yml

@@ -20,7 +20,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v3
 
       - name: Setup CodeQL
         uses: ./.github/actions/fetch-codeql

.pre-commit-config.yaml

@@ -5,9 +5,9 @@ repos:
     rev: v3.2.0
     hooks:
       - id: trailing-whitespace
-        exclude: /test/.*$(?<!\.ql)(?<!\.qll)(?<!\.qlref)|.*\.patch
+        exclude: /test/.*$(?<!\.ql)(?<!\.qll)(?<!\.qlref)
       - id: end-of-file-fixer
-        exclude: /test/.*$(?<!\.ql)(?<!\.qll)(?<!\.qlref)|.*\.patch
+        exclude: /test/.*$(?<!\.ql)(?<!\.qll)(?<!\.qlref)
 
   - repo: https://github.com/pre-commit/mirrors-clang-format
     rev: v13.0.1
@@ -19,12 +19,7 @@ repos:
     rev: v1.6.0
     hooks:
       - id: autopep8
-        files: ^misc/codegen/.*\.py
-
-  - repo: https://github.com/warchant/pre-commit-buildifier
-    rev: 0.0.2
-    hooks:
-      - id: buildifier
+        files: ^swift/.*\.py
 
   - repo: local
     hooks:

.vscode/tasks.json

@@ -22,22 +22,6 @@
                 "command": "${config:python.pythonPath}",
             },
             "problemMatcher": []
-        },
-        {
-            "label": "Accept .expected changes from CI",
-            "type": "process",
-            // Non-Windows OS will usually have Python 3 already installed at /usr/bin/python3.
-            "command": "python3",
-            "args": [
-                "misc/scripts/accept-expected-changes-from-ci.py"
-            ],
-            "group": "build",
-            "windows": {
-                // On Windows, use whatever Python interpreter is configured for this workspace. The default is
-                // just `python`, so if Python is already on the path, this will find it.
-                "command": "${config:python.pythonPath}",
-            },
-            "problemMatcher": []
         }
     ]
-}
+}

CODEOWNERS

@@ -8,6 +8,7 @@
 /swift/ @github/codeql-swift
 /misc/codegen/ @github/codeql-swift
 /java/kotlin-extractor/ @github/codeql-kotlin
+/java/kotlin-explorer/ @github/codeql-kotlin
 
 # ML-powered queries
 /javascript/ql/experimental/adaptivethreatmodeling/ @github/codeql-ml-powered-queries-reviewers
@@ -39,6 +40,3 @@ WORKSPACE.bazel @github/codeql-ci-reviewers
 /.github/workflows/ql-for-ql-* @github/codeql-ql-for-ql-reviewers
 /.github/workflows/ruby-* @github/codeql-ruby
 /.github/workflows/swift.yml @github/codeql-swift
-
-# Misc
-/misc/scripts/accept-expected-changes-from-ci.py @RasmusWL

CONTRIBUTING.md

@@ -14,16 +14,14 @@ If you have an idea for a query that you would like to share with other CodeQL u
 
 1. **Directory structure**
 
-    There are eight language-specific query directories in this repository:
+    There are six language-specific query directories in this repository:
 
       * C/C++: `cpp/ql/src`
       * C#: `csharp/ql/src`
-      * Go: `go/ql/src`
-      * Java/Kotlin: `java/ql/src`
+      * Java: `java/ql/src`
       * JavaScript: `javascript/ql/src`
       * Python: `python/ql/src`
       * Ruby: `ruby/ql/src`
-      * Swift: `swift/ql/src`
 
     Each language-specific directory contains further subdirectories that group queries based on their `@tags` or purpose.
     - Experimental queries and libraries are stored in the `experimental` subdirectory within each language-specific directory in the [CodeQL repository](https://github.com/github/codeql). For example, experimental Java queries and libraries are stored in `java/ql/src/experimental` and any corresponding tests in `java/ql/test/experimental`.

codeql-workspace.yml

@@ -4,8 +4,6 @@ provide:
   - "*/ql/test/qlpack.yml"
   - "*/ql/examples/qlpack.yml"
   - "*/ql/consistency-queries/qlpack.yml"
-  - "*/ql/automodel/src/qlpack.yml"
-  - "*/ql/automodel/test/qlpack.yml"
   - "shared/*/qlpack.yml"
   - "cpp/ql/test/query-tests/Security/CWE/CWE-190/semmle/tainted/qlpack.yml"
   - "go/ql/config/legacy-support/qlpack.yml"

config/dbscheme-fragments.json

@@ -1,33 +0,0 @@
-{
-  "files": [
-    "javascript/ql/lib/semmlecode.javascript.dbscheme",
-    "python/ql/lib/semmlecode.python.dbscheme",
-    "ruby/ql/lib/ruby.dbscheme",
-    "ql/ql/src/ql.dbscheme"
-  ],
-  "fragments": [
-    "/*- External data -*/",
-    "/*- Files and folders -*/",
-    "/*- Diagnostic messages -*/",
-    "/*- Diagnostic messages: severity -*/",
-    "/*- Source location prefix -*/",
-    "/*- Lines of code -*/",
-    "/*- Configuration files with key value pairs -*/",
-    "/*- YAML -*/",
-    "/*- XML Files -*/",
-    "/*- XML: sourceline -*/",
-    "/*- DEPRECATED: External defects and metrics -*/",
-    "/*- DEPRECATED: Snapshot date -*/",
-    "/*- DEPRECATED: Duplicate code -*/",
-    "/*- DEPRECATED: Version control data -*/",
-    "/*- JavaScript-specific part -*/",
-    "/*- Ruby dbscheme -*/",
-    "/*- Erb dbscheme -*/",
-    "/*- QL dbscheme -*/",
-    "/*- Dbscheme dbscheme -*/",
-    "/*- Yaml dbscheme -*/",
-    "/*- Blame dbscheme -*/",
-    "/*- JSON dbscheme -*/",
-    "/*- Python dbscheme -*/"
-  ]
-}

config/identical-files.json

@@ -1,4 +1,24 @@
 {
+  "DataFlow Java/C++/C#/Go/Python/Ruby/Swift": [
+    "java/ql/lib/semmle/code/java/dataflow/internal/DataFlow.qll",
+    "cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlow.qll",
+    "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlow.qll",
+    "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlow.qll",
+    "go/ql/lib/semmle/go/dataflow/internal/DataFlow.qll",
+    "python/ql/lib/semmle/python/dataflow/new/internal/DataFlow.qll",
+    "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlow.qll",
+    "swift/ql/lib/codeql/swift/dataflow/internal/DataFlow.qll"
+  ],
+  "DataFlowImpl Java/C++/C#/Go/Python/Ruby/Swift": [
+    "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImpl.qll",
+    "cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowImpl.qll",
+    "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlowImpl.qll",
+    "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImpl.qll",
+    "go/ql/lib/semmle/go/dataflow/internal/DataFlowImpl.qll",
+    "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImpl.qll",
+    "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImpl.qll",
+    "swift/ql/lib/codeql/swift/dataflow/internal/DataFlowImpl.qll"
+  ],
   "DataFlow Java/C++/C#/Go/Python/Ruby/Swift Legacy Configuration": [
     "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImpl1.qll",
     "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImpl2.qll",
@@ -20,16 +40,41 @@
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImpl3.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImpl4.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImpl5.qll",
+    "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImplForContentDataFlow.qll",
     "go/ql/lib/semmle/go/dataflow/internal/DataFlowImpl1.qll",
     "go/ql/lib/semmle/go/dataflow/internal/DataFlowImpl2.qll",
+    "go/ql/lib/semmle/go/dataflow/internal/DataFlowImplForStringsNewReplacer.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImpl1.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImpl2.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImpl3.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImpl4.qll",
+    "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImplForRegExp.qll",
     "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImpl1.qll",
     "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImpl2.qll",
+    "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImplForHttpClientLibraries.qll",
+    "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImplForPathname.qll",
     "swift/ql/lib/codeql/swift/dataflow/internal/DataFlowImpl1.qll"
   ],
+  "DataFlow Java/C++/C#/Go/Python/Ruby/Swift Common": [
+    "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImplCommon.qll",
+    "cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowImplCommon.qll",
+    "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlowImplCommon.qll",
+    "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImplCommon.qll",
+    "go/ql/lib/semmle/go/dataflow/internal/DataFlowImplCommon.qll",
+    "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImplCommon.qll",
+    "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImplCommon.qll",
+    "swift/ql/lib/codeql/swift/dataflow/internal/DataFlowImplCommon.qll"
+  ],
+  "TaintTracking Java/C++/C#/Go/Python/Ruby/Swift": [
+    "cpp/ql/lib/semmle/code/cpp/dataflow/internal/tainttracking1/TaintTracking.qll",
+    "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/tainttracking1/TaintTracking.qll",
+    "csharp/ql/lib/semmle/code/csharp/dataflow/internal/tainttracking1/TaintTracking.qll",
+    "go/ql/lib/semmle/go/dataflow/internal/tainttracking1/TaintTracking.qll",
+    "java/ql/lib/semmle/code/java/dataflow/internal/tainttracking1/TaintTracking.qll",
+    "python/ql/lib/semmle/python/dataflow/new/internal/tainttracking1/TaintTracking.qll",
+    "ruby/ql/lib/codeql/ruby/dataflow/internal/tainttracking1/TaintTracking.qll",
+    "swift/ql/lib/codeql/swift/dataflow/internal/tainttracking1/TaintTracking.qll"
+  ],
   "TaintTracking Legacy Configuration Java/C++/C#/Go/Python/Ruby/Swift": [
     "cpp/ql/lib/semmle/code/cpp/dataflow/internal/tainttracking1/TaintTrackingImpl.qll",
     "cpp/ql/lib/semmle/code/cpp/dataflow/internal/tainttracking2/TaintTrackingImpl.qll",
@@ -53,6 +98,15 @@
     "ruby/ql/lib/codeql/ruby/dataflow/internal/tainttracking1/TaintTrackingImpl.qll",
     "swift/ql/lib/codeql/swift/dataflow/internal/tainttracking1/TaintTrackingImpl.qll"
   ],
+  "DataFlow Java/C++/C#/Python/Ruby/Swift Consistency checks": [
+    "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImplConsistency.qll",
+    "cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowImplConsistency.qll",
+    "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlowImplConsistency.qll",
+    "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImplConsistency.qll",
+    "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImplConsistency.qll",
+    "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImplConsistency.qll",
+    "swift/ql/lib/codeql/swift/dataflow/internal/DataFlowImplConsistency.qll"
+  ],
   "DataFlow Java/C#/Go/Ruby/Python/Swift Flow Summaries": [
     "java/ql/lib/semmle/code/java/dataflow/internal/FlowSummaryImpl.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/FlowSummaryImpl.qll",
@@ -69,10 +123,6 @@
     "java/ql/src/utils/modelgenerator/internal/CaptureModels.qll",
     "csharp/ql/src/utils/modelgenerator/internal/CaptureModels.qll"
   ],
-  "Model as Data Generation Java/C# - CaptureModelsPrinting": [
-    "java/ql/src/utils/modelgenerator/internal/CaptureModelsPrinting.qll",
-    "csharp/ql/src/utils/modelgenerator/internal/CaptureModelsPrinting.qll"
-  ],
   "Sign Java/C#": [
     "java/ql/lib/semmle/code/java/dataflow/internal/rangeanalysis/Sign.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/rangeanalysis/Sign.qll"
@@ -459,17 +509,17 @@
   "SensitiveDataHeuristics Python/JS": [
     "javascript/ql/lib/semmle/javascript/security/internal/SensitiveDataHeuristics.qll",
     "python/ql/lib/semmle/python/security/internal/SensitiveDataHeuristics.qll",
-    "ruby/ql/lib/codeql/ruby/security/internal/SensitiveDataHeuristics.qll",
-    "swift/ql/lib/codeql/swift/security/internal/SensitiveDataHeuristics.qll"
+    "ruby/ql/lib/codeql/ruby/security/internal/SensitiveDataHeuristics.qll"
+  ],
+  "CFG": [
+    "csharp/ql/lib/semmle/code/csharp/controlflow/internal/ControlFlowGraphImplShared.qll",
+    "ruby/ql/lib/codeql/ruby/controlflow/internal/ControlFlowGraphImplShared.qll",
+    "swift/ql/lib/codeql/swift/controlflow/internal/ControlFlowGraphImplShared.qll"
   ],
   "TypeTracker": [
     "python/ql/lib/semmle/python/dataflow/new/internal/TypeTracker.qll",
     "ruby/ql/lib/codeql/ruby/typetracking/TypeTracker.qll"
   ],
-  "SummaryTypeTracker": [
-    "python/ql/lib/semmle/python/dataflow/new/internal/SummaryTypeTracker.qll",
-    "ruby/ql/lib/codeql/ruby/typetracking/internal/SummaryTypeTracker.qll"
-  ],
   "AccessPathSyntax": [
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/AccessPathSyntax.qll",
     "go/ql/lib/semmle/go/dataflow/internal/AccessPathSyntax.qll",
@@ -545,9 +595,5 @@
   "EncryptionKeySizes Python/Java": [
     "python/ql/lib/semmle/python/security/internal/EncryptionKeySizes.qll",
     "java/ql/lib/semmle/code/java/security/internal/EncryptionKeySizes.qll"
-  ],
-  "Python model summaries test extension": [
-    "python/ql/test/experimental/dataflow/model-summaries/InlineTaintTest.ext.yml",
-    "python/ql/test/experimental/dataflow/model-summaries/NormalDataflowTest.ext.yml"
   ]
 }

config/sync-dbscheme-fragments.py

@@ -1,86 +0,0 @@
-#!/usr/bin/env python3
-
-import argparse
-import json
-import os
-import pathlib
-import re
-
-
-def make_groups(blocks):
-    groups = {}
-    for block in blocks:
-        groups.setdefault("".join(block["lines"]), []).append(block)
-    return list(groups.values())
-
-
-def validate_fragments(fragments):
-    ok = True
-    for header, blocks in fragments.items():
-        groups = make_groups(blocks)
-        if len(groups) > 1:
-            ok = False
-            print("Warning: dbscheme fragments with header '{}' are different for {}".format(header, ["{}:{}:{}".format(
-                group[0]["file"], group[0]["start"], group[0]["end"]) for group in groups]))
-    return ok
-
-
-def main():
-    script_path = os.path.realpath(__file__)
-    script_dir = os.path.dirname(script_path)
-    parser = argparse.ArgumentParser(
-        prog=os.path.basename(script_path),
-        description='Sync dbscheme fragments across files.'
-    )
-    parser.add_argument('files', metavar='dbscheme_file', type=pathlib.Path, nargs='*', default=[],
-                        help='dbscheme files to check')
-    args = parser.parse_args()
-
-    with open(os.path.join(script_dir, "dbscheme-fragments.json"), "r") as f:
-        config = json.load(f)
-
-    fragment_headers = set(config["fragments"])
-    fragments = {}
-    ok = True
-    for file in args.files + config["files"]:
-        with open(os.path.join(os.path.dirname(script_dir), file), "r") as dbscheme:
-            header = None
-            line_number = 1
-            block = {"file": file, "start": line_number,
-                     "end": None, "lines": []}
-
-            def end_block():
-                block["end"] = line_number - 1
-                if len(block["lines"]) > 0:
-                    if header is None:
-                        if re.match(r'(?m)\A(\s|//.*$|/\*(\**[^\*])*\*+/)*\Z', "".join(block["lines"])):
-                            # Ignore comments at the beginning of the file
-                            pass
-                        else:
-                            ok = False
-                            print("Warning: dbscheme fragment without header: {}:{}:{}".format(
-                                block["file"], block["start"], block["end"]))
-                    else:
-                        fragments.setdefault(header, []).append(block)
-            for line in dbscheme:
-                m = re.match(r"^\/\*-.*-\*\/$", line)
-                if m:
-                    end_block()
-                    header = line.strip()
-                    if header not in fragment_headers:
-                        ok = False
-                        print("Warning: unknown header for dbscheme fragment: '{}': {}:{}".format(
-                            header, file, line_number))
-                    block = {"file": file, "start": line_number,
-                             "end": None, "lines": []}
-                block["lines"].append(line)
-                line_number += 1
-            block["lines"].append('\n')
-            line_number += 1
-            end_block()
-    if not ok or not validate_fragments(fragments):
-        exit(1)
-
-
-if __name__ == "__main__":
-    main()

cpp/autobuilder/Semmle.Autobuild.Cpp.Tests/BuildScripts.cs

@@ -327,7 +327,7 @@ namespace Semmle.Autobuild.Cpp.Tests
         {
             Actions.RunProcess[@"cmd.exe /C nuget restore C:\Project\test.sln -DisableParallelProcessing"] = 1;
             Actions.RunProcess[@"cmd.exe /C C:\Project\.nuget\nuget.exe restore C:\Project\test.sln -DisableParallelProcessing"] = 0;
-            Actions.RunProcess[@"cmd.exe /C CALL ^""C:\Program^ Files^ ^(x86^)\Microsoft^ Visual^ Studio^ 14.0\VC\vcvarsall.bat^"" && set Platform=&& type NUL && msbuild C:\Project\test.sln /t:rebuild /p:Platform=""x86"" /p:Configuration=""Release"""] = 0;
+            Actions.RunProcess[@"cmd.exe /C CALL ^""C:\Program Files ^(x86^)\Microsoft Visual Studio 14.0\VC\vcvarsall.bat^"" && set Platform=&& type NUL && msbuild C:\Project\test.sln /t:rebuild /p:Platform=""x86"" /p:Configuration=""Release"""] = 0;
             Actions.RunProcessOut[@"C:\Program Files (x86)\Microsoft Visual Studio\Installer\vswhere.exe -prerelease -legacy -property installationPath"] = "";
             Actions.RunProcess[@"C:\Program Files (x86)\Microsoft Visual Studio\Installer\vswhere.exe -prerelease -legacy -property installationPath"] = 1;
             Actions.RunProcess[@"C:\Program Files (x86)\Microsoft Visual Studio\Installer\vswhere.exe -prerelease -legacy -property installationVersion"] = 0;

cpp/downgrades/19887dbd33327fb07d54251786e0cb2578539775/upgrade.properties

@@ -1,4 +0,0 @@
-description: Revert support for repeated initializers, which are allowed in C with designated initializers.
-compatibility: full
-aggregate_field_init.rel: reorder aggregate_field_init.rel (int aggregate, int initializer, int field, int position) aggregate initializer field
-aggregate_array_init.rel: reorder aggregate_array_init.rel (int aggregate, int initializer, int element_index, int position) aggregate initializer element_index

cpp/downgrades/d77c09d8bdc172c9201dec293de1e14c931d3f05/upgrade.properties

@@ -1,2 +0,0 @@
-description: Remove _Float128 type
-compatibility: full

cpp/downgrades/dbe9c8eb5fc6f54b7ae08c7317d0795b24961564/upgrade.properties

@@ -1,2 +0,0 @@
-description: Make __is_trivial a builtin operation
-compatibility: full

cpp/downgrades/qlpack.yml

@@ -2,4 +2,3 @@ name: codeql/cpp-downgrades
 groups: cpp
 downgrades: .
 library: true
-warnOnImplicitThis: true

cpp/ql/examples/qlpack.yml

@@ -4,4 +4,3 @@ groups:
   - examples
 dependencies:
   codeql/cpp-all: ${workspace}
-warnOnImplicitThis: true

cpp/ql/examples/queries.xml

@@ -0,0 +1 @@
+<queries language="cpp"/>

cpp/ql/lib/CHANGELOG.md

@@ -1,143 +1,3 @@
-## 0.10.0
-
-### Minor Analysis Improvements
-
-* Functions that do not return due to calling functions that don't return (e.g. `exit`) are now detected as
- non-returning in the IR and dataflow.
-* Treat functions that reach the end of the function as returning in the IR.
-  They used to be treated as unreachable but it is allowed in C. 
-* The `DataFlow::asDefiningArgument` predicate now takes its argument from the range starting at `1` instead of `2`. Queries that depend on the single-parameter version of `DataFlow::asDefiningArgument` should have their arguments updated accordingly.
-
-## 0.9.3
-
-No user-facing changes.
-
-## 0.9.2
-
-### Deprecated APIs
-
-* `getAllocatorCall` on `DeleteExpr` and `DeleteArrayExpr` has been deprecated. `getDeallocatorCall` should be used instead.
-
-### New Features
-
-* Added `DeleteOrDeleteArrayExpr` as a super type of `DeleteExpr` and `DeleteArrayExpr`
-
-### Minor Analysis Improvements
-
-* `delete` and `delete[]` are now modeled as calls to the relevant `operator delete` in the IR. In the case of a dynamic delete call a new instruction `VirtualDeleteFunctionAddress` is used to represent a function that dispatches to the correct delete implementation.
-* Only the 2 level indirection of `argv` (corresponding to `**argv`) is consided for `FlowSource`.
-
-## 0.9.1
-
-No user-facing changes.
-
-## 0.9.0
-
-### Breaking Changes
-
-* The `shouldPrintFunction` predicate from `PrintAstConfiguration` has been replaced by `shouldPrintDeclaration`. Users should now override `shouldPrintDeclaration` if they want to limit the declarations that should be printed.
-* The `shouldPrintFunction` predicate from `PrintIRConfiguration` has been replaced by `shouldPrintDeclaration`. Users should now override `shouldPrintDeclaration` if they want to limit the declarations that should be printed.
-
-### Major Analysis Improvements
-
-* The `PrintAST` library now also prints global and namespace variables and their initializers.
-
-### Minor Analysis Improvements
-
-* The `_Float128x` type is no longer exposed as a builtin type. As this type could not occur any code base, this should only affect queries that explicitly looked at the builtin types.
-
-## 0.8.1
-
-### Deprecated APIs
-
-* The library `semmle.code.cpp.dataflow.DataFlow` has been deprecated. Please use `semmle.code.cpp.dataflow.new.DataFlow` instead.
-
-### New Features
-
-* The `DataFlow::StateConfigSig` signature module has gained default implementations for `isBarrier/2` and `isAdditionalFlowStep/4`. 
-  Hence it is no longer needed to provide `none()` implementations of these predicates if they are not needed.
-
-### Minor Analysis Improvements
-
-* Data flow configurations can now include a predicate `neverSkip(Node node)`
-  in order to ensure inclusion of certain nodes in the path explanations. The
-  predicate defaults to the end-points of the additional flow steps provided in
-  the configuration, which means that such steps now always are visible by
-  default in path explanations.
-* The `IRGuards` library has improved handling of pointer addition and subtraction operations.
-
-## 0.8.0
-
-### New Features
-
-* The `ProductFlow::StateConfigSig` signature now includes default predicates for `isBarrier1`, `isBarrier2`, `isAdditionalFlowStep1`, and `isAdditionalFlowStep1`. Hence, it is no longer needed to provide `none()` implementations of these predicates if they are not needed.
-
-### Minor Analysis Improvements
-
-* Deleted the deprecated `getURL` predicate from the `Container`, `Folder`, and `File` classes. Use the `getLocation` predicate instead.
-
-## 0.7.4
-
-No user-facing changes.
-
-## 0.7.3
-
-### Minor Analysis Improvements
-
-* Deleted the deprecated `hasCopyConstructor` predicate from the `Class` class in `Class.qll`.
-* Deleted many deprecated predicates and classes with uppercase `AST`, `SSA`, `CFG`, `API`, etc. in their names. Use the PascalCased versions instead.
-* Deleted the deprecated `CodeDuplication.qll` file.
-
-## 0.7.2
-
-### New Features
-
-* Added an AST-based interface (`semmle.code.cpp.rangeanalysis.new.RangeAnalysis`) for the relative range analysis library.
-* A new predicate `BarrierGuard::getAnIndirectBarrierNode` has been added to the new dataflow library (`semmle.code.cpp.dataflow.new.DataFlow`) to mark indirect expressions as barrier nodes using the `BarrierGuard` API.
-
-### Major Analysis Improvements
-
-* In the intermediate representation, handling of control flow after non-returning calls has been improved. This should remove false positives in queries that use the intermedite representation or libraries based on it, including the new data flow library.
-
-### Minor Analysis Improvements
-
-* The `StdNamespace` class now also includes all inline namespaces that are children of `std` namespace.
-* The new dataflow (`semmle.code.cpp.dataflow.new.DataFlow`) and taint-tracking libraries (`semmle.code.cpp.dataflow.new.TaintTracking`) now support tracking flow through static local variables.
-
-## 0.7.1
-
-No user-facing changes.
-
-## 0.7.0
-
-### Breaking Changes
-
-* The internal `SsaConsistency` module has been moved from `SSAConstruction` to `SSAConsitency`, and the deprecated `SSAConsistency` module has been removed.
-
-### Deprecated APIs
-
-* The single-parameter predicates `ArrayOrVectorAggregateLiteral.getElementExpr` and `ClassAggregateLiteral.getFieldExpr` have been deprecated in favor of `ArrayOrVectorAggregateLiteral.getAnElementExpr` and `ClassAggregateLiteral.getAFieldExpr`.
-* The recently introduced new data flow and taint tracking APIs have had a
-  number of module and predicate renamings. The old APIs remain in place for
-  now.
-* The `SslContextCallAbstractConfig`, `SslContextCallConfig`, `SslContextCallBannedProtocolConfig`, `SslContextCallTls12ProtocolConfig`, `SslContextCallTls13ProtocolConfig`, `SslContextCallTlsProtocolConfig`, `SslContextFlowsToSetOptionConfig`, `SslOptionConfig` dataflow configurations from `BoostorgAsio` have been deprecated. Please use `SslContextCallConfigSig`, `SslContextCallGlobal`, `SslContextCallFlow`, `SslContextCallBannedProtocolFlow`, `SslContextCallTls12ProtocolFlow`, `SslContextCallTls13ProtocolFlow`, `SslContextCallTlsProtocolFlow`, `SslContextFlowsToSetOptionFlow`.
-
-### New Features
-
-* Added overridable predicates `getSizeExpr` and `getSizeMult` to the `BufferAccess` class (`semmle.code.cpp.security.BufferAccess.qll`). This makes it possible to model a larger class of buffer reads and writes using the library.
-
-### Minor Analysis Improvements
-
-* The `BufferAccess` library (`semmle.code.cpp.security.BufferAccess`) no longer matches buffer accesses inside unevaluated contexts (such as inside `sizeof` or `decltype` expressions). As a result, queries using this library may see fewer false positives.
-
-### Bug Fixes
-
-* Fixed some accidental predicate visibility in the backwards-compatible wrapper for data flow configurations. In particular `DataFlow::hasFlowPath`, `DataFlow::hasFlow`, `DataFlow::hasFlowTo`, and `DataFlow::hasFlowToExpr` were accidentally exposed in a single version.
-
-## 0.6.1
-
-No user-facing changes.
-
 ## 0.6.0
 
 ### Breaking Changes

cpp/ql/lib/change-notes/2013-03-20-ssa-consistency.md

@@ -0,0 +1,4 @@
+---
+category: breaking
+---
+* The internal `SsaConsistency` module has been moved from `SSAConstruction` to `SSAConsitency`, and the deprecated `SSAConsistency` module has been removed.

cpp/ql/lib/change-notes/2023-03-20-boost-deprecated-dataflow-configurations.md

@@ -0,0 +1,4 @@
+---
+category: deprecated
+---
+* The `SslContextCallAbstractConfig`, `SslContextCallConfig`, `SslContextCallBannedProtocolConfig`, `SslContextCallTls12ProtocolConfig`, `SslContextCallTls13ProtocolConfig`, `SslContextCallTlsProtocolConfig`, `SslContextFlowsToSetOptionConfig`, `SslOptionConfig` dataflow configurations from `BoostorgAsio` have been deprecated. Please use `SslContextCallConfigSig`, `SslContextCallMake`, `SslContextCallFlow`, `SslContextCallBannedProtocolFlow`, `SslContextCallTls12ProtocolFlow`, `SslContextCallTls13ProtocolFlow`, `SslContextCallTlsProtocolFlow`, `SslContextFlowsToSetOptionFlow`.

cpp/ql/lib/change-notes/2023-03-21-buffer-access.md

@@ -0,0 +1,4 @@
+---
+category: minorAnalysis
+---
+* The `BufferAccess` library (`semmle.code.cpp.security.BufferAccess`) no longer matches buffer accesses inside unevaluated contexts (such as inside `sizeof` or `decltype` expressions). As a result, queries using this library may see fewer false positives.

cpp/ql/lib/change-notes/released/0.10.0.md

@@ -1,9 +0,0 @@
-## 0.10.0
-
-### Minor Analysis Improvements
-
-* Functions that do not return due to calling functions that don't return (e.g. `exit`) are now detected as
- non-returning in the IR and dataflow.
-* Treat functions that reach the end of the function as returning in the IR.
-  They used to be treated as unreachable but it is allowed in C. 
-* The `DataFlow::asDefiningArgument` predicate now takes its argument from the range starting at `1` instead of `2`. Queries that depend on the single-parameter version of `DataFlow::asDefiningArgument` should have their arguments updated accordingly.

cpp/ql/lib/change-notes/released/0.6.1.md

@@ -1,3 +0,0 @@
-## 0.6.1
-
-No user-facing changes.

cpp/ql/lib/change-notes/released/0.7.0.md

@@ -1,25 +0,0 @@
-## 0.7.0
-
-### Breaking Changes
-
-* The internal `SsaConsistency` module has been moved from `SSAConstruction` to `SSAConsitency`, and the deprecated `SSAConsistency` module has been removed.
-
-### Deprecated APIs
-
-* The single-parameter predicates `ArrayOrVectorAggregateLiteral.getElementExpr` and `ClassAggregateLiteral.getFieldExpr` have been deprecated in favor of `ArrayOrVectorAggregateLiteral.getAnElementExpr` and `ClassAggregateLiteral.getAFieldExpr`.
-* The recently introduced new data flow and taint tracking APIs have had a
-  number of module and predicate renamings. The old APIs remain in place for
-  now.
-* The `SslContextCallAbstractConfig`, `SslContextCallConfig`, `SslContextCallBannedProtocolConfig`, `SslContextCallTls12ProtocolConfig`, `SslContextCallTls13ProtocolConfig`, `SslContextCallTlsProtocolConfig`, `SslContextFlowsToSetOptionConfig`, `SslOptionConfig` dataflow configurations from `BoostorgAsio` have been deprecated. Please use `SslContextCallConfigSig`, `SslContextCallGlobal`, `SslContextCallFlow`, `SslContextCallBannedProtocolFlow`, `SslContextCallTls12ProtocolFlow`, `SslContextCallTls13ProtocolFlow`, `SslContextCallTlsProtocolFlow`, `SslContextFlowsToSetOptionFlow`.
-
-### New Features
-
-* Added overridable predicates `getSizeExpr` and `getSizeMult` to the `BufferAccess` class (`semmle.code.cpp.security.BufferAccess.qll`). This makes it possible to model a larger class of buffer reads and writes using the library.
-
-### Minor Analysis Improvements
-
-* The `BufferAccess` library (`semmle.code.cpp.security.BufferAccess`) no longer matches buffer accesses inside unevaluated contexts (such as inside `sizeof` or `decltype` expressions). As a result, queries using this library may see fewer false positives.
-
-### Bug Fixes
-
-* Fixed some accidental predicate visibility in the backwards-compatible wrapper for data flow configurations. In particular `DataFlow::hasFlowPath`, `DataFlow::hasFlow`, `DataFlow::hasFlowTo`, and `DataFlow::hasFlowToExpr` were accidentally exposed in a single version.

cpp/ql/lib/change-notes/released/0.7.1.md

@@ -1,3 +0,0 @@
-## 0.7.1
-
-No user-facing changes.

cpp/ql/lib/change-notes/released/0.7.2.md

@@ -1,15 +0,0 @@
-## 0.7.2
-
-### New Features
-
-* Added an AST-based interface (`semmle.code.cpp.rangeanalysis.new.RangeAnalysis`) for the relative range analysis library.
-* A new predicate `BarrierGuard::getAnIndirectBarrierNode` has been added to the new dataflow library (`semmle.code.cpp.dataflow.new.DataFlow`) to mark indirect expressions as barrier nodes using the `BarrierGuard` API.
-
-### Major Analysis Improvements
-
-* In the intermediate representation, handling of control flow after non-returning calls has been improved. This should remove false positives in queries that use the intermedite representation or libraries based on it, including the new data flow library.
-
-### Minor Analysis Improvements
-
-* The `StdNamespace` class now also includes all inline namespaces that are children of `std` namespace.
-* The new dataflow (`semmle.code.cpp.dataflow.new.DataFlow`) and taint-tracking libraries (`semmle.code.cpp.dataflow.new.TaintTracking`) now support tracking flow through static local variables.

cpp/ql/lib/change-notes/released/0.7.3.md

@@ -1,7 +0,0 @@
-## 0.7.3
-
-### Minor Analysis Improvements
-
-* Deleted the deprecated `hasCopyConstructor` predicate from the `Class` class in `Class.qll`.
-* Deleted many deprecated predicates and classes with uppercase `AST`, `SSA`, `CFG`, `API`, etc. in their names. Use the PascalCased versions instead.
-* Deleted the deprecated `CodeDuplication.qll` file.

cpp/ql/lib/change-notes/released/0.7.4.md

@@ -1,3 +0,0 @@
-## 0.7.4
-
-No user-facing changes.

cpp/ql/lib/change-notes/released/0.8.0.md

@@ -1,9 +0,0 @@
-## 0.8.0
-
-### New Features
-
-* The `ProductFlow::StateConfigSig` signature now includes default predicates for `isBarrier1`, `isBarrier2`, `isAdditionalFlowStep1`, and `isAdditionalFlowStep1`. Hence, it is no longer needed to provide `none()` implementations of these predicates if they are not needed.
-
-### Minor Analysis Improvements
-
-* Deleted the deprecated `getURL` predicate from the `Container`, `Folder`, and `File` classes. Use the `getLocation` predicate instead.

cpp/ql/lib/change-notes/released/0.8.1.md

@@ -1,19 +0,0 @@
-## 0.8.1
-
-### Deprecated APIs
-
-* The library `semmle.code.cpp.dataflow.DataFlow` has been deprecated. Please use `semmle.code.cpp.dataflow.new.DataFlow` instead.
-
-### New Features
-
-* The `DataFlow::StateConfigSig` signature module has gained default implementations for `isBarrier/2` and `isAdditionalFlowStep/4`. 
-  Hence it is no longer needed to provide `none()` implementations of these predicates if they are not needed.
-
-### Minor Analysis Improvements
-
-* Data flow configurations can now include a predicate `neverSkip(Node node)`
-  in order to ensure inclusion of certain nodes in the path explanations. The
-  predicate defaults to the end-points of the additional flow steps provided in
-  the configuration, which means that such steps now always are visible by
-  default in path explanations.
-* The `IRGuards` library has improved handling of pointer addition and subtraction operations.

cpp/ql/lib/change-notes/released/0.9.0.md

@@ -1,14 +0,0 @@
-## 0.9.0
-
-### Breaking Changes
-
-* The `shouldPrintFunction` predicate from `PrintAstConfiguration` has been replaced by `shouldPrintDeclaration`. Users should now override `shouldPrintDeclaration` if they want to limit the declarations that should be printed.
-* The `shouldPrintFunction` predicate from `PrintIRConfiguration` has been replaced by `shouldPrintDeclaration`. Users should now override `shouldPrintDeclaration` if they want to limit the declarations that should be printed.
-
-### Major Analysis Improvements
-
-* The `PrintAST` library now also prints global and namespace variables and their initializers.
-
-### Minor Analysis Improvements
-
-* The `_Float128x` type is no longer exposed as a builtin type. As this type could not occur any code base, this should only affect queries that explicitly looked at the builtin types.

cpp/ql/lib/change-notes/released/0.9.1.md

@@ -1,3 +0,0 @@
-## 0.9.1
-
-No user-facing changes.

cpp/ql/lib/change-notes/released/0.9.2.md

@@ -1,14 +0,0 @@
-## 0.9.2
-
-### Deprecated APIs
-
-* `getAllocatorCall` on `DeleteExpr` and `DeleteArrayExpr` has been deprecated. `getDeallocatorCall` should be used instead.
-
-### New Features
-
-* Added `DeleteOrDeleteArrayExpr` as a super type of `DeleteExpr` and `DeleteArrayExpr`
-
-### Minor Analysis Improvements
-
-* `delete` and `delete[]` are now modeled as calls to the relevant `operator delete` in the IR. In the case of a dynamic delete call a new instruction `VirtualDeleteFunctionAddress` is used to represent a function that dispatches to the correct delete implementation.
-* Only the 2 level indirection of `argv` (corresponding to `**argv`) is consided for `FlowSource`.

cpp/ql/lib/change-notes/released/0.9.3.md

@@ -1,3 +0,0 @@
-## 0.9.3
-
-No user-facing changes.

cpp/ql/lib/codeql-pack.release.yml

@@ -1,2 +1,2 @@
 ---
-lastReleaseVersion: 0.10.0
+lastReleaseVersion: 0.6.0

cpp/ql/lib/experimental/semmle/code/cpp/dataflow/ProductFlow.qll

@@ -0,0 +1,301 @@
+import semmle.code.cpp.ir.dataflow.DataFlow
+import semmle.code.cpp.ir.dataflow.DataFlow2
+
+module ProductFlow {
+  abstract class Configuration extends string {
+    bindingset[this]
+    Configuration() { any() }
+
+    /**
+     * Holds if `(source1, source2)` is a relevant data flow source.
+     *
+     * `source1` and `source2` must belong to the same callable.
+     */
+    predicate isSourcePair(DataFlow::Node source1, DataFlow::Node source2) { none() }
+
+    /**
+     * Holds if `(source1, source2)` is a relevant data flow source with initial states `state1`
+     * and `state2`, respectively.
+     *
+     * `source1` and `source2` must belong to the same callable.
+     */
+    predicate isSourcePair(
+      DataFlow::Node source1, DataFlow::FlowState state1, DataFlow::Node source2,
+      DataFlow::FlowState state2
+    ) {
+      state1 = "" and
+      state2 = "" and
+      this.isSourcePair(source1, source2)
+    }
+
+    /**
+     * Holds if `(sink1, sink2)` is a relevant data flow sink.
+     *
+     * `sink1` and `sink2` must belong to the same callable.
+     */
+    predicate isSinkPair(DataFlow::Node sink1, DataFlow::Node sink2) { none() }
+
+    /**
+     * Holds if `(sink1, sink2)` is a relevant data flow sink with final states `state1`
+     * and `state2`, respectively.
+     *
+     * `sink1` and `sink2` must belong to the same callable.
+     */
+    predicate isSinkPair(
+      DataFlow::Node sink1, DataFlow::FlowState state1, DataFlow::Node sink2,
+      DataFlow::FlowState state2
+    ) {
+      state1 = "" and
+      state2 = "" and
+      this.isSinkPair(sink1, sink2)
+    }
+
+    /**
+     * Holds if data flow through `node` is prohibited through the first projection of the product
+     * dataflow graph when the flow state is `state`.
+     */
+    predicate isBarrier1(DataFlow::Node node, DataFlow::FlowState state) {
+      this.isBarrier1(node) and state = ""
+    }
+
+    /**
+     * Holds if data flow through `node` is prohibited through the second projection of the product
+     * dataflow graph when the flow state is `state`.
+     */
+    predicate isBarrier2(DataFlow::Node node, DataFlow::FlowState state) {
+      this.isBarrier2(node) and state = ""
+    }
+
+    /**
+     * Holds if data flow through `node` is prohibited through the first projection of the product
+     * dataflow graph.
+     */
+    predicate isBarrier1(DataFlow::Node node) { none() }
+
+    /**
+     * Holds if data flow through `node` is prohibited through the second projection of the product
+     * dataflow graph.
+     */
+    predicate isBarrier2(DataFlow::Node node) { none() }
+
+    /**
+     * Holds if data flow out of `node` is prohibited in the first projection of the product
+     * dataflow graph.
+     */
+    predicate isBarrierOut1(DataFlow::Node node) { none() }
+
+    /**
+     * Holds if data flow out of `node` is prohibited in the second projection of the product
+     * dataflow graph.
+     */
+    predicate isBarrierOut2(DataFlow::Node node) { none() }
+
+    /*
+     * Holds if data may flow from `node1` to `node2` in addition to the normal data-flow steps in
+     * the first projection of the product dataflow graph.
+     */
+
+    predicate isAdditionalFlowStep1(DataFlow::Node node1, DataFlow::Node node2) { none() }
+
+    /**
+     * Holds if data may flow from `node1` to `node2` in addition to the normal data-flow steps in
+     * the first projection of the product dataflow graph.
+     *
+     * This step is only applicable in `state1` and updates the flow state to `state2`.
+     */
+    predicate isAdditionalFlowStep1(
+      DataFlow::Node node1, DataFlow::FlowState state1, DataFlow::Node node2,
+      DataFlow::FlowState state2
+    ) {
+      state1 instanceof DataFlow::FlowStateEmpty and
+      state2 instanceof DataFlow::FlowStateEmpty and
+      this.isAdditionalFlowStep1(node1, node2)
+    }
+
+    /**
+     * Holds if data may flow from `node1` to `node2` in addition to the normal data-flow steps in
+     * the second projection of the product dataflow graph.
+     */
+    predicate isAdditionalFlowStep2(DataFlow::Node node1, DataFlow::Node node2) { none() }
+
+    /**
+     * Holds if data may flow from `node1` to `node2` in addition to the normal data-flow steps in
+     * the second projection of the product dataflow graph.
+     *
+     * This step is only applicable in `state1` and updates the flow state to `state2`.
+     */
+    predicate isAdditionalFlowStep2(
+      DataFlow::Node node1, DataFlow::FlowState state1, DataFlow::Node node2,
+      DataFlow::FlowState state2
+    ) {
+      state1 instanceof DataFlow::FlowStateEmpty and
+      state2 instanceof DataFlow::FlowStateEmpty and
+      this.isAdditionalFlowStep2(node1, node2)
+    }
+
+    /**
+     * Holds if data flow into `node` is prohibited in the first projection of the product
+     * dataflow graph.
+     */
+    predicate isBarrierIn1(DataFlow::Node node) { none() }
+
+    /**
+     * Holds if data flow into `node` is prohibited in the second projection of the product
+     * dataflow graph.
+     */
+    predicate isBarrierIn2(DataFlow::Node node) { none() }
+
+    predicate hasFlowPath(
+      DataFlow::PathNode source1, DataFlow2::PathNode source2, DataFlow::PathNode sink1,
+      DataFlow2::PathNode sink2
+    ) {
+      reachable(this, source1, source2, sink1, sink2)
+    }
+  }
+
+  private import Internal
+
+  module Internal {
+    class Conf1 extends DataFlow::Configuration {
+      Conf1() { this = "Conf1" }
+
+      override predicate isSource(DataFlow::Node source, DataFlow::FlowState state) {
+        exists(Configuration conf | conf.isSourcePair(source, state, _, _))
+      }
+
+      override predicate isSink(DataFlow::Node sink, DataFlow::FlowState state) {
+        exists(Configuration conf | conf.isSinkPair(sink, state, _, _))
+      }
+
+      override predicate isBarrier(DataFlow::Node node, DataFlow::FlowState state) {
+        exists(Configuration conf | conf.isBarrier1(node, state))
+      }
+
+      override predicate isBarrierOut(DataFlow::Node node) {
+        exists(Configuration conf | conf.isBarrierOut1(node))
+      }
+
+      override predicate isAdditionalFlowStep(
+        DataFlow::Node node1, DataFlow::FlowState state1, DataFlow::Node node2,
+        DataFlow::FlowState state2
+      ) {
+        exists(Configuration conf | conf.isAdditionalFlowStep1(node1, state1, node2, state2))
+      }
+
+      override predicate isBarrierIn(DataFlow::Node node) {
+        exists(Configuration conf | conf.isBarrierIn1(node))
+      }
+    }
+
+    class Conf2 extends DataFlow2::Configuration {
+      Conf2() { this = "Conf2" }
+
+      override predicate isSource(DataFlow::Node source, DataFlow::FlowState state) {
+        exists(Configuration conf, DataFlow::PathNode source1 |
+          conf.isSourcePair(source1.getNode(), source1.getState(), source, state) and
+          any(Conf1 c).hasFlowPath(source1, _)
+        )
+      }
+
+      override predicate isSink(DataFlow::Node sink, DataFlow::FlowState state) {
+        exists(Configuration conf, DataFlow::PathNode sink1 |
+          conf.isSinkPair(sink1.getNode(), sink1.getState(), sink, state) and
+          any(Conf1 c).hasFlowPath(_, sink1)
+        )
+      }
+
+      override predicate isBarrier(DataFlow::Node node, DataFlow::FlowState state) {
+        exists(Configuration conf | conf.isBarrier2(node, state))
+      }
+
+      override predicate isBarrierOut(DataFlow::Node node) {
+        exists(Configuration conf | conf.isBarrierOut2(node))
+      }
+
+      override predicate isAdditionalFlowStep(
+        DataFlow::Node node1, DataFlow::FlowState state1, DataFlow::Node node2,
+        DataFlow::FlowState state2
+      ) {
+        exists(Configuration conf | conf.isAdditionalFlowStep2(node1, state1, node2, state2))
+      }
+
+      override predicate isBarrierIn(DataFlow::Node node) {
+        exists(Configuration conf | conf.isBarrierIn2(node))
+      }
+    }
+  }
+
+  pragma[nomagic]
+  private predicate reachableInterprocEntry(
+    Configuration conf, DataFlow::PathNode source1, DataFlow2::PathNode source2,
+    DataFlow::PathNode node1, DataFlow2::PathNode node2
+  ) {
+    conf.isSourcePair(node1.getNode(), node1.getState(), node2.getNode(), node2.getState()) and
+    node1 = source1 and
+    node2 = source2
+    or
+    exists(
+      DataFlow::PathNode midEntry1, DataFlow2::PathNode midEntry2, DataFlow::PathNode midExit1,
+      DataFlow2::PathNode midExit2
+    |
+      reachableInterprocEntry(conf, source1, source2, midEntry1, midEntry2) and
+      interprocEdgePair(midExit1, midExit2, node1, node2) and
+      localPathStep1*(midEntry1, midExit1) and
+      localPathStep2*(midEntry2, midExit2)
+    )
+  }
+
+  private predicate localPathStep1(DataFlow::PathNode pred, DataFlow::PathNode succ) {
+    DataFlow::PathGraph::edges(pred, succ) and
+    pragma[only_bind_out](pred.getNode().getEnclosingCallable()) =
+      pragma[only_bind_out](succ.getNode().getEnclosingCallable())
+  }
+
+  private predicate localPathStep2(DataFlow2::PathNode pred, DataFlow2::PathNode succ) {
+    DataFlow2::PathGraph::edges(pred, succ) and
+    pragma[only_bind_out](pred.getNode().getEnclosingCallable()) =
+      pragma[only_bind_out](succ.getNode().getEnclosingCallable())
+  }
+
+  pragma[nomagic]
+  private predicate interprocEdge1(
+    Declaration predDecl, Declaration succDecl, DataFlow::PathNode pred1, DataFlow::PathNode succ1
+  ) {
+    DataFlow::PathGraph::edges(pred1, succ1) and
+    predDecl != succDecl and
+    pred1.getNode().getEnclosingCallable() = predDecl and
+    succ1.getNode().getEnclosingCallable() = succDecl
+  }
+
+  pragma[nomagic]
+  private predicate interprocEdge2(
+    Declaration predDecl, Declaration succDecl, DataFlow2::PathNode pred2, DataFlow2::PathNode succ2
+  ) {
+    DataFlow2::PathGraph::edges(pred2, succ2) and
+    predDecl != succDecl and
+    pred2.getNode().getEnclosingCallable() = predDecl and
+    succ2.getNode().getEnclosingCallable() = succDecl
+  }
+
+  private predicate interprocEdgePair(
+    DataFlow::PathNode pred1, DataFlow2::PathNode pred2, DataFlow::PathNode succ1,
+    DataFlow2::PathNode succ2
+  ) {
+    exists(Declaration predDecl, Declaration succDecl |
+      interprocEdge1(predDecl, succDecl, pred1, succ1) and
+      interprocEdge2(predDecl, succDecl, pred2, succ2)
+    )
+  }
+
+  private predicate reachable(
+    Configuration conf, DataFlow::PathNode source1, DataFlow2::PathNode source2,
+    DataFlow::PathNode sink1, DataFlow2::PathNode sink2
+  ) {
+    exists(DataFlow::PathNode mid1, DataFlow2::PathNode mid2 |
+      reachableInterprocEntry(conf, source1, source2, mid1, mid2) and
+      conf.isSinkPair(sink1.getNode(), sink1.getState(), sink2.getNode(), sink2.getState()) and
+      localPathStep1*(mid1, sink1) and
+      localPathStep2*(mid2, sink2)
+    )
+  }
+}

cpp/ql/lib/experimental/semmle/code/cpp/rangeanalysis/Bound.qll

@@ -1 +1,86 @@
-import semmle.code.cpp.rangeanalysis.new.internal.semantic.analysis.Bound
+import cpp
+private import semmle.code.cpp.ir.IR
+private import semmle.code.cpp.ir.ValueNumbering
+
+private newtype TBound =
+  TBoundZero() or
+  TBoundValueNumber(ValueNumber vn) {
+    exists(Instruction i |
+      vn.getAnInstruction() = i and
+      (
+        i.getResultIRType() instanceof IRIntegerType or
+        i.getResultIRType() instanceof IRAddressType
+      ) and
+      not vn.getAnInstruction() instanceof ConstantInstruction
+    |
+      i instanceof PhiInstruction
+      or
+      i instanceof InitializeParameterInstruction
+      or
+      i instanceof CallInstruction
+      or
+      i instanceof VariableAddressInstruction
+      or
+      i instanceof FieldAddressInstruction
+      or
+      i.(LoadInstruction).getSourceAddress() instanceof VariableAddressInstruction
+      or
+      i.(LoadInstruction).getSourceAddress() instanceof FieldAddressInstruction
+      or
+      i.getAUse() instanceof ArgumentOperand
+      or
+      i instanceof PointerArithmeticInstruction
+      or
+      i.getAUse() instanceof AddressOperand
+    )
+  }
+
+/**
+ * A bound that may be inferred for an expression plus/minus an integer delta.
+ */
+abstract class Bound extends TBound {
+  abstract string toString();
+
+  /** Gets an expression that equals this bound plus `delta`. */
+  abstract Instruction getInstruction(int delta);
+
+  /** Gets an expression that equals this bound. */
+  Instruction getInstruction() { result = getInstruction(0) }
+
+  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 Instruction getInstruction(int delta) {
+    result.(ConstantValueInstruction).getValue().toInt() = delta
+  }
+
+  override Location getLocation() { result instanceof UnknownDefaultLocation }
+}
+
+/**
+ * A bound corresponding to the value of an `Instruction`.
+ */
+class ValueNumberBound extends Bound, TBoundValueNumber {
+  ValueNumber vn;
+
+  ValueNumberBound() { this = TBoundValueNumber(vn) }
+
+  /** Gets an `Instruction` that equals this bound. */
+  override Instruction getInstruction(int delta) {
+    this = TBoundValueNumber(valueNumber(result)) and delta = 0
+  }
+
+  override string toString() { result = "ValueNumberBound" }
+
+  override Location getLocation() { result = vn.getLocation() }
+
+  /** Gets the value number that equals this bound. */
+  ValueNumber getValueNumber() { result = vn }
+}

cpp/ql/lib/experimental/semmle/code/cpp/rangeanalysis/ExtendedRangeAnalysis.qll

@@ -3,4 +3,3 @@ import semmle.code.cpp.rangeanalysis.SimpleRangeAnalysis
 // Import each extension we want to enable
 import extensions.SubtractSelf
 import extensions.ConstantBitwiseAndExprRange
-import extensions.StrlenLiteralRangeExpr

cpp/ql/lib/experimental/semmle/code/cpp/rangeanalysis/RangeAnalysis.qll

@@ -238,7 +238,7 @@ class NoReason extends Reason, TNoReason {
 class CondReason extends Reason, TCondReason {
   IRGuardCondition getCond() { this = TCondReason(result) }
 
-  override string toString() { result = this.getCond().toString() }
+  override string toString() { result = getCond().toString() }
 }
 
 /**
@@ -260,14 +260,14 @@ private predicate typeBound(IRIntegerType typ, int lowerbound, int upperbound) {
 private class NarrowingCastInstruction extends ConvertInstruction {
   NarrowingCastInstruction() {
     not this instanceof SafeCastInstruction and
-    typeBound(this.getResultIRType(), _, _)
+    typeBound(getResultIRType(), _, _)
   }
 
   /** Gets the lower bound of the resulting type. */
-  int getLowerBound() { typeBound(this.getResultIRType(), result, _) }
+  int getLowerBound() { typeBound(getResultIRType(), result, _) }
 
   /** Gets the upper bound of the resulting type. */
-  int getUpperBound() { typeBound(this.getResultIRType(), _, result) }
+  int getUpperBound() { typeBound(getResultIRType(), _, result) }
 }
 
 /**

cpp/ql/lib/experimental/semmle/code/cpp/rangeanalysis/RangeUtils.qll

@@ -109,8 +109,8 @@ private predicate safeCast(IRIntegerType fromtyp, IRIntegerType totyp) {
  */
 class PtrToPtrCastInstruction extends ConvertInstruction {
   PtrToPtrCastInstruction() {
-    this.getResultIRType() instanceof IRAddressType and
-    this.getUnary().getResultIRType() instanceof IRAddressType
+    getResultIRType() instanceof IRAddressType and
+    getUnary().getResultIRType() instanceof IRAddressType
   }
 }
 
@@ -119,7 +119,7 @@ class PtrToPtrCastInstruction extends ConvertInstruction {
  * that cannot overflow or underflow.
  */
 class SafeIntCastInstruction extends ConvertInstruction {
-  SafeIntCastInstruction() { safeCast(this.getUnary().getResultIRType(), this.getResultIRType()) }
+  SafeIntCastInstruction() { safeCast(getUnary().getResultIRType(), getResultIRType()) }
 }
 
 /**

cpp/ql/lib/experimental/semmle/code/cpp/rangeanalysis/extensions/ConstantBitwiseAndExprRange.qll

@@ -50,8 +50,8 @@ private class ConstantBitwiseAndExprRange extends SimpleRangeAnalysisExpr {
     // If an operand can have negative values, the lower bound is unconstrained.
     // Otherwise, the lower bound is zero.
     exists(float lLower, float rLower |
-      lLower = getFullyConvertedLowerBounds(this.getLeftOperand()) and
-      rLower = getFullyConvertedLowerBounds(this.getRightOperand()) and
+      lLower = getFullyConvertedLowerBounds(getLeftOperand()) and
+      rLower = getFullyConvertedLowerBounds(getRightOperand()) and
       (
         (lLower < 0 or rLower < 0) and
         result = exprMinVal(this)
@@ -68,10 +68,10 @@ private class ConstantBitwiseAndExprRange extends SimpleRangeAnalysisExpr {
     // If an operand can have negative values, the upper bound is unconstrained.
     // Otherwise, the upper bound is the minimum of the upper bounds of the operands
     exists(float lLower, float lUpper, float rLower, float rUpper |
-      lLower = getFullyConvertedLowerBounds(this.getLeftOperand()) and
-      lUpper = getFullyConvertedUpperBounds(this.getLeftOperand()) and
-      rLower = getFullyConvertedLowerBounds(this.getRightOperand()) and
-      rUpper = getFullyConvertedUpperBounds(this.getRightOperand()) and
+      lLower = getFullyConvertedLowerBounds(getLeftOperand()) and
+      lUpper = getFullyConvertedUpperBounds(getLeftOperand()) and
+      rLower = getFullyConvertedLowerBounds(getRightOperand()) and
+      rUpper = getFullyConvertedUpperBounds(getRightOperand()) and
       (
         (lLower < 0 or rLower < 0) and
         result = exprMaxVal(this)
@@ -85,6 +85,6 @@ private class ConstantBitwiseAndExprRange extends SimpleRangeAnalysisExpr {
   }
 
   override predicate dependsOnChild(Expr child) {
-    child = this.getLeftOperand() or child = this.getRightOperand()
+    child = getLeftOperand() or child = getRightOperand()
   }
 }

cpp/ql/lib/experimental/semmle/code/cpp/rangeanalysis/extensions/ConstantShiftExprRange.qll

@@ -50,7 +50,7 @@ class ConstantRShiftExprRange extends SimpleRangeAnalysisExpr {
    * We don't handle the case where `a` and `b` are both non-constant values.
    */
   ConstantRShiftExprRange() {
-    this.getUnspecifiedType() instanceof IntegralType and
+    getUnspecifiedType() instanceof IntegralType and
     exists(Expr l, Expr r |
       l = this.(RShiftExpr).getLeftOperand() and
       r = this.(RShiftExpr).getRightOperand()
@@ -84,10 +84,10 @@ class ConstantRShiftExprRange extends SimpleRangeAnalysisExpr {
 
   override float getLowerBounds() {
     exists(int lLower, int lUpper, int rLower, int rUpper |
-      lLower = getFullyConvertedLowerBounds(this.getLeftOperand()) and
-      lUpper = getFullyConvertedUpperBounds(this.getLeftOperand()) and
-      rLower = getFullyConvertedLowerBounds(this.getRightOperand()) and
-      rUpper = getFullyConvertedUpperBounds(this.getRightOperand()) and
+      lLower = getFullyConvertedLowerBounds(getLeftOperand()) and
+      lUpper = getFullyConvertedUpperBounds(getLeftOperand()) and
+      rLower = getFullyConvertedLowerBounds(getRightOperand()) and
+      rUpper = getFullyConvertedUpperBounds(getRightOperand()) and
       lLower <= lUpper and
       rLower <= rUpper
     |
@@ -95,8 +95,8 @@ class ConstantRShiftExprRange extends SimpleRangeAnalysisExpr {
         lLower < 0
         or
         not (
-          isValidShiftExprShift(rLower, this.getLeftOperand()) and
-          isValidShiftExprShift(rUpper, this.getLeftOperand())
+          isValidShiftExprShift(rLower, getLeftOperand()) and
+          isValidShiftExprShift(rUpper, getLeftOperand())
         )
       then
         // We don't want to deal with shifting negative numbers at the moment,
@@ -111,10 +111,10 @@ class ConstantRShiftExprRange extends SimpleRangeAnalysisExpr {
 
   override float getUpperBounds() {
     exists(int lLower, int lUpper, int rLower, int rUpper |
-      lLower = getFullyConvertedLowerBounds(this.getLeftOperand()) and
-      lUpper = getFullyConvertedUpperBounds(this.getLeftOperand()) and
-      rLower = getFullyConvertedLowerBounds(this.getRightOperand()) and
-      rUpper = getFullyConvertedUpperBounds(this.getRightOperand()) and
+      lLower = getFullyConvertedLowerBounds(getLeftOperand()) and
+      lUpper = getFullyConvertedUpperBounds(getLeftOperand()) and
+      rLower = getFullyConvertedLowerBounds(getRightOperand()) and
+      rUpper = getFullyConvertedUpperBounds(getRightOperand()) and
       lLower <= lUpper and
       rLower <= rUpper
     |
@@ -122,8 +122,8 @@ class ConstantRShiftExprRange extends SimpleRangeAnalysisExpr {
         lLower < 0
         or
         not (
-          isValidShiftExprShift(rLower, this.getLeftOperand()) and
-          isValidShiftExprShift(rUpper, this.getLeftOperand())
+          isValidShiftExprShift(rLower, getLeftOperand()) and
+          isValidShiftExprShift(rUpper, getLeftOperand())
         )
       then
         // We don't want to deal with shifting negative numbers at the moment,
@@ -137,7 +137,7 @@ class ConstantRShiftExprRange extends SimpleRangeAnalysisExpr {
   }
 
   override predicate dependsOnChild(Expr child) {
-    child = this.getLeftOperand() or child = this.getRightOperand()
+    child = getLeftOperand() or child = getRightOperand()
   }
 }
 
@@ -163,7 +163,7 @@ class ConstantLShiftExprRange extends SimpleRangeAnalysisExpr {
    * We don't handle the case where `a` and `b` are both non-constant values.
    */
   ConstantLShiftExprRange() {
-    this.getUnspecifiedType() instanceof IntegralType and
+    getUnspecifiedType() instanceof IntegralType and
     exists(Expr l, Expr r |
       l = this.(LShiftExpr).getLeftOperand() and
       r = this.(LShiftExpr).getRightOperand()
@@ -197,10 +197,10 @@ class ConstantLShiftExprRange extends SimpleRangeAnalysisExpr {
 
   override float getLowerBounds() {
     exists(int lLower, int lUpper, int rLower, int rUpper |
-      lLower = getFullyConvertedLowerBounds(this.getLeftOperand()) and
-      lUpper = getFullyConvertedUpperBounds(this.getLeftOperand()) and
-      rLower = getFullyConvertedLowerBounds(this.getRightOperand()) and
-      rUpper = getFullyConvertedUpperBounds(this.getRightOperand()) and
+      lLower = getFullyConvertedLowerBounds(getLeftOperand()) and
+      lUpper = getFullyConvertedUpperBounds(getLeftOperand()) and
+      rLower = getFullyConvertedLowerBounds(getRightOperand()) and
+      rUpper = getFullyConvertedUpperBounds(getRightOperand()) and
       lLower <= lUpper and
       rLower <= rUpper
     |
@@ -208,8 +208,8 @@ class ConstantLShiftExprRange extends SimpleRangeAnalysisExpr {
         lLower < 0
         or
         not (
-          isValidShiftExprShift(rLower, this.getLeftOperand()) and
-          isValidShiftExprShift(rUpper, this.getLeftOperand())
+          isValidShiftExprShift(rLower, getLeftOperand()) and
+          isValidShiftExprShift(rUpper, getLeftOperand())
         )
       then
         // We don't want to deal with shifting negative numbers at the moment,
@@ -228,10 +228,10 @@ class ConstantLShiftExprRange extends SimpleRangeAnalysisExpr {
 
   override float getUpperBounds() {
     exists(int lLower, int lUpper, int rLower, int rUpper |
-      lLower = getFullyConvertedLowerBounds(this.getLeftOperand()) and
-      lUpper = getFullyConvertedUpperBounds(this.getLeftOperand()) and
-      rLower = getFullyConvertedLowerBounds(this.getRightOperand()) and
-      rUpper = getFullyConvertedUpperBounds(this.getRightOperand()) and
+      lLower = getFullyConvertedLowerBounds(getLeftOperand()) and
+      lUpper = getFullyConvertedUpperBounds(getLeftOperand()) and
+      rLower = getFullyConvertedLowerBounds(getRightOperand()) and
+      rUpper = getFullyConvertedUpperBounds(getRightOperand()) and
       lLower <= lUpper and
       rLower <= rUpper
     |
@@ -239,8 +239,8 @@ class ConstantLShiftExprRange extends SimpleRangeAnalysisExpr {
         lLower < 0
         or
         not (
-          isValidShiftExprShift(rLower, this.getLeftOperand()) and
-          isValidShiftExprShift(rUpper, this.getLeftOperand())
+          isValidShiftExprShift(rLower, getLeftOperand()) and
+          isValidShiftExprShift(rUpper, getLeftOperand())
         )
       then
         // We don't want to deal with shifting negative numbers at the moment,
@@ -258,6 +258,6 @@ class ConstantLShiftExprRange extends SimpleRangeAnalysisExpr {
   }
 
   override predicate dependsOnChild(Expr child) {
-    child = this.getLeftOperand() or child = this.getRightOperand()
+    child = getLeftOperand() or child = getRightOperand()
   }
 }

cpp/ql/lib/experimental/semmle/code/cpp/rangeanalysis/extensions/RangeNode.qll

@@ -1,118 +0,0 @@
-/**
- * This module implements subclasses for various DataFlow nodes that extends
- * their `toString()` predicates with range information, if applicable. By
- * including this module in a `path-problem` query, this range information
- * will be displayed at each step in the query results.
- *
- * This is currently implemented for `DataFlow::ExprNode` and `DataFlow::DefinitionByReferenceNode`,
- * but it is not yet implemented for `DataFlow::ParameterNode`.
- */
-
-private import cpp
-private import semmle.code.cpp.dataflow.DataFlow
-private import semmle.code.cpp.rangeanalysis.SimpleRangeAnalysis
-
-string getExprBoundAsString(Expr e) {
-  if exists(lowerBound(e)) and exists(upperBound(e))
-  then result = "[" + lowerBound(e) + ", " + upperBound(e) + "]"
-  else result = "[unknown range]"
-}
-
-/**
- * Holds for any integer type after resolving typedefs and stripping `const`
- * specifiers, such as for `const size_t`
- */
-predicate isIntegralType(Type t) {
-  // We use `getUnspecifiedType` here because without it things like
-  // `const size_t` aren't considered to be integral
-  t.getUnspecifiedType() instanceof IntegralType
-}
-
-/**
- * Holds for any reference to an integer type after resolving typedefs and
- * stripping `const` specifiers, such as for `const size_t&`
- */
-predicate isIntegralReferenceType(Type t) { isIntegralType(t.(ReferenceType).stripType()) }
-
-/**
- * Holds for any pointer to an integer type after resolving typedefs and
- * stripping `const` specifiers, such as for `const size_t*`. This predicate
- * holds for any pointer depth, such as for `const size_t**`.
- */
-predicate isIntegralPointerType(Type t) { isIntegralType(t.(PointerType).stripType()) }
-
-predicate hasIntegralOrReferenceIntegralType(Locatable e) {
-  exists(Type t |
-    (
-      t = e.(Expr).getUnspecifiedType()
-      or
-      // This will cover variables, parameters, type declarations, etc.
-      t = e.(DeclarationEntry).getUnspecifiedType()
-    ) and
-    (isIntegralType(t) or isIntegralReferenceType(t))
-  )
-}
-
-Expr getLOp(Operation o) {
-  result = o.(BinaryOperation).getLeftOperand() or
-  result = o.(Assignment).getLValue()
-}
-
-Expr getROp(Operation o) {
-  result = o.(BinaryOperation).getRightOperand() or
-  result = o.(Assignment).getRValue()
-}
-
-/**
- * Display the ranges of expressions in the path view
- */
-private class ExprRangeNode extends DataFlow::ExprNode {
-  pragma[inline]
-  private string getIntegralBounds(Expr arg) {
-    if hasIntegralOrReferenceIntegralType(arg)
-    then result = getExprBoundAsString(arg)
-    else result = ""
-  }
-
-  private string getOperationBounds(Operation e) {
-    result =
-      getExprBoundAsString(e) + " = " + getExprBoundAsString(getLOp(e)) + e.getOperator() +
-        getExprBoundAsString(getROp(e))
-  }
-
-  private string getCallBounds(Call e) {
-    result =
-      getExprBoundAsString(e) + "(" +
-        concat(Expr arg, int i |
-          arg = e.getArgument(i)
-        |
-          this.getIntegralBounds(arg), "," order by i
-        ) + ")"
-  }
-
-  override string toString() {
-    exists(Expr e | e = this.getExpr() |
-      if hasIntegralOrReferenceIntegralType(e)
-      then
-        result = super.toString() + ": " + this.getOperationBounds(e)
-        or
-        result = super.toString() + ": " + this.getCallBounds(e)
-        or
-        not exists(this.getOperationBounds(e)) and
-        not exists(this.getCallBounds(e)) and
-        result = super.toString() + ": " + getExprBoundAsString(e)
-      else result = super.toString()
-    )
-  }
-}
-
-/**
- * Display the ranges of expressions in the path view
- */
-private class ReferenceArgumentRangeNode extends DataFlow::DefinitionByReferenceNode {
-  override string toString() {
-    if hasIntegralOrReferenceIntegralType(this.asDefiningArgument())
-    then result = super.toString() + ": " + getExprBoundAsString(this.getArgument())
-    else result = super.toString()
-  }
-}

cpp/ql/lib/experimental/semmle/code/cpp/rangeanalysis/extensions/StrlenLiteralRangeExpr.qll

@@ -1,18 +0,0 @@
-private import cpp
-private import experimental.semmle.code.cpp.models.interfaces.SimpleRangeAnalysisExpr
-
-/**
- * Provides range analysis information for calls to `strlen` on literal strings.
- * For example, the range of `strlen("literal")` will be 7.
- */
-class StrlenLiteralRangeExpr extends SimpleRangeAnalysisExpr, FunctionCall {
-  StrlenLiteralRangeExpr() {
-    this.getTarget().hasGlobalOrStdName("strlen") and this.getArgument(0).isConstant()
-  }
-
-  override int getLowerBounds() { result = this.getArgument(0).getValue().length() }
-
-  override int getUpperBounds() { result = this.getArgument(0).getValue().length() }
-
-  override predicate dependsOnChild(Expr e) { none() }
-}

cpp/ql/lib/experimental/semmle/code/cpp/rangeanalysis/extensions/SubtractSelf.qll

@@ -3,8 +3,8 @@ import experimental.semmle.code.cpp.models.interfaces.SimpleRangeAnalysisExpr
 private class SelfSub extends SimpleRangeAnalysisExpr, SubExpr {
   SelfSub() {
     // Match `x - x` but not `myInt - (unsigned char)myInt`.
-    this.getLeftOperand().getExplicitlyConverted().(VariableAccess).getTarget() =
-      this.getRightOperand().getExplicitlyConverted().(VariableAccess).getTarget()
+    getLeftOperand().getExplicitlyConverted().(VariableAccess).getTarget() =
+      getRightOperand().getExplicitlyConverted().(VariableAccess).getTarget()
   }
 
   override float getLowerBounds() { result = 0 }

cpp/ql/lib/experimental/semmle/code/cpp/security/PrivateCleartextWrite.qll

@@ -54,7 +54,7 @@ module PrivateCleartextWrite {
     predicate isBarrier(DataFlow::Node node) { node instanceof Sanitizer }
   }
 
-  module WriteFlow = TaintTracking::Global<WriteConfig>;
+  module WriteFlow = TaintTracking::Make<WriteConfig>;
 
   class PrivateDataSource extends Source {
     PrivateDataSource() { this.getExpr() instanceof PrivateDataExpr }

cpp/ql/lib/experimental/semmle/code/cpp/semantic/SemanticExpr.qll

@@ -87,7 +87,7 @@ class SemIntegerLiteralExpr extends SemNumericLiteralExpr {
   final int getIntValue() { Specific::integerLiteral(this, _, result) }
 
   final override float getApproximateFloatValue() {
-    result = this.getIntValue()
+    result = getIntValue()
     or
     Specific::largeIntegerLiteral(this, _, result)
   }
@@ -124,13 +124,13 @@ class SemBinaryExpr extends SemKnownExpr {
 
   /** Holds if `a` and `b` are the two operands, in either order. */
   final predicate hasOperands(SemExpr a, SemExpr b) {
-    a = this.getLeftOperand() and b = this.getRightOperand()
+    a = getLeftOperand() and b = getRightOperand()
     or
-    a = this.getRightOperand() and b = this.getLeftOperand()
+    a = getRightOperand() and b = getLeftOperand()
   }
 
   /** Gets the two operands. */
-  final SemExpr getAnOperand() { result = this.getLeftOperand() or result = this.getRightOperand() }
+  final SemExpr getAnOperand() { result = getLeftOperand() or result = getRightOperand() }
 }
 
 /** An expression that performs and ordered comparison of two operands. */
@@ -154,8 +154,8 @@ class SemRelationalExpr extends SemBinaryExpr {
    */
   final SemExpr getLesserOperand() {
     if opcode instanceof Opcode::CompareLT or opcode instanceof Opcode::CompareLE
-    then result = this.getLeftOperand()
-    else result = this.getRightOperand()
+    then result = getLeftOperand()
+    else result = getRightOperand()
   }
 
   /**
@@ -167,8 +167,8 @@ class SemRelationalExpr extends SemBinaryExpr {
    */
   final SemExpr getGreaterOperand() {
     if opcode instanceof Opcode::CompareGT or opcode instanceof Opcode::CompareGE
-    then result = this.getLeftOperand()
-    else result = this.getRightOperand()
+    then result = getLeftOperand()
+    else result = getRightOperand()
   }
 
   /** Holds if this comparison returns `false` if the two operands are equal. */
@@ -280,11 +280,11 @@ class SemLoadExpr extends SemNullaryExpr {
 }
 
 class SemSsaLoadExpr extends SemLoadExpr {
-  SemSsaLoadExpr() { exists(this.getDef()) }
+  SemSsaLoadExpr() { exists(getDef()) }
 }
 
 class SemNonSsaLoadExpr extends SemLoadExpr {
-  SemNonSsaLoadExpr() { not exists(this.getDef()) }
+  SemNonSsaLoadExpr() { not exists(getDef()) }
 }
 
 class SemStoreExpr extends SemUnaryExpr {

cpp/ql/lib/experimental/semmle/code/cpp/semantic/SemanticExprSpecific.qll

@@ -0,0 +1,356 @@
+/**
+ * C++-specific implementation of the semantic interface.
+ */
+
+private import cpp as Cpp
+private import semmle.code.cpp.ir.IR as IR
+private import Semantic
+private import experimental.semmle.code.cpp.rangeanalysis.Bound as IRBound
+private import semmle.code.cpp.controlflow.IRGuards as IRGuards
+private import semmle.code.cpp.ir.ValueNumbering
+
+module SemanticExprConfig {
+  class Location = Cpp::Location;
+
+  class Expr = IR::Instruction;
+
+  SemBasicBlock getExprBasicBlock(Expr e) { result = getSemanticBasicBlock(e.getBlock()) }
+
+  private predicate anyConstantExpr(Expr expr, SemType type, string value) {
+    exists(IR::ConstantInstruction instr | instr = expr |
+      type = getSemanticType(instr.getResultIRType()) and
+      value = instr.getValue()
+    )
+  }
+
+  predicate integerLiteral(Expr expr, SemIntegerType type, int value) {
+    exists(string valueString |
+      anyConstantExpr(expr, type, valueString) and
+      value = valueString.toInt()
+    )
+  }
+
+  predicate largeIntegerLiteral(Expr expr, SemIntegerType type, float approximateFloatValue) {
+    exists(string valueString |
+      anyConstantExpr(expr, type, valueString) and
+      not exists(valueString.toInt()) and
+      approximateFloatValue = valueString.toFloat()
+    )
+  }
+
+  predicate floatingPointLiteral(Expr expr, SemFloatingPointType type, float value) {
+    exists(string valueString |
+      anyConstantExpr(expr, type, valueString) and value = valueString.toFloat()
+    )
+  }
+
+  predicate booleanLiteral(Expr expr, SemBooleanType type, boolean value) {
+    exists(string valueString |
+      anyConstantExpr(expr, type, valueString) and
+      (
+        valueString = "true" and value = true
+        or
+        valueString = "false" and value = false
+      )
+    )
+  }
+
+  predicate nullLiteral(Expr expr, SemAddressType type) { anyConstantExpr(expr, type, _) }
+
+  predicate stringLiteral(Expr expr, SemType type, string value) {
+    anyConstantExpr(expr, type, value) and expr instanceof IR::StringConstantInstruction
+  }
+
+  predicate binaryExpr(Expr expr, Opcode opcode, SemType type, Expr leftOperand, Expr rightOperand) {
+    exists(IR::BinaryInstruction instr | instr = expr |
+      type = getSemanticType(instr.getResultIRType()) and
+      leftOperand = instr.getLeft() and
+      rightOperand = instr.getRight() and
+      // REVIEW: Merge the two `Opcode` types.
+      opcode.toString() = instr.getOpcode().toString()
+    )
+  }
+
+  predicate unaryExpr(Expr expr, Opcode opcode, SemType type, Expr operand) {
+    type = getSemanticType(expr.getResultIRType()) and
+    (
+      exists(IR::UnaryInstruction instr | instr = expr |
+        operand = instr.getUnary() and
+        // REVIEW: Merge the two operand types.
+        opcode.toString() = instr.getOpcode().toString()
+      )
+      or
+      exists(IR::StoreInstruction instr | instr = expr |
+        operand = instr.getSourceValue() and
+        opcode instanceof Opcode::Store
+      )
+    )
+  }
+
+  predicate nullaryExpr(Expr expr, Opcode opcode, SemType type) {
+    type = getSemanticType(expr.getResultIRType()) and
+    (
+      expr instanceof IR::LoadInstruction and opcode instanceof Opcode::Load
+      or
+      expr instanceof IR::InitializeParameterInstruction and
+      opcode instanceof Opcode::InitializeParameter
+    )
+  }
+
+  predicate conditionalExpr(
+    Expr expr, SemType type, Expr condition, Expr trueResult, Expr falseResult
+  ) {
+    none()
+  }
+
+  SemType getUnknownExprType(Expr expr) { result = getSemanticType(expr.getResultIRType()) }
+
+  class BasicBlock = IR::IRBlock;
+
+  predicate bbDominates(BasicBlock dominator, BasicBlock dominated) {
+    dominator.dominates(dominated)
+  }
+
+  predicate hasDominanceInformation(BasicBlock block) { any() }
+
+  private predicate id(Cpp::Locatable x, Cpp::Locatable y) { x = y }
+
+  private predicate idOf(Cpp::Locatable x, int y) = equivalenceRelation(id/2)(x, y)
+
+  int getBasicBlockUniqueId(BasicBlock block) { idOf(block.getFirstInstruction().getAst(), result) }
+
+  newtype TSsaVariable =
+    TSsaInstruction(IR::Instruction instr) { instr.hasMemoryResult() } or
+    TSsaOperand(IR::Operand op) { op.isDefinitionInexact() } or
+    TSsaPointerArithmeticGuard(IR::PointerArithmeticInstruction instr) {
+      exists(Guard g, IR::Operand use | use = instr.getAUse() |
+        g.comparesLt(use, _, _, _, _) or
+        g.comparesLt(_, use, _, _, _) or
+        g.comparesEq(use, _, _, _, _) or
+        g.comparesEq(_, use, _, _, _)
+      )
+    }
+
+  class SsaVariable extends TSsaVariable {
+    string toString() { none() }
+
+    Location getLocation() { none() }
+
+    IR::Instruction asInstruction() { none() }
+
+    IR::PointerArithmeticInstruction asPointerArithGuard() { none() }
+
+    IR::Operand asOperand() { none() }
+  }
+
+  class SsaInstructionVariable extends SsaVariable, TSsaInstruction {
+    IR::Instruction instr;
+
+    SsaInstructionVariable() { this = TSsaInstruction(instr) }
+
+    final override string toString() { result = instr.toString() }
+
+    final override Location getLocation() { result = instr.getLocation() }
+
+    final override IR::Instruction asInstruction() { result = instr }
+  }
+
+  class SsaPointerArithmeticGuard extends SsaVariable, TSsaPointerArithmeticGuard {
+    IR::PointerArithmeticInstruction instr;
+
+    SsaPointerArithmeticGuard() { this = TSsaPointerArithmeticGuard(instr) }
+
+    final override string toString() { result = instr.toString() }
+
+    final override Location getLocation() { result = instr.getLocation() }
+
+    final override IR::PointerArithmeticInstruction asPointerArithGuard() { result = instr }
+  }
+
+  class SsaOperand extends SsaVariable, TSsaOperand {
+    IR::Operand op;
+
+    SsaOperand() { this = TSsaOperand(op) }
+
+    final override string toString() { result = op.toString() }
+
+    final override Location getLocation() { result = op.getLocation() }
+
+    final override IR::Operand asOperand() { result = op }
+  }
+
+  predicate explicitUpdate(SsaVariable v, Expr sourceExpr) { v.asInstruction() = sourceExpr }
+
+  predicate phi(SsaVariable v) { v.asInstruction() instanceof IR::PhiInstruction }
+
+  SsaVariable getAPhiInput(SsaVariable v) {
+    exists(IR::PhiInstruction instr | v.asInstruction() = instr |
+      result.asInstruction() = instr.getAnInput()
+      or
+      result.asOperand() = instr.getAnInputOperand()
+    )
+  }
+
+  Expr getAUse(SsaVariable v) {
+    result.(IR::LoadInstruction).getSourceValue() = v.asInstruction()
+    or
+    result = valueNumber(v.asPointerArithGuard()).getAnInstruction()
+  }
+
+  SemType getSsaVariableType(SsaVariable v) {
+    result = getSemanticType(v.asInstruction().getResultIRType())
+  }
+
+  BasicBlock getSsaVariableBasicBlock(SsaVariable v) {
+    result = v.asInstruction().getBlock()
+    or
+    result = v.asOperand().getUse().getBlock()
+  }
+
+  private newtype TReadPosition =
+    TReadPositionBlock(IR::IRBlock block) or
+    TReadPositionPhiInputEdge(IR::IRBlock pred, IR::IRBlock succ) {
+      exists(IR::PhiInputOperand input |
+        pred = input.getPredecessorBlock() and
+        succ = input.getUse().getBlock()
+      )
+    }
+
+  class SsaReadPosition extends TReadPosition {
+    string toString() { none() }
+
+    Location getLocation() { none() }
+
+    predicate hasRead(SsaVariable v) { none() }
+  }
+
+  private class SsaReadPositionBlock extends SsaReadPosition, TReadPositionBlock {
+    IR::IRBlock block;
+
+    SsaReadPositionBlock() { this = TReadPositionBlock(block) }
+
+    final override string toString() { result = block.toString() }
+
+    final override Location getLocation() { result = block.getLocation() }
+
+    final override predicate hasRead(SsaVariable v) {
+      exists(IR::Operand operand |
+        operand.getDef() = v.asInstruction() or
+        operand.getDef() = valueNumber(v.asPointerArithGuard()).getAnInstruction()
+      |
+        not operand instanceof IR::PhiInputOperand and
+        operand.getUse().getBlock() = block
+      )
+    }
+  }
+
+  private class SsaReadPositionPhiInputEdge extends SsaReadPosition, TReadPositionPhiInputEdge {
+    IR::IRBlock pred;
+    IR::IRBlock succ;
+
+    SsaReadPositionPhiInputEdge() { this = TReadPositionPhiInputEdge(pred, succ) }
+
+    final override string toString() { result = pred.toString() + "->" + succ.toString() }
+
+    final override Location getLocation() { result = succ.getLocation() }
+
+    final override predicate hasRead(SsaVariable v) {
+      exists(IR::PhiInputOperand operand |
+        operand.getDef() = v.asInstruction() or
+        operand.getDef() = valueNumber(v.asPointerArithGuard()).getAnInstruction()
+      |
+        operand.getPredecessorBlock() = pred and
+        operand.getUse().getBlock() = succ
+      )
+    }
+  }
+
+  predicate hasReadOfSsaVariable(SsaReadPosition pos, SsaVariable v) { pos.hasRead(v) }
+
+  predicate readBlock(SsaReadPosition pos, BasicBlock block) { pos = TReadPositionBlock(block) }
+
+  predicate phiInputEdge(SsaReadPosition pos, BasicBlock origBlock, BasicBlock phiBlock) {
+    pos = TReadPositionPhiInputEdge(origBlock, phiBlock)
+  }
+
+  predicate phiInput(SsaReadPosition pos, SsaVariable phi, SsaVariable input) {
+    exists(IR::PhiInputOperand operand |
+      pos = TReadPositionPhiInputEdge(operand.getPredecessorBlock(), operand.getUse().getBlock())
+    |
+      phi.asInstruction() = operand.getUse() and
+      (
+        input.asInstruction() = operand.getDef()
+        or
+        input.asOperand() = operand
+      )
+    )
+  }
+
+  class Bound instanceof IRBound::Bound {
+    string toString() { result = super.toString() }
+
+    final Location getLocation() { result = super.getLocation() }
+  }
+
+  private class ValueNumberBound extends Bound instanceof IRBound::ValueNumberBound {
+    override string toString() { result = IRBound::ValueNumberBound.super.toString() }
+  }
+
+  predicate zeroBound(Bound bound) { bound instanceof IRBound::ZeroBound }
+
+  predicate ssaBound(Bound bound, SsaVariable v) {
+    v.asInstruction() = bound.(IRBound::ValueNumberBound).getValueNumber().getAnInstruction()
+  }
+
+  Expr getBoundExpr(Bound bound, int delta) {
+    result = bound.(IRBound::Bound).getInstruction(delta)
+  }
+
+  class Guard = IRGuards::IRGuardCondition;
+
+  predicate guard(Guard guard, BasicBlock block) { block = guard.getBlock() }
+
+  Expr getGuardAsExpr(Guard guard) { result = guard }
+
+  predicate equalityGuard(Guard guard, Expr e1, Expr e2, boolean polarity) {
+    guard.comparesEq(e1.getAUse(), e2.getAUse(), 0, true, polarity)
+  }
+
+  predicate guardDirectlyControlsBlock(Guard guard, BasicBlock controlled, boolean branch) {
+    guard.controls(controlled, branch)
+  }
+
+  predicate guardHasBranchEdge(Guard guard, BasicBlock bb1, BasicBlock bb2, boolean branch) {
+    guard.controlsEdge(bb1, bb2, branch)
+  }
+
+  Guard comparisonGuard(Expr e) { result = e }
+
+  predicate implies_v2(Guard g1, boolean b1, Guard g2, boolean b2) {
+    none() // TODO
+  }
+}
+
+SemExpr getSemanticExpr(IR::Instruction instr) { result = instr }
+
+IR::Instruction getCppInstruction(SemExpr e) { e = result }
+
+SemBasicBlock getSemanticBasicBlock(IR::IRBlock block) { result = block }
+
+IR::IRBlock getCppBasicBlock(SemBasicBlock block) { block = result }
+
+SemSsaVariable getSemanticSsaVariable(IR::Instruction instr) {
+  result.(SemanticExprConfig::SsaVariable).asInstruction() = instr
+}
+
+IR::Instruction getCppSsaVariableInstruction(SemSsaVariable var) {
+  var.(SemanticExprConfig::SsaVariable).asInstruction() = result
+}
+
+SemBound getSemanticBound(IRBound::Bound bound) { result = bound }
+
+IRBound::Bound getCppBound(SemBound bound) { bound = result }
+
+SemGuard getSemanticGuard(IRGuards::IRGuardCondition guard) { result = guard }
+
+IRGuards::IRGuardCondition getCppGuard(SemGuard guard) { guard = result }

cpp/ql/lib/experimental/semmle/code/cpp/semantic/SemanticGuard.qll

@@ -39,7 +39,6 @@ predicate semImplies_v2(SemGuard g1, boolean b1, SemGuard g2, boolean b2) {
  * Holds if `guard` directly controls the position `controlled` with the
  * value `testIsTrue`.
  */
-pragma[nomagic]
 predicate semGuardDirectlyControlsSsaRead(
   SemGuard guard, SemSsaReadPosition controlled, boolean testIsTrue
 ) {

cpp/ql/lib/experimental/semmle/code/cpp/semantic/SemanticSSA.qll

@@ -0,0 +1,75 @@
+/**
+ * Semantic interface to the SSA library.
+ */
+
+private import Semantic
+private import SemanticExprSpecific::SemanticExprConfig as Specific
+
+class SemSsaVariable instanceof Specific::SsaVariable {
+  final string toString() { result = super.toString() }
+
+  final Specific::Location getLocation() { result = super.getLocation() }
+
+  final SemExpr getAUse() { result = Specific::getAUse(this) }
+
+  final SemType getType() { result = Specific::getSsaVariableType(this) }
+
+  final SemBasicBlock getBasicBlock() { result = Specific::getSsaVariableBasicBlock(this) }
+}
+
+class SemSsaExplicitUpdate extends SemSsaVariable {
+  SemExpr sourceExpr;
+
+  SemSsaExplicitUpdate() { Specific::explicitUpdate(this, sourceExpr) }
+
+  final SemExpr getSourceExpr() { result = sourceExpr }
+}
+
+class SemSsaPhiNode extends SemSsaVariable {
+  SemSsaPhiNode() { Specific::phi(this) }
+
+  final SemSsaVariable getAPhiInput() { result = Specific::getAPhiInput(this) }
+}
+
+class SemSsaReadPosition instanceof Specific::SsaReadPosition {
+  final string toString() { result = super.toString() }
+
+  final Specific::Location getLocation() { result = super.getLocation() }
+
+  final predicate hasReadOfVar(SemSsaVariable var) { Specific::hasReadOfSsaVariable(this, var) }
+}
+
+class SemSsaReadPositionPhiInputEdge extends SemSsaReadPosition {
+  SemBasicBlock origBlock;
+  SemBasicBlock phiBlock;
+
+  SemSsaReadPositionPhiInputEdge() { Specific::phiInputEdge(this, origBlock, phiBlock) }
+
+  predicate phiInput(SemSsaPhiNode phi, SemSsaVariable inp) { Specific::phiInput(this, phi, inp) }
+
+  SemBasicBlock getOrigBlock() { result = origBlock }
+
+  SemBasicBlock getPhiBlock() { result = phiBlock }
+}
+
+class SemSsaReadPositionBlock extends SemSsaReadPosition {
+  SemBasicBlock block;
+
+  SemSsaReadPositionBlock() { Specific::readBlock(this, block) }
+
+  SemBasicBlock getBlock() { result = block }
+
+  SemExpr getAnExpr() { result = getBlock().getAnExpr() }
+}
+
+/**
+ * Holds if `inp` is an input to `phi` along a back edge.
+ */
+predicate semBackEdge(SemSsaPhiNode phi, SemSsaVariable inp, SemSsaReadPositionPhiInputEdge edge) {
+  edge.phiInput(phi, inp) and
+  // Conservatively assume that every edge is a back edge if we don't have dominance information.
+  (
+    phi.getBasicBlock().bbDominates(edge.getOrigBlock()) or
+    not edge.getOrigBlock().hasDominanceInformation()
+  )
+}

cpp/ql/lib/experimental/semmle/code/cpp/semantic/SemanticType.qll

@@ -38,7 +38,7 @@ class SemType extends TSemType {
    * Gets a string that uniquely identifies this `SemType`. This string is often the same as the
    * result of `SemType.toString()`, but for some types it may be more verbose to ensure uniqueness.
    */
-  string getIdentityString() { result = this.toString() }
+  string getIdentityString() { result = toString() }
 
   /**
    * Gets the size of the type, in bytes, if known.
@@ -132,7 +132,7 @@ class SemIntegerType extends SemNumericType {
   final predicate isSigned() { signed = true }
 
   /** Holds if this integer type is unsigned. */
-  final predicate isUnsigned() { not this.isSigned() }
+  final predicate isUnsigned() { not isSigned() }
   // Don't override `getByteSize()` here. The optimizer seems to generate better code when this is
   // overridden only in the leaf classes.
 }
@@ -250,26 +250,16 @@ SemType getSemanticType(Specific::Type type) {
   Specific::unknownType(type) and result = TSemUnknownType()
 }
 
-private class SemNumericOrBooleanType extends SemSizedType {
-  SemNumericOrBooleanType() {
-    this instanceof SemNumericType
-    or
-    this instanceof SemBooleanType
-  }
-}
-
 /**
  * Holds if the conversion from `fromType` to `toType` can never overflow or underflow.
  */
-predicate conversionCannotOverflow(SemNumericOrBooleanType fromType, SemNumericOrBooleanType toType) {
+predicate conversionCannotOverflow(SemNumericType fromType, SemNumericType toType) {
   // Identity cast
   fromType = toType
   or
   // Treat any cast to an FP type as safe. It can lose precision, but not overflow.
   toType instanceof SemFloatingPointType and fromType = any(SemNumericType n)
   or
-  fromType instanceof SemBooleanType and toType instanceof SemIntegerType
-  or
   exists(SemIntegerType fromInteger, SemIntegerType toInteger, int fromSize, int toSize |
     fromInteger = fromType and
     toInteger = toType and

cpp/ql/lib/experimental/semmle/code/cpp/semantic/analysis/ConstantAnalysis.qll

@@ -2,7 +2,7 @@
  * Simple constant analysis using the Semantic interface.
  */
 
-private import semmle.code.cpp.rangeanalysis.new.internal.semantic.Semantic
+private import experimental.semmle.code.cpp.semantic.Semantic
 private import ConstantAnalysisSpecific as Specific
 
 /** An expression that always has the same integer value. */