use ATM model from training run classification_1664756959_0265f4e5

.github/ISSUE_TEMPLATE/lgtm-com---false-positive.md

@@ -0,0 +1,24 @@
+---
+name: LGTM.com - false positive
+about: Tell us about an alert that shouldn't be reported
+title: LGTM.com - false positive
+labels: false-positive
+assignees: ''
+
+---
+
+**Description of the false positive**
+
+<!-- Please explain briefly why you think it shouldn't be included. -->
+
+**URL to the alert on the project page on LGTM.com**
+
+<!--
+1. Open the project on LGTM.com.
+For example, https://lgtm.com/projects/g/pallets/click/.
+2. Switch to the `Alerts` tab. For example, https://lgtm.com/projects/g/pallets/click/alerts/.
+3. Scroll to the alert that you would like to report.
+4. Click on the right most icon `View this alert within the complete file`.
+5. A new browser tab opens. Copy and paste the page URL here.
+For example, https://lgtm.com/projects/g/pallets/click/snapshot/719fb7d8322b0767cdd1e5903ba3eb3233ba8dd5/files/click/_winconsole.py#xa08d213ab3289f87:1.
+-->

.github/ISSUE_TEMPLATE/ql---general.md

@@ -10,5 +10,5 @@ assignees: ''
 **Description of the issue**
 
 <!-- Please explain briefly what is the problem.
-If it is about a GitHub project, please include its URL. -->
+If it is about an LGTM project, please include its URL.-->
 

.github/ISSUE_TEMPLATE/ql--false-positive.md

@@ -1,36 +0,0 @@
----
-name: CodeQL false positive
-about: Report CodeQL alerts that you think should not have been detected (not applicable, not exploitable, etc.)
-title: False positive
-labels: false-positive
-assignees: ''
-
----
-
-**Description of the false positive**
-
-<!-- Please explain briefly why you think it shouldn't be included. -->
-
-**Code samples or links to source code**
-
-<!--
-For open source code: file links with line numbers on GitHub, for example:
-https://github.com/github/codeql/blob/dc440aaee6695deb0d9676b87e06ea984e1b4ae5/javascript/ql/test/query-tests/Security/CWE-078/CommandInjection/exec-sh2.js#L10
-
-For closed source code: (redacted) code samples that illustrate the problem, for example:
-
-```
-function execSh(command, options) {
-    return cp.spawn(getShell(), ["-c", command], options) // <- command line injection
-};
-```
--->
-
-**URL to the alert on GitHub code scanning (optional)**
-
-<!--
-1. Open the project on GitHub.com.
-2. Switch to the `Security` tab.
-3. Browse to the alert that you would like to report.
-4. Copy and paste the page URL here.
--->

.github/actions/cache-query-compilation/action.yml

@@ -1,149 +0,0 @@
-name: Cache query compilation
-description: Caches CodeQL compilation caches - should be run both on PRs and pushes to main.
-
-inputs:
-  key:
-    description: 'The cache key to use - should be unique to the workflow'
-    required: true
-
-outputs:
-  cache-dir:
-    description: "The directory where the cache was stored"
-    value: ${{ steps.output-compilation-dir.outputs.compdir }}
-
-runs:
-  using: composite
-  steps:
-    # calculate the merge-base with main, in a way that works both on PRs and pushes to main.
-    - name: Calculate merge-base
-      shell: bash
-      if: ${{ github.event_name == 'pull_request' }}
-      env:
-        BASE_BRANCH: ${{ github.base_ref }}
-      run: |
-        MERGE_BASE=$(git cat-file commit $GITHUB_SHA | grep '^parent ' | head -1 | cut -f 2 -d " ")
-        echo "merge_base=$MERGE_BASE" >> $GITHUB_ENV
-    - name: Restore cache (PR)
-      if: ${{ github.event_name == 'pull_request' }}
-      uses: actions/cache/restore@v3
-      with:
-        path: |
-          **/.cache
-          ~/.codeql/compile-cache
-        key: codeql-compile-${{ inputs.key }}-pr-${{ github.sha }}
-        restore-keys: |
-          codeql-compile-${{ inputs.key }}-${{ github.base_ref }}-${{ env.merge_base }}
-          codeql-compile-${{ inputs.key }}-${{ github.base_ref }}-
-          codeql-compile-${{ inputs.key }}-main-
-    - name: Fill cache (only branch push)
-      if: ${{ github.event_name != 'pull_request' }}
-      uses: actions/cache@v3
-      with:
-        path: |
-          **/.cache
-          ~/.codeql/compile-cache
-        key: codeql-compile-${{ inputs.key }}-${{ github.ref_name }}-${{ github.sha }} # just fill on main
-        restore-keys: | # restore the latest cache if the exact cache is unavailable, to speed up compilation.
-          codeql-compile-${{ inputs.key }}-${{ github.ref_name }}-
-          codeql-compile-${{ inputs.key }}-main-
-    - name: Output-compilationdir
-      id: output-compilation-dir
-      shell: bash
-      run: |
-        echo "compdir=${COMBINED_CACHE_DIR}" >> $GITHUB_OUTPUT
-      env:
-        COMBINED_CACHE_DIR: ${{ runner.temp }}/compilation-dir
-    - name: Fill compilation cache directory
-      id: fill-compilation-dir
-      uses: actions/github-script@v6
-      env: 
-        COMBINED_CACHE_DIR: ${{ runner.temp }}/compilation-dir
-      with:
-        script: |
-          // # Move all the existing cache into another folder, so we only preserve the cache for the current queries.
-          // mkdir -p ${COMBINED_CACHE_DIR}
-          // rm -f **/.cache/{lock,size} # -f to avoid errors if the cache is empty.
-          // # copy the contents of the .cache folders into the combined cache folder.
-          // cp -r **/.cache/* ${COMBINED_CACHE_DIR}/ || : # ignore missing files
-          // # clean up the .cache folders
-          // rm -rf **/.cache/*
-
-          const fs = require("fs");
-          const path = require("path");
-          const os = require("os");
-
-          // the first argv is the cache folder to create.
-          const COMBINED_CACHE_DIR = process.env.COMBINED_CACHE_DIR;
-
-          function* walkCaches(dir) {
-            const files = fs.readdirSync(dir, { withFileTypes: true });
-            for (const file of files) {
-              if (file.isDirectory()) {
-                const filePath = path.join(dir, file.name);
-                yield* walkCaches(filePath);
-                if (file.name === ".cache") {
-                  yield filePath;
-                }
-              }
-            }
-          }
-
-          async function copyDir(src, dest) {
-            for await (const file of await fs.promises.readdir(src, { withFileTypes: true })) {
-              const srcPath = path.join(src, file.name);
-              const destPath = path.join(dest, file.name);
-              if (file.isDirectory()) {
-                if (!fs.existsSync(destPath)) {
-                  fs.mkdirSync(destPath);
-                }
-                await copyDir(srcPath, destPath);
-              } else {
-                await fs.promises.copyFile(srcPath, destPath);
-              }
-            }
-          }
-
-          async function main() {
-            const cacheDirs = [...walkCaches(".")];
-
-            for (const dir of cacheDirs) {
-              console.log(`Found .cache dir at ${dir}`);
-            }
-
-            const globalCacheDir = path.join(os.homedir(), ".codeql", "compile-cache");
-            if (fs.existsSync(globalCacheDir)) {
-              console.log("Found global home dir: " + globalCacheDir);
-              cacheDirs.push(globalCacheDir);
-            }
-
-            if (cacheDirs.length === 0) {
-              console.log("No cache dirs found");
-              return;
-            }
-
-            // mkdir -p ${COMBINED_CACHE_DIR}
-            fs.mkdirSync(COMBINED_CACHE_DIR, { recursive: true });
-
-            // rm -f **/.cache/{lock,size} # -f to avoid errors if the cache is empty.
-            await Promise.all(
-              cacheDirs.map((cacheDir) =>
-                (async function () {
-                  await fs.promises.rm(path.join(cacheDir, "lock"), { force: true });
-                  await fs.promises.rm(path.join(cacheDir, "size"), { force: true });
-                })()
-              )
-            );
-
-            // # copy the contents of the .cache folders into the combined cache folder.
-            // cp -r **/.cache/* ${COMBINED_CACHE_DIR}/ || : # ignore missing files
-            await Promise.all(
-              cacheDirs.map((cacheDir) => copyDir(cacheDir, COMBINED_CACHE_DIR))
-            );
-
-            // # clean up the .cache folders
-            // rm -rf **/.cache/*
-            await Promise.all(
-              cacheDirs.map((cacheDir) => fs.promises.rm(cacheDir, { recursive: true }))
-            );
-          }
-          main();

.github/actions/fetch-codeql/action.yml

@@ -1,24 +1,14 @@
 name: Fetch CodeQL
 description: Fetches the latest version of CodeQL
-
-inputs:
-  channel:
-    description: 'The CodeQL channel to use'
-    required: false
-    default: 'nightly'
-
 runs:
   using: composite
   steps:
     - name: Fetch CodeQL
       shell: bash
-      env:
-        GITHUB_TOKEN: ${{ github.token }}
-        CHANNEL: ${{ inputs.channel }}
       run: |
         gh extension install github/gh-codeql
-        gh codeql set-channel "$CHANNEL"
+        gh codeql set-channel nightly
         gh codeql version
-        printf "CODEQL_FETCHED_CODEQL_PATH=" >> "${GITHUB_ENV}"
-        gh codeql version --format=json | jq -r .unpackedLocation >> "${GITHUB_ENV}"
         gh codeql version --format=json | jq -r .unpackedLocation >> "${GITHUB_PATH}"
+      env:
+        GITHUB_TOKEN: ${{ github.token }}

.github/actions/os-version/action.yml

@@ -1,32 +0,0 @@
-name: OS Version
-description: Get OS version.
-
-outputs:
-  version:
-    description: "OS version"
-    value: ${{ steps.version.outputs.version }}
-
-runs:
-  using: composite
-  steps:
-    - if: runner.os == 'Linux'
-      shell: bash
-      run: |
-        . /etc/os-release
-        echo "VERSION=${NAME} ${VERSION}" >> $GITHUB_ENV
-    - if: runner.os == 'Windows'
-      shell: powershell
-      run: |
-        $objects = systeminfo.exe /FO CSV | ConvertFrom-Csv
-        "VERSION=$($objects.'OS Name') $($objects.'OS Version')" >> $env:GITHUB_ENV
-    - if: runner.os == 'macOS'
-      shell: bash
-      run: |
-        echo "VERSION=$(sw_vers -productName) $(sw_vers -productVersion)" >> $GITHUB_ENV
-    - name: Emit OS version
-      id: version
-      shell: bash
-      run: |
-        echo "$VERSION"
-        echo "version=${VERSION}" >> $GITHUB_OUTPUT
-

.github/dependabot.yml

@@ -1,12 +1,19 @@
 version: 2
 updates:
   - package-ecosystem: "cargo"
-    directory: "ruby"
+    directory: "ruby/node-types"
     schedule:
       interval: "daily"
-
   - package-ecosystem: "cargo"
-    directory: "ql"
+    directory: "ruby/generator"
+    schedule:
+      interval: "daily"
+  - package-ecosystem: "cargo"
+    directory: "ruby/extractor"
+    schedule:
+      interval: "daily"
+  - package-ecosystem: "cargo"
+    directory: "ruby/autobuilder"
     schedule:
       interval: "daily"
 

.github/labeler.yml

@@ -43,14 +43,3 @@ documentation:
 "QL-for-QL":
   - ql/**/*
   - .github/workflows/ql-for-ql*
-
-# Since these are all shared files that need to be synced, just pick _one_ copy of each.
-"DataFlow Library":
-  - "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

@@ -1,102 +0,0 @@
-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

@@ -1,12 +0,0 @@
-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

@@ -26,9 +26,3 @@ 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' 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$"))' |
-          grep true -c

.github/workflows/check-qldoc.yml

@@ -26,8 +26,9 @@ jobs:
         shell: bash
         run: |
           EXIT_CODE=0
+          # TODO: remove the swift exception from the regex when we fix generated QLdoc
           # TODO: remove the shared exception from the regex when coverage of qlpacks without dbschemes is supported
-          changed_lib_packs="$(git diff --name-only --diff-filter=ACMRT HEAD^ HEAD | { grep -Po '^(?!(shared))[a-z]*/ql/lib' || true; } | sort -u)"
+          changed_lib_packs="$(git diff --name-only --diff-filter=ACMRT HEAD^ HEAD | { grep -Po '^(?!(swift|shared))[a-z]*/ql/lib' || true; } | sort -u)"
           for pack_dir in ${changed_lib_packs}; do
             lang="${pack_dir%/ql/lib}"
             codeql generate library-doc-coverage --output="${RUNNER_TEMP}/${lang}-current.txt" --dir="${pack_dir}"

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

@@ -1,21 +0,0 @@
-name: Check query IDs
-
-on:
-  pull_request:
-    paths:
-      - "**/src/**/*.ql"
-      - misc/scripts/check-query-ids.py
-      - .github/workflows/check-query-ids.yml
-    branches:
-      - main
-      - "rc/*"
-  workflow_dispatch:
-
-jobs:
-  check:
-    name: Check query IDs
-    runs-on: ubuntu-latest
-    steps:
-      - 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@v7
+    - uses: actions/stale@v6
       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

@@ -28,9 +28,9 @@ jobs:
 
     steps:
     - name: Setup dotnet
-      uses: actions/setup-dotnet@v3
+      uses: actions/setup-dotnet@v2
       with:
-        dotnet-version: 7.0.102
+        dotnet-version: 6.0.202
 
     - name: Checkout repository
       uses: actions/checkout@v3

.github/workflows/compile-queries.yml

@@ -1,37 +0,0 @@
-name: "Compile all queries using the latest stable CodeQL CLI"
-
-on:
-  push:
-    branches:  # makes sure the cache gets populated - running on the branches people tend to merge into.
-      - main
-      - "rc/*"
-      - "codeql-cli-*"
-  pull_request:
-
-jobs:
-  compile-queries:
-    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: all-queries
-      - name: check formatting
-        run: find */ql -type f \( -name "*.qll" -o -name "*.ql" \) -print0 | xargs -0 -n 3000 -P 10 codeql query format -q --check-only
-      - name: compile queries - check-only
-        # run with --check-only if running in a PR (github.sha != main)
-        if : ${{ github.event_name == 'pull_request' }}
-        shell: bash
-        run: codeql query compile -q -j0 */ql/{src,examples} --keep-going --warnings=error --check-only --compilation-cache "${{ steps.query-cache.outputs.cache-dir }}"
-      - name: compile queries - full
-        # do full compile if running on main - this populates the cache
-        if : ${{ github.event_name != 'pull_request' }}
-        shell: bash
-        run: codeql query compile -q -j0 */ql/{src,examples} --keep-going --warnings=error --compilation-cache "${{ steps.query-cache.outputs.cache-dir }}"

.github/workflows/csharp-qltest.yml

@@ -1,86 +0,0 @@
-name: "C#: Run QL Tests"
-
-on:
-  push:
-    paths:
-      - "csharp/**"
-      - "shared/**"
-      - .github/actions/fetch-codeql/action.yml
-      - codeql-workspace.yml
-    branches:
-      - main
-      - "rc/*"
-  pull_request:
-    paths:
-      - "csharp/**"
-      - "shared/**"
-      - .github/workflows/csharp-qltest.yml
-      - .github/actions/fetch-codeql/action.yml
-      - codeql-workspace.yml
-    branches:
-      - main
-      - "rc/*"
-
-defaults:
-  run:
-    working-directory: csharp
-
-jobs:
-  qlupgrade:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-      - uses: ./.github/actions/fetch-codeql
-      - name: Check DB upgrade scripts
-        run: |
-          echo >empty.trap
-          codeql dataset import -S ql/lib/upgrades/initial/semmlecode.csharp.dbscheme testdb empty.trap
-          codeql dataset upgrade testdb --additional-packs ql/lib
-          diff -q testdb/semmlecode.csharp.dbscheme ql/lib/semmlecode.csharp.dbscheme
-      - name: Check DB downgrade scripts
-        run: |
-          echo >empty.trap
-          rm -rf testdb; codeql dataset import -S ql/lib/semmlecode.csharp.dbscheme testdb empty.trap
-          codeql resolve upgrades --format=lines --allow-downgrades --additional-packs downgrades \
-           --dbscheme=ql/lib/semmlecode.csharp.dbscheme --target-dbscheme=downgrades/initial/semmlecode.csharp.dbscheme |
-           xargs codeql execute upgrades testdb
-          diff -q testdb/semmlecode.csharp.dbscheme downgrades/initial/semmlecode.csharp.dbscheme
-  qltest:
-    runs-on: ubuntu-latest-xl
-    strategy:
-      fail-fast: false
-      matrix:
-        slice: ["1/2", "2/2"]
-    steps:
-      - uses: actions/checkout@v3
-      - uses: ./.github/actions/fetch-codeql
-      - uses: ./csharp/actions/create-extractor-pack
-      - name: Cache compilation cache
-        id: query-cache
-        uses: ./.github/actions/cache-query-compilation
-        with:
-          key: csharp-qltest-${{ matrix.slice }}
-      - name: Run QL tests
-        run: |
-          CODEQL_PATH=$(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: ${{ github.token }}
-  unit-tests:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-      - name: Setup dotnet
-        uses: actions/setup-dotnet@v3
-        with:
-          dotnet-version: 7.0.102
-      - name: Extractor unit tests
-        run: |
-          dotnet test -p:RuntimeFrameworkVersion=7.0.2 "${{ 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"

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

@@ -1,80 +0,0 @@
-name: "Go: Run Tests - Other OS"
-on:
-  pull_request:
-    paths:
-      - "go/**"
-      - "!go/ql/**" # don't run other-os if only ql/ files changed
-      - .github/workflows/go-tests-other-os.yml
-      - .github/actions/**
-      - codeql-workspace.yml
-jobs:
-  test-mac:
-    name: Test MacOS
-    runs-on: macos-latest
-    steps:
-      - name: Set up Go 1.20
-        uses: actions/setup-go@v3
-        with:
-          go-version: 1.20.0
-        id: go
-
-      - name: Check out code
-        uses: actions/checkout@v2
-
-      - name: Set up CodeQL CLI
-        uses: ./.github/actions/fetch-codeql
-
-      - name: Enable problem matchers in repository
-        shell: bash
-        run: 'find .github/problem-matchers -name \*.json -exec echo "::add-matcher::{}" \;'
-
-      - name: Build
-        run: |
-          cd go
-          make
-
-      - name: Cache compilation cache
-        id: query-cache
-        uses: ./.github/actions/cache-query-compilation
-        with:
-          key: go-qltest
-      - name: Test
-        run: |
-          cd go
-          make test cache="${{ steps.query-cache.outputs.cache-dir }}"
-
-  test-win:
-    name: Test Windows
-    runs-on: windows-latest-xl
-    steps:
-      - name: Set up Go 1.20
-        uses: actions/setup-go@v3
-        with:
-          go-version: 1.20.0
-        id: go
-
-      - name: Check out code
-        uses: actions/checkout@v2
-
-      - name: Set up CodeQL CLI
-        uses: ./.github/actions/fetch-codeql
-
-      - name: Enable problem matchers in repository
-        shell: bash
-        run: 'find .github/problem-matchers -name \*.json -exec echo "::add-matcher::{}" \;'
-
-      - name: Build
-        run: |
-          cd go
-          make
-
-      - name: Cache compilation cache
-        id: query-cache
-        uses: ./.github/actions/cache-query-compilation
-        with:
-          key: go-qltest
-
-      - name: Test
-        run: |
-          cd go
-          make test cache="${{ steps.query-cache.outputs.cache-dir }}"

.github/workflows/go-tests.yml

@@ -1,29 +1,20 @@
 name: "Go: Run Tests"
 on:
-  push:
-    paths:
-      - "go/**"
-      - .github/workflows/go-tests.yml
-      - .github/actions/**
-      - codeql-workspace.yml
-    branches:
-      - main
-      - "rc/*"
   pull_request:
     paths:
       - "go/**"
       - .github/workflows/go-tests.yml
-      - .github/actions/**
+      - .github/actions/fetch-codeql/action.yml
       - codeql-workspace.yml
 jobs:
   test-linux:
     name: Test Linux (Ubuntu)
-    runs-on: ubuntu-latest-xl
+    runs-on: ubuntu-latest
     steps:
-      - name: Set up Go 1.20
+      - name: Set up Go 1.19
         uses: actions/setup-go@v3
         with:
-          go-version: 1.20.0
+          go-version: 1.19
         id: go
 
       - name: Check out code
@@ -41,7 +32,7 @@ jobs:
           cd go
           make
 
-      - name: Check that all Go code is autoformatted
+      - name: Check that all QL and Go code is autoformatted
         run: |
           cd go
           make check-formatting
@@ -52,18 +43,72 @@ jobs:
           env QHELP_OUT_DIR=qhelp-out make qhelp-to-markdown
 
       - name: Upload qhelp markdown
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v2
         with:
           name: qhelp-markdown
           path: go/qhelp-out/**/*.md
 
-      - name: Cache compilation cache
-        id: query-cache
-        uses: ./.github/actions/cache-query-compilation
+      - name: Test
+        run: |
+          cd go
+          make test
+
+  test-mac:
+    name: Test MacOS
+    runs-on: macos-latest
+    steps:
+      - name: Set up Go 1.19
+        uses: actions/setup-go@v3
         with:
-          key: go-qltest
+          go-version: 1.19
+        id: go
+
+      - name: Check out code
+        uses: actions/checkout@v2
+
+      - name: Set up CodeQL CLI
+        uses: ./.github/actions/fetch-codeql
+
+      - name: Enable problem matchers in repository
+        shell: bash
+        run: 'find .github/problem-matchers -name \*.json -exec echo "::add-matcher::{}" \;'
+
+      - name: Build
+        run: |
+          cd go
+          make
 
       - name: Test
         run: |
           cd go
-          make test cache="${{ steps.query-cache.outputs.cache-dir }}"
+          make test
+
+  test-win:
+    name: Test Windows
+    runs-on: windows-2019
+    steps:
+      - name: Set up Go 1.19
+        uses: actions/setup-go@v3
+        with:
+          go-version: 1.19
+        id: go
+
+      - name: Check out code
+        uses: actions/checkout@v2
+
+      - name: Set up CodeQL CLI
+        uses: ./.github/actions/fetch-codeql
+
+      - name: Enable problem matchers in repository
+        shell: bash
+        run: 'find .github/problem-matchers -name \*.json -exec echo "::add-matcher::{}" \;'
+
+      - name: Build
+        run: |
+          cd go
+          make
+
+      - name: Test
+        run: |
+          cd go
+          make test

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

@@ -23,9 +23,22 @@ defaults:
     working-directory: javascript/ql/experimental/adaptivethreatmodeling
 
 jobs:
-  qltest:
-    name: Test QL
-    runs-on: ubuntu-latest-xl
+  qlformat:
+    name: Check QL formatting
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+
+      - uses: ./.github/actions/fetch-codeql
+
+      - name: Check QL formatting
+        run: |
+          find . "(" -name "*.ql" -or -name "*.qll" ")" -print0 | \
+            xargs -0 codeql query format --check-only
+
+  qlcompile:
+    name: Check QL compilation
+    runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v3
 
@@ -33,33 +46,36 @@ jobs:
 
       - name: Install pack dependencies
         run: |
-          for pack in modelbuilding src test; do
+          for pack in modelbuilding src; 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 \
+            --ram 5120 \
             --additional-packs "${{ github.workspace }}" \
             --threads=0 \
-            --compilation-cache "${{ steps.query-cache.outputs.cache-dir }}" \
             -- \
             lib modelbuilding src
 
+  qltest:
+    name: Run QL tests
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+
+      - uses: ./.github/actions/fetch-codeql
+
+      - name: Install pack dependencies
+        run: codeql pack install -- test
+
       - name: Run QL tests
         run: |
           codeql test run \
             --threads=0 \
-            --ram 50000 \
+            --ram 5120 \
             --additional-packs "${{ github.workspace }}" \
-            --compilation-cache "${{ steps.query-cache.outputs.cache-dir }}" \
             -- \
-            test
+            test

.github/workflows/mad_modelDiff.yml

@@ -11,7 +11,7 @@ on:
     branches:
       - main
     paths:
-      - "java/ql/src/utils/modelgenerator/**/*.*"
+      - "java/ql/src/utils/model-generator/**/*.*"
       - ".github/workflows/mad_modelDiff.yml"
 
 permissions:
@@ -40,12 +40,12 @@ jobs:
       - name: Download database
         env:
           SLUG: ${{ matrix.slug }}
-          GH_TOKEN: ${{ github.token }}
         run: |
           set -x
           mkdir lib-dbs
           SHORTNAME=${SLUG//[^a-zA-Z0-9_]/}
-          gh api -H "Accept: application/zip" "/repos/${SLUG}/code-scanning/codeql/databases/java" > "$SHORTNAME.zip"
+          projectId=`curl -s https://lgtm.com/api/v1.0/projects/g/${SLUG} | jq .id`
+          curl -L "https://lgtm.com/api/v1.0/snapshots/$projectId/java" -o "$SHORTNAME.zip"
           unzip -q -d "${SHORTNAME}-db" "${SHORTNAME}.zip"
           mkdir "lib-dbs/$SHORTNAME/"
           mv "${SHORTNAME}-db/"$(ls -1 "${SHORTNAME}"-db)/* "lib-dbs/${SHORTNAME}/"
@@ -61,8 +61,8 @@ jobs:
             DATABASE=$2
             cd codeql-$QL_VARIANT
             SHORTNAME=`basename $DATABASE`
-            python java/ql/src/utils/modelgenerator/GenerateFlowModel.py --with-summaries --with-sinks $DATABASE ${SHORTNAME}.temp.model.yml
-            mv java/ql/lib/ext/generated/${SHORTNAME}.temp.model.yml $MODELS/${SHORTNAME}Generated_${QL_VARIANT}.model.yml
+            python java/ql/src/utils/model-generator/GenerateFlowModel.py --with-summaries --with-sinks $DATABASE $MODELS/${SHORTNAME}.qll
+            mv $MODELS/${SHORTNAME}.qll $MODELS/${SHORTNAME}Generated_${QL_VARIANT}.qll
             cd ..
           }
 
@@ -85,21 +85,19 @@ jobs:
           set -x
           MODELS=`pwd`/tmp-models
           ls -1 tmp-models/
-          for m in $MODELS/*_main.model.yml ; do
+          for m in $MODELS/*_main.qll ; do
             t="${m/main/"pr"}"
             basename=`basename $m`
-            name="diff_${basename/_main.model.yml/""}"
+            name="diff_${basename/_main.qll/""}"
             (diff -w -u $m $t | diff2html -i stdin -F $MODELS/$name.html) || true
           done
       - uses: actions/upload-artifact@v3
         with:
           name: models
-          path: tmp-models/*.model.yml
+          path: tmp-models/*.qll
           retention-days: 20
       - uses: actions/upload-artifact@v3
         with:
           name: diffs
           path: tmp-models/*.html
-          # An html file is only produced if the generated models differ.
-          if-no-files-found: ignore
           retention-days: 20

.github/workflows/mad_regenerate-models.yml

@@ -50,10 +50,10 @@ jobs:
           SLUG: ${{ matrix.slug }}
         run: |
           SHORTNAME=${SLUG//[^a-zA-Z0-9_]/}
-          java/ql/src/utils/modelgenerator/RegenerateModels.py "${SLUG}" dbs/${SHORTNAME}
+          java/ql/src/utils/model-generator/RegenerateModels.py "${SLUG}" dbs/${SHORTNAME}
       - name: Stage changes
         run: |
-          find java -name "*.model.yml" -print0 | xargs -0 git add
+          find java -name "*.qll" -print0 | xargs -0 git add
           git status
           git diff --cached > models.patch
       - uses: actions/upload-artifact@v3

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

@@ -27,7 +27,7 @@ on:
       - main
       - "rc/*"
     paths:
-      - "**/*.qhelp"
+      - "ruby/**/*.qhelp"
 
 jobs:
   qhelp:
@@ -52,7 +52,7 @@ jobs:
         id: changes
         run: |
           (git diff -z --name-only --diff-filter=ACMRT HEAD~1 HEAD | grep -z '.qhelp$' | grep -z -v '.inc.qhelp';
-           git diff -z --name-only --diff-filter=ACMRT HEAD~1 HEAD | grep -z '.inc.qhelp$' | xargs --null -rn1 basename -z | xargs --null -rn1 git grep -z -l) |
+           git diff -z --name-only --diff-filter=ACMRT HEAD~1 HEAD | grep -z '.inc.qhelp$' | xargs --null -rn1 basename | xargs --null -rn1 git grep -z -l) |
            grep -z '.qhelp$' | grep -z -v '^-' | sort -z -u > "${RUNNER_TEMP}/paths.txt"
 
       - name: QHelp preview

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

@@ -5,6 +5,13 @@ on:
     branches: [main]
   pull_request:
     branches: [main]
+    paths:
+      - "ql/**"
+      - "**.qll"
+      - "**.ql"
+      - "**.dbscheme"
+      - "**/qlpack.yml"
+      - ".github/workflows/ql-for-ql-build.yml"
 
 env:
   CARGO_TERM_COLOR: always
@@ -15,60 +22,137 @@ jobs:
     steps:
       ### Build the queries ###
       - uses: actions/checkout@v3
-        with:
-          fetch-depth: 0
       - name: Find codeql
         id: find-codeql
-        uses: github/codeql-action/init@v2
+        uses: github/codeql-action/init@71a8b35ff4c80fcfcd05bc1cd932fe3c08f943ca
         with:
           languages: javascript # does not matter
-      - uses: ./.github/actions/os-version
-        id: os_version
+      - name: Get CodeQL version
+        id: get-codeql-version
+        run: |
+          echo "::set-output name=version::$("${CODEQL}" --version | head -n 1 | rev | cut -d " " -f 1 | rev)"
+        shell: bash
+        env:
+          CODEQL: ${{ steps.find-codeql.outputs.codeql-path }}
+      - name: Cache entire pack
+        id: cache-pack
+        uses: actions/cache@v3
+        with:
+          path: ${{ runner.temp }}/pack
+          key: ${{ runner.os }}-pack-${{ hashFiles('ql/**/Cargo.lock') }}-${{ hashFiles('ql/**/*.rs') }}-${{ hashFiles('ql/**/*.ql*') }}-${{ hashFiles('ql/**/qlpack.yml') }}-${{ hashFiles('ql/ql/src/ql.dbscheme*') }}-${{ steps.get-codeql-version.outputs.version }}--${{ hashFiles('.github/workflows/ql-for-ql-build.yml') }}
+      - name: Cache queries
+        if: steps.cache-pack.outputs.cache-hit != 'true'
+        id: cache-queries
+        uses: actions/cache@v3
+        with:
+          path: ${{ runner.temp }}/queries
+          key: queries-${{ hashFiles('ql/**/*.ql*') }}-${{ hashFiles('ql/**/qlpack.yml') }}-${{ hashFiles('ql/ql/src/ql.dbscheme*') }}-${{ steps.get-codeql-version.outputs.version }}--${{ hashFiles('.github/workflows/ql-for-ql-build.yml') }}
+      - name: Build query pack
+        if: steps.cache-queries.outputs.cache-hit != 'true' && steps.cache-pack.outputs.cache-hit != 'true'
+        run: |
+          cd ql/ql/src
+          "${CODEQL}" pack create -j 16
+          mv .codeql/pack/codeql/ql/0.0.0 ${{ runner.temp }}/queries
+        env:
+          CODEQL: ${{ steps.find-codeql.outputs.codeql-path }}
+      - name: Move cache queries to pack
+        if: steps.cache-pack.outputs.cache-hit != 'true'
+        run: |
+          cp -r ${{ runner.temp }}/queries ${{ runner.temp }}/pack
+        env:
+          CODEQL: ${{ steps.find-codeql.outputs.codeql-path }}
+
       ### Build the extractor ###
       - name: Cache entire extractor
+        if: steps.cache-pack.outputs.cache-hit != 'true'
         id: cache-extractor
         uses: actions/cache@v3
         with:
           path: |
-            ql/extractor-pack/
-            ql/target/release/buramu
-          key: ${{ runner.os }}-${{ steps.os_version.outputs.version }}-extractor-${{ hashFiles('ql/**/Cargo.lock') }}-${{ hashFiles('ql/**/*.rs') }}
+            ql/target/release/ql-autobuilder
+            ql/target/release/ql-autobuilder.exe
+            ql/target/release/ql-extractor
+            ql/target/release/ql-extractor.exe
+          key: ${{ runner.os }}-extractor-${{ hashFiles('ql/**/Cargo.lock') }}-${{ hashFiles('ql/**/*.rs') }}
       - name: Cache cargo
-        if: steps.cache-extractor.outputs.cache-hit != 'true'
+        if: steps.cache-extractor.outputs.cache-hit != 'true' && steps.cache-pack.outputs.cache-hit != 'true'
         uses: actions/cache@v3
         with:
           path: |
             ~/.cargo/registry
             ~/.cargo/git
             ql/target
-          key: ${{ runner.os }}-${{ steps.os_version.outputs.version }}-rust-cargo-${{ hashFiles('ql/**/Cargo.lock') }}
+          key: ${{ runner.os }}-rust-cargo-${{ hashFiles('ql/**/Cargo.lock') }}
+      - name: Check formatting
+        if: steps.cache-extractor.outputs.cache-hit != 'true' && steps.cache-pack.outputs.cache-hit != 'true'
+        run: cd ql; cargo fmt --all -- --check
+      - name: Build
+        if: steps.cache-extractor.outputs.cache-hit != 'true' && steps.cache-pack.outputs.cache-hit != 'true'
+        run: cd ql; cargo build --verbose
+      - name: Run tests
+        if: steps.cache-extractor.outputs.cache-hit != 'true' && steps.cache-pack.outputs.cache-hit != 'true'
+        run: cd ql; cargo test --verbose
       - name: Release build
-        if: steps.cache-extractor.outputs.cache-hit != 'true'
-        run: cd ql; ./scripts/create-extractor-pack.sh       
-        env:
-          GH_TOKEN: ${{ github.token }}   
-      - name: Cache compilation cache
-        id: query-cache
-        uses: ./.github/actions/cache-query-compilation
-        with: 
-          key: run-ql-for-ql
-      - name: Make database and analyze
+        if: steps.cache-extractor.outputs.cache-hit != 'true' && steps.cache-pack.outputs.cache-hit != 'true'
+        run: cd ql; cargo build --release
+      - name: Generate dbscheme
+        if: steps.cache-extractor.outputs.cache-hit != 'true' && steps.cache-pack.outputs.cache-hit != 'true'
+        run: ql/target/release/ql-generator --dbscheme ql/ql/src/ql.dbscheme --library ql/ql/src/codeql_ql/ast/internal/TreeSitter.qll
+
+      ### Package the queries and extractor ###
+      - name: Package pack
+        if: steps.cache-pack.outputs.cache-hit != 'true'
         run: |
-          ./ql/target/release/buramu | tee deprecated.blame # Add a blame file for the extractor to parse.
-          ${CODEQL} database create -l=ql --search-path ql/extractor-pack ${DB}
-          ${CODEQL} database analyze -j0 --format=sarif-latest --output=ql-for-ql.sarif ${DB} ql/ql/src/codeql-suites/ql-code-scanning.qls  --compilation-cache "${{ steps.query-cache.outputs.cache-dir }}"
-        env: 
-          CODEQL: ${{ steps.find-codeql.outputs.codeql-path }}
-          DB: ${{ runner.temp }}/DB
-          LGTM_INDEX_FILTERS: |
-            exclude:ql/ql/test
-            exclude:*/ql/lib/upgrades/
-            exclude:java/ql/integration-tests
-      - name: Upload sarif to code-scanning
-        uses: github/codeql-action/upload-sarif@v2
+          cp -r ql/codeql-extractor.yml ql/tools ql/ql/src/ql.dbscheme.stats ${PACK}/
+          mkdir -p ${PACK}/tools/linux64
+          cp ql/target/release/ql-autobuilder  ${PACK}/tools/linux64/autobuilder
+          cp ql/target/release/ql-extractor ${PACK}/tools/linux64/extractor
+          chmod +x ${PACK}/tools/linux64/autobuilder
+          chmod +x ${PACK}/tools/linux64/extractor
+        env:
+          PACK: ${{ runner.temp }}/pack
+
+      ### Run the analysis ###
+      - name: Hack codeql-action options
+        run: |
+          JSON=$(jq -nc --arg pack "${PACK}" '.database."run-queries"=["--search-path", $pack] | .resolve.queries=["--search-path", $pack] | .resolve.extractor=["--search-path", $pack] | .resolve.languages=["--search-path", $pack] | .database.init=["--search-path", $pack]')
+          echo "CODEQL_ACTION_EXTRA_OPTIONS=${JSON}" >> ${GITHUB_ENV}
+        env:
+          PACK: ${{ runner.temp }}/pack
+
+      - name: Create CodeQL config file
+        run: |
+          echo "paths-ignore:" >> ${CONF}
+          echo "  - ql/ql/test" >> ${CONF}
+          echo "  - \"*/ql/lib/upgrades/\"" >> ${CONF}
+          echo "disable-default-queries: true" >> ${CONF}
+          echo "queries:" >> ${CONF}
+          echo "  - uses: ./ql/ql/src/codeql-suites/ql-code-scanning.qls" >> ${CONF}
+          echo "Config file: "
+          cat ${CONF}
+        env:
+          CONF: ./ql-for-ql-config.yml
+      - name: Initialize CodeQL
+        uses: github/codeql-action/init@71a8b35ff4c80fcfcd05bc1cd932fe3c08f943ca
         with:
-          sarif_file: ql-for-ql.sarif
-          category: ql-for-ql
+          languages: ql
+          db-location: ${{ runner.temp }}/db
+          config-file: ./ql-for-ql-config.yml
+      - name: Move pack cache
+        run: |
+          cp -r ${PACK}/.cache ql/ql/src/.cache
+        env:
+          PACK: ${{ runner.temp }}/pack
+
+      - name: Perform CodeQL Analysis
+        uses: github/codeql-action/analyze@71a8b35ff4c80fcfcd05bc1cd932fe3c08f943ca
+        with:
+          category: "ql-for-ql"
+      - name: Copy sarif file to CWD
+        run: cp ../results/ql.sarif ./ql-for-ql.sarif
+      - name: Fixup the $scema in sarif  # Until https://github.com/microsoft/sarif-vscode-extension/pull/436/ is part in a stable release
+        run: |
+          sed -i 's/\$schema.*/\$schema": "https:\/\/raw.githubusercontent.com\/oasis-tcs\/sarif-spec\/master\/Schemata\/sarif-schema-2.1.0",/' ql-for-ql.sarif
       - name: Sarif as artifact
         uses: actions/upload-artifact@v3
         with:
@@ -83,4 +167,4 @@ jobs:
         with:
           name: ql-for-ql-langs
           path: split-sarif
-          retention-days: 1
+          retention-days: 1

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

@@ -25,18 +25,16 @@ jobs:
 
       - name: Find codeql
         id: find-codeql
-        uses: github/codeql-action/init@v2
+        uses: github/codeql-action/init@71a8b35ff4c80fcfcd05bc1cd932fe3c08f943ca
         with:
           languages: javascript # does not matter
-      - uses: ./.github/actions/os-version
-        id: os_version
       - uses: actions/cache@v3
         with:
           path: |
             ~/.cargo/registry
             ~/.cargo/git
             ql/target
-          key: ${{ runner.os }}-${{ steps.os_version.outputs.version }}-qltest-cargo-${{ hashFiles('ql/**/Cargo.lock') }}
+          key: ${{ runner.os }}-qltest-cargo-${{ hashFiles('ql/**/Cargo.lock') }}
       - name: Build Extractor
         run: cd ql; env "PATH=$PATH:`dirname ${CODEQL}`" ./scripts/create-extractor-pack.sh
         env:

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

@@ -6,13 +6,11 @@ on:
     paths:
       - "ql/**"
       - codeql-workspace.yml
-      - .github/workflows/ql-for-ql-tests.yml
   pull_request:
     branches: [main]
     paths:
       - "ql/**"
       - codeql-workspace.yml
-      - .github/workflows/ql-for-ql-tests.yml
 
 env:
   CARGO_TERM_COLOR: always
@@ -24,86 +22,33 @@ jobs:
       - uses: actions/checkout@v3
       - name: Find codeql
         id: find-codeql
-        uses: github/codeql-action/init@v2
+        uses: github/codeql-action/init@71a8b35ff4c80fcfcd05bc1cd932fe3c08f943ca
         with:
           languages: javascript # does not matter
-      - uses: ./.github/actions/os-version
-        id: os_version
       - uses: actions/cache@v3
         with:
           path: |
             ~/.cargo/registry
             ~/.cargo/git
             ql/target
-          key: ${{ runner.os }}-${{ steps.os_version.outputs.version }}-qltest-cargo-${{ hashFiles('ql/rust-toolchain.toml', 'ql/**/Cargo.lock') }}
-      - name: Check formatting
-        run: cd ql; cargo fmt --all -- --check
+          key: ${{ runner.os }}-qltest-cargo-${{ hashFiles('ql/**/Cargo.lock') }}
       - name: Build extractor
         run: |
           cd ql;
           codeqlpath=$(dirname ${{ steps.find-codeql.outputs.codeql-path }});
           env "PATH=$PATH:$codeqlpath" ./scripts/create-extractor-pack.sh
-      - name: Cache compilation cache
-        id: query-cache
-        uses: ./.github/actions/cache-query-compilation
-        with: 
-          key: ql-for-ql-tests
       - name: Run QL tests
         run: |
-          "${CODEQL}" test run --check-databases --check-unused-labels --check-repeated-labels --check-redefined-labels --check-use-before-definition --search-path "${{ github.workspace }}/ql/extractor-pack" --consistency-queries ql/ql/consistency-queries --compilation-cache "${{ steps.query-cache.outputs.cache-dir }}" ql/ql/test
+          "${CODEQL}" test run --check-databases --check-unused-labels --check-repeated-labels --check-redefined-labels --check-use-before-definition --search-path "${{ github.workspace }}/ql/extractor-pack" --consistency-queries ql/ql/consistency-queries ql/ql/test
         env:
           CODEQL: ${{ steps.find-codeql.outputs.codeql-path }}
-
-  other-os: 
-    strategy:
-      matrix:
-        os: [macos-latest, windows-latest]
-    needs: [qltest]
-    runs-on: ${{ matrix.os }}
-    steps:
-      - uses: actions/checkout@v3
-      - name: Install GNU tar 
-        if: runner.os == 'macOS'
+      - name: Check QL formatting
         run: |
-          brew install gnu-tar
-          echo "/usr/local/opt/gnu-tar/libexec/gnubin" >> $GITHUB_PATH
-      - name: Find codeql
-        id: find-codeql
-        uses: github/codeql-action/init@v2
-        with:
-          languages: javascript # does not matter
-      - uses: ./.github/actions/os-version
-        id: os_version
-      - uses: actions/cache@v3
-        with:
-          path: |
-            ~/.cargo/registry
-            ~/.cargo/git
-            ql/target
-          key: ${{ runner.os }}-${{ steps.os_version.outputs.version }}-qltest-cargo-${{ hashFiles('ql/rust-toolchain.toml', 'ql/**/Cargo.lock') }}
-      - name: Build extractor
-        if: runner.os != 'Windows'
-        run: |
-          cd ql;
-          codeqlpath=$(dirname ${{ steps.find-codeql.outputs.codeql-path }});
-          env "PATH=$PATH:$codeqlpath" ./scripts/create-extractor-pack.sh
-      - name: Build extractor (Windows)
-        if: runner.os == 'Windows'
-        shell: pwsh
-        run: |
-          cd ql;
-          $Env:PATH += ";$(dirname ${{ steps.find-codeql.outputs.codeql-path }})"
-          pwsh ./scripts/create-extractor-pack.ps1
-      - name: Run a single QL tests - Unix
-        if: runner.os != 'Windows'
-        run: |
-          "${CODEQL}" test run --check-databases --search-path "${{ github.workspace }}/ql/extractor-pack" ql/ql/test/queries/style/DeadCode/DeadCode.qlref
+          find ql/ql/src "(" -name "*.ql" -or -name "*.qll" ")" -print0 | xargs -0 "${CODEQL}" query format --check-only
         env:
           CODEQL: ${{ steps.find-codeql.outputs.codeql-path }}
-      - name: Run a single QL tests - Windows
-        if: runner.os == 'Windows'
-        shell: pwsh
+      - name: Check QL compilation
         run: |
-          $Env:PATH += ";$(dirname ${{ steps.find-codeql.outputs.codeql-path }})"
-          codeql test run --check-databases --search-path "${{ github.workspace }}/ql/extractor-pack" ql/ql/test/queries/style/DeadCode/DeadCode.qlref
-      
+          "${CODEQL}" query compile --check-only --threads=4 --warnings=error --search-path "${{ github.workspace }}/ql/extractor-pack" "ql/ql/src" "ql/ql/examples"
+        env:
+          CODEQL: ${{ steps.find-codeql.outputs.codeql-path }}

.github/workflows/ruby-build.yml

@@ -48,41 +48,23 @@ jobs:
         run: |
           brew install gnu-tar
           echo "/usr/local/opt/gnu-tar/libexec/gnubin" >> $GITHUB_PATH
-      - uses: ./.github/actions/os-version
-        id: os_version
-      - name: Cache entire extractor
-        uses: actions/cache@v3
-        id: cache-extractor
-        with:
-          path: |
-            ruby/target/release/ruby-autobuilder
-            ruby/target/release/ruby-autobuilder.exe
-            ruby/target/release/ruby-extractor
-            ruby/target/release/ruby-extractor.exe
-            ruby/ql/lib/codeql/ruby/ast/internal/TreeSitter.qll
-          key: ${{ runner.os }}-${{ steps.os_version.outputs.version }}-ruby-extractor-${{ hashFiles('ruby/rust-toolchain.toml', 'ruby/**/Cargo.lock') }}--${{ hashFiles('ruby/**/*.rs') }}
       - uses: actions/cache@v3
-        if: steps.cache-extractor.outputs.cache-hit != 'true'
         with:
           path: |
             ~/.cargo/registry
             ~/.cargo/git
             ruby/target
-          key: ${{ runner.os }}-${{ steps.os_version.outputs.version }}-ruby-rust-cargo-${{ hashFiles('ruby/rust-toolchain.toml', 'ruby/**/Cargo.lock') }}
+          key: ${{ runner.os }}-ruby-rust-cargo-${{ hashFiles('ruby/rust-toolchain.toml', 'ruby/**/Cargo.lock') }}
       - name: Check formatting
-        if: steps.cache-extractor.outputs.cache-hit != 'true'
         run: cargo fmt --all -- --check
       - name: Build
-        if: steps.cache-extractor.outputs.cache-hit != 'true'
         run: cargo build --verbose
       - name: Run tests
-        if: steps.cache-extractor.outputs.cache-hit != 'true'
         run: cargo test --verbose
       - name: Release build
-        if: steps.cache-extractor.outputs.cache-hit != 'true'
         run: cargo build --release
       - name: Generate dbscheme
-        if: ${{ matrix.os == 'ubuntu-latest' && steps.cache-extractor.outputs.cache-hit != 'true'}}
+        if: ${{ matrix.os == 'ubuntu-latest' }}
         run: target/release/ruby-generator --dbscheme ql/lib/ruby.dbscheme --library ql/lib/codeql/ruby/ast/internal/TreeSitter.qll
       - uses: actions/upload-artifact@v3
         if: ${{ matrix.os == 'ubuntu-latest' }}
@@ -104,25 +86,19 @@ jobs:
             ruby/target/release/ruby-extractor.exe
           retention-days: 1
   compile-queries:
-    runs-on: ubuntu-latest-xl
+    runs-on: ubuntu-latest
+    env:
+      CODEQL_THREADS: 4 # TODO: remove this once it's set by the CLI
     steps:
       - uses: actions/checkout@v3
       - name: Fetch CodeQL
         uses: ./.github/actions/fetch-codeql
-      - name: Cache compilation cache
-        id: query-cache
-        uses: ./.github/actions/cache-query-compilation
-        with: 
-          key: ruby-build
       - name: Build Query Pack
         run: |
-          rm -rf target/packs
-          codeql pack create ../misc/suite-helpers --output target/packs
-          codeql pack create ../shared/regex --output target/packs
           codeql pack create ../shared/ssa --output target/packs
-          codeql pack create ../shared/tutorial --output target/packs
           codeql pack create ql/lib --output target/packs
-          codeql pack create -j0 ql/src --output target/packs --compilation-cache "${{ steps.query-cache.outputs.cache-dir }}"
+          codeql pack install ql/src
+          codeql pack create ql/src --output target/packs
           PACK_FOLDER=$(readlink -f target/packs/codeql/ruby-queries/*)
           codeql generate query-help --format=sarifv2.1.0 --output="${PACK_FOLDER}/rules.sarif" ql/src
           (cd ql/src; find queries \( -name '*.qhelp' -o -name '*.rb' -o -name '*.erb' \) -exec bash -c 'mkdir -p "'"${PACK_FOLDER}"'/$(dirname "{}")"' \; -exec cp "{}" "${PACK_FOLDER}/{}" \;)
@@ -205,6 +181,11 @@ jobs:
       - name: Fetch CodeQL
         uses: ./.github/actions/fetch-codeql
 
+      - uses: actions/checkout@v3
+        with:
+          repository: Shopify/example-ruby-app
+          ref: 67a0decc5eb550f3a9228eda53925c3afd40dfe9
+
       - name: Download Ruby bundle
         uses: actions/download-artifact@v3
         with:
@@ -213,15 +194,26 @@ jobs:
       - name: Unzip Ruby bundle
         shell: bash
         run: unzip -q -d "${{ runner.temp }}/ruby-bundle" "${{ runner.temp }}/codeql-ruby-bundle.zip"
-
+      - name: Prepare test files
+        shell: bash
+        run: |
+          echo "import codeql.ruby.AST select count(File f)" > "test.ql"
+          echo "| 4 |" > "test.expected"
+          echo 'name: sample-tests
+          version: 0.0.0
+          dependencies:
+            codeql/ruby-all: 0.0.1
+          extractor: ruby
+          tests: .
+          ' > qlpack.yml
       - 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/
+          codeql test run --search-path "${{ runner.temp }}/ruby-bundle" --additional-packs "${{ runner.temp }}/ruby-bundle" .
       - name: Create database
         shell: bash
         run: |
-          codeql database create --search-path "${{ runner.temp }}/ruby-bundle" --language ruby --source-root ruby/ql/test/library-tests/ast/constants/ ../database
+          codeql database create --search-path "${{ runner.temp }}/ruby-bundle" --language ruby --source-root . ../database
       - name: Analyze database
         shell: bash
         run: |

.github/workflows/ruby-qltest.yml

@@ -4,7 +4,7 @@ on:
   push:
     paths:
       - "ruby/**"
-      - .github/workflows/ruby-build.yml
+      - .github/workflows/ruby-qltest.yml
       - .github/actions/fetch-codeql/action.yml
       - codeql-workspace.yml
     branches:
@@ -28,6 +28,23 @@ defaults:
     working-directory: ruby
 
 jobs:
+  qlformat:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: ./.github/actions/fetch-codeql
+      - name: Check QL formatting
+        run: find ql "(" -name "*.ql" -or -name "*.qll" ")" -print0 | xargs -0 codeql query format --check-only
+  qlcompile:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: ./.github/actions/fetch-codeql
+      - name: Check QL compilation
+        run: |
+          codeql query compile --check-only --threads=0 --ram 5000 --warnings=error "ql/src" "ql/examples"
+        env:
+          GITHUB_TOKEN: ${{ github.token }}
   qlupgrade:
     runs-on: ubuntu-latest
     steps:
@@ -48,20 +65,17 @@ jobs:
            xargs codeql execute upgrades testdb
           diff -q testdb/ruby.dbscheme downgrades/initial/ruby.dbscheme
   qltest:
-    runs-on: ubuntu-latest-xl
+    runs-on: ubuntu-latest
     strategy:
       fail-fast: false
+      matrix:
+        slice: ["1/2", "2/2"]
     steps:
       - uses: actions/checkout@v3
       - uses: ./.github/actions/fetch-codeql
       - uses: ./ruby/actions/create-extractor-pack
-      - name: Cache compilation cache
-        id: query-cache
-        uses: ./.github/actions/cache-query-compilation
-        with: 
-          key: ruby-qltest
       - name: Run QL tests
         run: |
-          codeql test run --threads=0 --ram 50000 --search-path "${{ github.workspace }}/ruby/extractor-pack" --check-databases --check-undefined-labels --check-unused-labels --check-repeated-labels --check-redefined-labels --check-use-before-definition --consistency-queries ql/consistency-queries ql/test --compilation-cache "${{ steps.query-cache.outputs.cache-dir }}"
+          codeql test run --threads=0 --ram 5000 --slice ${{ matrix.slice }} --search-path "${{ github.workspace }}/ruby/extractor-pack" --check-databases --check-unused-labels --check-repeated-labels --check-redefined-labels --check-use-before-definition --consistency-queries ql/consistency-queries ql/test
         env:
           GITHUB_TOKEN: ${{ github.token }}

.github/workflows/swift-codegen.yml

@@ -0,0 +1,39 @@
+name: "Swift: Check code generation"
+
+on:
+  pull_request:
+    paths:
+      - "swift/**"
+      - "misc/bazel/**"
+      - "*.bazel*"
+      - .github/workflows/swift-codegen.yml
+      - .github/actions/fetch-codeql/action.yml
+    branches:
+      - main
+
+jobs:
+  codegen:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: ./.github/actions/fetch-codeql
+      - uses: bazelbuild/setup-bazelisk@v2
+      - uses: actions/setup-python@v3
+      - uses: pre-commit/action@v3.0.0
+        name: Check that python code is properly formatted
+        with:
+          extra_args: autopep8 --all-files
+      - name: Run unit tests
+        run: |
+          bazel test //swift/codegen/test --test_output=errors
+      - uses: pre-commit/action@v3.0.0
+        name: Check that QL generated code was checked in
+        with:
+          extra_args: swift-codegen --all-files
+      - name: Generate C++ files
+        run: |
+          bazel run //swift/codegen:codegen -- --generate=trap,cpp --cpp-output=$PWD/swift-generated-cpp-files
+      - uses: actions/upload-artifact@v3
+        with:
+          name: swift-generated-cpp-files
+          path: swift-generated-cpp-files/**

.github/workflows/swift-integration-tests.yml

@@ -0,0 +1,45 @@
+name: "Swift: Run Integration Tests"
+
+on:
+  pull_request:
+    paths:
+      - "swift/**"
+      - "misc/bazel/**"
+      - "*.bazel*"
+      - .github/workflows/swift-integration-tests.yml
+      - .github/actions/fetch-codeql/action.yml
+      - codeql-workspace.yml
+    branches:
+      - main
+defaults:
+  run:
+    working-directory: swift
+
+jobs:
+  integration-tests:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os:
+          - ubuntu-20.04
+#          - macos-latest  TODO
+    steps:
+      - uses: actions/checkout@v3
+      - uses: ./.github/actions/fetch-codeql
+      - uses: bazelbuild/setup-bazelisk@v2
+      - uses: actions/setup-python@v3
+      - name: Build Swift extractor
+        run: |
+          bazel run //swift:create-extractor-pack
+      - name: Get Swift version
+        id: get_swift_version
+        run: |
+          VERSION=$(bazel run //swift/extractor -- --version | sed -ne 's/.*version \(\S*\).*/\1/p')
+          echo "::set-output name=version::$VERSION"
+      - uses: swift-actions/setup-swift@v1
+        with:
+          swift-version: "${{steps.get_swift_version.outputs.version}}"
+      - name: Run integration tests
+        run: |
+          python integration-tests/runner.py

.github/workflows/swift-qltest.yml

@@ -0,0 +1,43 @@
+name: "Swift: Run QL Tests"
+
+on:
+  pull_request:
+    paths:
+      - "swift/**"
+      - "misc/bazel/**"
+      - "*.bazel*"
+      - .github/workflows/swift-qltest.yml
+      - .github/actions/fetch-codeql/action.yml
+      - codeql-workspace.yml
+    branches:
+      - main
+defaults:
+  run:
+    working-directory: swift
+
+jobs:
+  qlformat:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: ./.github/actions/fetch-codeql
+      - name: Check QL formatting
+        run: find ql "(" -name "*.ql" -or -name "*.qll" ")" -print0 | xargs -0 codeql query format --check-only
+  qltest:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os : [ubuntu-20.04, macos-latest]
+    steps:
+      - uses: actions/checkout@v3
+      - uses: ./.github/actions/fetch-codeql
+      - uses: bazelbuild/setup-bazelisk@v2
+      - name: Build Swift extractor
+        run: |
+          bazel run //swift:create-extractor-pack
+      - name: Run QL tests
+        run: |
+          codeql test run --threads=0 --ram 5000 --search-path "${{ github.workspace }}/swift/extractor-pack" --check-databases --check-unused-labels --check-repeated-labels --check-redefined-labels --check-use-before-definition ql/test
+        env:
+          GITHUB_TOKEN: ${{ github.token }}

.github/workflows/swift.yml

@@ -1,105 +0,0 @@
-name: "Swift"
-
-on:
-  pull_request:
-    paths:
-      - "swift/**"
-      - "misc/bazel/**"
-      - "misc/codegen/**"
-      - "*.bazel*"
-      - .github/workflows/swift.yml
-      - .github/actions/**
-      - codeql-workspace.yml
-      - .pre-commit-config.yaml
-      - "!**/*.md"
-      - "!**/*.qhelp"
-    branches:
-      - main
-      - rc/*
-  push:
-    paths:
-      - "swift/**"
-      - "misc/bazel/**"
-      - "misc/codegen/**"
-      - "*.bazel*"
-      - .github/workflows/swift.yml
-      - .github/actions/**
-      - codeql-workspace.yml
-      - "!**/*.md"
-      - "!**/*.qhelp"
-    branches:
-      - main
-      - rc/*
-
-jobs:
-  # not using a matrix as you cannot depend on a specific job in a matrix, and we want to start linux checks
-  # without waiting for the macOS build
-  build-and-test-macos:
-    runs-on: macos-12-xl
-    steps:
-      - uses: actions/checkout@v3
-      - uses: ./swift/actions/build-and-test
-  build-and-test-linux:
-    runs-on: ubuntu-latest-xl
-    steps:
-      - 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@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@v3
-      - uses: ./swift/actions/run-ql-tests
-  integration-tests-linux:
-    needs: build-and-test-linux
-    runs-on: ubuntu-latest-xl
-    steps:
-      - uses: actions/checkout@v3
-      - uses: ./swift/actions/run-integration-tests
-  integration-tests-macos:
-    if : ${{ github.event_name == 'pull_request' }}
-    needs: build-and-test-macos
-    runs-on: macos-12-xl
-    timeout-minutes: 60
-    steps:
-      - uses: actions/checkout@v3
-      - uses: ./swift/actions/run-integration-tests
-  codegen:
-    if : ${{ github.event_name == 'pull_request' }}
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-      - uses: bazelbuild/setup-bazelisk@v2
-      - uses: actions/setup-python@v4
-        with:
-          python-version-file: 'swift/.python-version'
-      - uses: pre-commit/action@v3.0.0
-        name: Check that python code is properly formatted
-        with:
-          extra_args: autopep8 --all-files
-      - uses: ./.github/actions/fetch-codeql
-      - uses: pre-commit/action@v3.0.0
-        name: Check that QL generated code was checked in
-        with:
-          extra_args: swift-codegen --all-files
-      - name: Generate C++ files
-        run: |
-          bazel run //swift/codegen:codegen -- --generate=trap,cpp --cpp-output=$PWD/generated-cpp-files
-      - uses: actions/upload-artifact@v3
-        with:
-          name: swift-generated-cpp-files
-          path: generated-cpp-files/**
-  database-upgrade-scripts:
-    if : ${{ github.event_name == 'pull_request' }}
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-      - uses: ./.github/actions/fetch-codeql
-      - uses: ./swift/actions/database-upgrade-scripts

.gitignore

@@ -27,6 +27,8 @@
 # It's useful (though not required) to be able to unpack codeql in the ql checkout itself
 /codeql/
 
+csharp/extractor/Semmle.Extraction.CSharp.Driver/Properties/launchSettings.json
+
 # Avoid committing cached package components
 .codeql
 

.pre-commit-config.yaml

@@ -19,7 +19,7 @@ repos:
     rev: v1.6.0
     hooks:
       - id: autopep8
-        files: ^swift/.*\.py
+        files: ^swift/codegen/.*\.py
 
   - repo: local
     hooks:
@@ -31,7 +31,7 @@ repos:
 
       - id: sync-files
         name: Fix files required to be identical
-        files: \.(qll?|qhelp|swift)$|^config/identical-files\.json$
+        files: \.(qll?|qhelp|swift)$
         language: system
         entry: python3 config/sync-files.py --latest
         pass_filenames: false
@@ -44,7 +44,7 @@ repos:
 
       - id: swift-codegen
         name: Run Swift checked in code generation
-        files: ^swift/(schema.py$|codegen/|.*/generated/|ql/lib/(swift\.dbscheme$|codeql/swift/elements)|ql/\.generated.list)
+        files: ^swift/(codegen/|.*/generated/|ql/lib/(swift\.dbscheme$|codeql/swift/elements))
         language: system
         entry: bazel run //swift/codegen -- --quiet
         pass_filenames: false
@@ -53,5 +53,5 @@ repos:
         name: Run Swift code generation unit tests
         files: ^swift/codegen/.*\.py$
         language: system
-        entry: bazel test //misc/codegen/test
+        entry: bazel test //swift/codegen/test
         pass_filenames: false

.vscode/settings.json

@@ -1,5 +1,3 @@
 {
-  "omnisharp.autoStart": false,
-  "cmake.sourceDirectory": "${workspaceFolder}/swift",
-  "cmake.buildDirectory": "${workspaceFolder}/bazel-cmake-build"
+    "omnisharp.autoStart": false
 }

CODEOWNERS

@@ -2,21 +2,27 @@
 /csharp/ @github/codeql-csharp
 /go/ @github/codeql-go
 /java/ @github/codeql-java
-/javascript/ @github/codeql-dynamic
-/python/ @github/codeql-dynamic
-/ruby/ @github/codeql-dynamic
-/swift/ @github/codeql-swift
-/misc/codegen/ @github/codeql-swift
+/javascript/ @github/codeql-javascript
+/python/ @github/codeql-python
+/ruby/ @github/codeql-ruby
+/swift/ @github/codeql-c
 /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
 
+# Notify members of codeql-go about PRs to the shared data-flow library files
+/java/ql/src/semmle/code/java/dataflow/internal/DataFlowImpl.qll @github/codeql-java @github/codeql-go
+/java/ql/src/semmle/code/java/dataflow/internal/DataFlowImpl2.qll @github/codeql-java @github/codeql-go
+/java/ql/src/semmle/code/java/dataflow/internal/DataFlowImplCommon.qll @github/codeql-java @github/codeql-go
+/java/ql/src/semmle/code/java/dataflow/internal/tainttracking1/TaintTrackingImpl.qll @github/codeql-java @github/codeql-go
+/java/ql/src/semmle/code/java/dataflow/internal/tainttracking2/TaintTrackingImpl.qll @github/codeql-java @github/codeql-go
+
 # CodeQL tools and associated docs
-/docs/codeql/codeql-cli/ @github/codeql-cli-reviewers
-/docs/codeql/codeql-for-visual-studio-code/ @github/codeql-vscode-reviewers
-/docs/codeql/ql-language-reference/ @github/codeql-frontend-reviewers
+/docs/codeql-cli/ @github/codeql-cli-reviewers
+/docs/codeql-for-visual-studio-code/ @github/codeql-vscode-reviewers
+/docs/ql-language-reference/ @github/codeql-frontend-reviewers
 /docs/query-*-style-guide.md @github/codeql-analysis-reviewers
 
 # QL for QL reviewers
@@ -34,9 +40,8 @@ WORKSPACE.bazel @github/codeql-ci-reviewers
 
 # Workflows
 /.github/workflows/ @github/codeql-ci-reviewers
-/.github/workflows/atm-* @github/codeql-ml-powered-queries-reviewers
 /.github/workflows/go-* @github/codeql-go
 /.github/workflows/js-ml-tests.yml @github/codeql-ml-powered-queries-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
+/.github/workflows/swift-* @github/codeql-c

CONTRIBUTING.md

@@ -25,7 +25,6 @@ If you have an idea for a query that you would like to share with other CodeQL u
 
     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`.
-    - Experimental queries need to include `experimental` in their `@tags`
     - The structure of an `experimental` subdirectory mirrors the structure of its parent directory.
     - Select or create an appropriate directory in `experimental` based on the existing directory structure of `experimental` or its parent directory.
 

README.md

@@ -4,14 +4,13 @@ This open source repository contains the standard CodeQL libraries and queries t
 
 ## How do I learn CodeQL and run queries?
 
-There is [extensive documentation](https://codeql.github.com/docs/) on getting started with writing CodeQL using the [CodeQL extension for Visual Studio Code](https://codeql.github.com/docs/codeql-for-visual-studio-code/) and the [CodeQL CLI](https://codeql.github.com/docs/codeql-cli/).
+There is [extensive documentation](https://codeql.github.com/docs/) on getting started with writing CodeQL.
+You can use the [CodeQL for Visual Studio Code](https://codeql.github.com/docs/codeql-for-visual-studio-code/) extension or the [interactive query console](https://lgtm.com/help/lgtm/using-query-console) on LGTM.com (Semmle Legacy product) to try out your queries on any open source project that's currently being analyzed.
 
 ## Contributing
 
 We welcome contributions to our standard library and standard checks. Do you have an idea for a new check, or how to improve an existing query? Then please go ahead and open a pull request! Before you do, though, please take the time to read our [contributing guidelines](CONTRIBUTING.md). You can also consult our [style guides](https://github.com/github/codeql/tree/main/docs) to learn how to format your code for consistency and clarity, how to write query metadata, and how to write query help documentation for your query.
 
-For information on contributing to CodeQL documentation, see the "[contributing guide](docs/codeql/CONTRIBUTING.md)" for docs.
-
 ## License
 
 The code in this repository is licensed under the [MIT License](LICENSE) by [GitHub](https://github.com).

change-notes/1.20/analysis-javascript.md

@@ -52,7 +52,7 @@
 | Unneeded defensive code | More true positive and fewer false positive results | This query now recognizes additional defensive code patterns. |
 | Unsafe dynamic method access              | Fewer false positive results | This query no longer flags concatenated strings as unsafe method names. |
 | Unused parameter                           | Fewer false positive results | This query no longer flags parameters with leading underscore. |
-| Unused variable, import, function or class | Fewer false positive results | This query now flags fewer variables that are implicitly used by JSX elements. It no longer flags variables with a leading underscore and variables in dead code. |
+| Unused variable, import, function or class | Fewer false positive results | This query now flags fewer variables that are implictly used by JSX elements. It no longer flags variables with a leading underscore and variables in dead code. |
 | Unvalidated dynamic method call           | More true positive results | This query now flags concatenated strings as unvalidated method names in more cases. |
 | Useless assignment to property. | Fewer false positive results | This query now treats assignments with complex right-hand sides correctly. |
 | Useless conditional | Fewer results | Additional defensive coding patterns are now ignored. |

change-notes/1.23/analysis-cpp.md

@@ -19,7 +19,7 @@ The following changes in version 1.23 affect C/C++ analysis in all applications.
 | Hard-coded Japanese era start date in call (`cpp/japanese-era/constructor-or-method-with-exact-era-date`) | Deprecated | This query has been deprecated.  Use the new combined query Hard-coded Japanese era start date (`cpp/japanese-era/exact-era-date`) instead. |
 | Hard-coded Japanese era start date in struct (`cpp/japanese-era/struct-with-exact-era-date`) | Deprecated | This query has been deprecated.  Use the new combined query Hard-coded Japanese era start date (`cpp/japanese-era/exact-era-date`) instead. |
 | Hard-coded Japanese era start date (`cpp/japanese-era/exact-era-date`) | More correct results | This query now checks for the beginning date of the Reiwa era (1st May 2019). |
-| Non-constant format string (`cpp/non-constant-format`) | Fewer false positive results | Fixed false positive results triggered by mismatching declarations of a formatting function. |
+| Non-constant format string (`cpp/non-constant-format`) | Fewer false positive results | Fixed false positive results triggrered by mismatching declarations of a formatting function. |
 | Sign check of bitwise operation (`cpp/bitwise-sign-check`) | Fewer false positive results | Results involving `>=` or `<=` are no longer reported. |
 | Too few arguments to formatting function (`cpp/wrong-number-format-arguments`) | Fewer false positive results | Fixed false positive results triggered by mismatching declarations of a formatting function. |
 | Too many arguments to formatting function (`cpp/too-many-format-arguments`) | Fewer false positive results | Fixed false positive results triggered by mismatching declarations of a formatting function. |

change-notes/1.24/analysis-javascript.md

@@ -91,7 +91,7 @@
 
 ## Changes to libraries
 
-* The predicates `RegExpTerm.getSuccessor` and `RegExpTerm.getPredecessor` have been changed to reflect textual, not operational, matching order. This only makes a difference in lookbehind assertions, which are operationally matched backwards. Previously, `getSuccessor` would mimic this, so in an assertion `(?<=ab)` the term `b` would be considered the predecessor, not the successor, of `a`. Textually, however, `a` is still matched before `b`, and this is the order we now follow.
+* The predicates `RegExpTerm.getSuccessor` and `RegExpTerm.getPredecessor` have been changed to reflect textual, not operational, matching order. This only makes a difference in lookbehind assertions, which are operationally matched backwards. Previously, `getSuccessor` would mimick this, so in an assertion `(?<=ab)` the term `b` would be considered the predecessor, not the successor, of `a`. Textually, however, `a` is still matched before `b`, and this is the order we now follow.
 * An extensible model of the `EventEmitter` pattern has been implemented.
 * Taint-tracking configurations now interact differently with the `data` flow label, which may affect queries
   that combine taint-tracking and flow labels.

codeql-workspace.yml

@@ -17,7 +17,6 @@ provide:
   # - "javascript/ql/experimental/adaptivethreatmodeling/model/qlpack.yml"
   - "javascript/ql/experimental/adaptivethreatmodeling/modelbuilding/qlpack.yml"
   - "javascript/ql/experimental/adaptivethreatmodeling/src/qlpack.yml"
-  - "javascript/ql/experimental/adaptivethreatmodeling/test/qlpack.yml"
   - "csharp/ql/campaigns/Solorigate/lib/qlpack.yml"
   - "csharp/ql/campaigns/Solorigate/src/qlpack.yml"
   - "csharp/ql/campaigns/Solorigate/test/qlpack.yml"
@@ -25,8 +24,7 @@ provide:
   - "misc/suite-helpers/qlpack.yml"
   - "ruby/extractor-pack/codeql-extractor.yml"
   - "swift/extractor-pack/codeql-extractor.yml"
-  - "swift/integration-tests/qlpack.yml"
-  - "ql/extractor-pack/codeql-extractor.yml"
+  - "ql/extractor-pack/codeql-extractor.ym"
 
 versionPolicies:
   default:

config/atm/ml-powered-queries-repo/add-note.js

@@ -1,21 +0,0 @@
-const mongoose = require('mongoose');
-
-Logger = require('./logger').Logger;
-Note = require('./models/note').Note;
-
-(async () => {
-  if (process.argv.length != 5) {
-    Logger.log("Creates a private note.  Usage: node add-note.js <token> <title> <body>")
-    return;
-  }
-
-  // Open the default mongoose connection
-  await mongoose.connect('mongodb://localhost:27017/notes', { useFindAndModify: false });
-
-  const [userToken, title, body] = process.argv.slice(2);
-  await Note.create({ title, body, userToken });
-
-  Logger.log(`Created private note with title ${title} and body ${body} belonging to user with token ${userToken}.`);
-
-  await mongoose.connection.close();
-})();

config/atm/ml-powered-queries-repo/app.js

@@ -1,68 +0,0 @@
-const bodyParser = require('body-parser');
-const express = require('express');
-const mongoose = require('mongoose');
-
-const notesApi = require('./notes-api');
-const usersApi = require('./users-api');
-
-const addSampleData = module.exports.addSampleData = async () => {
-  const [userA, userB] = await User.create([
-    {
-      name: "A",
-      token: "tokenA"
-    },
-    {
-      name: "B",
-      token: "tokenB"
-    }
-  ]);
-
-  await Note.create([
-    {
-      title: "Public note belonging to A",
-      body: "This is a public note belonging to A",
-      isPublic: true,
-      ownerToken: userA.token
-    },
-    {
-      title: "Public note belonging to B",
-      body: "This is a public note belonging to B",
-      isPublic: true,
-      ownerToken: userB.token
-    },
-    {
-      title: "Private note belonging to A",
-      body: "This is a private note belonging to A",
-      ownerToken: userA.token
-    },
-    {
-      title: "Private note belonging to B",
-      body: "This is a private note belonging to B",
-      ownerToken: userB.token
-    }
-  ]);
-}
-
-module.exports.startApp = async () => {
-  // Open the default mongoose connection
-  await mongoose.connect('mongodb://mongo:27017/notes', { useFindAndModify: false });
-  // Drop contents of DB
-  mongoose.connection.dropDatabase();
-  // Add some sample data
-  await addSampleData();
-
-  const app = express();
-
-  app.use(bodyParser.json());
-  app.use(bodyParser.urlencoded());
-
-  app.get('/', async (_req, res) => {
-    res.send('Hello World');
-  });
-
-  app.use('/api/notes', notesApi.router);
-  app.use('/api/users', usersApi.router);
-
-  app.listen(3000);
-  Logger.log('Express started on port 3000');
-};

config/atm/ml-powered-queries-repo/index.js

@@ -1,7 +0,0 @@
-const startApp = require('./app').startApp;
-
-Logger = require('./logger').Logger;
-Note = require('./models/note').Note;
-User = require('./models/user').User;
-
-startApp();

config/atm/ml-powered-queries-repo/logger.js

@@ -1,5 +0,0 @@
-module.exports.Logger = class {
-  log(message, ...objs) {
-    console.log(message, objs);
-  }
-};

config/atm/ml-powered-queries-repo/models/note.js

@@ -1,8 +0,0 @@
-const mongoose = require('mongoose');
-
-module.exports.Note = mongoose.model('Note', new mongoose.Schema({
-  title: String,
-  body: String,
-  ownerToken: String,
-  isPublic: Boolean
-}));

config/atm/ml-powered-queries-repo/models/user.js

@@ -1,6 +0,0 @@
-const mongoose = require('mongoose');
-
-module.exports.User = mongoose.model('User', new mongoose.Schema({
-  name: String,
-  token: String
-}));

config/atm/ml-powered-queries-repo/notes-api.js

@@ -1,44 +0,0 @@
-const express = require('express')
-
-const router = module.exports.router = express.Router();
-
-function serializeNote(note) {
-  return {
-    title: note.title,
-    body: note.body
-  };
-}
-
-router.post('/find', async (req, res) => {
-  const notes = await Note.find({
-    ownerToken: req.body.token
-  }).exec();
-  res.json({
-    notes: notes.map(serializeNote)
-  });
-});
-
-router.get('/findPublic', async (_req, res) => {
-  const notes = await Note.find({
-    isPublic: true
-  }).exec();
-  res.json({
-    notes: notes.map(serializeNote)
-  });
-});
-
-router.post('/findVisible', async (req, res) => {
-  const notes = await Note.find({
-    $or: [
-      {
-        isPublic: true
-      },
-      {
-        ownerToken: req.body.token
-      }
-    ]
-  }).exec();
-  res.json({
-    notes: notes.map(serializeNote)
-  });
-});

config/atm/ml-powered-queries-repo/read-notes.js

@@ -1,37 +0,0 @@
-const mongoose = require('mongoose');
-
-Logger = require('./logger').Logger;
-Note = require('./models/note').Note;
-User = require('./models/user').User;
-
-(async () => {
-  if (process.argv.length != 3) {
-    Logger.log("Outputs all notes visible to a user.  Usage: node read-notes.js <token>")
-    return;
-  }
-
-  // Open the default mongoose connection
-  await mongoose.connect('mongodb://localhost:27017/notes', { useFindAndModify: false });
-
-  const ownerToken = process.argv[2];
-
-  const user = await User.findOne({
-    token: ownerToken
-  }).exec();
-
-  const notes = await Note.find({
-    $or: [
-      { isPublic: true },
-      { ownerToken }
-    ]
-  }).exec();
-
-  notes.map(note => {
-    Logger.log("Title:" + note.title);
-    Logger.log("By:" + user.name);
-    Logger.log("Body:" + note.body);
-    Logger.log();
-  });
-
-  await mongoose.connection.close();
-})();

config/atm/ml-powered-queries-repo/users-api.js

@@ -1,25 +0,0 @@
-const express = require('express')
-
-Logger = require('./logger').Logger;
-const router = module.exports.router = express.Router();
-
-router.post('/updateName', async (req, res) => {
-  Logger.log("/updateName called with new name", req.body.name);
-  await User.findOneAndUpdate({
-    token: req.body.token
-  }, {
-    name: req.body.name
-  }).exec();
-  res.json({
-    name: req.body.name
-  });
-});
-
-router.post('/getName', async (req, res) => {
-  const user = await User.findOne({
-    token: req.body.token
-  }).exec();
-  res.json({
-    name: user.name
-  });
-});

config/identical-files.json

@@ -1,5 +1,5 @@
 {
-  "DataFlow Java/C++/C#/Go/Python/Ruby/Swift": [
+  "DataFlow Java/C++/C#/Python": [
     "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImpl.qll",
     "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImpl2.qll",
     "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImpl3.qll",
@@ -27,32 +27,27 @@
     "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/DataFlowImpl.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/DataFlowImpl.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/DataFlowImpl.qll",
     "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImpl2.qll",
+    "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImplForLibraries.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/DataFlowImpl.qll"
   ],
-  "DataFlow Java/C++/C#/Go/Python/Ruby/Swift Common": [
+  "DataFlow Java/C++/C#/Python 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",
     "cpp/ql/lib/experimental/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::Configuration Java/C++/C#/Go/Python/Ruby/Swift": [
+  "TaintTracking::Configuration Java/C++/C#/Python": [
     "cpp/ql/lib/semmle/code/cpp/dataflow/internal/tainttracking1/TaintTrackingImpl.qll",
     "cpp/ql/lib/semmle/code/cpp/dataflow/internal/tainttracking2/TaintTrackingImpl.qll",
     "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/tainttracking1/TaintTrackingImpl.qll",
@@ -66,8 +61,6 @@
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/tainttracking3/TaintTrackingImpl.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/tainttracking4/TaintTrackingImpl.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/tainttracking5/TaintTrackingImpl.qll",
-    "go/ql/lib/semmle/go/dataflow/internal/tainttracking1/TaintTrackingImpl.qll",
-    "go/ql/lib/semmle/go/dataflow/internal/tainttracking2/TaintTrackingImpl.qll",
     "java/ql/lib/semmle/code/java/dataflow/internal/tainttracking1/TaintTrackingImpl.qll",
     "java/ql/lib/semmle/code/java/dataflow/internal/tainttracking2/TaintTrackingImpl.qll",
     "java/ql/lib/semmle/code/java/dataflow/internal/tainttracking3/TaintTrackingImpl.qll",
@@ -76,9 +69,10 @@
     "python/ql/lib/semmle/python/dataflow/new/internal/tainttracking3/TaintTrackingImpl.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/tainttracking4/TaintTrackingImpl.qll",
     "ruby/ql/lib/codeql/ruby/dataflow/internal/tainttracking1/TaintTrackingImpl.qll",
+    "ruby/ql/lib/codeql/ruby/dataflow/internal/tainttrackingforlibraries/TaintTrackingImpl.qll",
     "swift/ql/lib/codeql/swift/dataflow/internal/tainttracking1/TaintTrackingImpl.qll"
   ],
-  "DataFlow Java/C++/C#/Python/Ruby/Swift Consistency checks": [
+  "DataFlow Java/C++/C#/Python 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",
@@ -88,10 +82,9 @@
     "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": [
+  "DataFlow Java/C#/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",
-    "go/ql/lib/semmle/go/dataflow/internal/FlowSummaryImpl.qll",
     "ruby/ql/lib/codeql/ruby/dataflow/internal/FlowSummaryImpl.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/FlowSummaryImpl.qll",
     "swift/ql/lib/codeql/swift/dataflow/internal/FlowSummaryImpl.qll"
@@ -101,8 +94,8 @@
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/rangeanalysis/SsaReadPositionCommon.qll"
   ],
   "Model as Data Generation Java/C# - CaptureModels": [
-    "java/ql/src/utils/modelgenerator/internal/CaptureModels.qll",
-    "csharp/ql/src/utils/modelgenerator/internal/CaptureModels.qll"
+    "java/ql/src/utils/model-generator/internal/CaptureModels.qll",
+    "csharp/ql/src/utils/model-generator/internal/CaptureModels.qll"
   ],
   "Sign Java/C#": [
     "java/ql/lib/semmle/code/java/dataflow/internal/rangeanalysis/Sign.qll",
@@ -403,6 +396,16 @@
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/ControlFlowReachability.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/rangeanalysis/ControlFlowReachability.qll"
   ],
+  "Inline Test Expectations": [
+    "cpp/ql/test/TestUtilities/InlineExpectationsTest.qll",
+    "csharp/ql/test/TestUtilities/InlineExpectationsTest.qll",
+    "java/ql/test/TestUtilities/InlineExpectationsTest.qll",
+    "python/ql/test/TestUtilities/InlineExpectationsTest.qll",
+    "ruby/ql/test/TestUtilities/InlineExpectationsTest.qll",
+    "ql/ql/test/TestUtilities/InlineExpectationsTest.qll",
+    "go/ql/test/TestUtilities/InlineExpectationsTest.qll",
+    "swift/ql/test/TestUtilities/InlineExpectationsTest.qll"
+  ],
   "C++ ExternalAPIs": [
     "cpp/ql/src/Security/CWE/CWE-020/ExternalAPIs.qll",
     "cpp/ql/src/Security/CWE/CWE-020/ir/ExternalAPIs.qll"
@@ -461,10 +464,6 @@
     "javascript/ql/src/Comments/CommentedOutCodeReferences.inc.qhelp",
     "python/ql/src/Lexical/CommentedOutCodeReferences.inc.qhelp"
   ],
-  "ThreadResourceAbuse qhelp": [
-    "java/ql/src/experimental/Security/CWE/CWE-400/LocalThreadResourceAbuse.qhelp",
-    "java/ql/src/experimental/Security/CWE/CWE-400/ThreadResourceAbuse.qhelp"
-  ],
   "IDE Contextual Queries": [
     "cpp/ql/lib/IDEContextual.qll",
     "csharp/ql/lib/IDEContextual.qll",
@@ -487,6 +486,40 @@
     "python/ql/lib/semmle/python/security/internal/SensitiveDataHeuristics.qll",
     "ruby/ql/lib/codeql/ruby/security/internal/SensitiveDataHeuristics.qll"
   ],
+  "ReDoS Util Python/JS/Ruby/Java": [
+    "javascript/ql/lib/semmle/javascript/security/regexp/NfaUtils.qll",
+    "python/ql/lib/semmle/python/security/regexp/NfaUtils.qll",
+    "ruby/ql/lib/codeql/ruby/security/regexp/NfaUtils.qll",
+    "java/ql/lib/semmle/code/java/security/regexp/NfaUtils.qll"
+  ],
+  "ReDoS Exponential Python/JS/Ruby/Java": [
+    "javascript/ql/lib/semmle/javascript/security/regexp/ExponentialBackTracking.qll",
+    "python/ql/lib/semmle/python/security/regexp/ExponentialBackTracking.qll",
+    "ruby/ql/lib/codeql/ruby/security/regexp/ExponentialBackTracking.qll",
+    "java/ql/lib/semmle/code/java/security/regexp/ExponentialBackTracking.qll"
+  ],
+  "ReDoS Polynomial Python/JS/Ruby/Java": [
+    "javascript/ql/lib/semmle/javascript/security/regexp/SuperlinearBackTracking.qll",
+    "python/ql/lib/semmle/python/security/regexp/SuperlinearBackTracking.qll",
+    "ruby/ql/lib/codeql/ruby/security/regexp/SuperlinearBackTracking.qll",
+    "java/ql/lib/semmle/code/java/security/regexp/SuperlinearBackTracking.qll"
+  ],
+  "RegexpMatching Python/JS/Ruby": [
+    "javascript/ql/lib/semmle/javascript/security/regexp/RegexpMatching.qll",
+    "python/ql/lib/semmle/python/security/regexp/RegexpMatching.qll",
+    "ruby/ql/lib/codeql/ruby/security/regexp/RegexpMatching.qll"
+  ],
+  "BadTagFilterQuery Python/JS/Ruby": [
+    "javascript/ql/lib/semmle/javascript/security/BadTagFilterQuery.qll",
+    "python/ql/lib/semmle/python/security/BadTagFilterQuery.qll",
+    "ruby/ql/lib/codeql/ruby/security/BadTagFilterQuery.qll"
+  ],
+  "OverlyLargeRange Python/JS/Ruby/Java": [
+    "javascript/ql/lib/semmle/javascript/security/OverlyLargeRangeQuery.qll",
+    "python/ql/lib/semmle/python/security/OverlyLargeRangeQuery.qll",
+    "ruby/ql/lib/codeql/ruby/security/OverlyLargeRangeQuery.qll",
+    "java/ql/lib/semmle/code/java/security/OverlyLargeRangeQuery.qll"
+  ],
   "CFG": [
     "csharp/ql/lib/semmle/code/csharp/controlflow/internal/ControlFlowGraphImplShared.qll",
     "ruby/ql/lib/codeql/ruby/controlflow/internal/ControlFlowGraphImplShared.qll",
@@ -496,9 +529,16 @@
     "python/ql/lib/semmle/python/dataflow/new/internal/TypeTracker.qll",
     "ruby/ql/lib/codeql/ruby/typetracking/TypeTracker.qll"
   ],
+  "CodeQL Tutorial": [
+    "cpp/ql/lib/tutorial.qll",
+    "csharp/ql/lib/tutorial.qll",
+    "java/ql/lib/tutorial.qll",
+    "javascript/ql/lib/tutorial.qll",
+    "python/ql/lib/tutorial.qll",
+    "ruby/ql/lib/tutorial.qll"
+  ],
   "AccessPathSyntax": [
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/AccessPathSyntax.qll",
-    "go/ql/lib/semmle/go/dataflow/internal/AccessPathSyntax.qll",
     "java/ql/lib/semmle/code/java/dataflow/internal/AccessPathSyntax.qll",
     "javascript/ql/lib/semmle/javascript/frameworks/data/internal/AccessPathSyntax.qll",
     "ruby/ql/lib/codeql/ruby/dataflow/internal/AccessPathSyntax.qll",
@@ -514,16 +554,16 @@
     "ruby/ql/lib/codeql/ruby/internal/ConceptsShared.qll",
     "javascript/ql/lib/semmle/javascript/internal/ConceptsShared.qll"
   ],
+  "Hostname Regexp queries": [
+    "javascript/ql/src/Security/CWE-020/HostnameRegexpShared.qll",
+    "python/ql/src/Security/CWE-020/HostnameRegexpShared.qll",
+    "ruby/ql/src/queries/security/cwe-020/HostnameRegexpShared.qll"
+  ],
   "ApiGraphModels": [
     "javascript/ql/lib/semmle/javascript/frameworks/data/internal/ApiGraphModels.qll",
     "ruby/ql/lib/codeql/ruby/frameworks/data/internal/ApiGraphModels.qll",
     "python/ql/lib/semmle/python/frameworks/data/internal/ApiGraphModels.qll"
   ],
-  "ApiGraphModelsExtensions": [
-    "javascript/ql/lib/semmle/javascript/frameworks/data/internal/ApiGraphModelsExtensions.qll",
-    "ruby/ql/lib/codeql/ruby/frameworks/data/internal/ApiGraphModelsExtensions.qll",
-    "python/ql/lib/semmle/python/frameworks/data/internal/ApiGraphModelsExtensions.qll"
-  ],
   "TaintedFormatStringQuery Ruby/JS": [
     "javascript/ql/lib/semmle/javascript/security/dataflow/TaintedFormatStringQuery.qll",
     "ruby/ql/lib/codeql/ruby/security/TaintedFormatStringQuery.qll"
@@ -560,16 +600,8 @@
     "swift/ql/test/extractor-tests/patterns/patterns.swift",
     "swift/ql/test/library-tests/ast/patterns.swift"
   ],
-  "Swift control flow test file": [
-    "swift/ql/test/library-tests/controlflow/graph/cfg.swift",
-    "swift/ql/test/library-tests/ast/cfg.swift"
-  ],
   "IncompleteMultiCharacterSanitization JS/Ruby": [
     "javascript/ql/lib/semmle/javascript/security/IncompleteMultiCharacterSanitizationQuery.qll",
     "ruby/ql/lib/codeql/ruby/security/IncompleteMultiCharacterSanitizationQuery.qll"
-  ],
-  "EncryptionKeySizes Python/Java": [
-    "python/ql/lib/semmle/python/security/internal/EncryptionKeySizes.qll",
-    "java/ql/lib/semmle/code/java/security/internal/EncryptionKeySizes.qll"
   ]
-}
+}

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

@@ -131,14 +131,6 @@ namespace Semmle.Autobuild.Cpp.Tests
 
         bool IBuildActions.IsWindows() => IsWindows;
 
-        public bool IsMacOs { get; set; }
-
-        bool IBuildActions.IsMacOs() => IsMacOs;
-
-        public bool IsArm { get; set; }
-
-        bool IBuildActions.IsArm() => IsArm;
-
         string IBuildActions.PathCombine(params string[] parts)
         {
             return string.Join(IsWindows ? '\\' : '/', parts.Where(p => !string.IsNullOrWhiteSpace(p)));
@@ -265,11 +257,11 @@ namespace Semmle.Autobuild.Cpp.Tests
             Actions.GetCurrentDirectory = cwd;
             Actions.IsWindows = isWindows;
 
-            var options = new CppAutobuildOptions(Actions);
+            var options = new AutobuildOptions(Actions, Language.Cpp);
             return new CppAutobuilder(Actions, options);
         }
 
-        void TestAutobuilderScript(CppAutobuilder autobuilder, int expectedOutput, int commandsRun)
+        void TestAutobuilderScript(Autobuilder autobuilder, int expectedOutput, int commandsRun)
         {
             Assert.Equal(expectedOutput, autobuilder.GetBuildScript().Run(Actions, StartCallback, EndCallback));
 
@@ -307,7 +299,7 @@ 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 && C:\odasa\tools\odasa index --auto msbuild C:\Project\test.sln /t:rebuild /p:Platform=""x86"" /p:Configuration=""Release"" /p:MvcBuildViews=true"] = 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/autobuilder/Semmle.Autobuild.Cpp.Tests/Semmle.Autobuild.Cpp.Tests.csproj

@@ -2,7 +2,7 @@
 
   <PropertyGroup>
     <OutputType>Exe</OutputType>
-    <TargetFramework>net7.0</TargetFramework>
+    <TargetFramework>net6.0</TargetFramework>
     <GenerateAssemblyInfo>false</GenerateAssemblyInfo>
     <RuntimeIdentifiers>win-x64;linux-x64;osx-x64</RuntimeIdentifiers>
     <Nullable>enable</Nullable>
@@ -11,12 +11,11 @@
   <ItemGroup>
     <PackageReference Include="System.IO.FileSystem" Version="4.3.0" />
     <PackageReference Include="System.IO.FileSystem.Primitives" Version="4.3.0" />
-    <PackageReference Include="xunit" Version="2.4.2" />
-    <PackageReference Include="xunit.runner.visualstudio" Version="2.4.5">
+    <PackageReference Include="xunit" Version="2.4.1" />
+    <PackageReference Include="xunit.runner.visualstudio" Version="2.4.1">
       <PrivateAssets>all</PrivateAssets>
       <IncludeAssets>runtime; build; native; contentfiles; analyzers</IncludeAssets>
     </PackageReference>
-    <PackageReference Include="Microsoft.NET.Test.Sdk" Version="17.4.0" />
   </ItemGroup>
 
   <ItemGroup>

cpp/autobuilder/Semmle.Autobuild.Cpp/CppAutobuilder.cs

@@ -2,26 +2,9 @@
 
 namespace Semmle.Autobuild.Cpp
 {
-    /// <summary>
-    /// Encapsulates C++ build options.
-    /// </summary>
-    public class CppAutobuildOptions : AutobuildOptionsShared
+    public class CppAutobuilder : Autobuilder
     {
-        public override Language Language => Language.Cpp;
-
-
-        /// <summary>
-        /// Reads options from environment variables.
-        /// Throws ArgumentOutOfRangeException for invalid arguments.
-        /// </summary>
-        public CppAutobuildOptions(IBuildActions actions) : base(actions)
-        {
-        }
-    }
-
-    public class CppAutobuilder : Autobuilder<CppAutobuildOptions>
-    {
-        public CppAutobuilder(IBuildActions actions, CppAutobuildOptions options) : base(actions, options) { }
+        public CppAutobuilder(IBuildActions actions, AutobuildOptions options) : base(actions, options) { }
 
         public override BuildScript GetBuildScript()
         {

cpp/autobuilder/Semmle.Autobuild.Cpp/Program.cs

@@ -11,14 +11,14 @@ namespace Semmle.Autobuild.Cpp
             try
             {
                 var actions = SystemBuildActions.Instance;
-                var options = new CppAutobuildOptions(actions);
+                var options = new AutobuildOptions(actions, Language.Cpp);
                 try
                 {
                     Console.WriteLine("CodeQL C++ autobuilder");
                     var builder = new CppAutobuilder(actions, options);
                     return builder.AttemptBuild();
                 }
-                catch (InvalidEnvironmentException ex)
+                catch(InvalidEnvironmentException ex)
                 {
                     Console.WriteLine("The environment is invalid: {0}", ex.Message);
                 }

cpp/autobuilder/Semmle.Autobuild.Cpp/Semmle.Autobuild.Cpp.csproj

@@ -1,7 +1,7 @@
 <Project Sdk="Microsoft.NET.Sdk">
 
   <PropertyGroup>
-    <TargetFramework>net7.0</TargetFramework>
+    <TargetFramework>net6.0</TargetFramework>
     <AssemblyName>Semmle.Autobuild.Cpp</AssemblyName>
     <RootNamespace>Semmle.Autobuild.Cpp</RootNamespace>
     <ApplicationIcon />
@@ -17,7 +17,7 @@
   </ItemGroup>
 
   <ItemGroup>
-    <PackageReference Include="Microsoft.Build" Version="17.3.2" />
+    <PackageReference Include="Microsoft.Build" Version="16.11.0" />
   </ItemGroup>
 
   <ItemGroup>

cpp/downgrades/23f7cbb88a4eb29f30c3490363dc201bc054c5ff/exprs.ql

@@ -13,5 +13,5 @@ predicate isExprWithNewBuiltin(Expr expr) {
 from Expr expr, int kind, int kind_new, Location location
 where
   exprs(expr, kind, location) and
-  if isExprWithNewBuiltin(expr) then kind_new = 1 else kind_new = kind
+  if isExprWithNewBuiltin(expr) then kind_new = 0 else kind_new = kind
 select expr, kind_new, location

cpp/downgrades/73af5058c6899dcdb05754c27ca966aeb3a68c94/exprs.ql

@@ -9,5 +9,5 @@ class Location extends @location_expr {
 from Expr expr, int kind, int kind_new, Location location
 where
   exprs(expr, kind, location) and
-  if expr instanceof @blockassignexpr then kind_new = 1 else kind_new = kind
+  if expr instanceof @blockassignexpr then kind_new = 0 else kind_new = kind
 select expr, kind_new, location

cpp/downgrades/a5bb28ed29f73855d64cc5f939cef977fa8fd19a/builtintypes.ql

@@ -1,11 +0,0 @@
-class BuiltinType extends @builtintype {
-  string toString() { none() }
-}
-
-from BuiltinType type, string name, int kind, int kind_new, int size, int sign, int alignment
-where
-  builtintypes(type, name, kind, size, sign, alignment) and
-  if type instanceof @float16 or type instanceof @complex_float16
-  then kind_new = 2
-  else kind_new = kind
-select type, name, kind_new, size, sign, alignment

cpp/downgrades/a5bb28ed29f73855d64cc5f939cef977fa8fd19a/upgrade.properties

@@ -1,3 +0,0 @@
-description: Introduce (_Complex) _Float16 type
-compatibility: backwards
-builtintypes.rel: run builtintypes.qlo

cpp/downgrades/ba86bebea4c7a8235c2fa0e220391fbd4446a087/upgrade.properties

@@ -1,2 +0,0 @@
-description: Uncomment case splits in dbscheme
-compatibility: full

cpp/ql/examples/qlpack.yml

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

cpp/ql/lib/CHANGELOG.md

@@ -1,81 +1,3 @@
-## 0.5.4
-
-No user-facing changes.
-
-## 0.5.3
-
-No user-facing changes.
-
-## 0.5.2
-
-No user-facing changes.
-
-## 0.5.1
-
-No user-facing changes.
-
-## 0.5.0
-
-### Breaking Changes
-
-The predicates in the `MustFlow::Configuration` class used by the `MustFlow` library (`semmle.code.cpp.ir.dataflow.MustFlow`) have changed to be defined directly in terms of the C++ IR instead of IR dataflow nodes.
-
-### Deprecated APIs
-
-* Deprecated `semmle.code.cpp.ir.dataflow.DefaultTaintTracking`. Use `semmle.code.cpp.ir.dataflow.TaintTracking`.
-* Deprecated `semmle.code.cpp.security.TaintTrackingImpl`. Use `semmle.code.cpp.ir.dataflow.TaintTracking`.
-* Deprecated `semmle.code.cpp.valuenumbering.GlobalValueNumberingImpl`. Use `semmle.code.cpp.valuenumbering.GlobalValueNumbering`, which exposes the same API.
-
-### Minor Analysis Improvements
-
-* The `ArgvSource` flow source now uses the second parameter of `main` as its source instead of the uses of this parameter.
-* The `ArgvSource` flow source has been generalized to handle cases where the argument vector of `main` is not named `argv`.
-* The `getaddrinfo` function is now recognized as a flow source.
-* The `secure_getenv` and `_wgetenv` functions are now recognized as local flow sources.
-* The `scanf` and `fscanf` functions and their variants are now recognized as flow sources.
-* Deleted the deprecated `getName` and `getShortName` predicates from the `Folder` class.
-
-## 0.4.6
-
-No user-facing changes.
-
-## 0.4.5
-
-No user-facing changes.
-
-## 0.4.4
-
-No user-facing changes.
-
-## 0.4.3
-
-### Minor Analysis Improvements
-
-* Fixed bugs in the `FormatLiteral` class that were causing `getMaxConvertedLength` and related predicates to return no results when the format literal was `%e`, `%f` or `%g` and an explicit precision was specified.
-
-## 0.4.2
-
-No user-facing changes.
-
-## 0.4.1
-
-No user-facing changes.
-
-## 0.4.0
-
-### Deprecated APIs
-
-* Some classes/modules with upper-case acronyms in their name have been renamed to follow our style-guide. 
-  The old name still exists as a deprecated alias.
-
-### New Features
-
-* Added subclasses of `BuiltInOperations` for `__is_same`, `__is_function`, `__is_layout_compatible`, `__is_pointer_interconvertible_base_of`, `__is_array`, `__array_rank`, `__array_extent`, `__is_arithmetic`, `__is_complete_type`, `__is_compound`, `__is_const`, `__is_floating_point`, `__is_fundamental`, `__is_integral`, `__is_lvalue_reference`, `__is_member_function_pointer`, `__is_member_object_pointer`, `__is_member_pointer`, `__is_object`, `__is_pointer`, `__is_reference`, `__is_rvalue_reference`, `__is_scalar`, `__is_signed`, `__is_unsigned`, `__is_void`, and `__is_volatile`.
-
-### Bug Fixes
-
-* Fixed an issue in the taint tracking analysis where implicit reads were not allowed by default in sinks or additional taint steps that used flow states.
-
 ## 0.3.5
 
 ## 0.3.4

cpp/ql/lib/change-notes/2022-09-06-additional-builtin-support.md

@@ -0,0 +1,4 @@
+---
+category: feature
+---
+* Added subclasses of `BuiltInOperations` for `__is_same`, `__is_function`, `__is_layout_compatible`, `__is_pointer_interconvertible_base_of`, `__is_array`, `__array_rank`, `__array_extent`, `__is_arithmetic`, `__is_complete_type`, `__is_compound`, `__is_const`, `__is_floating_point`, `__is_fundamental`, `__is_integral`, `__is_lvalue_reference`, `__is_member_function_pointer`, `__is_member_object_pointer`, `__is_member_pointer`, `__is_object`, `__is_pointer`, `__is_reference`, `__is_rvalue_reference`, `__is_scalar`, `__is_signed`, `__is_unsigned`, `__is_void`, and `__is_volatile`.

cpp/ql/lib/change-notes/2022-09-08-implicit-read-flowstates.md

@@ -0,0 +1,4 @@
+---
+category: fix
+---
+* Fixed an issue in the taint tracking analysis where implicit reads were not allowed by default in sinks or additional taint steps that used flow states.

cpp/ql/lib/change-notes/2022-09-12-uppercase.md

@@ -0,0 +1,5 @@
+---
+category: deprecated
+---
+* Some classes/modules with upper-case acronyms in their name have been renamed to follow our style-guide. 
+  The old name still exists as a deprecated alias.

cpp/ql/lib/change-notes/released/0.4.0.md

@@ -1,14 +0,0 @@
-## 0.4.0
-
-### Deprecated APIs
-
-* Some classes/modules with upper-case acronyms in their name have been renamed to follow our style-guide. 
-  The old name still exists as a deprecated alias.
-
-### New Features
-
-* Added subclasses of `BuiltInOperations` for `__is_same`, `__is_function`, `__is_layout_compatible`, `__is_pointer_interconvertible_base_of`, `__is_array`, `__array_rank`, `__array_extent`, `__is_arithmetic`, `__is_complete_type`, `__is_compound`, `__is_const`, `__is_floating_point`, `__is_fundamental`, `__is_integral`, `__is_lvalue_reference`, `__is_member_function_pointer`, `__is_member_object_pointer`, `__is_member_pointer`, `__is_object`, `__is_pointer`, `__is_reference`, `__is_rvalue_reference`, `__is_scalar`, `__is_signed`, `__is_unsigned`, `__is_void`, and `__is_volatile`.
-
-### Bug Fixes
-
-* Fixed an issue in the taint tracking analysis where implicit reads were not allowed by default in sinks or additional taint steps that used flow states.

cpp/ql/lib/change-notes/released/0.4.1.md

@@ -1,3 +0,0 @@
-## 0.4.1
-
-No user-facing changes.

cpp/ql/lib/change-notes/released/0.4.2.md

@@ -1,3 +0,0 @@
-## 0.4.2
-
-No user-facing changes.

cpp/ql/lib/change-notes/released/0.4.3.md

@@ -1,5 +0,0 @@
-## 0.4.3
-
-### Minor Analysis Improvements
-
-* Fixed bugs in the `FormatLiteral` class that were causing `getMaxConvertedLength` and related predicates to return no results when the format literal was `%e`, `%f` or `%g` and an explicit precision was specified.

cpp/ql/lib/change-notes/released/0.4.4.md

@@ -1,3 +0,0 @@
-## 0.4.4
-
-No user-facing changes.

cpp/ql/lib/change-notes/released/0.4.5.md

@@ -1,3 +0,0 @@
-## 0.4.5
-
-No user-facing changes.

cpp/ql/lib/change-notes/released/0.4.6.md

@@ -1,3 +0,0 @@
-## 0.4.6
-
-No user-facing changes.

cpp/ql/lib/change-notes/released/0.5.0.md

@@ -1,20 +0,0 @@
-## 0.5.0
-
-### Breaking Changes
-
-The predicates in the `MustFlow::Configuration` class used by the `MustFlow` library (`semmle.code.cpp.ir.dataflow.MustFlow`) have changed to be defined directly in terms of the C++ IR instead of IR dataflow nodes.
-
-### Deprecated APIs
-
-* Deprecated `semmle.code.cpp.ir.dataflow.DefaultTaintTracking`. Use `semmle.code.cpp.ir.dataflow.TaintTracking`.
-* Deprecated `semmle.code.cpp.security.TaintTrackingImpl`. Use `semmle.code.cpp.ir.dataflow.TaintTracking`.
-* Deprecated `semmle.code.cpp.valuenumbering.GlobalValueNumberingImpl`. Use `semmle.code.cpp.valuenumbering.GlobalValueNumbering`, which exposes the same API.
-
-### Minor Analysis Improvements
-
-* The `ArgvSource` flow source now uses the second parameter of `main` as its source instead of the uses of this parameter.
-* The `ArgvSource` flow source has been generalized to handle cases where the argument vector of `main` is not named `argv`.
-* The `getaddrinfo` function is now recognized as a flow source.
-* The `secure_getenv` and `_wgetenv` functions are now recognized as local flow sources.
-* The `scanf` and `fscanf` functions and their variants are now recognized as flow sources.
-* Deleted the deprecated `getName` and `getShortName` predicates from the `Folder` class.

cpp/ql/lib/change-notes/released/0.5.1.md

@@ -1,3 +0,0 @@
-## 0.5.1
-
-No user-facing changes.

cpp/ql/lib/change-notes/released/0.5.2.md

@@ -1,3 +0,0 @@
-## 0.5.2
-
-No user-facing changes.

cpp/ql/lib/change-notes/released/0.5.3.md

@@ -1,3 +0,0 @@
-## 0.5.3
-
-No user-facing changes.

cpp/ql/lib/change-notes/released/0.5.4.md

@@ -1,3 +0,0 @@
-## 0.5.4
-
-No user-facing changes.

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

@@ -1,2 +1,2 @@
 ---
-lastReleaseVersion: 0.5.4
+lastReleaseVersion: 0.3.5

cpp/ql/lib/definitions.qll

@@ -12,8 +12,8 @@ import IDEContextual
  *
  * In some cases it is preferable to modify locations (the
  * `hasLocationInfo()` predicate) so that they are short, and
- * non-overlapping with other locations that might be reported as
- * code scanning alerts on GitHub.
+ * non-overlapping with other locations that might be highlighted in
+ * the LGTM interface.
  *
  * We need to give locations that may not be in the database, so
  * we use `hasLocationInfo()` rather than `getLocation()`.
@@ -123,13 +123,6 @@ private predicate constructorCallTypeMention(ConstructorCall cc, TypeMention tm)
   )
 }
 
-/** Holds if `loc` has the container `container` and is on the line starting at `startLine`. */
-pragma[nomagic]
-private predicate hasContainerAndStartLine(Location loc, Container container, int startLine) {
-  loc.getStartLine() = startLine and
-  loc.getContainer() = container
-}
-
 /**
  * Gets an element, of kind `kind`, that element `e` uses, if any.
  * Attention: This predicate yields multiple definitions for a single location.
@@ -166,9 +159,9 @@ Top definitionOf(Top e, string kind) {
     // Multiple type mentions can be generated when a typedef is used, and
     // in such cases we want to exclude all but the originating typedef.
     not exists(Type secondary |
-      exists(File f, int startline, int startcol |
+      exists(TypeMention tm, File f, int startline, int startcol |
         typeMentionStartLoc(e, result, f, startline, startcol) and
-        typeMentionStartLoc(_, secondary, f, startline, startcol) and
+        typeMentionStartLoc(tm, secondary, f, startline, startcol) and
         (
           result = secondary.(TypedefType).getBaseType() or
           result = secondary.(TypedefType).getBaseType().(SpecifiedType).getBaseType()
@@ -191,9 +184,11 @@ Top definitionOf(Top e, string kind) {
     kind = "I" and
     result = e.(Include).getIncludedFile() and
     // exclude `#include` directives containing macros
-    not exists(MacroInvocation mi, Container container, int startLine |
-      hasContainerAndStartLine(e.(Include).getLocation(), container, startLine) and
-      hasContainerAndStartLine(mi.getLocation(), container, startLine)
+    not exists(MacroInvocation mi, Location l1, Location l2 |
+      l1 = e.(Include).getLocation() and
+      l2 = mi.getLocation() and
+      l1.getContainer() = l2.getContainer() and
+      l1.getStartLine() = l2.getStartLine()
       // (an #include directive must be always on it's own line)
     )
   ) and

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

@@ -20,8 +20,7 @@ module ProductFlow {
      * `source1` and `source2` must belong to the same callable.
      */
     predicate isSourcePair(
-      DataFlow::Node source1, DataFlow::FlowState state1, DataFlow::Node source2,
-      DataFlow::FlowState state2
+      DataFlow::Node source1, string state1, DataFlow::Node source2, string state2
     ) {
       state1 = "" and
       state2 = "" and
@@ -50,101 +49,6 @@ module ProductFlow {
       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
@@ -159,78 +63,38 @@ module ProductFlow {
     class Conf1 extends DataFlow::Configuration {
       Conf1() { this = "Conf1" }
 
-      override predicate isSource(DataFlow::Node source, DataFlow::FlowState state) {
+      override predicate isSource(DataFlow::Node source, string state) {
         exists(Configuration conf | conf.isSourcePair(source, state, _, _))
       }
 
-      override predicate isSink(DataFlow::Node sink, DataFlow::FlowState state) {
+      override predicate isSink(DataFlow::Node sink, string 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 isSource(DataFlow::Node source, string state) {
+        exists(Configuration conf, DataFlow::Node source1 |
+          conf.isSourcePair(source1, _, source, state) and
+          any(Conf1 c).hasFlow(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 isSink(DataFlow::Node sink, string state) {
+        exists(Configuration conf, DataFlow::Node sink1 |
+          conf.isSinkPair(sink1, _, sink, state) and any(Conf1 c).hasFlow(_, 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
+    conf.isSourcePair(node1.getNode(), _, node2.getNode(), _) and
     node1 = source1 and
     node2 = source2
     or
@@ -293,7 +157,7 @@ module ProductFlow {
   ) {
     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
+      conf.isSinkPair(sink1.getNode(), _, sink2.getNode(), _) and
       localPathStep1*(mid1, sink1) and
       localPathStep2*(mid2, sink2)
     )

cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/DataFlowImplCommon.qll

@@ -707,8 +707,8 @@ private module Cached {
      * Gets a viable dispatch target of `call` in the context `ctx`. This is
      * restricted to those `call`s for which a context might make a difference.
      */
-    cached
-    DataFlowCallable viableImplInCallContextExt(DataFlowCall call, DataFlowCall ctx) {
+    pragma[nomagic]
+    private DataFlowCallable viableImplInCallContextExt(DataFlowCall call, DataFlowCall ctx) {
       result = viableImplInCallContext(call, ctx) and
       result = viableCallable(call)
       or
@@ -915,57 +915,18 @@ private module Cached {
     TDataFlowCallNone() or
     TDataFlowCallSome(DataFlowCall call)
 
-  cached
-  newtype TParamNodeOption =
-    TParamNodeNone() or
-    TParamNodeSome(ParamNode p)
-
-  cached
-  newtype TReturnCtx =
-    TReturnCtxNone() or
-    TReturnCtxNoFlowThrough() or
-    TReturnCtxMaybeFlowThrough(ReturnPosition pos)
-
-  cached
-  newtype TTypedContentApprox =
-    MkTypedContentApprox(ContentApprox c, DataFlowType t) {
-      exists(Content cont |
-        c = getContentApprox(cont) and
-        store(_, cont, _, _, t)
-      )
-    }
-
   cached
   newtype TTypedContent = MkTypedContent(Content c, DataFlowType t) { store(_, c, _, _, t) }
 
-  cached
-  TypedContent getATypedContent(TypedContentApprox c) {
-    exists(ContentApprox cls, DataFlowType t, Content cont |
-      c = MkTypedContentApprox(cls, pragma[only_bind_into](t)) and
-      result = MkTypedContent(cont, pragma[only_bind_into](t)) and
-      cls = getContentApprox(cont)
-    )
-  }
-
   cached
   newtype TAccessPathFront =
     TFrontNil(DataFlowType t) or
     TFrontHead(TypedContent tc)
 
-  cached
-  newtype TApproxAccessPathFront =
-    TApproxFrontNil(DataFlowType t) or
-    TApproxFrontHead(TypedContentApprox tc)
-
   cached
   newtype TAccessPathFrontOption =
     TAccessPathFrontNone() or
     TAccessPathFrontSome(AccessPathFront apf)
-
-  cached
-  newtype TApproxAccessPathFrontOption =
-    TApproxAccessPathFrontNone() or
-    TApproxAccessPathFrontSome(ApproxAccessPathFront apf)
 }
 
 /**
@@ -1343,118 +1304,6 @@ class DataFlowCallOption extends TDataFlowCallOption {
   }
 }
 
-/** An optional `ParamNode`. */
-class ParamNodeOption extends TParamNodeOption {
-  string toString() {
-    this = TParamNodeNone() and
-    result = "(none)"
-    or
-    exists(ParamNode p |
-      this = TParamNodeSome(p) and
-      result = p.toString()
-    )
-  }
-}
-
-/**
- * A return context used to calculate flow summaries in reverse flow.
- *
- * The possible values are:
- *
- * - `TReturnCtxNone()`: no return flow.
- * - `TReturnCtxNoFlowThrough()`: return flow, but flow through is not possible.
- * - `TReturnCtxMaybeFlowThrough(ReturnPosition pos)`: return flow, of kind `pos`, and
- *    flow through may be possible.
- */
-class ReturnCtx extends TReturnCtx {
-  string toString() {
-    this = TReturnCtxNone() and
-    result = "(none)"
-    or
-    this = TReturnCtxNoFlowThrough() and
-    result = "(no flow through)"
-    or
-    exists(ReturnPosition pos |
-      this = TReturnCtxMaybeFlowThrough(pos) and
-      result = pos.toString()
-    )
-  }
-}
-
-/** An approximated `Content` tagged with the type of a containing object. */
-class TypedContentApprox extends MkTypedContentApprox {
-  private ContentApprox c;
-  private DataFlowType t;
-
-  TypedContentApprox() { this = MkTypedContentApprox(c, t) }
-
-  /** Gets a typed content approximated by this value. */
-  TypedContent getATypedContent() { result = getATypedContent(this) }
-
-  /** Gets the content. */
-  ContentApprox getContent() { result = c }
-
-  /** Gets the container type. */
-  DataFlowType getContainerType() { result = t }
-
-  /** Gets a textual representation of this approximated content. */
-  string toString() { result = c.toString() }
-}
-
-/**
- * The front of an approximated access path. This is either a head or a nil.
- */
-abstract class ApproxAccessPathFront extends TApproxAccessPathFront {
-  abstract string toString();
-
-  abstract DataFlowType getType();
-
-  abstract boolean toBoolNonEmpty();
-
-  TypedContentApprox getHead() { this = TApproxFrontHead(result) }
-
-  pragma[nomagic]
-  TypedContent getAHead() {
-    exists(TypedContentApprox cont |
-      this = TApproxFrontHead(cont) and
-      result = cont.getATypedContent()
-    )
-  }
-}
-
-class ApproxAccessPathFrontNil extends ApproxAccessPathFront, TApproxFrontNil {
-  private DataFlowType t;
-
-  ApproxAccessPathFrontNil() { this = TApproxFrontNil(t) }
-
-  override string toString() { result = ppReprType(t) }
-
-  override DataFlowType getType() { result = t }
-
-  override boolean toBoolNonEmpty() { result = false }
-}
-
-class ApproxAccessPathFrontHead extends ApproxAccessPathFront, TApproxFrontHead {
-  private TypedContentApprox tc;
-
-  ApproxAccessPathFrontHead() { this = TApproxFrontHead(tc) }
-
-  override string toString() { result = tc.toString() }
-
-  override DataFlowType getType() { result = tc.getContainerType() }
-
-  override boolean toBoolNonEmpty() { result = true }
-}
-
-/** An optional approximated access path front. */
-class ApproxAccessPathFrontOption extends TApproxAccessPathFrontOption {
-  string toString() {
-    this = TApproxAccessPathFrontNone() and result = "<none>"
-    or
-    this = TApproxAccessPathFrontSome(any(ApproxAccessPathFront apf | result = apf.toString()))
-  }
-}
-
 /** A `Content` tagged with the type of a containing object. */
 class TypedContent extends MkTypedContent {
   private Content c;
@@ -1487,7 +1336,7 @@ abstract class AccessPathFront extends TAccessPathFront {
 
   abstract DataFlowType getType();
 
-  abstract ApproxAccessPathFront toApprox();
+  abstract boolean toBoolNonEmpty();
 
   TypedContent getHead() { this = TFrontHead(result) }
 }
@@ -1501,7 +1350,7 @@ class AccessPathFrontNil extends AccessPathFront, TFrontNil {
 
   override DataFlowType getType() { result = t }
 
-  override ApproxAccessPathFront toApprox() { result = TApproxFrontNil(t) }
+  override boolean toBoolNonEmpty() { result = false }
 }
 
 class AccessPathFrontHead extends AccessPathFront, TFrontHead {
@@ -1513,7 +1362,7 @@ class AccessPathFrontHead extends AccessPathFront, TFrontHead {
 
   override DataFlowType getType() { result = tc.getContainerType() }
 
-  override ApproxAccessPathFront toApprox() { result.getAHead() = tc }
+  override boolean toBoolNonEmpty() { result = true }
 }
 
 /** An optional access path front. */

cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/DataFlowImplConsistency.qll

@@ -45,16 +45,6 @@ module Consistency {
     ) {
       none()
     }
-
-    /** Holds if `(c, pos, p)` should be excluded from the consistency test `uniqueParameterNodeAtPosition`. */
-    predicate uniqueParameterNodeAtPositionExclude(DataFlowCallable c, ParameterPosition pos, Node p) {
-      none()
-    }
-
-    /** Holds if `(c, pos, p)` should be excluded from the consistency test `uniqueParameterNodePosition`. */
-    predicate uniqueParameterNodePositionExclude(DataFlowCallable c, ParameterPosition pos, Node p) {
-      none()
-    }
   }
 
   private class RelevantNode extends Node {
@@ -111,7 +101,9 @@ module Consistency {
     exists(int c |
       c =
         strictcount(Node n |
-          not n.hasLocationInfo(_, _, _, _, _) and
+          not exists(string filepath, int startline, int startcolumn, int endline, int endcolumn |
+            n.hasLocationInfo(filepath, startline, startcolumn, endline, endcolumn)
+          ) and
           not any(ConsistencyConfiguration conf).missingLocationExclude(n)
         ) and
       msg = "Nodes without location: " + c
@@ -144,18 +136,6 @@ module Consistency {
     msg = "Local flow step does not preserve enclosing callable."
   }
 
-  query predicate readStepIsLocal(Node n1, Node n2, string msg) {
-    readStep(n1, _, n2) and
-    nodeGetEnclosingCallable(n1) != nodeGetEnclosingCallable(n2) and
-    msg = "Read step does not preserve enclosing callable."
-  }
-
-  query predicate storeStepIsLocal(Node n1, Node n2, string msg) {
-    storeStep(n1, _, n2) and
-    nodeGetEnclosingCallable(n1) != nodeGetEnclosingCallable(n2) and
-    msg = "Store step does not preserve enclosing callable."
-  }
-
   private DataFlowType typeRepr() { result = getNodeType(_) }
 
   query predicate compatibleTypesReflexive(DataFlowType t, string msg) {
@@ -252,27 +232,4 @@ module Consistency {
     not callable = viableCallable(call) and
     not any(ConsistencyConfiguration c).viableImplInCallContextTooLargeExclude(call, ctx, callable)
   }
-
-  query predicate uniqueParameterNodeAtPosition(
-    DataFlowCallable c, ParameterPosition pos, Node p, string msg
-  ) {
-    not any(ConsistencyConfiguration conf).uniqueParameterNodeAtPositionExclude(c, pos, p) and
-    isParameterNode(p, c, pos) and
-    not exists(unique(Node p0 | isParameterNode(p0, c, pos))) and
-    msg = "Parameters with overlapping positions."
-  }
-
-  query predicate uniqueParameterNodePosition(
-    DataFlowCallable c, ParameterPosition pos, Node p, string msg
-  ) {
-    not any(ConsistencyConfiguration conf).uniqueParameterNodePositionExclude(c, pos, p) and
-    isParameterNode(p, c, pos) and
-    not exists(unique(ParameterPosition pos0 | isParameterNode(p, c, pos0))) and
-    msg = "Parameter node with multiple positions."
-  }
-
-  query predicate uniqueContentApprox(Content c, string msg) {
-    not exists(unique(ContentApprox approx | approx = getContentApprox(c))) and
-    msg = "Non-unique content approximation."
-  }
 }

cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/DataFlowPrivate.qll

@@ -137,7 +137,7 @@ private newtype TReturnKind =
     exists(IndirectReturnNode return, ReturnIndirectionInstruction returnInd |
       returnInd.hasIndex(argumentIndex) and
       return.getAddressOperand() = returnInd.getSourceAddressOperand() and
-      indirectionIndex = return.getIndirectionIndex()
+      indirectionIndex = return.getIndirectionIndex() - 1 // We subtract one because the return loads the value.
     )
   }
 
@@ -197,7 +197,7 @@ class ReturnIndirectionNode extends IndirectReturnNode, ReturnNode {
     exists(int argumentIndex, ReturnIndirectionInstruction returnInd |
       returnInd.hasIndex(argumentIndex) and
       this.getAddressOperand() = returnInd.getSourceAddressOperand() and
-      result = TIndirectReturnKind(argumentIndex, this.getIndirectionIndex()) and
+      result = TIndirectReturnKind(argumentIndex, this.getIndirectionIndex() - 1) and
       hasNonInitializeParameterDef(returnInd.getIRVariable())
     )
     or
@@ -241,7 +241,7 @@ private Instruction getANonConversionUse(Operand operand) {
 
 /**
  * Gets the operand that represents the first use of the value of `call` following
- * a sequence of conversion-like instructions.
+ * a sequnce of conversion-like instructions.
  */
 predicate operandForfullyConvertedCall(Operand operand, CallInstruction call) {
   exists(getANonConversionUse(operand)) and
@@ -254,7 +254,7 @@ predicate operandForfullyConvertedCall(Operand operand, CallInstruction call) {
 
 /**
  * Gets the instruction that represents the first use of the value of `call` following
- * a sequence of conversion-like instructions.
+ * a sequnce of conversion-like instructions.
  *
  * This predicate only holds if there is no suitable operand (i.e., no operand of a non-
  * conversion instruction) to use to represent the value of `call` after conversions.
@@ -365,7 +365,7 @@ predicate jumpStep(Node n1, Node n2) {
 predicate storeStep(Node node1, Content c, PostFieldUpdateNode node2) {
   exists(int indirectionIndex1, int numberOfLoads, StoreInstruction store |
     nodeHasInstruction(node1, store, pragma[only_bind_into](indirectionIndex1)) and
-    node2.getIndirectionIndex() = 1 and
+    node2.getIndirectionIndex() = 0 and
     numberOfLoadsFromOperand(node2.getFieldAddress(), store.getDestinationAddressOperand(),
       numberOfLoads)
   |
@@ -465,20 +465,20 @@ predicate clearsContent(Node n, Content c) {
 predicate expectsContent(Node n, ContentSet c) { none() }
 
 /** Gets the type of `n` used for type pruning. */
-DataFlowType getNodeType(Node n) {
+IRType getNodeType(Node n) {
   suppressUnusedNode(n) and
-  result instanceof VoidType // stub implementation
+  result instanceof IRVoidType // stub implementation
 }
 
 /** Gets a string representation of a type returned by `getNodeType`. */
-string ppReprType(DataFlowType t) { none() } // stub implementation
+string ppReprType(IRType t) { none() } // stub implementation
 
 /**
  * Holds if `t1` and `t2` are compatible, that is, whether data can flow from
  * a node of type `t1` to a node of type `t2`.
  */
 pragma[inline]
-predicate compatibleTypes(DataFlowType t1, DataFlowType t2) {
+predicate compatibleTypes(IRType t1, IRType t2) {
   any() // stub implementation
 }
 
@@ -502,7 +502,7 @@ class DataFlowCallable = Cpp::Declaration;
 
 class DataFlowExpr = Expr;
 
-class DataFlowType = Type;
+class DataFlowType = IRType;
 
 /** A function call relevant for data flow. */
 class DataFlowCall extends CallInstruction {
@@ -551,13 +551,6 @@ predicate additionalLambdaFlowStep(Node nodeFrom, Node nodeTo, boolean preserves
  */
 predicate allowParameterReturnInSelf(ParameterNode p) { none() }
 
-/** An approximated `Content`. */
-class ContentApprox = Unit;
-
-/** Gets an approximated value for content `c`. */
-pragma[inline]
-ContentApprox getContentApprox(Content c) { any() }
-
 private class MyConsistencyConfiguration extends Consistency::ConsistencyConfiguration {
   override predicate argHasPostUpdateExclude(ArgumentNode n) {
     // The rules for whether an IR argument gets a post-update node are too

cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/DataFlowUtil.qll

@@ -38,12 +38,13 @@ private module Cached {
     TVariableNode(Variable var) or
     TPostFieldUpdateNode(FieldAddress operand, int indirectionIndex) {
       indirectionIndex =
-        [1 .. Ssa::countIndirectionsForCppType(operand.getObjectAddress().getResultLanguageType())]
+        [0 .. Ssa::countIndirectionsForCppType(operand.getObjectAddress().getResultLanguageType()) -
+            1]
     } or
     TSsaPhiNode(Ssa::PhiNode phi) or
     TIndirectArgumentOutNode(ArgumentOperand operand, int indirectionIndex) {
       Ssa::isModifiableByCall(operand) and
-      indirectionIndex = [1 .. Ssa::countIndirectionsForCppType(operand.getLanguageType())]
+      indirectionIndex = [0 .. Ssa::countIndirectionsForCppType(operand.getLanguageType()) - 1]
     } or
     TIndirectOperand(Operand op, int indirectionIndex) {
       Ssa::hasIndirectOperand(op, indirectionIndex)
@@ -112,7 +113,7 @@ class Node extends TIRDataFlowNode {
   Declaration getFunction() { none() } // overridden in subclasses
 
   /** Gets the type of this node. */
-  DataFlowType getType() { none() } // overridden in subclasses
+  IRType getType() { none() } // overridden in subclasses
 
   /** Gets the instruction corresponding to this node, if any. */
   Instruction asInstruction() { result = this.(InstructionNode).getInstruction() }
@@ -229,13 +230,7 @@ class Node extends TIRDataFlowNode {
   Expr asIndirectArgument() { result = this.asIndirectArgument(_) }
 
   /** Gets the positional parameter corresponding to this node, if any. */
-  Parameter asParameter() { result = this.asParameter(0) }
-
-  /**
-   * Gets the uninitialized local variable corresponding to this node, if
-   * any.
-   */
-  LocalVariable asUninitialized() { result = this.(UninitializedNode).getLocalVariable() }
+  Parameter asParameter() { result = asParameter(0) }
 
   /**
    * Gets the positional parameter corresponding to the node that represents
@@ -278,7 +273,7 @@ class Node extends TIRDataFlowNode {
   /**
    * Gets an upper bound on the type of this node.
    */
-  DataFlowType getTypeBound() { result = this.getType() }
+  IRType getTypeBound() { result = this.getType() }
 
   /** Gets the location of this element. */
   cached
@@ -327,7 +322,7 @@ class InstructionNode extends Node, TInstructionNode {
 
   override Declaration getFunction() { result = instr.getEnclosingFunction() }
 
-  override DataFlowType getType() { result = instr.getResultType() }
+  override IRType getType() { result = instr.getResultIRType() }
 
   final override Location getLocationImpl() { result = instr.getLocation() }
 
@@ -353,32 +348,13 @@ class OperandNode extends Node, TOperandNode {
 
   override Declaration getFunction() { result = op.getUse().getEnclosingFunction() }
 
-  override DataFlowType getType() { result = op.getType() }
+  override IRType getType() { result = op.getIRType() }
 
   final override Location getLocationImpl() { result = op.getLocation() }
 
   override string toStringImpl() { result = this.getOperand().toString() }
 }
 
-/**
- * Returns `t`, but stripped of the `n` outermost pointers, references, etc.
- *
- * For example, `stripPointers(int*&, 2)` is `int` and `stripPointers(int*, 0)` is `int*`.
- */
-private Type stripPointers(Type t, int n) {
-  result = t and n = 0
-  or
-  result = stripPointers(t.(PointerType).getBaseType(), n - 1)
-  or
-  result = stripPointers(t.(ArrayType).getBaseType(), n - 1)
-  or
-  result = stripPointers(t.(ReferenceType).getBaseType(), n - 1)
-  or
-  result = stripPointers(t.(PointerToMemberType).getBaseType(), n - 1)
-  or
-  result = stripPointers(t.(FunctionPointerIshType).getBaseType(), n - 1)
-}
-
 /**
  * INTERNAL: do not use.
  *
@@ -394,6 +370,8 @@ class PostFieldUpdateNode extends TPostFieldUpdateNode, PartialDefinitionNode {
 
   override Declaration getEnclosingCallable() { result = this.getFunction() }
 
+  override IRType getType() { result = fieldAddress.getIRType() }
+
   FieldAddress getFieldAddress() { result = fieldAddress }
 
   Field getUpdatedField() { result = fieldAddress.getField() }
@@ -401,8 +379,10 @@ class PostFieldUpdateNode extends TPostFieldUpdateNode, PartialDefinitionNode {
   int getIndirectionIndex() { result = indirectionIndex }
 
   override Node getPreUpdateNode() {
+    // + 1 because we're storing into an lvalue, and the original node should be the rvalue of
+    // the same address.
     hasOperandAndIndex(result, pragma[only_bind_into](fieldAddress).getObjectAddressOperand(),
-      indirectionIndex)
+      indirectionIndex + 1)
   }
 
   override Expr getDefinedExpr() {
@@ -431,26 +411,11 @@ class SsaPhiNode extends Node, TSsaPhiNode {
 
   override Declaration getFunction() { result = phi.getBasicBlock().getEnclosingFunction() }
 
-  override DataFlowType getType() { result = this.getAnInput().getType() }
+  override IRType getType() { result instanceof IRVoidType }
 
   final override Location getLocationImpl() { result = phi.getBasicBlock().getLocation() }
 
   override string toStringImpl() { result = "Phi" }
-
-  /**
-   * Gets a node that is used as input to this phi node.
-   * `fromBackEdge` is true if data flows along a back-edge,
-   * and `false` otherwise.
-   */
-  final Node getAnInput(boolean fromBackEdge) {
-    localFlowStep(result, this) and
-    if phi.getBasicBlock().dominates(getBasicBlock(result))
-    then fromBackEdge = true
-    else fromBackEdge = false
-  }
-
-  /** Gets a node that is used as input to this phi node. */
-  final Node getAnInput() { result = this.getAnInput(_) }
 }
 
 /**
@@ -474,6 +439,8 @@ class SideEffectOperandNode extends Node, IndirectOperand {
 
   override Function getFunction() { result = call.getEnclosingFunction() }
 
+  override IRType getType() { result instanceof IRVoidType }
+
   Expr getArgument() { result = call.getArgument(argumentIndex).getUnconvertedResultExpression() }
 }
 
@@ -496,6 +463,8 @@ class IndirectParameterNode extends Node, IndirectInstruction {
 
   override Function getFunction() { result = this.getInstruction().getEnclosingFunction() }
 
+  override IRType getType() { result instanceof IRVoidType }
+
   override string toStringImpl() {
     result = this.getParameter().toString() + " indirection"
     or
@@ -520,6 +489,8 @@ class IndirectReturnNode extends IndirectOperand {
   Operand getAddressOperand() { result = operand }
 
   override Declaration getEnclosingCallable() { result = this.getFunction() }
+
+  override IRType getType() { result instanceof IRVoidType }
 }
 
 /**
@@ -550,7 +521,9 @@ class IndirectArgumentOutNode extends Node, TIndirectArgumentOutNode, PostUpdate
 
   override Function getFunction() { result = this.getCallInstruction().getEnclosingFunction() }
 
-  override Node getPreUpdateNode() { hasOperandAndIndex(result, operand, indirectionIndex) }
+  override IRType getType() { result instanceof IRVoidType }
+
+  override Node getPreUpdateNode() { hasOperandAndIndex(result, operand, indirectionIndex + 1) }
 
   override string toStringImpl() {
     // This string should be unique enough to be helpful but common enough to
@@ -606,38 +579,6 @@ class IndirectReturnOutNode extends Node {
   int getIndirectionIndex() { result = indirectionIndex }
 }
 
-private PointerType getGLValueType(Type t, int indirectionIndex) {
-  result.getBaseType() = stripPointers(t, indirectionIndex - 1)
-}
-
-bindingset[isGLValue]
-private DataFlowType getTypeImpl(Type t, int indirectionIndex, boolean isGLValue) {
-  if isGLValue = true
-  then
-    result = getGLValueType(t, indirectionIndex)
-    or
-    // Ideally, the above case would cover all glvalue cases. However, consider the case where
-    // the database consists only of:
-    // ```
-    // void test() {
-    //   int* x;
-    //   x = nullptr;
-    // }
-    // ```
-    // and we want to compute the type of `*x` in the assignment `x = nullptr`. Here, `x` is an lvalue
-    // of type int* (which morally is an int**). So when we call `getTypeImpl` it will be with the
-    // parameters:
-    // - t = int*
-    // - indirectionIndex = 1 (when we want to model the dataflow node corresponding to *x)
-    // - isGLValue = true
-    // In this case, `getTypeImpl(t, indirectionIndex, isGLValue)` should give back `int**`. In this
-    // case, however, `int**` does not exist in the database. So instead we return int* (which is
-    // wrong, but at least we have a type).
-    not exists(getGLValueType(t, indirectionIndex)) and
-    result = stripPointers(t, indirectionIndex - 1)
-  else result = stripPointers(t, indirectionIndex)
-}
-
 /**
  * INTERNAL: Do not use.
  *
@@ -659,11 +600,7 @@ class IndirectOperand extends Node, TIndirectOperand {
 
   override Declaration getEnclosingCallable() { result = this.getFunction() }
 
-  override DataFlowType getType() {
-    exists(boolean isGLValue | if operand.isGLValue() then isGLValue = true else isGLValue = false |
-      result = getTypeImpl(operand.getType().getUnspecifiedType(), indirectionIndex, isGLValue)
-    )
-  }
+  override IRType getType() { result = this.getOperand().getIRType() }
 
   final override Location getLocationImpl() { result = this.getOperand().getLocation() }
 
@@ -672,25 +609,6 @@ class IndirectOperand extends Node, TIndirectOperand {
   }
 }
 
-/**
- * The value of an uninitialized local variable, viewed as a node in a data
- * flow graph.
- */
-class UninitializedNode extends Node {
-  LocalVariable v;
-
-  UninitializedNode() {
-    exists(Ssa::Def def |
-      def.getDefiningInstruction() instanceof UninitializedInstruction and
-      Ssa::nodeToDefOrUse(this, def) and
-      v = def.getSourceVariable().getBaseVariable().(Ssa::BaseIRVariable).getIRVariable().getAst()
-    )
-  }
-
-  /** Gets the uninitialized local variable corresponding to this node. */
-  LocalVariable getLocalVariable() { result = v }
-}
-
 /**
  * INTERNAL: Do not use.
  *
@@ -712,11 +630,7 @@ class IndirectInstruction extends Node, TIndirectInstruction {
 
   override Declaration getEnclosingCallable() { result = this.getFunction() }
 
-  override DataFlowType getType() {
-    exists(boolean isGLValue | if instr.isGLValue() then isGLValue = true else isGLValue = false |
-      result = getTypeImpl(instr.getResultType().getUnspecifiedType(), indirectionIndex, isGLValue)
-    )
-  }
+  override IRType getType() { result = this.getInstruction().getResultIRType() }
 
   final override Location getLocationImpl() { result = this.getInstruction().getLocation() }
 
@@ -746,7 +660,7 @@ predicate exprNodeShouldBeOperand(Node node, Expr e) {
 
 /**
  * Holds if `load` is a `LoadInstruction` that is the result of evaluating `e`
- * and `node` is an `IndirectOperandNode` that should map `node.asExpr()` to `e`.
+ * and `node` is an `IndirctOperandNode` that should map `node.asExpr()` to `e`.
  *
  * We map `e` to `node.asExpr()` when `node` semantically represents the
  * same value as `load`. A subsequent flow step will flow `node` to
@@ -930,8 +844,6 @@ abstract class PostUpdateNode extends Node {
    * Gets the node before the state update.
    */
   abstract Node getPreUpdateNode();
-
-  final override DataFlowType getType() { result = this.getPreUpdateNode().getType() }
 }
 
 /**
@@ -995,7 +907,7 @@ class VariableNode extends Node, TVariableNode {
     result = v
   }
 
-  override DataFlowType getType() { result = v.getType() }
+  override IRType getType() { result.getCanonicalLanguageType().hasUnspecifiedType(v.getType(), _) }
 
   final override Location getLocationImpl() { result = v.getLocation() }
 
@@ -1148,7 +1060,7 @@ predicate simpleLocalFlowStep(Node nodeFrom, Node nodeTo) {
       store.getDestinationAddressOperand() = address
     )
     or
-    Ssa::outNodeHasAddressAndIndex(nodeFrom, address, indirectionIndex)
+    Ssa::outNodeHasAddressAndIndex(nodeFrom, address, indirectionIndex - 1)
   )
 }
 

cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/ModelUtil.qll

@@ -41,7 +41,7 @@ Node callOutput(CallInstruction call, FunctionOutput output) {
   // The side effect of a call on the value pointed to by an argument or qualifier
   exists(int index, int indirectionIndex |
     result.(IndirectArgumentOutNode).getArgumentIndex() = index and
-    result.(IndirectArgumentOutNode).getIndirectionIndex() = indirectionIndex and
+    result.(IndirectArgumentOutNode).getIndirectionIndex() + 1 = indirectionIndex and
     result.(IndirectArgumentOutNode).getCallInstruction() = call and
     output.isParameterDerefOrQualifierObject(index, indirectionIndex)
   )

cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/PrintIRLocalFlow.qll

@@ -100,7 +100,7 @@ private string getNodeProperty(DataFlow::Node node, string key) {
   or
   // Is there partial flow from a source to this node?
   // This property will only be emitted if partial flow is enabled by overriding
-  // `DataFlow::Configuration::explorationLimit()`.
+  // `DataFlow::Configration::explorationLimit()`.
   key = "pflow" and
   result =
     strictconcat(DataFlow::PartialPathNode sourceNode, DataFlow::PartialPathNode destNode, int dist,

cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/SsaInternals.qll

@@ -301,12 +301,7 @@ private predicate defToNode(Node nodeFrom, Def def) {
   nodeHasInstruction(nodeFrom, def.getDefiningInstruction(), def.getIndirectionIndex())
 }
 
-/**
- * INTERNAL: Do not use.
- *
- * Holds if `nodeFrom` is the node that correspond to the definition or use `defOrUse`.
- */
-predicate nodeToDefOrUse(Node nodeFrom, SsaDefOrUse defOrUse) {
+private predicate nodeToDefOrUse(Node nodeFrom, SsaDefOrUse defOrUse) {
   // Node -> Def
   defToNode(nodeFrom, defOrUse)
   or

cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/SsaInternalsCommon.qll

@@ -11,9 +11,7 @@ private import DataFlowUtil
  * corresponding `(Indirect)OperandNode`.
  */
 predicate ignoreOperand(Operand operand) {
-  operand = any(Instruction instr | ignoreInstruction(instr)).getAnOperand() or
-  operand = any(Instruction instr | ignoreInstruction(instr)).getAUse() or
-  operand instanceof MemoryOperand
+  operand = any(Instruction instr | ignoreInstruction(instr)).getAnOperand()
 }
 
 /**

cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/ssa0/SsaInternals.qll

@@ -36,7 +36,7 @@ private module SourceVariables {
 
     override string toString() { result = var.toString() }
 
-    override DataFlowType getType() { result = var.getType() }
+    override DataFlowType getType() { result = var.getIRType() }
   }
 
   class BaseCallVariable extends BaseSourceVariable, TBaseCallVariable {
@@ -48,7 +48,7 @@ private module SourceVariables {
 
     override string toString() { result = call.toString() }
 
-    override DataFlowType getType() { result = call.getResultType() }
+    override DataFlowType getType() { result = call.getResultIRType() }
   }
 
   private newtype TSourceVariable =

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

@@ -218,7 +218,7 @@ private predicate allocation(Instruction array, Length length, int delta) {
           length.(VNLength).getInstruction().getConvertedResultExpression() = lengthExpr
         )
         or
-        not deconstructMallocSizeExpr(alloc.getSizeExpr(), _, _) and
+        not exists(int d | deconstructMallocSizeExpr(alloc.getSizeExpr(), _, d)) and
         length.(VNLength).getInstruction().getConvertedResultExpression() = alloc.getSizeExpr() and
         delta = 0
       )