Merge pull request #4321 from jf205/sd-216-ql

CodeQL docs: mention `generate query-help` CLI command

.codeqlmanifest.json

@@ -1,5 +1,6 @@
 { "provide": [ "*/ql/src/qlpack.yml",
                "*/ql/test/qlpack.yml",
+               "*/ql/examples/qlpack.yml",
                "*/upgrades/qlpack.yml",
                "misc/legacy-support/*/qlpack.yml",
                "misc/suite-helpers/qlpack.yml" ] }

.devcontainer/devcontainer.json

@@ -0,0 +1,9 @@
+{
+  "extensions": [
+    "github.vscode-codeql",
+    "slevesque.vscode-zipexplorer"
+  ],
+  "settings": {
+    "codeQL.experimentalBqrsParsing": true
+  }
+}

.github/codeql/codeql-config.yml

@@ -0,0 +1,9 @@
+name: "CodeQL config"
+
+queries:
+  - uses: security-and-quality
+
+paths-ignore:
+  - '/cpp/'
+  - '/java/'
+  - '/python/'

.github/workflows/codeql-analysis.yml

@@ -0,0 +1,52 @@
+name: "Code scanning - action"
+
+on:
+  push:
+  pull_request:
+  schedule:
+    - cron: '0 9 * * 1'
+
+jobs:
+  CodeQL-Build:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v2
+      with:
+        # We must fetch at least the immediate parents so that if this is
+        # a pull request then we can checkout the head.
+        fetch-depth: 2
+
+    # If this run was triggered by a pull request event, then checkout
+    # the head of the pull request instead of the merge commit.
+    - run: git checkout HEAD^2
+      if: ${{ github.event_name == 'pull_request' }}
+      
+    # Initializes the CodeQL tools for scanning.
+    - name: Initialize CodeQL
+      uses: github/codeql-action/init@v1
+      # Override language selection by uncommenting this and choosing your languages
+      with:
+        languages: csharp
+        config-file: ./.github/codeql/codeql-config.yml
+
+    # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
+    # If this step fails, then you should remove it and run the build manually (see below)
+    - name: Autobuild
+      uses: github/codeql-action/autobuild@v1
+
+    # ℹ️ Command-line programs to run using the OS shell.
+    # 📚 https://git.io/JvXDl
+
+    # ✏️ If the Autobuild fails above, remove it and uncomment the following three lines
+    #    and modify them (or add more) to build your code if your project
+    #    uses a compiled language
+
+    #- run: |
+    #   make bootstrap
+    #   make release
+
+    - name: Perform CodeQL Analysis
+      uses: github/codeql-action/analyze@v1

.gitignore

@@ -21,4 +21,3 @@
 /codeql/
 
 csharp/extractor/Semmle.Extraction.CSharp.Driver/Properties/launchSettings.json
-.vscode

.vscode/.gitattributes

@@ -0,0 +1 @@
+*.json  linguist-language=JSON-with-Comments

.vscode/extensions.json

@@ -0,0 +1,10 @@
+{
+    // See https://go.microsoft.com/fwlink/?LinkId=827846 to learn about workspace recommendations.
+    // Extension identifier format: ${publisher}.${name}. Example: vscode.csharp
+    // List of extensions which should be recommended for users of this workspace.
+    "recommendations": [
+        "github.vscode-codeql"
+    ],
+    // List of extensions recommended by VS Code that should not be recommended for users of this workspace.
+    "unwantedRecommendations": []
+}

.vscode/settings.json

@@ -0,0 +1,3 @@
+{
+    "omnisharp.autoStart": false
+}

.vscode/tasks.json

@@ -0,0 +1,27 @@
+{
+    // To run a task, select the `Terminal | Run Task...` menu option, and then select the task from
+    // the list in the dropdown, or invoke the `Tasks: Run Task` command from the command palette/
+    // To bind a keyboard shortcut to invoke a task, see https://code.visualstudio.com/docs/editor/tasks#_binding-keyboard-shortcuts-to-tasks.
+    // See https://go.microsoft.com/fwlink/?LinkId=733558
+    // for the documentation about the tasks.json format
+    "version": "2.0.0",
+    "tasks": [
+        {
+            "label": "Sync Identical Files",
+            "type": "process",
+            // Non-Windows OS will usually have Python 3 already installed at /usr/bin/python3.
+            "command": "python3",
+            "args": [
+                "config/sync-files.py",
+                "--latest"
+            ],
+            "group": "build",
+            "windows": {
+                // On Windows, use whatever Python interpreter is configured for this workspace. The default is
+                // just `python`, so if Python is already on the path, this will find it.
+                "command": "${config:python.pythonPath}",
+            },
+            "problemMatcher": []
+        }
+    ]
+}

CODEOWNERS

@@ -1,11 +1,20 @@
-/cpp/ @Semmle/cpp-analysis
-/csharp/ @Semmle/cs
-/java/ @Semmle/java
-/javascript/ @Semmle/js
-/python/ @Semmle/python
+/cpp/ @github/codeql-c-analysis
+/csharp/ @github/codeql-csharp
+/java/ @github/codeql-java
+/javascript/ @github/codeql-javascript
+/python/ @github/codeql-python
+
+# Assign query help for docs review
 /cpp/**/*.qhelp @hubwriter
 /csharp/**/*.qhelp @jf205
 /java/**/*.qhelp @felicitymay
 /javascript/**/*.qhelp @mchammer01
 /python/**/*.qhelp @felicitymay
 /docs/language/ @shati-patel @jf205
+
+# Exclude help for experimental queries from docs review
+/cpp/**/experimental/**/*.qhelp @github/codeql-c-analysis
+/csharp/**/experimental/**/*.qhelp @github/codeql-csharp
+/java/**/experimental/**/*.qhelp @github/codeql-java
+/javascript/**/experimental/**/*.qhelp @github/codeql-javascript
+/python/**/experimental/**/*.qhelp @github/codeql-python

CODE_OF_CONDUCT.md

@@ -1,39 +1,126 @@
-# Code of Conduct
+## Our Pledge
 
-This code of conduct outlines expectations for participation in the Semmle open source community, including any open source repositories on GitHub.com, as well as steps for reporting unacceptable behavior. We are committed to providing a welcoming and inspiring community for all.
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, religion, or sexual identity
+and orientation.
 
-People violating this code of conduct may be banned from the community.
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
 
-Our community strives to:
-* Be friendly and patient: Remember you might not be communicating in someone else’s primary spoken or programming language, and others may not have your level of understanding.
-* Be welcoming: Our community welcomes and supports people of all backgrounds and identities. This includes, but is not limited to members of any race, ethnicity, culture, national origin, color, immigration status, social and economic class, educational level, sex, sexual orientation, gender identity and expression, age, size, family status, political belief, religion, and mental and physical ability.
-* Be respectful: We are a world-wide community of professionals, and we conduct ourselves professionally. Disagreement is no excuse for poor behavior and poor manners. Disrespectful and unacceptable behavior includes, but is not limited to:
-  * Violent threats or language.
-  * Discriminatory or derogatory jokes and language.
-  * Posting sexually explicit or violent material.
-  * Posting, or threatening to post, people’s personally identifying information (“doxing”).
-  * Insults, especially those using discriminatory terms or slurs.
-  * Behavior that could be perceived as sexual attention.
-  * Advocating for or encouraging any of the above behaviors.
-* Understand disagreements: Disagreements, both social and technical, are useful learning opportunities. Seek to understand others’ viewpoints and resolve differences constructively.
+## Our Standards
 
-This code is not exhaustive or complete. It serves to capture our common understanding of a productive, collaborative environment. We expect the code to be followed in spirit as much as in the letter.
+Examples of behavior that contributes to a positive environment for our
+community include:
 
-# Scope
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the
+  overall community
 
-This code of conduct applies to all repositories and communities for Semmle open source projects, regardless of whether or not the repository explicitly calls out its use of this code. The code also applies in public spaces when an individual is representing the Semmle open source community. Examples include using an official project email address, posting via an official social media account, or acting as an appointed representative at an online or offline event. 
+Examples of unacceptable behavior include:
 
+* The use of sexualized language or imagery, and sexual attention or
+  advances of any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
 
-# Reporting Code of Conduct Issues
-We encourage members of the community to resolve issues on their own whenever possible. This builds a broader and deeper understanding and ultimately a healthier interaction. In the event that an issue cannot be resolved locally, please feel free to report your concerns by contacting code-of-conduct@semmle.com. 
-In your report please include:
-* Your contact information.
-* Names (real, usernames or pseudonyms) of any individuals involved. If there are additional witnesses, please include them as well.
-* Your account of what occurred, and if you believe the incident is ongoing. If there is a publicly available record (e.g. a mailing list archive or a public chat log), please include a link or attachment.
-* Any additional information that may be helpful.
+## Enforcement Responsibilities
 
-All reports will be reviewed by a multi-person team and will result in a response that is deemed necessary and appropriate to the circumstances. Where additional perspectives are needed, the team may seek insight from others with relevant expertise or experience. The confidentiality of the person reporting the incident will be kept at all times. Involved parties are never part of the review team.
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
 
-Anyone asked to stop unacceptable behavior is expected to comply immediately. If an individual engages in unacceptable behavior, the review team may take any action they deem appropriate, including a permanent ban from the community.
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
 
-*This text is licensed under the [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/) license. It is based on a template established by the [TODO Group](http://todogroup.org/) and variants thereof used by numerous other large communities (e.g., [Microsoft](https://microsoft.github.io/codeofconduct/), [Facebook](https://code.fb.com/codeofconduct/), [Yahoo](https://yahoo.github.io/codeofconduct), [Twitter](https://github.com/twitter/code-of-conduct), [GitHub](https://blog.github.com/2015-07-20-adopting-the-open-code-of-conduct/)) and the Scope section from the [Contributor Covenant version 1.4](http://contributor-covenant.org/version/1/4/).*
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official e-mail address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at
+opensource@github.com.
+All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series
+of actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or
+permanent ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior,  harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within
+the community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.0, available at
+https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
+
+Community Impact Guidelines were inspired by [Mozilla's code of conduct
+enforcement ladder](https://github.com/mozilla/diversity).
+
+[homepage]: https://www.contributor-covenant.org
+
+For answers to common questions about this code of conduct, see the FAQ at
+https://www.contributor-covenant.org/faq. Translations are available at
+https://www.contributor-covenant.org/translations.

CONTRIBUTING.md

@@ -53,14 +53,6 @@ After the experimental query is merged, we welcome pull requests to improve it.
 
 ## Using your personal data
 
-If you contribute to this project, we will record your name and email
-address (as provided by you with your contributions) as part of the code
-repositories, which are public. We might also use this information
-to contact you in relation to your contributions, as well as in the
-normal course of software development. We also store records of your
-CLA agreements. Under GDPR legislation, we do this
-on the basis of our legitimate interest in creating the CodeQL product.
-
-Please do get in touch (privacy@github.com) if you have any questions about
-this or our data protection policies.
+If you contribute to this project, we will record your name and email address (as provided by you with your contributions) as part of the code repositories, which are public. We might also use this information to contact you in relation to your contributions, as well as in the normal course of software development. We also store records of CLA agreements signed in the past, but no longer require contributors to sign a CLA. Under GDPR legislation, we do this on the basis of our legitimate interest in creating the CodeQL product. 
 
+Please do get in touch (privacy@github.com) if you have any questions about this or our data protection policies.

README.md

@@ -1,6 +1,6 @@
 # CodeQL
 
-This open source repository contains the standard CodeQL libraries and queries that power [LGTM](https://lgtm.com) and the other CodeQL products that [GitHub](https://github.com) makes available to its customers worldwide.
+This open source repository contains the standard CodeQL libraries and queries that power [LGTM](https://lgtm.com) and the other CodeQL products that [GitHub](https://github.com) makes available to its customers worldwide. For the queries, libraries, and extractor that power Go analysis, visit the [CodeQL for Go repository](https://github.com/github/codeql-go).
 
 ## How do I learn CodeQL and run queries?
 
@@ -9,8 +9,20 @@ You can use the [interactive query console](https://lgtm.com/help/lgtm/using-que
 
 ## 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/master/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.
+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.
 
 ## License
 
-The code in this repository is licensed under [Apache License 2.0](LICENSE) by [GitHub](https://github.com).
+The code in this repository is licensed under the [MIT License](LICENSE) by [GitHub](https://github.com).
+
+## Visual Studio Code integration
+
+If you use Visual Studio Code to work in this repository, there are a few integration features to make development easier.
+
+### CodeQL for Visual Studio Code
+
+You can install the [CodeQL for Visual Studio Code](https://marketplace.visualstudio.com/items?itemName=GitHub.vscode-codeql) extension to get syntax highlighting, IntelliSense, and code navigation for the QL language, as well as unit test support for testing CodeQL libraries and queries.
+
+### Tasks
+
+The `.vscode/tasks.json` file defines custom tasks specific to working in this repository. To invoke one of these tasks, select the `Terminal | Run Task...` menu option, and then select the desired task from the dropdown. You can also invoke the `Tasks: Run Task` command from the command palette.

change-notes/1.25/analysis-cpp.md

@@ -0,0 +1,46 @@
+# Improvements to C/C++ analysis
+
+The following changes in version 1.25 affect C/C++ analysis in all applications.
+
+## General improvements
+
+## New queries
+
+| **Query**                   | **Tags**  | **Purpose**                                                        |
+|-----------------------------|-----------|--------------------------------------------------------------------|
+
+## Changes to existing queries
+
+| **Query**                  | **Expected impact**    | **Change**                                                       |
+|----------------------------|------------------------|------------------------------------------------------------------|
+| Uncontrolled format string (`cpp/tainted-format-string`) |  | This query is now displayed by default on LGTM. |
+| Uncontrolled format string (through global variable) (`cpp/tainted-format-string-through-global`) |  | This query is now displayed by default on LGTM. |
+
+## Changes to libraries
+
+* The library `VCS.qll` and all queries that imported it have been removed.
+* The data-flow library has been improved, which affects most security queries by potentially
+  adding more results. Flow through functions now takes nested field reads/writes into account.
+  For example, the library is able to track flow from `taint()` to `sink()` via the method
+  `getf2f1()` in
+  ```c
+  struct C {
+      int f1;
+  };
+
+  struct C2
+  {
+      C f2;
+
+      int getf2f1() {
+          return f2.f1; // Nested field read
+      }
+
+      void m() {
+          f2.f1 = taint();
+          sink(getf2f1()); // NEW: taint() reaches here
+      }
+  };
+  ```
+* The security pack taint tracking library (`semmle.code.cpp.security.TaintTracking`) now considers that equality checks may block the flow of taint.  This results in fewer false positive results from queries that use this library.
+* The length of a tainted string (such as the return value of a call to `strlen` or `strftime` with tainted parameters) is no longer itself considered tainted by the `models` library.  This leads to fewer false positive results in queries that use any of our taint libraries.

change-notes/1.25/analysis-csharp.md

@@ -0,0 +1,78 @@
+# Improvements to C# analysis
+
+The following changes in version 1.25 affect C# analysis in all applications.
+
+## New queries
+
+| **Query**                   | **Tags**  | **Purpose**                                                        |
+|-----------------------------|-----------|--------------------------------------------------------------------|
+
+
+## Changes to existing queries
+
+| **Query**                    | **Expected impact**    | **Change**                        |
+|------------------------------|------------------------|-----------------------------------|
+
+
+## Removal of old queries
+
+## Changes to code extraction
+
+* Index initializers, of the form `{ [1] = "one" }`, are extracted correctly. Previously, the kind of the
+  expression was incorrect, and the index was not extracted.
+
+## Changes to libraries
+
+* The class `UnboundGeneric` has been refined to only be those declarations that actually
+  have type parameters. This means that non-generic nested types inside constructed types,
+  such as `A<int>.B`, no longer are considered unbound generics. (Such nested types do,
+  however, still have relevant `.getSourceDeclaration()`s, for example `A<>.B`.)
+* The data-flow library has been improved, which affects most security queries by potentially
+  adding more results:
+  - Flow through methods now takes nested field reads/writes into account.
+    For example, the library is able to track flow from `"taint"` to `Sink()` via the method
+    `GetF2F1()` in
+    ```csharp
+    class C1
+    {
+        string F1;
+    }
+
+    class C2
+    {
+        C1 F2;
+
+        string GetF2F1() => F2.F1; // Nested field read
+
+        void M()
+        {
+            F2 = new C1() { F1 = "taint" };
+            Sink(GetF2F1()); // NEW: "taint" reaches here
+        }
+    }
+    ```
+  - Flow through collections is now modeled precisely. For example, instead of modeling an array
+    store `a[i] = x` as a taint-step from `x` to `a`, we now model it as a data-flow step that
+    stores `x` into `a`. To get the value back out, a matching read step must be taken.
+
+    For source-code based data-flow analysis, the following constructs are modeled as stores into
+    collections:
+    - Direct array assignments, `a[i] = x`.
+    - Array initializers, `new [] { x }`.
+    - C# 6-style array initializers, `new C() { Array = { [i] = x } }`.
+    - Call arguments that match a `params` parameter, where the C# compiler creates an array under-the-hood.
+    - `yield return` statements.
+
+    The following source-code constructs read from a collection:
+    - Direct array reads, `a[i]`.
+    - `foreach` statements.
+
+    For calls out to library code, existing flow summaries have been refined to precisely
+    capture how they interact with collection contents. For example, a call to
+    `System.Collections.Generic.List<T>.Add(T)` stores the value of the argument into the
+    qualifier, and a call to `System.Collections.Generic.List<T>.get_Item(int)` (that is, an
+    indexer call) reads contents out of the qualifier. Moreover, the effect of
+    collection-clearing methods such as `System.Collections.Generic.List<T>.Clear()` is now
+    also modeled.
+
+## Changes to autobuilder

change-notes/1.25/analysis-java.md

@@ -0,0 +1,49 @@
+# Improvements to Java analysis
+
+The following changes in version 1.25 affect Java analysis in all applications.
+
+## General improvements
+
+The Java autobuilder has been improved to detect more Gradle Java versions.
+
+## Changes to existing queries
+
+| **Query**                    | **Expected impact**    | **Change**                        |
+|------------------------------|------------------------|-----------------------------------|
+| Hard-coded credential in API call (`java/hardcoded-credential-api-call`) | More results | The query now recognizes the `BasicAWSCredentials` class of the Amazon client SDK library with hardcoded access key/secret key. |
+| Deserialization of user-controlled data (`java/unsafe-deserialization`) | Fewer false positive results | The query no longer reports results using `org.apache.commons.io.serialization.ValidatingObjectInputStream`. |
+| Use of a broken or risky cryptographic algorithm (`java/weak-cryptographic-algorithm`) | More results | The query now recognizes the `MessageDigest.getInstance` method. |
+| Use of a potentially broken or risky cryptographic algorithm (`java/potentially-weak-cryptographic-algorithm`) | More results | The query now recognizes the `MessageDigest.getInstance` method. |
+| Reading from a world writable file (`java/world-writable-file-read`) | More results | The query now recognizes more JDK file operations. |
+
+## Changes to libraries
+
+* The data-flow library has been improved with more taint flow modeling for the
+  Collections framework and other classes of the JDK. This affects all security
+  queries using data flow and can yield additional results.
+* The data-flow library has been improved with more taint flow modeling for the
+  Spring framework. This affects all security queries using data flow and can
+  yield additional results on project that rely on the Spring framework.
+* The data-flow library has been improved, which affects most security queries by potentially
+  adding more results. Flow through methods now takes nested field reads/writes into account.
+  For example, the library is able to track flow from `"taint"` to `sink()` via the method
+  `getF2F1()` in
+  ```java
+  class C1 {
+    String f1;
+    C1(String f1) { this.f1 = f1; }
+  }
+
+  class C2 {
+    C1 f2;
+    String getF2F1() {
+        return this.f2.f1; // Nested field read
+    }
+    void m() {
+        this.f2 = new C1("taint");
+        sink(this.getF2F1()); // NEW: "taint" reaches here
+    }
+  }
+  ```
+* The library has been extended with more support for Java 14 features
+  (`switch` expressions and pattern-matching for `instanceof`).

change-notes/1.25/analysis-javascript.md

@@ -0,0 +1,111 @@
+# Improvements to JavaScript analysis
+
+## General improvements
+
+* Support for the following frameworks and libraries has been improved:
+  - [Promise](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Promise)
+  - [bluebird](http://bluebirdjs.com/)
+  - [express](https://www.npmjs.com/package/express)
+  - [execa](https://www.npmjs.com/package/execa)
+  - [fancy-log](https://www.npmjs.com/package/fancy-log)
+  - [fastify](https://www.npmjs.com/package/fastify)
+  - [foreground-child](https://www.npmjs.com/package/foreground-child)
+  - [fstream](https://www.npmjs.com/package/fstream)
+  - [jGrowl](https://github.com/stanlemon/jGrowl)
+  - [jQuery](https://jquery.com/)
+  - [marsdb](https://www.npmjs.com/package/marsdb)
+  - [micro](https://www.npmjs.com/package/micro/)
+  - [minimongo](https://www.npmjs.com/package/minimongo/)
+  - [mssql](https://www.npmjs.com/package/mssql)
+  - [mysql](https://www.npmjs.com/package/mysql)
+  - [npmlog](https://www.npmjs.com/package/npmlog)
+  - [opener](https://www.npmjs.com/package/opener)
+  - [pg](https://www.npmjs.com/package/pg)
+  - [sequelize](https://www.npmjs.com/package/sequelize)
+  - [spanner](https://www.npmjs.com/package/spanner)
+  - [sqlite](https://www.npmjs.com/package/sqlite)
+  - [ssh2-streams](https://www.npmjs.com/package/ssh2-streams)
+  - [ssh2](https://www.npmjs.com/package/ssh2)
+  - [vue](https://www.npmjs.com/package/vue)
+  - [yargs](https://www.npmjs.com/package/yargs)
+  - [webpack-dev-server](https://www.npmjs.com/package/webpack-dev-server)
+
+* TypeScript 3.9 is now supported.
+
+* TypeScript code embedded in HTML and Vue files is now extracted and analyzed.
+
+* The analysis of sanitizers has improved, leading to more accurate
+  results from the security queries.
+
+## New queries
+
+| **Query**                                                                       | **Tags**                                                          | **Purpose**                                                                                                                                                                            |
+|---------------------------------------------------------------------------------|-------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| DOM text reinterpreted as HTML (`js/xss-through-dom`) | security, external/cwe/cwe-079, external/cwe/cwe-116 | Highlights potential XSS vulnerabilities where existing text from the DOM is used as HTML. Results are shown on LGTM by default. |
+| Incomplete HTML attribute sanitization (`js/incomplete-html-attribute-sanitization`) | security, external/cwe/cwe-20, external/cwe/cwe-079, external/cwe/cwe-116 | Highlights potential XSS vulnerabilities due to incomplete sanitization of HTML meta-characters. Results are shown on LGTM by default. |
+| Unsafe expansion of self-closing HTML tag (`js/unsafe-html-expansion`) | security, external/cwe/cwe-079, external/cwe/cwe-116 | Highlights potential XSS vulnerabilities caused by unsafe expansion of self-closing HTML tags. |
+| Unsafe shell command constructed from library input (`js/shell-command-constructed-from-input`) | correctness, security, external/cwe/cwe-078, external/cwe/cwe-088 | Highlights potential command injections due to a shell command being constructed from library inputs. Results are shown on LGTM by default. |
+| Download of sensitive file through insecure connection (`js/insecure-download`) | security, external/cwe/cwe-829 | Highlights downloads of sensitive files through an unencrypted protocol. Results are shown on LGTM by default. |
+| Exposure of private files (`js/exposure-of-private-files`) | security, external/cwe/cwe-200 | Highlights servers that serve private files. Results are shown on LGTM by default. |
+| Creating biased random numbers from a cryptographically secure source (`js/biased-cryptographic-random`) | security, external/cwe/cwe-327 | Highlights mathematical operations on cryptographically secure numbers that can create biased results. Results are shown on LGTM by default. |
+| Storage of sensitive information in build artifact (`js/build-artifact-leak`) | security, external/cwe/cwe-312 | Highlights storage of sensitive information in build artifacts. Results are shown on LGTM by default. |
+| Improper code sanitization (`js/bad-code-sanitization`) | security, external/cwe/cwe-094, external/cwe/cwe-079, external/cwe/cwe-116 | Highlights string concatenation where code is constructed without proper sanitization. Results are shown on LGTM by default. |
+| Disabling certificate validation (`js/disabling-certificate-validation`) | security, external/cwe-295 | Highlights locations where SSL certificate validation is disabled. Results are shown on LGTM by default. | 
+| Incomplete multi-character sanitization (`js/incomplete-multi-character-sanitization`) | correctness, security, external/cwe/cwe-20, external/cwe/cwe-116 | Highlights sanitizers that fail to remove dangerous substrings completely. Results are shown on LGTM by default. |
+
+## Changes to existing queries
+
+| **Query**                      | **Expected impact**          | **Change**                                                                |
+|--------------------------------|------------------------------|---------------------------------------------------------------------------|
+| Client-side cross-site scripting (`js/xss`) | Fewer results | This query now recognizes additional safe patterns of constructing HTML. |
+| Client-side URL redirect (`js/client-side-unvalidated-url-redirection`) | Fewer results | This query now recognizes additional safe patterns of doing URL redirects. |
+| Code injection (`js/code-injection`) | More results | More potential vulnerabilities involving NoSQL code operators are now recognized. |
+| Exception text reinterpreted as HTML (`js/exception-xss`) | Rephrased and changed visibility | Rephrased name and alert message. Severity lowered from error to warning. Results are now shown on LGTM by default. |
+| Expression has no effect (`js/useless-expression`) | Fewer results | This query no longer flags an expression when that expression is the only content of the containing file. |
+| Hard-coded credentials (`js/hardcoded-credentials`) | More results | This query now recognizes hard-coded credentials sent via HTTP authorization headers. |
+| Incomplete URL scheme check (`js/incomplete-url-scheme-check`) | More results | This query now recognizes additional url scheme checks. |
+| Insecure randomness (`js/insecure-randomness`) | Fewer results | This query now recognizes when an insecure random value is used as a fallback when secure random values are unsupported. |
+| Misspelled variable name (`js/misspelled-variable-name`) | Message changed | The message for this query now correctly identifies the misspelled variable in additional cases. |
+| Non-linear pattern (`js/non-linear-pattern`) | Fewer duplicates and message changed | This query now generates fewer duplicate alerts and has a clearer explanation in case of type annotations used in a pattern. |
+| Prototype pollution in utility function (`js/prototype-pollution-utility`) | More results | This query now recognizes additional utility functions as vulnerable to prototype polution. |
+| Uncontrolled command line (`js/command-line-injection`) | More results | This query now recognizes additional command execution calls. |
+| Uncontrolled data used in path expression (`js/path-injection`) | More results | This query now recognizes additional file system calls. |
+| Uncontrolled data used in path expression (`js/path-injection`) | Fewer results | This query no longer flags paths that have been checked to be part of a collection. |
+| Unknown directive (`js/unknown-directive`) | Fewer results | This query no longer flags directives generated by the Babel compiler. |
+| Unneeded defensive code (`js/unneeded-defensive-code`) | Fewer false-positive results | This query now recognizes checks meant to handle the `document.all` object. |
+| Unused property (`js/unused-property`) | Fewer results | This query no longer flags properties of objects that are operands of `yield` expressions. |
+| Zip Slip (`js/zipslip`) | More results | This query now recognizes additional vulnerabilities. |
+
+The following low-precision queries are no longer run by default on LGTM (their results already were not displayed):
+
+  - `js/angular/dead-event-listener`
+  - `js/angular/unused-dependency`
+  - `js/bitwise-sign-check`
+  - `js/comparison-of-identical-expressions`
+  - `js/conflicting-html-attribute`
+  - `js/ignored-setter-parameter`
+  - `js/jsdoc/malformed-param-tag`
+  - `js/jsdoc/missing-parameter`
+  - `js/jsdoc/unknown-parameter`
+  - `js/json-in-javascript-file`
+  - `js/misspelled-identifier`
+  - `js/nested-loops-with-same-variable`
+  - `js/node/cyclic-import`
+  - `js/node/unused-npm-dependency`
+  - `js/omitted-array-element`
+  - `js/return-outside-function`
+  - `js/single-run-loop`
+  - `js/too-many-parameters`
+  - `js/unused-property`
+  - `js/useless-assignment-to-global`
+
+## Changes to libraries
+
+* A library `semmle.javascript.explore.CallGraph` has been added to help write queries for exploring the call graph.
+* Added data flow for `Map` and `Set`, and added matching type-tracking steps that can accessed using the `CollectionsTypeTracking` module.
+* The data-flow node representing a parameter or destructuring pattern is now always the `ValueNode` corresponding to that AST node. This has a few consequences:
+  - `Parameter.flow()` now gets the correct data flow node for a parameter. Previously this had a result, but the node was disconnected from the data flow graph.
+  - `ParameterNode.asExpr()` and `.getAstNode()` now gets the parameter's AST node, whereas previously it had no result.
+  - `Expr.flow()` now has a more meaningful result for destructuring patterns. Previously this node was disconnected from the data flow graph. Now it represents the values being destructured by the pattern.
+* The global data-flow and taint-tracking libraries now model indirect parameter accesses through the `arguments` object in some cases, which may lead to additional results from some of the security queries, particularly "Prototype pollution in utility function".
+* The predicates `Type.getProperty()` and variants of `Type.getMethod()` have been deprecated due to lack of use-cases. Looking up a named property of a static type is no longer supported, favoring faster extraction times instead.

change-notes/1.25/analysis-python.md

@@ -0,0 +1,9 @@
+# Improvements to Python analysis
+
+* Importing `semmle.python.web.HttpRequest` will no longer import `UntrustedStringKind` transitively. `UntrustedStringKind` is the most commonly used non-abstract subclass of `ExternalStringKind`. If not imported (by one mean or another), taint-tracking queries that concern `ExternalStringKind` will not produce any results. Please ensure such queries contain an explicit import (`import semmle.python.security.strings.Untrusted`).
+* Added model of taint sources for HTTP servers using `http.server`.
+* Added taint modeling of routed parameters in Flask.
+* Improved modeling of built-in methods on strings for taint tracking.
+* Improved classification of test files.
+* New class `BoundMethodValue` represents a bound method during runtime.
+* The query `py/command-line-injection` now recognizes command execution with the `fabric` and `invoke` Python libraries.

config/identical-files.json

@@ -1,5 +1,5 @@
 {
-  "DataFlow Java/C++/C#": [
+  "DataFlow Java/C++/C#/Python": [
     "java/ql/src/semmle/code/java/dataflow/internal/DataFlowImpl.qll",
     "java/ql/src/semmle/code/java/dataflow/internal/DataFlowImpl2.qll",
     "java/ql/src/semmle/code/java/dataflow/internal/DataFlowImpl3.qll",
@@ -18,15 +18,18 @@
     "csharp/ql/src/semmle/code/csharp/dataflow/internal/DataFlowImpl2.qll",
     "csharp/ql/src/semmle/code/csharp/dataflow/internal/DataFlowImpl3.qll",
     "csharp/ql/src/semmle/code/csharp/dataflow/internal/DataFlowImpl4.qll",
-    "csharp/ql/src/semmle/code/csharp/dataflow/internal/DataFlowImpl5.qll"
+    "csharp/ql/src/semmle/code/csharp/dataflow/internal/DataFlowImpl5.qll",
+    "python/ql/src/experimental/dataflow/internal/DataFlowImpl.qll",
+    "python/ql/src/experimental/dataflow/internal/DataFlowImpl2.qll"
   ],
-  "DataFlow Java/C++/C# Common": [
+  "DataFlow Java/C++/C#/Python Common": [
     "java/ql/src/semmle/code/java/dataflow/internal/DataFlowImplCommon.qll",
     "cpp/ql/src/semmle/code/cpp/dataflow/internal/DataFlowImplCommon.qll",
     "cpp/ql/src/semmle/code/cpp/ir/dataflow/internal/DataFlowImplCommon.qll",
-    "csharp/ql/src/semmle/code/csharp/dataflow/internal/DataFlowImplCommon.qll"
+    "csharp/ql/src/semmle/code/csharp/dataflow/internal/DataFlowImplCommon.qll",
+    "python/ql/src/experimental/dataflow/internal/DataFlowImplCommon.qll"
   ],
-  "TaintTracking::Configuration Java/C++/C#": [
+  "TaintTracking::Configuration Java/C++/C#/Python": [
     "cpp/ql/src/semmle/code/cpp/dataflow/internal/tainttracking1/TaintTrackingImpl.qll",
     "cpp/ql/src/semmle/code/cpp/dataflow/internal/tainttracking2/TaintTrackingImpl.qll",
     "cpp/ql/src/semmle/code/cpp/ir/dataflow/internal/tainttracking1/TaintTrackingImpl.qll",
@@ -37,13 +40,15 @@
     "csharp/ql/src/semmle/code/csharp/dataflow/internal/tainttracking4/TaintTrackingImpl.qll",
     "csharp/ql/src/semmle/code/csharp/dataflow/internal/tainttracking5/TaintTrackingImpl.qll",
     "java/ql/src/semmle/code/java/dataflow/internal/tainttracking1/TaintTrackingImpl.qll",
-    "java/ql/src/semmle/code/java/dataflow/internal/tainttracking2/TaintTrackingImpl.qll"
+    "java/ql/src/semmle/code/java/dataflow/internal/tainttracking2/TaintTrackingImpl.qll",
+    "python/ql/src/experimental/dataflow/internal/tainttracking1/TaintTrackingImpl.qll"
   ],
-  "DataFlow Java/C++/C# Consistency checks": [
+  "DataFlow Java/C++/C#/Python Consistency checks": [
     "java/ql/src/semmle/code/java/dataflow/internal/DataFlowImplConsistency.qll",
     "cpp/ql/src/semmle/code/cpp/dataflow/internal/DataFlowImplConsistency.qll",
     "cpp/ql/src/semmle/code/cpp/ir/dataflow/internal/DataFlowImplConsistency.qll",
-    "csharp/ql/src/semmle/code/csharp/dataflow/internal/DataFlowImplConsistency.qll"
+    "csharp/ql/src/semmle/code/csharp/dataflow/internal/DataFlowImplConsistency.qll",
+    "python/ql/src/experimental/dataflow/internal/DataFlowImplConsistency.qll"
   ],
   "C++ SubBasicBlocks": [
     "cpp/ql/src/semmle/code/cpp/controlflow/SubBasicBlocks.qll",
@@ -53,114 +58,122 @@
     "cpp/ql/src/semmle/code/cpp/ir/implementation/raw/Instruction.qll",
     "cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/Instruction.qll",
     "cpp/ql/src/semmle/code/cpp/ir/implementation/aliased_ssa/Instruction.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/raw/Instruction.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/Instruction.qll"
+    "csharp/ql/src/experimental/ir/implementation/raw/Instruction.qll",
+    "csharp/ql/src/experimental/ir/implementation/unaliased_ssa/Instruction.qll"
   ],
   "IR IRBlock": [
     "cpp/ql/src/semmle/code/cpp/ir/implementation/raw/IRBlock.qll",
     "cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/IRBlock.qll",
     "cpp/ql/src/semmle/code/cpp/ir/implementation/aliased_ssa/IRBlock.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/raw/IRBlock.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/IRBlock.qll"
+    "csharp/ql/src/experimental/ir/implementation/raw/IRBlock.qll",
+    "csharp/ql/src/experimental/ir/implementation/unaliased_ssa/IRBlock.qll"
   ],
   "IR IRVariable": [
     "cpp/ql/src/semmle/code/cpp/ir/implementation/raw/IRVariable.qll",
     "cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/IRVariable.qll",
     "cpp/ql/src/semmle/code/cpp/ir/implementation/aliased_ssa/IRVariable.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/raw/IRVariable.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/IRVariable.qll"
+    "csharp/ql/src/experimental/ir/implementation/raw/IRVariable.qll",
+    "csharp/ql/src/experimental/ir/implementation/unaliased_ssa/IRVariable.qll"
   ],
   "IR IRFunction": [
     "cpp/ql/src/semmle/code/cpp/ir/implementation/raw/IRFunction.qll",
     "cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/IRFunction.qll",
     "cpp/ql/src/semmle/code/cpp/ir/implementation/aliased_ssa/IRFunction.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/raw/IRFunction.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/IRFunction.qll"
+    "csharp/ql/src/experimental/ir/implementation/raw/IRFunction.qll",
+    "csharp/ql/src/experimental/ir/implementation/unaliased_ssa/IRFunction.qll"
   ],
   "IR Operand": [
     "cpp/ql/src/semmle/code/cpp/ir/implementation/raw/Operand.qll",
     "cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/Operand.qll",
     "cpp/ql/src/semmle/code/cpp/ir/implementation/aliased_ssa/Operand.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/raw/Operand.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/Operand.qll" 
+    "csharp/ql/src/experimental/ir/implementation/raw/Operand.qll",
+    "csharp/ql/src/experimental/ir/implementation/unaliased_ssa/Operand.qll" 
   ],
   "IR IRType": [
     "cpp/ql/src/semmle/code/cpp/ir/implementation/IRType.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/IRType.qll"
+    "csharp/ql/src/experimental/ir/implementation/IRType.qll"
   ],
   "IR IRConfiguration": [
     "cpp/ql/src/semmle/code/cpp/ir/implementation/IRConfiguration.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/IRConfiguration.qll"
+    "csharp/ql/src/experimental/ir/implementation/IRConfiguration.qll"
   ],
   "IR UseSoundEscapeAnalysis": [
     "cpp/ql/src/semmle/code/cpp/ir/implementation/UseSoundEscapeAnalysis.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/UseSoundEscapeAnalysis.qll"
+    "csharp/ql/src/experimental/ir/implementation/UseSoundEscapeAnalysis.qll"
+  ],
+  "IR IRFunctionBase": [
+    "cpp/ql/src/semmle/code/cpp/ir/implementation/internal/IRFunctionBase.qll",
+    "csharp/ql/src/experimental/ir/implementation/internal/IRFunctionBase.qll"
   ],
   "IR Operand Tag": [
     "cpp/ql/src/semmle/code/cpp/ir/implementation/internal/OperandTag.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/internal/OperandTag.qll"
+    "csharp/ql/src/experimental/ir/implementation/internal/OperandTag.qll"
+  ],
+  "IR TInstruction":[
+    "cpp/ql/src/semmle/code/cpp/ir/implementation/internal/TInstruction.qll",
+    "csharp/ql/src/experimental/ir/implementation/internal/TInstruction.qll"
   ],
   "IR TIRVariable":[
     "cpp/ql/src/semmle/code/cpp/ir/implementation/internal/TIRVariable.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/internal/TIRVariable.qll"
+    "csharp/ql/src/experimental/ir/implementation/internal/TIRVariable.qll"
   ],
   "IR IR": [
     "cpp/ql/src/semmle/code/cpp/ir/implementation/raw/IR.qll",
     "cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/IR.qll",
     "cpp/ql/src/semmle/code/cpp/ir/implementation/aliased_ssa/IR.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/raw/IR.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/IR.qll"
+    "csharp/ql/src/experimental/ir/implementation/raw/IR.qll",
+    "csharp/ql/src/experimental/ir/implementation/unaliased_ssa/IR.qll"
   ],
-  "IR IRSanity": [
-    "cpp/ql/src/semmle/code/cpp/ir/implementation/raw/IRSanity.qll",
-    "cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/IRSanity.qll",
-    "cpp/ql/src/semmle/code/cpp/ir/implementation/aliased_ssa/IRSanity.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/raw/IRSanity.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/IRSanity.qll"
+  "IR IRConsistency": [
+    "cpp/ql/src/semmle/code/cpp/ir/implementation/raw/IRConsistency.qll",
+    "cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/IRConsistency.qll",
+    "cpp/ql/src/semmle/code/cpp/ir/implementation/aliased_ssa/IRConsistency.qll",
+    "csharp/ql/src/experimental/ir/implementation/raw/IRConsistency.qll",
+    "csharp/ql/src/experimental/ir/implementation/unaliased_ssa/IRConsistency.qll"
   ],
   "IR PrintIR": [
     "cpp/ql/src/semmle/code/cpp/ir/implementation/raw/PrintIR.qll",
     "cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/PrintIR.qll",
     "cpp/ql/src/semmle/code/cpp/ir/implementation/aliased_ssa/PrintIR.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/raw/PrintIR.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/PrintIR.qll"
+    "csharp/ql/src/experimental/ir/implementation/raw/PrintIR.qll",
+    "csharp/ql/src/experimental/ir/implementation/unaliased_ssa/PrintIR.qll"
   ],
   "IR IntegerConstant": [
     "cpp/ql/src/semmle/code/cpp/ir/internal/IntegerConstant.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/internal/IntegerConstant.qll"
+    "csharp/ql/src/experimental/ir/internal/IntegerConstant.qll"
   ],
   "IR IntegerInteval": [
     "cpp/ql/src/semmle/code/cpp/ir/internal/IntegerInterval.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/internal/IntegerInterval.qll"
+    "csharp/ql/src/experimental/ir/internal/IntegerInterval.qll"
   ],
   "IR IntegerPartial": [
     "cpp/ql/src/semmle/code/cpp/ir/internal/IntegerPartial.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/internal/IntegerPartial.qll"
+    "csharp/ql/src/experimental/ir/internal/IntegerPartial.qll"
   ],
   "IR Overlap": [
     "cpp/ql/src/semmle/code/cpp/ir/internal/Overlap.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/internal/Overlap.qll"
+    "csharp/ql/src/experimental/ir/internal/Overlap.qll"
   ],
   "IR EdgeKind": [
     "cpp/ql/src/semmle/code/cpp/ir/implementation/EdgeKind.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/EdgeKind.qll"
+    "csharp/ql/src/experimental/ir/implementation/EdgeKind.qll"
   ],
   "IR MemoryAccessKind": [
     "cpp/ql/src/semmle/code/cpp/ir/implementation/MemoryAccessKind.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/MemoryAccessKind.qll"
+    "csharp/ql/src/experimental/ir/implementation/MemoryAccessKind.qll"
   ],
   "IR TempVariableTag": [
     "cpp/ql/src/semmle/code/cpp/ir/implementation/TempVariableTag.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/TempVariableTag.qll"
+    "csharp/ql/src/experimental/ir/implementation/TempVariableTag.qll"
   ],
   "IR Opcode": [
     "cpp/ql/src/semmle/code/cpp/ir/implementation/Opcode.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/Opcode.qll"
+    "csharp/ql/src/experimental/ir/implementation/Opcode.qll"
   ],
-  "IR SSASanity": [
-    "cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/internal/SSASanity.qll",
-    "cpp/ql/src/semmle/code/cpp/ir/implementation/aliased_ssa/internal/SSASanity.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/internal/SSASanity.qll"
+  "IR SSAConsistency": [
+    "cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/internal/SSAConsistency.qll",
+    "cpp/ql/src/semmle/code/cpp/ir/implementation/aliased_ssa/internal/SSAConsistency.qll",
+    "csharp/ql/src/experimental/ir/implementation/unaliased_ssa/internal/SSAConsistency.qll"
   ],
   "C++ IR InstructionImports": [
     "cpp/ql/src/semmle/code/cpp/ir/implementation/raw/internal/InstructionImports.qll",
@@ -177,6 +190,11 @@
     "cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/internal/IRBlockImports.qll",
     "cpp/ql/src/semmle/code/cpp/ir/implementation/aliased_ssa/internal/IRBlockImports.qll"
   ],
+  "C++ IR IRFunctionImports": [
+    "cpp/ql/src/semmle/code/cpp/ir/implementation/raw/internal/IRFunctionImports.qll",
+    "cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/internal/IRFunctionImports.qll",
+    "cpp/ql/src/semmle/code/cpp/ir/implementation/aliased_ssa/internal/IRFunctionImports.qll"
+  ],
   "C++ IR IRVariableImports": [
     "cpp/ql/src/semmle/code/cpp/ir/implementation/raw/internal/IRVariableImports.qll",
     "cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/internal/IRVariableImports.qll",
@@ -199,7 +217,7 @@
   "SSA AliasAnalysis": [
     "cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/internal/AliasAnalysis.qll",
     "cpp/ql/src/semmle/code/cpp/ir/implementation/aliased_ssa/internal/AliasAnalysis.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/internal/AliasAnalysis.qll"
+    "csharp/ql/src/experimental/ir/implementation/unaliased_ssa/internal/AliasAnalysis.qll"
   ],
   "C++ SSA AliasAnalysisImports": [
     "cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/internal/AliasAnalysisImports.qll",
@@ -212,42 +230,42 @@
   ],
   "IR SSA SimpleSSA": [
     "cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/internal/SimpleSSA.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/internal/SimpleSSA.qll"
+    "csharp/ql/src/experimental/ir/implementation/unaliased_ssa/internal/SimpleSSA.qll"
   ],
   "IR AliasConfiguration (unaliased_ssa)": [
     "cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/internal/AliasConfiguration.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/internal/AliasConfiguration.qll"
+    "csharp/ql/src/experimental/ir/implementation/unaliased_ssa/internal/AliasConfiguration.qll"
   ],
   "IR SSA SSAConstruction": [
     "cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/internal/SSAConstruction.qll",
     "cpp/ql/src/semmle/code/cpp/ir/implementation/aliased_ssa/internal/SSAConstruction.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/internal/SSAConstruction.qll"
+    "csharp/ql/src/experimental/ir/implementation/unaliased_ssa/internal/SSAConstruction.qll"
   ],
   "IR SSA PrintSSA": [
     "cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/internal/PrintSSA.qll",
     "cpp/ql/src/semmle/code/cpp/ir/implementation/aliased_ssa/internal/PrintSSA.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/internal/PrintSSA.qll"
+    "csharp/ql/src/experimental/ir/implementation/unaliased_ssa/internal/PrintSSA.qll"
   ],
   "IR ValueNumberInternal": [
     "cpp/ql/src/semmle/code/cpp/ir/implementation/raw/gvn/internal/ValueNumberingInternal.qll",
     "cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/gvn/internal/ValueNumberingInternal.qll",
     "cpp/ql/src/semmle/code/cpp/ir/implementation/aliased_ssa/gvn/internal/ValueNumberingInternal.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/raw/gvn/internal/ValueNumberingInternal.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/gvn/internal/ValueNumberingInternal.qll"
+    "csharp/ql/src/experimental/ir/implementation/raw/gvn/internal/ValueNumberingInternal.qll",
+    "csharp/ql/src/experimental/ir/implementation/unaliased_ssa/gvn/internal/ValueNumberingInternal.qll"
   ],
   "C++ IR ValueNumber": [
     "cpp/ql/src/semmle/code/cpp/ir/implementation/raw/gvn/ValueNumbering.qll",
     "cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/gvn/ValueNumbering.qll",
     "cpp/ql/src/semmle/code/cpp/ir/implementation/aliased_ssa/gvn/ValueNumbering.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/raw/gvn/ValueNumbering.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/gvn/ValueNumbering.qll"
+    "csharp/ql/src/experimental/ir/implementation/raw/gvn/ValueNumbering.qll",
+    "csharp/ql/src/experimental/ir/implementation/unaliased_ssa/gvn/ValueNumbering.qll"
   ],
   "C++ IR PrintValueNumbering": [
     "cpp/ql/src/semmle/code/cpp/ir/implementation/raw/gvn/PrintValueNumbering.qll",
     "cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/gvn/PrintValueNumbering.qll",
     "cpp/ql/src/semmle/code/cpp/ir/implementation/aliased_ssa/gvn/PrintValueNumbering.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/raw/gvn/PrintValueNumbering.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/gvn/PrintValueNumbering.qll"
+    "csharp/ql/src/experimental/ir/implementation/raw/gvn/PrintValueNumbering.qll",
+    "csharp/ql/src/experimental/ir/implementation/unaliased_ssa/gvn/PrintValueNumbering.qll"
   ],
   "C++ IR ConstantAnalysis": [
     "cpp/ql/src/semmle/code/cpp/ir/implementation/raw/constant/ConstantAnalysis.qll",
@@ -276,32 +294,36 @@
     "cpp/ql/src/semmle/code/cpp/ir/implementation/unaliased_ssa/internal/reachability/PrintDominance.qll"
   ],
   "C# IR InstructionImports": [
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/raw/internal/InstructionImports.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/internal/InstructionImports.qll"
+    "csharp/ql/src/experimental/ir/implementation/raw/internal/InstructionImports.qll",
+    "csharp/ql/src/experimental/ir/implementation/unaliased_ssa/internal/InstructionImports.qll"
   ],
   "C# IR IRImports": [
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/raw/internal/IRImports.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/internal/IRImports.qll"
+    "csharp/ql/src/experimental/ir/implementation/raw/internal/IRImports.qll",
+    "csharp/ql/src/experimental/ir/implementation/unaliased_ssa/internal/IRImports.qll"
   ],
   "C# IR IRBlockImports": [
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/raw/internal/IRBlockImports.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/internal/IRBlockImports.qll"
+    "csharp/ql/src/experimental/ir/implementation/raw/internal/IRBlockImports.qll",
+    "csharp/ql/src/experimental/ir/implementation/unaliased_ssa/internal/IRBlockImports.qll"
+  ],
+  "C# IR IRFunctionImports": [
+    "csharp/ql/src/experimental/ir/implementation/raw/internal/IRFunctionImports.qll",
+    "csharp/ql/src/experimental/ir/implementation/unaliased_ssa/internal/IRFunctionImports.qll"
   ],
   "C# IR IRVariableImports": [
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/raw/internal/IRVariableImports.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/internal/IRVariableImports.qll"
+    "csharp/ql/src/experimental/ir/implementation/raw/internal/IRVariableImports.qll",
+    "csharp/ql/src/experimental/ir/implementation/unaliased_ssa/internal/IRVariableImports.qll"
   ],
   "C# IR OperandImports": [
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/raw/internal/OperandImports.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/internal/OperandImports.qll"
+    "csharp/ql/src/experimental/ir/implementation/raw/internal/OperandImports.qll",
+    "csharp/ql/src/experimental/ir/implementation/unaliased_ssa/internal/OperandImports.qll"
   ],
   "C# IR PrintIRImports": [
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/raw/internal/PrintIRImports.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/internal/PrintIRImports.qll"
+    "csharp/ql/src/experimental/ir/implementation/raw/internal/PrintIRImports.qll",
+    "csharp/ql/src/experimental/ir/implementation/unaliased_ssa/internal/PrintIRImports.qll"
   ],
   "C# IR ValueNumberingImports": [
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/raw/gvn/internal/ValueNumberingImports.qll",
-    "csharp/ql/src/semmle/code/csharp/ir/implementation/unaliased_ssa/gvn/internal/ValueNumberingImports.qll"
+    "csharp/ql/src/experimental/ir/implementation/raw/gvn/internal/ValueNumberingImports.qll",
+    "csharp/ql/src/experimental/ir/implementation/unaliased_ssa/gvn/internal/ValueNumberingImports.qll"
   ],
   "XML": [
     "cpp/ql/src/semmle/code/cpp/XML.qll",

config/opcode-qldoc.py

@@ -0,0 +1,102 @@
+#!/usr/bin/env python3
+
+import os
+import re
+path = os.path
+
+needs_an_re = re.compile(r'^(?!Unary)[AEIOU]')  # Name requiring "an" instead of "a".
+start_qldoc_re = re.compile(r'^\s*/\*\*')  # Start of a QLDoc comment
+end_qldoc_re = re.compile(r'\*/\s*$')  # End of a QLDoc comment
+blank_qldoc_line_re = re.compile(r'^\s*\*\s*$')  # A line in a QLDoc comment with only the '*'
+instruction_class_re = re.compile(r'^class (?P<name>[A-aa-z0-9]+)Instruction\s')  # Declaration of an `Instruction` class
+opcode_base_class_re = re.compile(r'^abstract class (?P<name>[A-aa-z0-9]+)Opcode\s')  # Declaration of an `Opcode` base class
+opcode_class_re = re.compile(r'^  class (?P<name>[A-aa-z0-9]+)\s')  # Declaration of an `Opcode` class
+
+script_dir = path.realpath(path.dirname(__file__))
+instruction_path = path.realpath(path.join(script_dir, '../cpp/ql/src/semmle/code/cpp/ir/implementation/raw/Instruction.qll'))
+opcode_path = path.realpath(path.join(script_dir, '../cpp/ql/src/semmle/code/cpp/ir/implementation/Opcode.qll'))
+
+# Scan `Instruction.qll`, keeping track of the QLDoc comment attached to each declaration of a class
+# whose name ends with `Instruction`.
+instruction_comments = {}
+in_qldoc = False
+saw_blank_line_in_qldoc = False
+qldoc_lines = []
+with open(instruction_path, 'r', encoding='utf-8') as instr:
+    for line in instr:
+        if in_qldoc:
+            if end_qldoc_re.search(line):
+                qldoc_lines.append(line)
+                in_qldoc = False
+            elif blank_qldoc_line_re.search(line):
+                # We're going to skip any lines after the first blank line, to avoid duplicating all
+                # of the verbose description.
+                saw_blank_line_in_qldoc = True
+            elif not saw_blank_line_in_qldoc:
+                qldoc_lines.append(line)
+        else:
+            if start_qldoc_re.search(line):
+                # Starting a new QLDoc comment.
+                saw_blank_line_in_qldoc = False
+                qldoc_lines.append(line)
+                if not end_qldoc_re.search(line):
+                    in_qldoc = True
+            else:
+                instruction_match = instruction_class_re.search(line)
+                if instruction_match:
+                    # Found the declaration of an `Instruction` class. Record the QLDoc comments.
+                    instruction_comments[instruction_match.group('name')] = qldoc_lines
+                qldoc_lines = []
+
+# Scan `Opcode.qll`. Whenever we see the declaration of an `Opcode` class for which we have a
+# corresponding `Instruction` class, we'll attach a copy of the `Instruction`'s QLDoc comment.
+in_qldoc = False
+qldoc_lines = []
+output_lines = []
+with open(opcode_path, 'r', encoding='utf-8') as opcode:
+    for line in opcode:
+        if in_qldoc:
+            qldoc_lines.append(line)
+            if end_qldoc_re.search(line):
+                in_qldoc = False
+        else:
+            if start_qldoc_re.search(line):
+                qldoc_lines.append(line)
+                if not end_qldoc_re.search(line):
+                    in_qldoc = True
+            else:
+                name_without_suffix = None
+                name = None
+                indent = ''
+                opcode_base_match = opcode_base_class_re.search(line)
+                if opcode_base_match:
+                    name_without_suffix = opcode_base_match.group('name')
+                    name = name_without_suffix + 'Opcode'
+                else:
+                    opcode_match = opcode_class_re.search(line)
+                    if opcode_match:
+                        name_without_suffix = opcode_match.group('name')
+                        name = name_without_suffix
+                        # Indent by two additional spaces, since opcodes are declared in the
+                        # `Opcode` module.
+                        indent = '  '
+                
+                if name_without_suffix:
+                    # Found an `Opcode` that matches a known `Instruction`. Replace the QLDoc with
+                    # a copy of the one from the `Instruction`.
+                    if instruction_comments.get(name_without_suffix):
+                        article = 'an' if needs_an_re.search(name_without_suffix) else 'a'
+                        qldoc_lines = [
+                            indent + '/**\n',
+                            indent + ' * The `Opcode` for ' + article + ' `' + name_without_suffix + 'Instruction`.\n',
+                            indent + ' *\n',
+                            indent + ' * See the `' + name_without_suffix + 'Instruction` documentation for more details.\n',
+                            indent + ' */\n'
+                        ]
+                output_lines.extend(qldoc_lines)
+                qldoc_lines = []
+                output_lines.append(line)
+
+# Write out the updated `Opcode.qll`
+with open(opcode_path, 'w', encoding='utf-8') as opcode:
+    opcode.writelines(output_lines)

config/sync-files.py

@@ -59,21 +59,32 @@ def file_checksum(filename):
         return hashlib.sha1(file_handle.read()).hexdigest()
 
 def check_group(group_name, files, master_file_picker, emit_error):
-    checksums = {file_checksum(f) for f in files}
-
-    if len(checksums) == 1:
+    extant_files = [f for f in files if path.isfile(f)]
+    if len(extant_files) == 0:
+        emit_error(__file__, 0, "No files found from group '" + group_name + "'.")
+        emit_error(__file__, 0,
+                "Create one of the following files, and then run this script with "
+                "the --latest switch to sync it to the other file locations.")
+        for filename in files:
+            emit_error(__file__, 0, "    " + filename)
         return
 
-    master_file = master_file_picker(files)
+    checksums = {file_checksum(f) for f in extant_files}
+
+    if len(checksums) == 1 and len(extant_files) == len(files):
+        # All files are present and identical.
+        return
+
+    master_file = master_file_picker(extant_files)
     if master_file is None:
         emit_error(__file__, 0,
                 "Files from group '"+ group_name +"' not in sync.")
         emit_error(__file__, 0,
                 "Run this script with a file-name argument among the "
                 "following to overwrite the remaining files with the contents "
-                "of that file or run with the --latest switch to update each "
+                "of that file, or run with the --latest switch to update each "
                 "group of files from the most recently modified file in the group.")
-        for filename in files:
+        for filename in extant_files:
             emit_error(__file__, 0, "    " + filename)
     else:
         print("  Syncing others from", master_file)
@@ -81,7 +92,8 @@ def check_group(group_name, files, master_file_picker, emit_error):
             if filename == master_file:
                 continue
             print("    " + filename)
-            os.replace(filename, filename + '~')
+            if path.isfile(filename):
+                os.replace(filename, filename + '~')
             shutil.copy(master_file, filename)
         print("  Backups written with '~' appended to file names")
 
@@ -107,7 +119,7 @@ def choose_latest_file(files):
 
 local_error_count = 0
 def emit_local_error(path, line, error):
-    print('ERROR: ' + path + ':' + line + " - " + error)
+    print('ERROR: ' + path + ':' + str(line) + " - " + error)
     global local_error_count
     local_error_count += 1
 

cpp/autobuilder/.gitignore

@@ -0,0 +1,13 @@
+obj/
+TestResults/
+*.manifest
+*.pdb
+*.suo
+*.mdb
+*.vsmdi
+csharp.log
+**/bin/Debug
+**/bin/Release
+*.tlog
+.vs
+*.user

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

@@ -0,0 +1,296 @@
+using Xunit;
+using Semmle.Autobuild.Shared;
+using System.Collections.Generic;
+using System;
+using System.Linq;
+using Microsoft.Build.Construction;
+using System.Xml;
+
+namespace Semmle.Autobuild.Cpp.Tests
+{
+    /// <summary>
+    /// Test class to script Autobuilder scenarios.
+    /// For most methods, it uses two fields:
+    /// - an IList to capture the the arguments passed to it
+    /// - an IDictionary of possible return values.
+    /// </summary>
+    class TestActions : IBuildActions
+    {
+        /// <summary>
+        /// List of strings passed to FileDelete.
+        /// </summary>
+        public IList<string> FileDeleteIn = new List<string>();
+
+        void IBuildActions.FileDelete(string file)
+        {
+            FileDeleteIn.Add(file);
+        }
+
+        public IList<string> FileExistsIn = new List<string>();
+        public IDictionary<string, bool> FileExists = new Dictionary<string, bool>();
+
+        bool IBuildActions.FileExists(string file)
+        {
+            FileExistsIn.Add(file);
+            if (FileExists.TryGetValue(file, out var ret))
+                return ret;
+            if (FileExists.TryGetValue(System.IO.Path.GetFileName(file), out ret))
+                return ret;
+            throw new ArgumentException("Missing FileExists " + file);
+        }
+
+        public IList<string> RunProcessIn = new List<string>();
+        public IDictionary<string, int> RunProcess = new Dictionary<string, int>();
+        public IDictionary<string, string> RunProcessOut = new Dictionary<string, string>();
+        public IDictionary<string, string> RunProcessWorkingDirectory = new Dictionary<string, string>();
+
+        int IBuildActions.RunProcess(string cmd, string args, string? workingDirectory, IDictionary<string, string>? env, out IList<string> stdOut)
+        {
+            var pattern = cmd + " " + args;
+            RunProcessIn.Add(pattern);
+            if (RunProcessOut.TryGetValue(pattern, out var str))
+                stdOut = str.Split("\n");
+            else
+                throw new ArgumentException("Missing RunProcessOut " + pattern);
+            RunProcessWorkingDirectory.TryGetValue(pattern, out var wd);
+            if (wd != workingDirectory)
+                throw new ArgumentException("Missing RunProcessWorkingDirectory " + pattern);
+            if (RunProcess.TryGetValue(pattern, out var ret))
+                return ret;
+            throw new ArgumentException("Missing RunProcess " + pattern);
+        }
+
+        int IBuildActions.RunProcess(string cmd, string args, string? workingDirectory, IDictionary<string, string>? env)
+        {
+            var pattern = cmd + " " + args;
+            RunProcessIn.Add(pattern);
+            RunProcessWorkingDirectory.TryGetValue(pattern, out var wd);
+            if (wd != workingDirectory)
+                throw new ArgumentException("Missing RunProcessWorkingDirectory " + pattern);
+            if (RunProcess.TryGetValue(pattern, out var ret))
+                return ret;
+            throw new ArgumentException("Missing RunProcess " + pattern);
+        }
+
+        public IList<string> DirectoryDeleteIn = new List<string>();
+
+        void IBuildActions.DirectoryDelete(string dir, bool recursive)
+        {
+            DirectoryDeleteIn.Add(dir);
+        }
+
+        public IDictionary<string, bool> DirectoryExists = new Dictionary<string, bool>();
+        public IList<string> DirectoryExistsIn = new List<string>();
+
+        bool IBuildActions.DirectoryExists(string dir)
+        {
+            DirectoryExistsIn.Add(dir);
+            if (DirectoryExists.TryGetValue(dir, out var ret))
+                return ret;
+            throw new ArgumentException("Missing DirectoryExists " + dir);
+        }
+
+        public IDictionary<string, string?> GetEnvironmentVariable = new Dictionary<string, string?>();
+
+        string? IBuildActions.GetEnvironmentVariable(string name)
+        {
+            if (GetEnvironmentVariable.TryGetValue(name, out var ret))
+                return ret;
+            throw new ArgumentException("Missing GetEnvironmentVariable " + name);
+        }
+
+        public string GetCurrentDirectory = "";
+
+        string IBuildActions.GetCurrentDirectory()
+        {
+            return GetCurrentDirectory;
+        }
+
+        public IDictionary<string, string> EnumerateFiles = new Dictionary<string, string>();
+
+        IEnumerable<string> IBuildActions.EnumerateFiles(string dir)
+        {
+            if (EnumerateFiles.TryGetValue(dir, out var str))
+                return str.Split("\n");
+            throw new ArgumentException("Missing EnumerateFiles " + dir);
+        }
+
+        public IDictionary<string, string> EnumerateDirectories = new Dictionary<string, string>();
+
+        IEnumerable<string> IBuildActions.EnumerateDirectories(string dir)
+        {
+            if (EnumerateDirectories.TryGetValue(dir, out var str))
+                return string.IsNullOrEmpty(str) ? Enumerable.Empty<string>() : str.Split("\n");
+            throw new ArgumentException("Missing EnumerateDirectories " + dir);
+        }
+
+        public bool IsWindows;
+
+        bool IBuildActions.IsWindows() => IsWindows;
+
+        string IBuildActions.PathCombine(params string[] parts)
+        {
+            return string.Join(IsWindows ? '\\' : '/', parts.Where(p => !string.IsNullOrWhiteSpace(p)));
+        }
+
+        string IBuildActions.GetFullPath(string path) => path;
+
+        void IBuildActions.WriteAllText(string filename, string contents)
+        {
+        }
+
+        public IDictionary<string, XmlDocument> LoadXml = new Dictionary<string, XmlDocument>();
+        XmlDocument IBuildActions.LoadXml(string filename)
+        {
+            if (LoadXml.TryGetValue(filename, out var xml))
+                return xml;
+            throw new ArgumentException("Missing LoadXml " + filename);
+        }
+
+        public string EnvironmentExpandEnvironmentVariables(string s)
+        {
+            foreach (var kvp in GetEnvironmentVariable)
+                s = s.Replace($"%{kvp.Key}%", kvp.Value);
+            return s;
+        }
+    }
+
+    /// <summary>
+    /// A fake solution to build.
+    /// </summary>
+    class TestSolution : ISolution
+    {
+        public IEnumerable<SolutionConfigurationInSolution> Configurations => throw new NotImplementedException();
+
+        public string DefaultConfigurationName => "Release";
+
+        public string DefaultPlatformName => "x86";
+
+        public string FullPath { get; set; }
+
+        public Version ToolsVersion => new Version("14.0");
+
+        public IEnumerable<IProjectOrSolution> IncludedProjects => throw new NotImplementedException();
+
+        public TestSolution(string path)
+        {
+            FullPath = path;
+        }
+    }
+
+    public class BuildScriptTests
+    {
+        TestActions Actions = new TestActions();
+
+        // Records the arguments passed to StartCallback.
+        IList<string> StartCallbackIn = new List<string>();
+
+        void StartCallback(string s, bool silent)
+        {
+            StartCallbackIn.Add(s);
+        }
+
+        // Records the arguments passed to EndCallback
+        IList<string> EndCallbackIn = new List<string>();
+        IList<int> EndCallbackReturn = new List<int>();
+
+        void EndCallback(int ret, string s, bool silent)
+        {
+            EndCallbackReturn.Add(ret);
+            EndCallbackIn.Add(s);
+        }
+
+        CppAutobuilder CreateAutoBuilder(bool isWindows,
+            string? buildless = null, string? solution = null, string? buildCommand = null, string? ignoreErrors = null,
+            string? msBuildArguments = null, string? msBuildPlatform = null, string? msBuildConfiguration = null, string? msBuildTarget = null,
+            string? dotnetArguments = null, string? dotnetVersion = null, string? vsToolsVersion = null,
+            string? nugetRestore = null, string? allSolutions = null,
+            string cwd = @"C:\Project")
+        {
+            string codeqlUpperLanguage = Language.Cpp.UpperCaseName;
+            Actions.GetEnvironmentVariable[$"CODEQL_AUTOBUILDER_{codeqlUpperLanguage}_NO_INDEXING"] = "false";
+            Actions.GetEnvironmentVariable[$"CODEQL_EXTRACTOR_{codeqlUpperLanguage}_TRAP_DIR"] = "";
+            Actions.GetEnvironmentVariable[$"CODEQL_EXTRACTOR_{codeqlUpperLanguage}_SOURCE_ARCHIVE_DIR"] = "";
+            Actions.GetEnvironmentVariable[$"CODEQL_EXTRACTOR_{codeqlUpperLanguage}_ROOT"] = $@"C:\codeql\{codeqlUpperLanguage.ToLowerInvariant()}";
+            Actions.GetEnvironmentVariable["CODEQL_JAVA_HOME"] = @"C:\codeql\tools\java";
+            Actions.GetEnvironmentVariable["SEMMLE_DIST"] = @"C:\odasa";
+            Actions.GetEnvironmentVariable["SEMMLE_JAVA_HOME"] = @"C:\odasa\tools\java";
+            Actions.GetEnvironmentVariable["SEMMLE_PLATFORM_TOOLS"] = @"C:\odasa\tools";
+            Actions.GetEnvironmentVariable["LGTM_INDEX_VSTOOLS_VERSION"] = vsToolsVersion;
+            Actions.GetEnvironmentVariable["LGTM_INDEX_MSBUILD_ARGUMENTS"] = msBuildArguments;
+            Actions.GetEnvironmentVariable["LGTM_INDEX_MSBUILD_PLATFORM"] = msBuildPlatform;
+            Actions.GetEnvironmentVariable["LGTM_INDEX_MSBUILD_CONFIGURATION"] = msBuildConfiguration;
+            Actions.GetEnvironmentVariable["LGTM_INDEX_MSBUILD_TARGET"] = msBuildTarget;
+            Actions.GetEnvironmentVariable["LGTM_INDEX_DOTNET_ARGUMENTS"] = dotnetArguments;
+            Actions.GetEnvironmentVariable["LGTM_INDEX_DOTNET_VERSION"] = dotnetVersion;
+            Actions.GetEnvironmentVariable["LGTM_INDEX_BUILD_COMMAND"] = buildCommand;
+            Actions.GetEnvironmentVariable["LGTM_INDEX_SOLUTION"] = solution;
+            Actions.GetEnvironmentVariable["LGTM_INDEX_IGNORE_ERRORS"] = ignoreErrors;
+            Actions.GetEnvironmentVariable["LGTM_INDEX_BUILDLESS"] = buildless;
+            Actions.GetEnvironmentVariable["LGTM_INDEX_ALL_SOLUTIONS"] = allSolutions;
+            Actions.GetEnvironmentVariable["LGTM_INDEX_NUGET_RESTORE"] = nugetRestore;
+            Actions.GetEnvironmentVariable["ProgramFiles(x86)"] = isWindows ? @"C:\Program Files (x86)" : null;
+            Actions.GetCurrentDirectory = cwd;
+            Actions.IsWindows = isWindows;
+
+            var options = new AutobuildOptions(Actions, Language.Cpp);
+            return new CppAutobuilder(Actions, options);
+        }
+
+        void TestAutobuilderScript(Autobuilder autobuilder, int expectedOutput, int commandsRun)
+        {
+            Assert.Equal(expectedOutput, autobuilder.GetBuildScript().Run(Actions, StartCallback, EndCallback));
+
+            // Check expected commands actually ran
+            Assert.Equal(commandsRun, StartCallbackIn.Count);
+            Assert.Equal(commandsRun, EndCallbackIn.Count);
+            Assert.Equal(commandsRun, EndCallbackReturn.Count);
+
+            var action = Actions.RunProcess.GetEnumerator();
+            for (int cmd = 0; cmd < commandsRun; ++cmd)
+            {
+                Assert.True(action.MoveNext());
+
+                Assert.Equal(action.Current.Key, StartCallbackIn[cmd]);
+                Assert.Equal(action.Current.Value, EndCallbackReturn[cmd]);
+            }
+        }
+
+
+        [Fact]
+        public void TestDefaultCppAutobuilder()
+        {
+            Actions.EnumerateFiles[@"C:\Project"] = "";
+            Actions.EnumerateDirectories[@"C:\Project"] = "";
+
+            var autobuilder = CreateAutoBuilder(true);
+            var script = autobuilder.GetBuildScript();
+
+            // Fails due to no solutions present.
+            Assert.NotEqual(0, script.Run(Actions, StartCallback, EndCallback));
+        }
+
+        [Fact]
+        public void TestCppAutobuilderSuccess()
+        {
+            Actions.RunProcess[@"cmd.exe /C C:\odasa\tools\csharp\nuget\nuget.exe restore C:\Project\test.sln"] = 1;
+            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 /p:UseSharedCompilation=false /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;
+            Actions.RunProcessOut[@"C:\Program Files (x86)\Microsoft Visual Studio\Installer\vswhere.exe -prerelease -legacy -property installationVersion"] = "";
+            Actions.FileExists[@"C:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\vcvarsall.bat"] = true;
+            Actions.FileExists[@"C:\Program Files (x86)\Microsoft Visual Studio 12.0\VC\vcvarsall.bat"] = true;
+            Actions.FileExists[@"C:\Program Files (x86)\Microsoft Visual Studio 11.0\VC\vcvarsall.bat"] = true;
+            Actions.FileExists[@"C:\Program Files (x86)\Microsoft Visual Studio 10.0\VC\vcvarsall.bat"] = true;
+            Actions.FileExists[@"C:\Program Files (x86)\Microsoft Visual Studio\Installer\vswhere.exe"] = true;
+            Actions.EnumerateFiles[@"C:\Project"] = "foo.cs\ntest.slx";
+            Actions.EnumerateDirectories[@"C:\Project"] = "";
+
+            var autobuilder = CreateAutoBuilder(true);
+            var solution = new TestSolution(@"C:\Project\test.sln");
+            autobuilder.ProjectsOrSolutionsToBuild.Add(solution);
+            TestAutobuilderScript(autobuilder, 0, 2);
+        }
+    }
+}

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

@@ -0,0 +1,25 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <OutputType>Exe</OutputType>
+    <TargetFramework>netcoreapp3.0</TargetFramework>
+    <GenerateAssemblyInfo>false</GenerateAssemblyInfo>
+    <RuntimeIdentifiers>win-x64;linux-x64;osx-x64</RuntimeIdentifiers>
+    <Nullable>enable</Nullable>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <PackageReference Include="System.IO.FileSystem" Version="4.3.0" />
+    <PackageReference Include="System.IO.FileSystem.Primitives" Version="4.3.0" />
+    <PackageReference Include="xunit" Version="2.4.1" />
+    <PackageReference Include="xunit.runner.visualstudio" Version="2.4.1">
+      <PrivateAssets>all</PrivateAssets>
+      <IncludeAssets>runtime; build; native; contentfiles; analyzers</IncludeAssets>
+    </PackageReference>
+  </ItemGroup>
+
+  <ItemGroup>
+    <ProjectReference Include="..\Semmle.Autobuild.Cpp\Semmle.Autobuild.Cpp.csproj" />
+    <ProjectReference Include="..\..\..\csharp\autobuilder\Semmle.Autobuild.Shared\Semmle.Autobuild.Shared.csproj" />
+  </ItemGroup>
+</Project>

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

@@ -0,0 +1,23 @@
+using Semmle.Autobuild.Shared;
+
+namespace Semmle.Autobuild.Cpp
+{
+    public class CppAutobuilder : Autobuilder
+    {
+        public CppAutobuilder(IBuildActions actions, AutobuildOptions options) : base(actions, options) { }
+
+        public override BuildScript GetBuildScript()
+        {
+            if (Options.BuildCommand != null)
+                return new BuildCommandRule((_, f) => f(null)).Analyse(this, false);
+
+            return
+                // First try MSBuild
+                new MsBuildRule().Analyse(this, true) |
+                // Then look for a script that might be a build script
+                (() => new BuildCommandAutoRule((_, f) => f(null)).Analyse(this, true)) |
+                // All attempts failed: print message
+                AutobuildFailure();
+        }
+    }
+}

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

@@ -1,6 +1,7 @@
 using System;
+using Semmle.Autobuild.Shared;
 
-namespace Semmle.Autobuild
+namespace Semmle.Autobuild.Cpp
 {
     class Program
     {
@@ -10,11 +11,11 @@ namespace Semmle.Autobuild
             try
             {
                 var actions = SystemBuildActions.Instance;
-                var options = new AutobuildOptions(actions);
+                var options = new AutobuildOptions(actions, Language.Cpp);
                 try
                 {
-                    Console.WriteLine($"Semmle autobuilder for {options.Language}");
-                    var builder = new Autobuilder(actions, options);
+                    Console.WriteLine("CodeQL C++ autobuilder");
+                    var builder = new CppAutobuilder(actions, options);
                     return builder.AttemptBuild();
                 }
                 catch(InvalidEnvironmentException ex)

cpp/autobuilder/Semmle.Autobuild.Cpp/Properties/AssemblyInfo.cs

@@ -4,12 +4,12 @@ using System.Runtime.InteropServices;
 // General Information about an assembly is controlled through the following
 // set of attributes. Change these attribute values to modify the information
 // associated with an assembly.
-[assembly: AssemblyTitle("Semmle.Autobuild.Tests")]
+[assembly: AssemblyTitle("Semmle.Autobuild.Cpp")]
 [assembly: AssemblyDescription("")]
 [assembly: AssemblyConfiguration("")]
-[assembly: AssemblyCompany("")]
-[assembly: AssemblyProduct("Semmle.Extraction.Tests")]
-[assembly: AssemblyCopyright("Copyright ©  2018")]
+[assembly: AssemblyCompany("GitHub")]
+[assembly: AssemblyProduct("CodeQL autobuilder for C++")]
+[assembly: AssemblyCopyright("Copyright © GitHub 2020")]
 [assembly: AssemblyTrademark("")]
 [assembly: AssemblyCulture("")]
 

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

@@ -0,0 +1,28 @@
+<Project Sdk="Microsoft.NET.Sdk">
+
+  <PropertyGroup>
+    <TargetFramework>netcoreapp3.0</TargetFramework>
+    <AssemblyName>Semmle.Autobuild.Cpp</AssemblyName>
+    <RootNamespace>Semmle.Autobuild.Cpp</RootNamespace>
+    <ApplicationIcon />
+    <OutputType>Exe</OutputType>
+    <StartupObject />
+    <GenerateAssemblyInfo>false</GenerateAssemblyInfo>
+    <RuntimeIdentifiers>win-x64;linux-x64;osx-x64</RuntimeIdentifiers>
+    <Nullable>enable</Nullable>
+  </PropertyGroup>
+
+  <ItemGroup>
+    <Folder Include="Properties\" />
+  </ItemGroup>
+
+  <ItemGroup>
+    <PackageReference Include="Microsoft.Build" Version="16.0.461" />
+  </ItemGroup>
+
+  <ItemGroup>
+    <ProjectReference Include="..\..\..\csharp\extractor\Semmle.Util\Semmle.Util.csproj" />
+    <ProjectReference Include="..\..\..\csharp\autobuilder\Semmle.Autobuild.Shared\Semmle.Autobuild.Shared.csproj" />
+  </ItemGroup>
+
+</Project>

cpp/ql/examples/qlpack.yml

@@ -0,0 +1,3 @@
+name: codeql-cpp-examples
+version: 0.0.0
+libraryPathDependencies: codeql-cpp

cpp/ql/src/Critical/FileClosed.qll

@@ -1,5 +1,6 @@
 import semmle.code.cpp.pointsto.PointsTo
 
+/** Holds if there exists a call to a function that might close the file specified by `e`. */
 predicate closed(Expr e) {
   fcloseCall(_, e) or
   exists(ExprCall c |
@@ -8,10 +9,19 @@ predicate closed(Expr e) {
   )
 }
 
+/** An expression for which there exists a function call that might close it. */
 class ClosedExpr extends PointsToExpr {
   ClosedExpr() { closed(this) }
 
   override predicate interesting() { closed(this) }
 }
 
+/**
+ * Holds if `fc` is a call to a function that opens a file that might be closed. For example:
+ * ```
+ * FILE* f = fopen("file.txt", "r");
+ * ...
+ * fclose(f);
+ * ```
+ */
 predicate fopenCallMayBeClosed(FunctionCall fc) { fopenCall(fc) and anythingPointsTo(fc) }

cpp/ql/src/Critical/LoopBounds.qll

@@ -2,12 +2,24 @@
 
 import cpp
 
+/**
+ * An assignment to a variable with the value `0`. For example:
+ * ```
+ * int x;
+ * x = 0;
+ * ```
+ * but not:
+ * ```
+ * int x = 0;
+ * ```
+ */
 class ZeroAssignment extends AssignExpr {
   ZeroAssignment() {
     this.getAnOperand() instanceof VariableAccess and
     this.getAnOperand() instanceof Zero
   }
 
+  /** Gets a variable that is assigned the value `0`. */
   Variable assignedVariable() { result.getAnAccess() = this.getAnOperand() }
 }
 

cpp/ql/src/Critical/MemoryFreed.qll

@@ -9,10 +9,19 @@ private predicate freed(Expr e) {
   )
 }
 
+/** An expression that might be deallocated. */
 class FreedExpr extends PointsToExpr {
   FreedExpr() { freed(this) }
 
   override predicate interesting() { freed(this) }
 }
 
+/**
+ * An allocation expression that might be deallocated. For example:
+ * ```
+ * int* p = new int;
+ * ...
+ * delete p;
+ * ```
+ */
 predicate allocMayBeFreed(AllocationExpr alloc) { anythingPointsTo(alloc) }

cpp/ql/src/Critical/Negativity.qll

@@ -1,10 +1,19 @@
 import cpp
 
+/**
+ * Holds if `val` is an access to the variable `v`, or if `val`
+ * is an assignment with an access to `v` on the left-hand side.
+ */
 predicate valueOfVar(Variable v, Expr val) {
   val = v.getAnAccess() or
   val.(AssignExpr).getLValue() = v.getAnAccess()
 }
 
+/**
+ * Holds if either:
+ * - `cond` is an (in)equality expression that compares the variable `v` to the value `-1`, or
+ * - `cond` is a relational expression that compares the variable `v` to a constant.
+ */
 predicate boundsCheckExpr(Variable v, Expr cond) {
   exists(EQExpr eq |
     cond = eq and
@@ -43,6 +52,18 @@ predicate boundsCheckExpr(Variable v, Expr cond) {
   )
 }
 
+/**
+ * Holds if `node` is an expression in a conditional statement and `succ` is an
+ * immediate successor of `node` that may be reached after evaluating `node`.
+ * For example, given
+ * ```
+ * if (a < 10 && b) func1();
+ * else func2();
+ * ```
+ * this predicate holds when either:
+ * - `node` is `a < 10` and `succ` is `func2()` or `b`, or
+ * - `node` is `b` and `succ` is `func1()` or `func2()`
+ */
 predicate conditionalSuccessor(ControlFlowNode node, ControlFlowNode succ) {
   if node.isCondition()
   then succ = node.getATrueSuccessor() or succ = node.getAFalseSuccessor()
@@ -52,6 +73,12 @@ predicate conditionalSuccessor(ControlFlowNode node, ControlFlowNode succ) {
     )
 }
 
+/**
+ * Holds if the current value of the variable `v` at control-flow
+ * node `n` has been used either in:
+ * - an (in)equality comparison with the value `-1`, or
+ * - a relational comparison that compares `v` to a constant.
+ */
 predicate boundsChecked(Variable v, ControlFlowNode node) {
   exists(Expr test |
     boundsCheckExpr(v, test) and
@@ -63,6 +90,14 @@ predicate boundsChecked(Variable v, ControlFlowNode node) {
   )
 }
 
+/**
+ * Holds if `cond` compares `v` to some common error values. Specifically, this
+ * predicate holds when:
+ * - `cond` checks that `v` is equal to `-1`, or
+ * - `cond` checks that `v` is less than `0`, or
+ * - `cond` checks that `v` is less than or equal to `-1`, or
+ * - `cond` checks that `v` is not some common success value (see `successCondition`).
+ */
 predicate errorCondition(Variable v, Expr cond) {
   exists(EQExpr eq |
     cond = eq and
@@ -88,6 +123,14 @@ predicate errorCondition(Variable v, Expr cond) {
   )
 }
 
+/**
+ * Holds if `cond` compares `v` to some common success values. Specifically, this
+ * predicate holds when:
+ * - `cond` checks that `v` is not equal to `-1`, or
+ * - `cond` checks that `v` is greater than or equal than `0`, or
+ * - `cond` checks that `v` is greater than `-1`, or
+ * - `cond` checks that `v` is not some common error value (see `errorCondition`).
+ */
 predicate successCondition(Variable v, Expr cond) {
   exists(NEExpr ne |
     cond = ne and
@@ -113,6 +156,11 @@ predicate successCondition(Variable v, Expr cond) {
   )
 }
 
+/**
+ * Holds if there exists a comparison operation that checks whether `v`
+ * represents some common *error* values, and `n` may be reached
+ * immediately following the comparison operation.
+ */
 predicate errorSuccessor(Variable v, ControlFlowNode n) {
   exists(Expr cond |
     errorCondition(v, cond) and n = cond.getATrueSuccessor()
@@ -121,6 +169,11 @@ predicate errorSuccessor(Variable v, ControlFlowNode n) {
   )
 }
 
+/**
+ * Holds if there exists a comparison operation that checks whether `v`
+ * represents some common *success* values, and `n` may be reached
+ * immediately following the comparison operation.
+ */
 predicate successSuccessor(Variable v, ControlFlowNode n) {
   exists(Expr cond |
     successCondition(v, cond) and n = cond.getATrueSuccessor()
@@ -129,6 +182,10 @@ predicate successSuccessor(Variable v, ControlFlowNode n) {
   )
 }
 
+/**
+ * Holds if the current value of the variable `v` at control-flow node
+ * `n` may have been checked against a common set of *error* values.
+ */
 predicate checkedError(Variable v, ControlFlowNode n) {
   errorSuccessor(v, n)
   or
@@ -139,6 +196,10 @@ predicate checkedError(Variable v, ControlFlowNode n) {
   )
 }
 
+/**
+ * Holds if the current value of the variable `v` at control-flow node
+ * `n` may have been checked against a common set of *success* values.
+ */
 predicate checkedSuccess(Variable v, ControlFlowNode n) {
   successSuccessor(v, n)
   or

cpp/ql/src/Documentation/CaptionedComments.qll

@@ -4,6 +4,10 @@
 
 import cpp
 
+/**
+ * Gets a string representation of the comment `c` containing the caption 'TODO' or 'FIXME'.
+ * If `c` spans multiple lines, all lines after the first are abbreviated as [...].
+ */
 string getCommentTextCaptioned(Comment c, string caption) {
   (caption = "TODO" or caption = "FIXME") and
   exists(

cpp/ql/src/Documentation/CommentedOutCode.qll

@@ -1,3 +1,7 @@
+/**
+ * Provides classes and predicates for identifying C/C++ comments that look like code.
+ */
+
 import cpp
 
 /**
@@ -137,8 +141,14 @@ class CommentBlock extends Comment {
     )
   }
 
+  /**
+   * Gets the last comment associated with this comment block.
+   */
   Comment lastComment() { result = this.getComment(max(int i | exists(this.getComment(i)))) }
 
+  /**
+   * Gets the contents of the `i`'th comment associated with this comment block.
+   */
   string getLine(int i) {
     this instanceof CStyleComment and
     result = this.getContents().regexpCapture("(?s)/\\*+(.*)\\*+/", 1).splitAt("\n", i)
@@ -146,14 +156,24 @@ class CommentBlock extends Comment {
     this instanceof CppStyleComment and result = this.getComment(i).getContents().suffix(2)
   }
 
+  /**
+   * Gets the number of lines in the comments associated with this comment block.
+   */
   int numLines() {
     result = strictcount(int i, string line | line = this.getLine(i) and line.trim() != "")
   }
 
+  /**
+   * Gets the number of lines that look like code in the comments associated with this comment block.
+   */
   int numCodeLines() {
     result = strictcount(int i, string line | line = this.getLine(i) and looksLikeCode(line))
   }
 
+  /**
+   * Holds if the comment block is a C-style comment, and each
+   * comment line starts with a *.
+   */
   predicate isDocumentation() {
     // If a C-style comment starts each line with a *, then it's
     // probably documentation rather than code.
@@ -161,6 +181,12 @@ class CommentBlock extends Comment {
     forex(int i | i in [1 .. this.numLines() - 1] | this.getLine(i).trim().matches("*%"))
   }
 
+  /**
+   * Holds if this comment block looks like code that has been commented out. Specifically:
+   * 1. It does not look like documentation (see `isDocumentation`).
+   * 2. It is not in a header file without any declaration entries or top level declarations.
+   * 3. More than half of the lines in the comment block look like code.
+   */
   predicate isCommentedOutCode() {
     not this.isDocumentation() and
     not this.getFile().(HeaderFile).noTopLevelCode() and

cpp/ql/src/JPL_C/LOC-3/Rule 17/BasicIntTypes.ql

@@ -30,7 +30,7 @@ predicate allowedTypedefs(TypedefType t) {
  * Gets a type which appears literally in the declaration of `d`.
  */
 Type getAnImmediateUsedType(Declaration d) {
-  d.isDefined() and
+  d.hasDefinition() and
   (
     result = d.(Function).getType() or
     result = d.(Variable).getType()

cpp/ql/src/Likely Bugs/Likely Typos/UsingStrcpyAsBoolean.ql

@@ -15,6 +15,15 @@ import cpp
 import semmle.code.cpp.models.implementations.Strcpy
 import semmle.code.cpp.dataflow.DataFlow
 
+/**
+ * A string copy function that returns a string, rather than an error code (for
+ * example, `strcpy` returns a string, whereas `strcpy_s` returns an error
+ * code).
+ */
+class InterestingStrcpyFunction extends StrcpyFunction {
+  InterestingStrcpyFunction() { getType().getUnspecifiedType() instanceof PointerType }
+}
+
 predicate isBoolean(Expr e1) {
   exists(Type t1 |
     t1 = e1.getType() and
@@ -25,12 +34,12 @@ predicate isBoolean(Expr e1) {
 predicate isStringCopyCastedAsBoolean(FunctionCall func, Expr expr1, string msg) {
   DataFlow::localExprFlow(func, expr1) and
   isBoolean(expr1.getConversion*()) and
-  func.getTarget() instanceof StrcpyFunction and
+  func.getTarget() instanceof InterestingStrcpyFunction and
   msg = "Return value of " + func.getTarget().getName() + " used as a Boolean."
 }
 
 predicate isStringCopyUsedInLogicalOperationOrCondition(FunctionCall func, Expr expr1, string msg) {
-  func.getTarget() instanceof StrcpyFunction and
+  func.getTarget() instanceof InterestingStrcpyFunction and
   (
     (
       // it is being used in an equality or logical operation

cpp/ql/src/Likely Bugs/RedundantNullCheckSimple.ql

@@ -23,7 +23,7 @@ import semmle.code.cpp.ir.ValueNumbering
 class NullInstruction extends ConstantValueInstruction {
   NullInstruction() {
     this.getValue() = "0" and
-    this.getResultType().getUnspecifiedType() instanceof PointerType
+    this.getResultIRType() instanceof IRAddressType
   }
 }
 
@@ -44,8 +44,8 @@ predicate explicitNullTestOfInstruction(Instruction checked, Instruction bool) {
   bool =
     any(ConvertInstruction convert |
       checked = convert.getUnary() and
-      convert.getResultType() instanceof BoolType and
-      checked.getResultType() instanceof PointerType
+      convert.getResultIRType() instanceof IRBooleanType and
+      checked.getResultIRType() instanceof IRAddressType
     )
 }
 

cpp/ql/src/Likely Bugs/Underspecified Functions/TooFewArguments.qll

@@ -6,29 +6,50 @@
 
 import cpp
 
-// True if function was ()-declared, but not (void)-declared or K&R-defined
+/**
+ * Holds if `fde` has a parameter declaration that's clear on the minimum
+ * number of parameters. This is essentially true for everything except
+ * `()`-declarations.
+ */
+private predicate hasDefiniteNumberOfParameters(FunctionDeclarationEntry fde) {
+  fde.hasVoidParamList()
+  or
+  fde.getNumberOfParameters() > 0
+  or
+  fde.isDefinition()
+}
+
+/* Holds if function was ()-declared, but not (void)-declared or K&R-defined. */
 private predicate hasZeroParamDecl(Function f) {
   exists(FunctionDeclarationEntry fde | fde = f.getADeclarationEntry() |
-    not fde.hasVoidParamList() and fde.getNumberOfParameters() = 0 and not fde.isDefinition()
+    not hasDefiniteNumberOfParameters(fde)
   )
 }
 
-// True if this file (or header) was compiled as a C file
+/* Holds if this file (or header) was compiled as a C file. */
 private predicate isCompiledAsC(File f) {
   f.compiledAsC()
   or
   exists(File src | isCompiledAsC(src) | src.getAnIncludedFile() = f)
 }
 
+/** Holds if `fc` is a call to `f` with too few arguments. */
 predicate tooFewArguments(FunctionCall fc, Function f) {
   f = fc.getTarget() and
   not f.isVarargs() and
   not f instanceof BuiltInFunction and
+  // This query should only have results on C (not C++) functions that have a
+  // `()` parameter list somewhere. If it has results on other functions, then
+  // it's probably because the extractor only saw a partial compilation.
   hasZeroParamDecl(f) and
   isCompiledAsC(f.getFile()) and
-  // There is an explicit declaration of the function whose parameter count is larger
-  // than the number of call arguments
-  exists(FunctionDeclarationEntry fde | fde = f.getADeclarationEntry() |
+  // Produce an alert when all declarations that are authoritative on the
+  // parameter count specify a parameter count larger than the number of call
+  // arguments.
+  forex(FunctionDeclarationEntry fde |
+    fde = f.getADeclarationEntry() and
+    hasDefiniteNumberOfParameters(fde)
+  |
     fde.getNumberOfParameters() > fc.getNumberOfArguments()
   )
 }

cpp/ql/src/Metrics/History/HChurn.ql

@@ -1,27 +0,0 @@
-/**
- * @name Churned lines per file
- * @description Number of churned lines per file, across the revision
- *              history in the database.
- * @kind treemap
- * @id cpp/historical-churn
- * @treemap.warnOn highValues
- * @metricType file
- * @metricAggregate avg sum max
- * @tags external-data
- * @deprecated
- */
-
-import cpp
-import external.VCS
-
-from File f, int n
-where
-  n =
-    sum(Commit entry, int churn |
-      churn = entry.getRecentChurnForFile(f) and
-      not artificialChange(entry)
-    |
-      churn
-    ) and
-  exists(f.getMetrics().getNumberOfLinesOfCode())
-select f, n order by n desc

cpp/ql/src/Metrics/History/HLinesAdded.ql

@@ -1,27 +0,0 @@
-/**
- * @name Added lines per file
- * @description Number of added lines per file, across the revision
- *              history in the database.
- * @kind treemap
- * @id cpp/historical-lines-added
- * @treemap.warnOn highValues
- * @metricType file
- * @metricAggregate avg sum max
- * @tags external-data
- * @deprecated
- */
-
-import cpp
-import external.VCS
-
-from File f, int n
-where
-  n =
-    sum(Commit entry, int churn |
-      churn = entry.getRecentAdditionsForFile(f) and
-      not artificialChange(entry)
-    |
-      churn
-    ) and
-  exists(f.getMetrics().getNumberOfLinesOfCode())
-select f, n order by n desc

cpp/ql/src/Metrics/History/HLinesDeleted.ql

@@ -1,27 +0,0 @@
-/**
- * @name Deleted lines per file
- * @description Number of deleted lines per file, across the revision
- *              history in the database.
- * @kind treemap
- * @id cpp/historical-lines-deleted
- * @treemap.warnOn highValues
- * @metricType file
- * @metricAggregate avg sum max
- * @tags external-data
- * @deprecated
- */
-
-import cpp
-import external.VCS
-
-from File f, int n
-where
-  n =
-    sum(Commit entry, int churn |
-      churn = entry.getRecentDeletionsForFile(f) and
-      not artificialChange(entry)
-    |
-      churn
-    ) and
-  exists(f.getMetrics().getNumberOfLinesOfCode())
-select f, n order by n desc

cpp/ql/src/Metrics/History/HNumberOfAuthors.ql

@@ -1,18 +0,0 @@
-/**
- * @name Number of authors
- * @description Number of distinct authors for each file.
- * @kind treemap
- * @id cpp/historical-number-of-authors
- * @treemap.warnOn highValues
- * @metricType file
- * @metricAggregate avg min max
- * @tags external-data
- * @deprecated
- */
-
-import cpp
-import external.VCS
-
-from File f
-where exists(f.getMetrics().getNumberOfLinesOfCode())
-select f, count(Author author | author.getAnEditedFile() = f)

cpp/ql/src/Metrics/History/HNumberOfChanges.ql

@@ -1,19 +0,0 @@
-/**
- * @name Number of file-level changes
- * @description The number of file-level changes made (by version
- *              control history).
- * @kind treemap
- * @id cpp/historical-number-of-changes
- * @treemap.warnOn highValues
- * @metricType file
- * @metricAggregate avg min max sum
- * @tags external-data
- * @deprecated
- */
-
-import cpp
-import external.VCS
-
-from File f
-where exists(f.getMetrics().getNumberOfLinesOfCode())
-select f, count(Commit svn | f = svn.getAnAffectedFile() and not artificialChange(svn))

cpp/ql/src/Metrics/History/HNumberOfCoCommits.ql

@@ -1,21 +0,0 @@
-/**
- * @name Number of co-committed files
- * @description The average number of other files that are touched
- *              whenever a file is affected by a commit.
- * @kind treemap
- * @id cpp/historical-number-of-co-commits
- * @treemap.warnOn highValues
- * @metricType file
- * @metricAggregate avg min max
- * @tags external-data
- * @deprecated
- */
-
-import cpp
-import external.VCS
-
-int committedFiles(Commit commit) { result = count(commit.getAnAffectedFile()) }
-
-from File f
-where exists(f.getMetrics().getNumberOfLinesOfCode())
-select f, avg(Commit commit | commit.getAnAffectedFile() = f | committedFiles(commit) - 1)

cpp/ql/src/Metrics/History/HNumberOfReCommits.ql

@@ -1,37 +0,0 @@
-/**
- * @name Number of re-commits for each file
- * @description A re-commit is taken to mean a commit to a file that
- *              was touched less than five days ago.
- * @kind treemap
- * @id cpp/historical-number-of-re-commits
- * @treemap.warnOn highValues
- * @metricType file
- * @metricAggregate avg min max
- * @tags external-data
- * @deprecated
- */
-
-import cpp
-import external.VCS
-
-predicate inRange(Commit first, Commit second) {
-  first.getAnAffectedFile() = second.getAnAffectedFile() and
-  first != second and
-  exists(int n |
-    n = first.getDate().daysTo(second.getDate()) and
-    n >= 0 and
-    n < 5
-  )
-}
-
-int recommitsForFile(File f) {
-  result =
-    count(Commit recommit |
-      f = recommit.getAnAffectedFile() and
-      exists(Commit prev | inRange(prev, recommit))
-    )
-}
-
-from File f
-where exists(f.getMetrics().getNumberOfLinesOfCode())
-select f, recommitsForFile(f)

cpp/ql/src/Metrics/History/HNumberOfRecentAuthors.ql

@@ -1,27 +0,0 @@
-/**
- * @name Number of recent authors
- * @description Number of distinct authors that have recently made
- *              changes.
- * @kind treemap
- * @id cpp/historical-number-of-recent-authors
- * @treemap.warnOn highValues
- * @metricType file
- * @metricAggregate avg min max
- * @tags external-data
- * @deprecated
- */
-
-import cpp
-import external.VCS
-
-from File f
-where exists(f.getMetrics().getNumberOfLinesOfCode())
-select f,
-  count(Author author |
-    exists(Commit e |
-      e = author.getACommit() and
-      f = e.getAnAffectedFile() and
-      e.daysToNow() <= 180 and
-      not artificialChange(e)
-    )
-  )

cpp/ql/src/Metrics/History/HNumberOfRecentChangedFiles.ql

@@ -1,24 +0,0 @@
-/**
- * @name Recently changed files
- * @description Number of files recently edited.
- * @kind treemap
- * @id cpp/historical-number-of-recent-changed-files
- * @treemap.warnOn highValues
- * @metricType file
- * @metricAggregate avg min max sum
- * @tags external-data
- * @deprecated
- */
-
-import cpp
-import external.VCS
-
-from File f
-where
-  exists(Commit e |
-    e.getAnAffectedFile() = f and
-    e.daysToNow() <= 180 and
-    not artificialChange(e)
-  ) and
-  exists(f.getMetrics().getNumberOfLinesOfCode())
-select f, 1

cpp/ql/src/Metrics/History/HNumberOfRecentChanges.ql

@@ -1,25 +0,0 @@
-/**
- * @name Recent changes
- * @description Number of recent commits to this file.
- * @kind treemap
- * @id cpp/historical-number-of-recent-changes
- * @treemap.warnOn highValues
- * @metricType file
- * @metricAggregate avg min max sum
- * @tags external-data
- * @deprecated
- */
-
-import cpp
-import external.VCS
-
-from File f, int n
-where
-  n =
-    count(Commit e |
-      e.getAnAffectedFile() = f and
-      e.daysToNow() <= 180 and
-      not artificialChange(e)
-    ) and
-  exists(f.getMetrics().getNumberOfLinesOfCode())
-select f, n order by n desc

cpp/ql/src/Security/CWE/CWE-134/UncontrolledFormatString.ql

@@ -5,7 +5,7 @@
  *              or data representation problems.
  * @kind path-problem
  * @problem.severity warning
- * @precision medium
+ * @precision high
  * @id cpp/tainted-format-string
  * @tags reliability
  *       security

cpp/ql/src/Security/CWE/CWE-134/UncontrolledFormatStringThroughGlobalVar.ql

@@ -5,7 +5,7 @@
  *              or data representation problems.
  * @kind path-problem
  * @problem.severity warning
- * @precision medium
+ * @precision high
  * @id cpp/tainted-format-string-through-global
  * @tags reliability
  *       security

cpp/ql/src/Security/CWE/CWE-327/BrokenCryptoAlgorithm.ql

@@ -18,7 +18,7 @@ abstract class InsecureCryptoSpec extends Locatable {
 }
 
 Function getAnInsecureFunction() {
-  result.getName().regexpMatch(algorithmBlacklistRegex()) and
+  result.getName().regexpMatch(getInsecureAlgorithmRegex()) and
   exists(result.getACallToThisFunction())
 }
 
@@ -33,7 +33,7 @@ class InsecureFunctionCall extends InsecureCryptoSpec, FunctionCall {
 }
 
 Macro getAnInsecureMacro() {
-  result.getName().regexpMatch(algorithmBlacklistRegex()) and
+  result.getName().regexpMatch(getInsecureAlgorithmRegex()) and
   exists(result.getAnInvocation())
 }
 

cpp/ql/src/Security/CWE/CWE-457/InitializationFunctions.qll

@@ -198,12 +198,12 @@ class InitializationFunction extends Function {
     )
     or
     // If we have no definition, we look at SAL annotations
-    not this.isDefined() and
+    not this.hasDefinition() and
     this.getParameter(i).(SALParameter).isOut() and
     evidence = SuggestiveSALAnnotation()
     or
     // We have some external information that this function conditionally initializes
-    not this.isDefined() and
+    not this.hasDefinition() and
     any(ValidatedExternalCondInitFunction vc).isExternallyVerified(this, i) and
     evidence = ExternalEvidence()
   }
@@ -406,7 +406,7 @@ class ConditionalInitializationFunction extends InitializationFunction {
        * Explicitly ignore pure virtual functions.
        */
 
-      this.isDefined() and
+      this.hasDefinition() and
       this.paramNotReassignedAt(this, i, c) and
       not this instanceof PureVirtualFunction
     )
@@ -616,11 +616,11 @@ private predicate functionSignature(Function f, string qualifiedName, string typ
  * are never statically linked together.
  */
 private Function getAPossibleDefinition(Function undefinedFunction) {
-  not undefinedFunction.isDefined() and
+  not undefinedFunction.hasDefinition() and
   exists(string qn, string typeSig |
     functionSignature(undefinedFunction, qn, typeSig) and functionSignature(result, qn, typeSig)
   ) and
-  result.isDefined()
+  result.hasDefinition()
 }
 
 /**
@@ -631,7 +631,7 @@ private Function getAPossibleDefinition(Function undefinedFunction) {
  */
 private Function getTarget1(Call c) {
   result = VirtualDispatch::getAViableTarget(c) and
-  result.isDefined()
+  result.hasDefinition()
 }
 
 /**

cpp/ql/src/Security/CWE/CWE-468/IncorrectPointerScaling.ql

@@ -21,7 +21,7 @@ where
   destBase = baseType(destType) and
   destBase.getSize() != sourceBase.getSize() and
   not dest.isInMacroExpansion() and
-  // If the source type is a char* or void* then don't
+  // If the source type is a `char*` or `void*` then don't
   // produce a result, because it is likely to be a false
   // positive.
   not sourceBase instanceof CharType and

cpp/ql/src/Security/CWE/CWE-468/IncorrectPointerScalingChar.ql

@@ -21,7 +21,7 @@ where
   destBase = baseType(destType) and
   destBase.getSize() != sourceBase.getSize() and
   not dest.isInMacroExpansion() and
-  // If the source type is a char* or void* then don't
+  // If the source type is a `char*` or `void*` then don't
   // produce a result, because it is likely to be a false
   // positive.
   not sourceBase instanceof CharType and

cpp/ql/src/Security/CWE/CWE-468/SuspiciousAddWithSizeof.ql

@@ -24,7 +24,7 @@ private predicate isCharSzPtrExpr(Expr e) {
 from Expr sizeofExpr, Expr e
 where
   // If we see an addWithSizeof then we expect the type of
-  // the pointer expression to be char* or void*. Otherwise it
+  // the pointer expression to be `char*` or `void*`. Otherwise it
   // is probably a mistake.
   addWithSizeof(e, sizeofExpr, _) and not isCharSzPtrExpr(e)
 select sizeofExpr,

cpp/ql/src/codeql-suites/cpp-code-scanning.qls

@@ -2,3 +2,5 @@
 - qlpack: codeql-cpp
 - apply: code-scanning-selectors.yml
   from: codeql-suite-helpers
+- apply: codeql-suites/exclude-slow-queries.yml
+  from: codeql-cpp

cpp/ql/src/codeql-suites/cpp-lgtm-full.qls

@@ -2,13 +2,17 @@
 - qlpack: codeql-cpp
 - apply: lgtm-selectors.yml
   from: codeql-suite-helpers
-# These queries are infeasible to compute on large projects:
+- apply: codeql-suites/exclude-slow-queries.yml
+  from: codeql-cpp 
+# These are only for IDE use.
 - exclude:
-    query path:
-      - Security/CWE/CWE-497/ExposedSystemData.ql
-      - Critical/DescriptorMayNotBeClosed.ql
-      - Critical/DescriptorNeverClosed.ql
-      - Critical/FileMayNotBeClosed.ql
-      - Critical/FileNeverClosed.ql
-      - Critical/MemoryMayNotBeFreed.ql
-      - Critical/MemoryNeverFreed.ql
+    tags contain:
+      - ide-contextual-queries/local-definitions
+      - ide-contextual-queries/local-references
+- query: Metrics/Dependencies/ExternalDependencies.ql
+- query: Metrics/Dependencies/ExternalDependenciesSourceLinks.ql
+- query: Metrics/Files/FLinesOfCode.ql
+- query: Metrics/Files/FLinesOfCommentedOutCode.ql
+- query: Metrics/Files/FLinesOfComments.ql
+- query: Metrics/Files/FLinesOfDuplicatedCode.ql
+- query: Metrics/Files/FNumberOfTests.ql

cpp/ql/src/codeql-suites/cpp-security-and-quality.qls

@@ -0,0 +1,6 @@
+- description: Security-and-quality queries for C and C++
+- qlpack: codeql-cpp
+- apply: security-and-quality-selectors.yml
+  from: codeql-suite-helpers
+- apply: codeql-suites/exclude-slow-queries.yml
+  from: codeql-cpp

cpp/ql/src/codeql-suites/cpp-security-extended.qls

@@ -0,0 +1,6 @@
+- description: Security-extended queries for C and C++
+- qlpack: codeql-cpp
+- apply: security-extended-selectors.yml
+  from: codeql-suite-helpers
+- apply: codeql-suites/exclude-slow-queries.yml
+  from: codeql-cpp

cpp/ql/src/codeql-suites/exclude-slow-queries.yml

@@ -0,0 +1,11 @@
+- description: C/C++ queries which are infeasible to compute on large projects
+# These queries are infeasible to compute on large projects:
+- exclude:
+    query path:
+      - Security/CWE/CWE-497/ExposedSystemData.ql
+      - Critical/DescriptorMayNotBeClosed.ql
+      - Critical/DescriptorNeverClosed.ql
+      - Critical/FileMayNotBeClosed.ql
+      - Critical/FileNeverClosed.ql
+      - Critical/MemoryMayNotBeFreed.ql
+      - Critical/MemoryNeverFreed.ql

cpp/ql/src/cpp.qll

@@ -32,6 +32,7 @@ import semmle.code.cpp.Enum
 import semmle.code.cpp.Member
 import semmle.code.cpp.Field
 import semmle.code.cpp.Function
+import semmle.code.cpp.MemberFunction
 import semmle.code.cpp.Parameter
 import semmle.code.cpp.Variable
 import semmle.code.cpp.Initializer

cpp/ql/src/default.qll

@@ -1 +1,7 @@
+/**
+ * DEPRECATED: use `import cpp` instead of `import default`.
+ *
+ * Provides classes and predicates for working with C/C++ code.
+ */
+
 import cpp

cpp/ql/src/definitions.qll

@@ -132,6 +132,7 @@ private predicate constructorCallTypeMention(ConstructorCall cc, TypeMention tm)
  *  - `"X"` for macro accesses
  *  - `"I"` for import / include directives
  */
+cached
 Top definitionOf(Top e, string kind) {
   (
     // call -> function called
@@ -213,3 +214,11 @@ Top definitionOf(Top e, string kind) {
   // later on.
   strictcount(result.getLocation()) < 10
 }
+
+/**
+ * Returns an appropriately encoded version of a filename `name`
+ * passed by the VS Code extension in order to coincide with the
+ * output of `.getFile()` on locatable entities.
+ */
+cached
+File getEncodedFile(string name) { result.getAbsolutePath().replaceAll(":", "_") = name }

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

@@ -0,0 +1,282 @@
+/**
+ * Provides precise tracking of how big the memory pointed to by pointers is.
+ * For each pointer, we start tracking (starting from the allocation or an array declaration)
+ * 1) how long is the chunk of memory allocated
+ * 2) where the current pointer is in this chunk of memory
+ * As computing this information is obviously not possible for all pointers,
+ * we do not guarantee the existence of length/offset information for all pointers.
+ * However, when it exists it is guaranteed to be accurate.
+ *
+ * The  length and offset are tracked in a similar way to the Rangeanalysis.
+ * Each length is a `ValueNumber + delta`, and each Offset is an `Operand + delta`.
+ * We choose to track a `ValueNumber` for length, because the Rangeanalysis offers
+ * integer bounds on instructions and operands in terms of `ValueNumber`s,
+ * and `Operand` for offset because integer bounds on `Operand`s are
+ * tighter than bounds on `Instruction`s.
+ */
+
+import cpp
+import semmle.code.cpp.ir.IR
+private import semmle.code.cpp.ir.ValueNumbering
+private import semmle.code.cpp.ir.internal.CppType
+private import semmle.code.cpp.models.interfaces.Allocation
+private import experimental.semmle.code.cpp.rangeanalysis.RangeUtils
+
+private newtype TLength =
+  TZeroLength() or
+  TVNLength(ValueNumber vn) {
+    not vn.getAnInstruction() instanceof ConstantInstruction and
+    exists(Instruction i |
+      vn.getAnInstruction() = i and
+      (
+        i.getResultIRType() instanceof IRSignedIntegerType or
+        i.getResultIRType() instanceof IRUnsignedIntegerType
+      )
+    |
+      i instanceof PhiInstruction
+      or
+      i instanceof InitializeParameterInstruction
+      or
+      i instanceof CallInstruction
+      or
+      i.(LoadInstruction).getSourceAddress() instanceof VariableAddressInstruction
+      or
+      i.(LoadInstruction).getSourceAddress() instanceof FieldAddressInstruction
+      or
+      i.getAUse() instanceof ArgumentOperand
+    )
+  }
+
+/**
+ * Array lengths are represented in a ValueNumber | Zero + delta format.
+ * This class keeps track of the ValueNumber or Zero.
+ * The delta is tracked in the predicate `knownArrayLength`.
+ */
+class Length extends TLength {
+  string toString() { none() } // overridden in subclasses
+}
+
+/**
+ * This length class corresponds to an array having a constant length
+ * that is tracked by the delta value.
+ */
+class ZeroLength extends Length, TZeroLength {
+  override string toString() { result = "ZeroLength" }
+}
+
+/**
+ * This length class corresponds to an array having variable length, i.e. the
+ * length is tracked by a value number. One example is an array having length
+ * `count` for an integer variable `count` in the program.
+ */
+class VNLength extends Length, TVNLength {
+  ValueNumber vn;
+
+  VNLength() { this = TVNLength(vn) }
+
+  /** Gets an instruction with this value number bound. */
+  Instruction getInstruction() { this = TVNLength(valueNumber(result)) }
+
+  ValueNumber getValueNumber() { result = vn }
+
+  override string toString() { result = "VNLength(" + vn.getExampleInstruction().toString() + ")" }
+}
+
+private newtype TOffset =
+  TZeroOffset() or
+  TOpOffset(Operand op) {
+    op.getAnyDef().getResultIRType() instanceof IRSignedIntegerType or
+    op.getAnyDef().getResultIRType() instanceof IRUnsignedIntegerType
+  }
+
+/**
+ * This class describes the offset of a pointer in a chunk of memory.
+ * It is either an `Operand` or zero, an additional integer delta is added later.
+ */
+class Offset extends TOffset {
+  string toString() { none() } // overridden in subclasses
+}
+
+/**
+ * This class represents a fixed offset, only specified by a delta.
+ */
+class ZeroOffset extends Offset, TZeroOffset {
+  override string toString() { result = "ZeroOffset" }
+}
+
+/**
+ * This class represents an offset of an operand.
+ */
+class OpOffset extends Offset, TOpOffset {
+  Operand op;
+
+  OpOffset() { this = TOpOffset(op) }
+
+  Operand getOperand() { result = op }
+
+  override string toString() { result = "OpOffset(" + op.getDef().toString() + ")" }
+}
+
+private int getBaseSizeForPointerType(PointerType type) { result = type.getBaseType().getSize() }
+
+/**
+ * Holds if pointer `prev` that points at offset `prevOffset + prevOffsetDelta`
+ * steps to `array` that points to `offset + offsetDelta` in one step.
+ * This predicate does not contain any recursive steps.
+ */
+bindingset[prevOffset, prevOffsetDelta]
+predicate simpleArrayLengthStep(
+  Instruction array, Offset offset, int offsetDelta, Instruction prev, Offset prevOffset,
+  int prevOffsetDelta
+) {
+  // array assign
+  array.(CopyInstruction).getSourceValue() = prev and
+  offset = prevOffset and
+  offsetDelta = prevOffsetDelta
+  or
+  // pointer add with constant
+  array.(PointerAddInstruction).getLeft() = prev and
+  offset = prevOffset and
+  offsetDelta = prevOffsetDelta + getConstantValue(array.(PointerAddInstruction).getRight())
+  or
+  // pointer add with variable
+  array.(PointerAddInstruction).getLeft() = prev and
+  prevOffset instanceof ZeroOffset and
+  offset.(OpOffset).getOperand() = array.(PointerAddInstruction).getRightOperand() and
+  offsetDelta = prevOffsetDelta and
+  not exists(getConstantValue(array.(PointerAddInstruction).getRight()))
+  or
+  // pointer sub with constant
+  array.(PointerSubInstruction).getLeft() = prev and
+  offset = prevOffset and
+  offsetDelta = prevOffsetDelta - getConstantValue(array.(PointerSubInstruction).getRight())
+  or
+  // array to pointer decay
+  array.(ConvertInstruction).getUnary() = prev and
+  array.getConvertedResultExpression() instanceof ArrayToPointerConversion and
+  offset = prevOffset and
+  offsetDelta = prevOffsetDelta
+  or
+  // cast of pointer to pointer with the same element size
+  exists(PointerType fromTyp, PointerType toTyp |
+    array.(PtrToPtrCastInstruction).getUnary() = prev and
+    prev.getResultLanguageType().hasType(fromTyp, false) and
+    array.getResultLanguageType().hasType(toTyp, false) and
+    offset = prevOffset and
+    offsetDelta = prevOffsetDelta and
+    if fromTyp instanceof VoidPointerType
+    then getBaseSizeForPointerType(toTyp) = 1
+    else (
+      if toTyp instanceof VoidPointerType
+      then getBaseSizeForPointerType(fromTyp) = 1
+      else getBaseSizeForPointerType(toTyp) = getBaseSizeForPointerType(fromTyp)
+    )
+  )
+}
+
+/**
+ * Parses a `sizeExpr` of malloc into a variable part (`lengthExpr`) and an integer offset (`delta`).
+ */
+private predicate deconstructMallocSizeExpr(Expr sizeExpr, Expr lengthExpr, int delta) {
+  sizeExpr instanceof AddExpr and
+  exists(Expr constantExpr |
+    lengthExpr = sizeExpr.(AddExpr).getAnOperand() and
+    constantExpr = sizeExpr.(AddExpr).getAnOperand() and
+    lengthExpr != constantExpr and
+    delta = constantExpr.getValue().toInt()
+  )
+  or
+  sizeExpr instanceof SubExpr and
+  exists(Expr constantExpr |
+    lengthExpr = sizeExpr.(SubExpr).getLeftOperand() and
+    constantExpr = sizeExpr.(SubExpr).getRightOperand() and
+    delta = -constantExpr.getValue().toInt()
+  )
+}
+
+/**
+ * Holds if the instruction `array` is a dynamic memory allocation of `length`+`delta` elements.
+ */
+private predicate allocation(Instruction array, Length length, int delta) {
+  exists(AllocationExpr alloc, Type ptrTyp |
+    array.getUnconvertedResultExpression() = alloc and
+    array.getResultLanguageType().hasType(ptrTyp, false) and
+    // ensure that we have the same type of the allocation and the pointer
+    ptrTyp.stripTopLevelSpecifiers().(PointerType).getBaseType().getUnspecifiedType() =
+      alloc.getAllocatedElementType().getUnspecifiedType() and
+    // ensure that the size multiplier of the allocation is the same as the
+    // size of the type we are allocating
+    alloc.getSizeMult() = getBaseSizeForPointerType(ptrTyp) and
+    (
+      length instanceof ZeroLength and
+      delta = alloc.getSizeExpr().getValue().toInt()
+      or
+      not exists(alloc.getSizeExpr().getValue().toInt()) and
+      (
+        exists(Expr lengthExpr |
+          deconstructMallocSizeExpr(alloc.getSizeExpr(), lengthExpr, delta) and
+          length.(VNLength).getInstruction().getConvertedResultExpression() = lengthExpr
+        )
+        or
+        not exists(int d | deconstructMallocSizeExpr(alloc.getSizeExpr(), _, d)) and
+        length.(VNLength).getInstruction().getConvertedResultExpression() = alloc.getSizeExpr() and
+        delta = 0
+      )
+    )
+  )
+}
+
+/**
+ * Holds if `array` is declared as an array with length `length + lengthDelta`
+ */
+private predicate arrayDeclaration(Instruction array, Length length, int lengthDelta) {
+  (
+    array instanceof VariableAddressInstruction or
+    array instanceof FieldAddressInstruction
+  ) and
+  exists(ArrayType type | array.getResultLanguageType().hasType(type, _) |
+    length instanceof ZeroLength and
+    lengthDelta = type.getArraySize()
+  )
+}
+
+/**
+ * Holds if `array` is declared as an array or allocated
+ * with length `length + lengthDelta`
+ */
+predicate arrayAllocationOrDeclaration(Instruction array, Length length, int lengthDelta) {
+  allocation(array, length, lengthDelta)
+  or
+  // declaration of variable of array type
+  arrayDeclaration(array, length, lengthDelta)
+}
+
+/**
+ * Holds if the instruction `array` represents a pointer to a chunk of memory that holds
+ * `length + lengthDelta` elements, using only local analysis.
+ * `array` points at `offset + offsetDelta` in the chunk of memory.
+ * The pointer is in-bounds if `offset + offsetDelta < length + lengthDelta` and
+ * `offset + offsetDelta >= 0` holds.
+ * The pointer is out-of-bounds if `offset + offsetDelta >= length + lengthDelta`
+ * or `offset + offsetDelta < 0` holds.
+ * All pointers in this predicate are guaranteed to be non-null,
+ * but are not guaranteed to be live.
+ */
+predicate knownArrayLength(
+  Instruction array, Length length, int lengthDelta, Offset offset, int offsetDelta
+) {
+  arrayAllocationOrDeclaration(array, length, lengthDelta) and
+  offset instanceof ZeroOffset and
+  offsetDelta = 0
+  or
+  // simple step (no phi nodes)
+  exists(Instruction prev, Offset prevOffset, int prevOffsetDelta |
+    knownArrayLength(prev, length, lengthDelta, prevOffset, prevOffsetDelta) and
+    simpleArrayLengthStep(array, offset, offsetDelta, prev, prevOffset, prevOffsetDelta)
+  )
+  or
+  // merge control flow after phi node - but only if all the bounds agree
+  forex(Instruction input | array.(PhiInstruction).getAnInput() = input |
+    knownArrayLength(input, length, lengthDelta, offset, offsetDelta)
+  )
+}

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

@@ -8,8 +8,8 @@ private newtype TBound =
     exists(Instruction i |
       vn.getAnInstruction() = i and
       (
-        i.getResultType() instanceof IntegralType or
-        i.getResultType() instanceof PointerType
+        i.getResultIRType() instanceof IRIntegerType or
+        i.getResultIRType() instanceof IRAddressType
       ) and
       not vn.getAnInstruction() instanceof ConstantInstruction
     |
@@ -68,7 +68,7 @@ class ValueNumberBound extends Bound, TBoundValueNumber {
 
   ValueNumberBound() { this = TBoundValueNumber(vn) }
 
-  /** Gets the SSA variable that equals this bound. */
+  /** Gets an `Instruction` that equals this bound. */
   override Instruction getInstruction(int delta) {
     this = TBoundValueNumber(valueNumber(result)) and delta = 0
   }
@@ -76,4 +76,7 @@ class ValueNumberBound extends Bound, TBoundValueNumber {
   override string toString() { result = vn.getExampleInstruction().toString() }
 
   override Location getLocation() { result = vn.getLocation() }
+
+  /** Gets the value number that equals this bound. */
+  ValueNumber getValueNumber() { result = vn }
 }

cpp/ql/src/experimental/semmle/code/cpp/rangeanalysis/InBoundsPointerDeref.qll

@@ -0,0 +1,105 @@
+/**
+ * This library proves that a subset of pointer dereferences in a program are
+ * safe, i.e. in-bounds.
+ * It does so by first defining what a pointer dereference is (on the IR
+ * `Instruction` level), and then using the array length analysis and the range
+ * analysis together to prove that some of these pointer dereferences are safe.
+ *
+ * The analysis is soundy, i.e. it is sound if no undefined behaviour is present
+ * in the program.
+ * Furthermore, it crucially depends on the soundiness of the range analysis and
+ * the array length analysis.
+ */
+
+import cpp
+private import experimental.semmle.code.cpp.rangeanalysis.ArrayLengthAnalysis
+private import experimental.semmle.code.cpp.rangeanalysis.RangeAnalysis
+
+/**
+ * Gets the instruction that computes the address of memory that `i` accesses.
+ * Only holds if `i` dereferences a pointer, not when the computation of the
+ * memory address is constant, or if the address of a local variable is loaded/stored to.
+ */
+private Instruction getMemoryAddressInstruction(Instruction i) {
+  (
+    result = i.(FieldAddressInstruction).getObjectAddress() or
+    result = i.(LoadInstruction).getSourceAddress() or
+    result = i.(StoreInstruction).getDestinationAddress()
+  ) and
+  not result instanceof FieldAddressInstruction and
+  not result instanceof VariableAddressInstruction and
+  not result instanceof ConstantValueInstruction
+}
+
+/**
+ * All instructions that dereference a pointer.
+ */
+class PointerDereferenceInstruction extends Instruction {
+  PointerDereferenceInstruction() { exists(getMemoryAddressInstruction(this)) }
+
+  Instruction getAddress() { result = getMemoryAddressInstruction(this) }
+}
+
+/**
+ * Holds if `ptrDeref` can be proven to always access allocated memory.
+ */
+predicate inBounds(PointerDereferenceInstruction ptrDeref) {
+  exists(Length length, int lengthDelta, Offset offset, int offsetDelta |
+    knownArrayLength(ptrDeref.getAddress(), length, lengthDelta, offset, offsetDelta) and
+    // lower bound - note that we treat a pointer that accesses an array of
+    // length 0 as on upper-bound violation, but not as a lower-bound violation
+    (
+      offset instanceof ZeroOffset and
+      offsetDelta >= 0
+      or
+      offset instanceof OpOffset and
+      exists(int lowerBoundDelta |
+        boundedOperand(offset.(OpOffset).getOperand(), any(ZeroBound b), lowerBoundDelta,
+          /*upper*/ false, _) and
+        lowerBoundDelta + offsetDelta >= 0
+      )
+    ) and
+    // upper bound
+    (
+      // both offset and length are only integers
+      length instanceof ZeroLength and
+      offset instanceof ZeroOffset and
+      offsetDelta < lengthDelta
+      or
+      exists(int lengthBound |
+        // array length is variable+integer, and there's a fixed (integer-only)
+        // lower bound on the variable, so we can guarantee this access is always in-bounds
+        length instanceof VNLength and
+        offset instanceof ZeroOffset and
+        boundedInstruction(length.(VNLength).getInstruction(), any(ZeroBound b), lengthBound,
+          /* upper*/ false, _) and
+        offsetDelta < lengthBound + lengthDelta
+      )
+      or
+      exists(int offsetBoundDelta |
+        length instanceof ZeroLength and
+        offset instanceof OpOffset and
+        boundedOperand(offset.(OpOffset).getOperand(), any(ZeroBound b), offsetBoundDelta,
+          /* upper */ true, _) and
+        // offset <= offsetBoundDelta, so offset + offsetDelta <= offsetDelta + offsetBoundDelta
+        // Thus, in-bounds if offsetDelta + offsetBoundDelta < lengthDelta
+        // as we have length instanceof ZeroLength
+        offsetDelta + offsetBoundDelta < lengthDelta
+      )
+      or
+      exists(ValueNumberBound b, int offsetBoundDelta |
+        length instanceof VNLength and
+        offset instanceof OpOffset and
+        b.getValueNumber() = length.(VNLength).getValueNumber() and
+        // It holds that offset <= length + offsetBoundDelta
+        boundedOperand(offset.(OpOffset).getOperand(), b, offsetBoundDelta, /*upper*/ true, _) and
+        // it also holds that
+        offsetDelta < lengthDelta - offsetBoundDelta
+        // taking both inequalities together we get
+        //    offset <= length + offsetBoundDelta
+        // => offset + offsetDelta <= length + offsetBoundDelta + offsetDelta < length + offsetBoundDelta + lengthDelta - offsetBoundDelta
+        // as required
+      )
+    )
+  )
+}

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

@@ -241,49 +241,17 @@ class CondReason extends Reason, TCondReason {
   override string toString() { result = getCond().toString() }
 }
 
-/**
- * Holds if a cast from `fromtyp` to `totyp` can be ignored for the purpose of
- * range analysis.
- */
-pragma[inline]
-private predicate safeCast(IntegralType fromtyp, IntegralType totyp) {
-  fromtyp.getSize() < totyp.getSize() and
-  (
-    fromtyp.isUnsigned()
-    or
-    totyp.isSigned()
-  )
-  or
-  fromtyp.getSize() <= totyp.getSize() and
-  (
-    fromtyp.isSigned() and
-    totyp.isSigned()
-    or
-    fromtyp.isUnsigned() and
-    totyp.isUnsigned()
-  )
-}
-
-private class SafeCastInstruction extends ConvertInstruction {
-  SafeCastInstruction() {
-    safeCast(getUnary().getResultType(), getResultType())
-    or
-    getResultType() instanceof PointerType and
-    getUnary().getResultType() instanceof PointerType
-  }
-}
-
 /**
  * Holds if `typ` is a small integral type with the given lower and upper bounds.
  */
-private predicate typeBound(IntegralType typ, int lowerbound, int upperbound) {
-  typ.isSigned() and typ.getSize() = 1 and lowerbound = -128 and upperbound = 127
+private predicate typeBound(IRIntegerType typ, int lowerbound, int upperbound) {
+  typ.isSigned() and typ.getByteSize() = 1 and lowerbound = -128 and upperbound = 127
   or
-  typ.isUnsigned() and typ.getSize() = 1 and lowerbound = 0 and upperbound = 255
+  typ.isUnsigned() and typ.getByteSize() = 1 and lowerbound = 0 and upperbound = 255
   or
-  typ.isSigned() and typ.getSize() = 2 and lowerbound = -32768 and upperbound = 32767
+  typ.isSigned() and typ.getByteSize() = 2 and lowerbound = -32768 and upperbound = 32767
   or
-  typ.isUnsigned() and typ.getSize() = 2 and lowerbound = 0 and upperbound = 65535
+  typ.isUnsigned() and typ.getByteSize() = 2 and lowerbound = 0 and upperbound = 65535
 }
 
 /**
@@ -292,14 +260,14 @@ private predicate typeBound(IntegralType typ, int lowerbound, int upperbound) {
 private class NarrowingCastInstruction extends ConvertInstruction {
   NarrowingCastInstruction() {
     not this instanceof SafeCastInstruction and
-    typeBound(getResultType(), _, _)
+    typeBound(getResultIRType(), _, _)
   }
 
   /** Gets the lower bound of the resulting type. */
-  int getLowerBound() { typeBound(getResultType(), result, _) }
+  int getLowerBound() { typeBound(getResultIRType(), result, _) }
 
   /** Gets the upper bound of the resulting type. */
-  int getUpperBound() { typeBound(getResultType(), _, result) }
+  int getUpperBound() { typeBound(getResultIRType(), _, result) }
 }
 
 /**

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

@@ -80,3 +80,55 @@ predicate backEdge(PhiInstruction phi, PhiInputOperand op) {
   phi.getAnOperand() = op and
   phi.getBlock() = op.getPredecessorBlock().getBackEdgeSuccessor(_)
 }
+
+/**
+ * Holds if a cast from `fromtyp` to `totyp` can be ignored for the purpose of
+ * range analysis.
+ */
+pragma[inline]
+private predicate safeCast(IRIntegerType fromtyp, IRIntegerType totyp) {
+  fromtyp.getByteSize() < totyp.getByteSize() and
+  (
+    fromtyp.isUnsigned()
+    or
+    totyp.isSigned()
+  )
+  or
+  fromtyp.getByteSize() <= totyp.getByteSize() and
+  (
+    fromtyp.isSigned() and
+    totyp.isSigned()
+    or
+    fromtyp.isUnsigned() and
+    totyp.isUnsigned()
+  )
+}
+
+/**
+ * A `ConvertInstruction` which casts from one pointer type to another.
+ */
+class PtrToPtrCastInstruction extends ConvertInstruction {
+  PtrToPtrCastInstruction() {
+    getResultIRType() instanceof IRAddressType and
+    getUnary().getResultIRType() instanceof IRAddressType
+  }
+}
+
+/**
+ * A `ConvertInstruction` which casts from one integer type to another in a way
+ * that cannot overflow or underflow.
+ */
+class SafeIntCastInstruction extends ConvertInstruction {
+  SafeIntCastInstruction() { safeCast(getUnary().getResultIRType(), getResultIRType()) }
+}
+
+/**
+ * A `ConvertInstruction` which does not invalidate bounds determined by
+ * range analysis.
+ */
+class SafeCastInstruction extends ConvertInstruction {
+  SafeCastInstruction() {
+    this instanceof PtrToPtrCastInstruction or
+    this instanceof SafeIntCastInstruction
+  }
+}

cpp/ql/src/experimental/semmle/code/cpp/rangeanalysis/SignAnalysis.qll

@@ -278,8 +278,6 @@ private predicate unknownSign(Instruction i) {
   // non-positive, non-zero}, which would mean that the representation of the sign of an unknown
   // value would be the empty set.
   (
-    i instanceof UnmodeledDefinitionInstruction
-    or
     i instanceof UninitializedInstruction
     or
     i instanceof InitializeParameterInstruction
@@ -471,7 +469,7 @@ module SignAnalysisCached {
     not exists(certainInstructionSign(i)) and
     not (
       result = TNeg() and
-      i.getResultType().(IntegralType).isUnsigned()
+      i.getResultIRType().(IRIntegerType).isUnsigned()
     ) and
     (
       unknownSign(i)
@@ -479,9 +477,13 @@ module SignAnalysisCached {
       exists(ConvertInstruction ci, Instruction prior, boolean fromSigned, boolean toSigned |
         i = ci and
         prior = ci.getUnary() and
-        (if ci.getResultType().(IntegralType).isSigned() then toSigned = true else toSigned = false) and
         (
-          if prior.getResultType().(IntegralType).isSigned()
+          if ci.getResultIRType().(IRIntegerType).isSigned()
+          then toSigned = true
+          else toSigned = false
+        ) and
+        (
+          if prior.getResultIRType().(IRIntegerType).isSigned()
           then fromSigned = true
           else fromSigned = false
         ) and
@@ -514,11 +516,11 @@ module SignAnalysisCached {
         i instanceof ShiftLeftInstruction and result = s1.lshift(s2)
         or
         i instanceof ShiftRightInstruction and
-        i.getResultType().(IntegralType).isSigned() and
+        i.getResultIRType().(IRIntegerType).isSigned() and
         result = s1.rshift(s2)
         or
         i instanceof ShiftRightInstruction and
-        not i.getResultType().(IntegralType).isSigned() and
+        not i.getResultIRType().(IRIntegerType).isSigned() and
         result = s1.urshift(s2)
       )
       or

cpp/ql/src/external/CodeDuplication.qll

@@ -1,3 +1,5 @@
+/** Provides classes for detecting duplicate or similar code. */
+
 import cpp
 
 private string relativePath(File file) { result = file.getRelativePath().replaceAll("\\", "/") }
@@ -8,9 +10,12 @@ private predicate tokenLocation(string path, int sl, int sc, int ec, int el, Cop
   tokens(copy, index, sl, sc, ec, el)
 }
 
+/** A token block used for detection of duplicate and similar code. */
 class Copy extends @duplication_or_similarity {
+  /** Gets the index of the last token in this block. */
   private int lastToken() { result = max(int i | tokens(this, i, _, _, _, _) | i) }
 
+  /** Gets the index of the token in this block starting at the location `loc`, if any. */
   int tokenStartingAt(Location loc) {
     exists(string filepath, int startline, int startcol |
       loc.hasLocationInfo(filepath, startline, startcol, _, _) and
@@ -18,6 +23,7 @@ class Copy extends @duplication_or_similarity {
     )
   }
 
+  /** Gets the index of the token in this block ending at the location `loc`, if any. */
   int tokenEndingAt(Location loc) {
     exists(string filepath, int endline, int endcol |
       loc.hasLocationInfo(filepath, _, _, endline, endcol) and
@@ -25,24 +31,38 @@ class Copy extends @duplication_or_similarity {
     )
   }
 
+  /** Gets the line on which the first token in this block starts. */
   int sourceStartLine() { tokens(this, 0, result, _, _, _) }
 
+  /** Gets the column on which the first token in this block starts. */
   int sourceStartColumn() { tokens(this, 0, _, result, _, _) }
 
+  /** Gets the line on which the last token in this block ends. */
   int sourceEndLine() { tokens(this, lastToken(), _, _, result, _) }
 
+  /** Gets the column on which the last token in this block ends. */
   int sourceEndColumn() { tokens(this, lastToken(), _, _, _, result) }
 
+  /** Gets the number of lines containing at least (part of) one token in this block. */
   int sourceLines() { result = this.sourceEndLine() + 1 - this.sourceStartLine() }
 
+  /** Gets an opaque identifier for the equivalence class of this block. */
   int getEquivalenceClass() { duplicateCode(this, _, result) or similarCode(this, _, result) }
 
+  /** Gets the source file in which this block appears. */
   File sourceFile() {
     exists(string name | duplicateCode(this, name, _) or similarCode(this, name, _) |
       name.replaceAll("\\", "/") = relativePath(result)
     )
   }
 
+  /**
+   * Holds if this element is at the specified location.
+   * The location spans column `startcolumn` of line `startline` to
+   * column `endcolumn` of line `endline` in file `filepath`.
+   * For more information, see
+   * [Locations](https://help.semmle.com/QL/learn-ql/ql/locations.html).
+   */
   predicate hasLocationInfo(
     string filepath, int startline, int startcolumn, int endline, int endcolumn
   ) {
@@ -53,25 +73,30 @@ class Copy extends @duplication_or_similarity {
     endcolumn = sourceEndColumn()
   }
 
+  /** Gets a textual representation of this element. */
   string toString() { none() }
 }
 
+/** A block of duplicated code. */
 class DuplicateBlock extends Copy, @duplication {
   override string toString() { result = "Duplicate code: " + sourceLines() + " duplicated lines." }
 }
 
+/** A block of similar code. */
 class SimilarBlock extends Copy, @similarity {
   override string toString() {
     result = "Similar code: " + sourceLines() + " almost duplicated lines."
   }
 }
 
+/** Gets a function with a body and a location. */
 FunctionDeclarationEntry sourceMethod() {
   result.isDefinition() and
   exists(result.getLocation()) and
   numlines(unresolveElement(result.getFunction()), _, _, _)
 }
 
+/** Gets the number of member functions in `c` with a body and a location. */
 int numberOfSourceMethods(Class c) {
   result =
     count(FunctionDeclarationEntry m |
@@ -108,6 +133,10 @@ private predicate duplicateStatement(
   )
 }
 
+/**
+ * Holds if `m1` is a function with `total` lines, and `m2` is a function
+ * that has `duplicate` lines in common with `m1`.
+ */
 predicate duplicateStatements(
   FunctionDeclarationEntry m1, FunctionDeclarationEntry m2, int duplicate, int total
 ) {
@@ -115,13 +144,16 @@ predicate duplicateStatements(
   total = strictcount(statementInMethod(m1))
 }
 
-/**
- * Find pairs of methods are identical
- */
+/** Holds if `m` and other are identical functions. */
 predicate duplicateMethod(FunctionDeclarationEntry m, FunctionDeclarationEntry other) {
   exists(int total | duplicateStatements(m, other, total, total))
 }
 
+/**
+ * INTERNAL: do not use.
+ *
+ * Holds if `line` in `f` is similar to a line somewhere else.
+ */
 predicate similarLines(File f, int line) {
   exists(SimilarBlock b | b.sourceFile() = f and line in [b.sourceStartLine() .. b.sourceEndLine()])
 }
@@ -152,6 +184,7 @@ private predicate similarLinesCoveredFiles(File f, File otherFile) {
   )
 }
 
+/** Holds if `coveredLines` lines of `f` are similar to lines in `otherFile`. */
 predicate similarLinesCovered(File f, int coveredLines, File otherFile) {
   exists(int numLines | numLines = f.getMetrics().getNumberOfLines() |
     similarLinesCoveredFiles(f, otherFile) and
@@ -166,6 +199,11 @@ predicate similarLinesCovered(File f, int coveredLines, File otherFile) {
   )
 }
 
+/**
+ * INTERNAL: do not use.
+ *
+ * Holds if `line` in `f` is duplicated by a line somewhere else.
+ */
 predicate duplicateLines(File f, int line) {
   exists(DuplicateBlock b |
     b.sourceFile() = f and line in [b.sourceStartLine() .. b.sourceEndLine()]
@@ -182,6 +220,7 @@ private predicate duplicateLinesPerEquivalenceClass(int equivClass, int lines, F
     )
 }
 
+/** Holds if `coveredLines` lines of `f` are duplicates of lines in `otherFile`. */
 predicate duplicateLinesCovered(File f, int coveredLines, File otherFile) {
   exists(int numLines | numLines = f.getMetrics().getNumberOfLines() |
     exists(int coveredApprox |
@@ -206,6 +245,7 @@ predicate duplicateLinesCovered(File f, int coveredLines, File otherFile) {
   )
 }
 
+/** Holds if most of `f` (`percent`%) is similar to `other`. */
 predicate similarFiles(File f, File other, int percent) {
   exists(int covered, int total |
     similarLinesCovered(f, covered, other) and
@@ -216,6 +256,7 @@ predicate similarFiles(File f, File other, int percent) {
   not duplicateFiles(f, other, _)
 }
 
+/** Holds if most of `f` (`percent`%) is duplicated by `other`. */
 predicate duplicateFiles(File f, File other, int percent) {
   exists(int covered, int total |
     duplicateLinesCovered(f, covered, other) and
@@ -225,6 +266,10 @@ predicate duplicateFiles(File f, File other, int percent) {
   )
 }
 
+/**
+ * Holds if most member functions of `c` (`numDup` out of `total`) are
+ * duplicates of member functions in `other`.
+ */
 predicate mostlyDuplicateClassBase(Class c, Class other, int numDup, int total) {
   numDup =
     strictcount(FunctionDeclarationEntry m1 |
@@ -240,6 +285,11 @@ predicate mostlyDuplicateClassBase(Class c, Class other, int numDup, int total)
   (numDup * 100) / total > 80
 }
 
+/**
+ * Holds if most member functions of `c` are duplicates of member functions in
+ * `other`. Provides the human-readable `message` to describe the amount of
+ * duplication.
+ */
 predicate mostlyDuplicateClass(Class c, Class other, string message) {
   exists(int numDup, int total |
     mostlyDuplicateClassBase(c, other, numDup, total) and
@@ -264,12 +314,21 @@ predicate mostlyDuplicateClass(Class c, Class other, string message) {
   )
 }
 
+/** Holds if `f` and `other` are similar or duplicates. */
 predicate fileLevelDuplication(File f, File other) {
   similarFiles(f, other, _) or duplicateFiles(f, other, _)
 }
 
+/**
+ * Holds if most member functions of `c` are duplicates of member functions in
+ * `other`.
+ */
 predicate classLevelDuplication(Class c, Class other) { mostlyDuplicateClass(c, other, _) }
 
+/**
+ * Holds if `line` in `f` should be allowed to be duplicated. This is the case
+ * for `#include` directives.
+ */
 predicate whitelistedLineForDuplication(File f, int line) {
   exists(Include i | i.getFile() = f and i.getLocation().getStartLine() = line)
 }

cpp/ql/src/external/DefectFilter.qll

@@ -1,31 +1,52 @@
+/** Provides a class for working with defect query results stored in dashboard databases. */
+
 import cpp
 
+/**
+ * Holds if `id` in the opaque identifier of a result reported by query `queryPath`,
+ * such that `message` is the associated message and the location of the result spans
+ * column `startcolumn` of line `startline` to column `endcolumn` of line `endline`
+ * in file `filepath`.
+ *
+ * For more information, see [Locations](https://help.semmle.com/QL/learn-ql/ql/locations.html).
+ */
 external predicate defectResults(
   int id, string queryPath, string file, int startline, int startcol, int endline, int endcol,
   string message
 );
 
+/**
+ * A defect query result stored in a dashboard database.
+ */
 class DefectResult extends int {
   DefectResult() { defectResults(this, _, _, _, _, _, _, _) }
 
+  /** Gets the path of the query that reported the result. */
   string getQueryPath() { defectResults(this, result, _, _, _, _, _, _) }
 
+  /** Gets the file in which this query result was reported. */
   File getFile() {
     exists(string path |
       defectResults(this, _, path, _, _, _, _, _) and result.getAbsolutePath() = path
     )
   }
 
+  /** Gets the line on which the location of this query result starts. */
   int getStartLine() { defectResults(this, _, _, result, _, _, _, _) }
 
+  /** Gets the column on which the location of this query result starts. */
   int getStartColumn() { defectResults(this, _, _, _, result, _, _, _) }
 
+  /** Gets the line on which the location of this query result ends. */
   int getEndLine() { defectResults(this, _, _, _, _, result, _, _) }
 
+  /** Gets the column on which the location of this query result ends. */
   int getEndColumn() { defectResults(this, _, _, _, _, _, result, _) }
 
+  /** Gets the message associated with this query result. */
   string getMessage() { defectResults(this, _, _, _, _, _, _, result) }
 
+  /** Gets the URL corresponding to the location of this query result. */
   string getURL() {
     result =
       "file://" + getFile().getAbsolutePath() + ":" + getStartLine() + ":" + getStartColumn() + ":" +

cpp/ql/src/external/ExternalArtifact.qll

@@ -1,26 +1,45 @@
+/**
+ * Provides classes for working with external data.
+ */
+
 import cpp
 
+/**
+ * An external data item.
+ */
 class ExternalData extends @externalDataElement {
+  /** Gets the path of the file this data was loaded from. */
   string getDataPath() { externalData(this, result, _, _) }
 
+  /**
+   * Gets the path of the file this data was loaded from, with its
+   * extension replaced by `.ql`.
+   */
   string getQueryPath() { result = getDataPath().regexpReplaceAll("\\.[^.]*$", ".ql") }
 
+  /** Gets the number of fields in this data item. */
   int getNumFields() { result = 1 + max(int i | externalData(this, _, i, _) | i) }
 
-  string getField(int index) { externalData(this, _, index, result) }
+  /** Gets the value of the `i`th field of this data item. */
+  string getField(int i) { externalData(this, _, i, result) }
 
-  int getFieldAsInt(int index) { result = getField(index).toInt() }
+  /** Gets the integer value of the `i`th field of this data item. */
+  int getFieldAsInt(int i) { result = getField(i).toInt() }
 
-  float getFieldAsFloat(int index) { result = getField(index).toFloat() }
+  /** Gets the floating-point value of the `i`th field of this data item. */
+  float getFieldAsFloat(int i) { result = getField(i).toFloat() }
 
-  date getFieldAsDate(int index) { result = getField(index).toDate() }
+  /** Gets the value of the `i`th field of this data item, interpreted as a date. */
+  date getFieldAsDate(int i) { result = getField(i).toDate() }
 
+  /** Gets a textual representation of this data item. */
   string toString() { result = getQueryPath() + ": " + buildTupleString(0) }
 
-  private string buildTupleString(int start) {
-    start = getNumFields() - 1 and result = getField(start)
+  /** Gets a textual representation of this data item, starting with the `n`th field. */
+  private string buildTupleString(int n) {
+    n = getNumFields() - 1 and result = getField(n)
     or
-    start < getNumFields() - 1 and result = getField(start) + "," + buildTupleString(start + 1)
+    n < getNumFields() - 1 and result = getField(n) + "," + buildTupleString(n + 1)
   }
 }
 
@@ -33,7 +52,9 @@ class DefectExternalData extends ExternalData {
     this.getNumFields() = 2
   }
 
+  /** Gets the URL associated with this data item. */
   string getURL() { result = getField(0) }
 
+  /** Gets the message associated with this data item. */
   string getMessage() { result = getField(1) }
 }

cpp/ql/src/external/MetricFilter.qll

@@ -1,31 +1,58 @@
+/** Provides a class for working with metric query results stored in dashboard databases. */
+
 import cpp
 
+/**
+ * Holds if `id` in the opaque identifier of a result reported by query `queryPath`,
+ * such that `value` is the reported metric value and the location of the result spans
+ * column `startcolumn` of line `startline` to column `endcolumn` of line `endline`
+ * in file `filepath`.
+ *
+ * For more information, see [Locations](https://help.semmle.com/QL/learn-ql/ql/locations.html).
+ */
 external predicate metricResults(
   int id, string queryPath, string file, int startline, int startcol, int endline, int endcol,
   float value
 );
 
+/**
+ * A metric query result stored in a dashboard database.
+ */
 class MetricResult extends int {
   MetricResult() { metricResults(this, _, _, _, _, _, _, _) }
 
+  /** Gets the path of the query that reported the result. */
   string getQueryPath() { metricResults(this, result, _, _, _, _, _, _) }
 
+  /** Gets the file in which this query result was reported. */
   File getFile() {
     exists(string path |
       metricResults(this, _, path, _, _, _, _, _) and result.getAbsolutePath() = path
     )
   }
 
+  /** Gets the line on which the location of this query result starts. */
   int getStartLine() { metricResults(this, _, _, result, _, _, _, _) }
 
+  /** Gets the column on which the location of this query result starts. */
   int getStartColumn() { metricResults(this, _, _, _, result, _, _, _) }
 
+  /** Gets the line on which the location of this query result ends. */
   int getEndLine() { metricResults(this, _, _, _, _, result, _, _) }
 
+  /** Gets the column on which the location of this query result ends. */
   int getEndColumn() { metricResults(this, _, _, _, _, _, result, _) }
 
+  /**
+   * Holds if there is a `Location` entity whose location is the same as
+   * the location of this query result.
+   */
   predicate hasMatchingLocation() { exists(this.getMatchingLocation()) }
 
+  /**
+   * Gets the `Location` entity whose location is the same as the location
+   * of this query result.
+   */
   Location getMatchingLocation() {
     result.getFile() = this.getFile() and
     result.getStartLine() = this.getStartLine() and
@@ -34,8 +61,10 @@ class MetricResult extends int {
     result.getEndColumn() = this.getEndColumn()
   }
 
+  /** Gets the value associated with this query result. */
   float getValue() { metricResults(this, _, _, _, _, _, _, result) }
 
+  /** Gets the URL corresponding to the location of this query result. */
   string getURL() {
     result =
       "file://" + getFile().getAbsolutePath() + ":" + getStartLine() + ":" + getStartColumn() + ":" +

cpp/ql/src/external/VCS.qll

@@ -1,92 +0,0 @@
-import cpp
-
-class Commit extends @svnentry {
-  Commit() {
-    svnaffectedfiles(this, _, _) and
-    exists(date svnDate, date snapshotDate |
-      svnentries(this, _, _, svnDate, _) and
-      snapshotDate(snapshotDate) and
-      svnDate <= snapshotDate
-    )
-  }
-
-  string toString() { result = this.getRevisionName() }
-
-  string getRevisionName() { svnentries(this, result, _, _, _) }
-
-  string getAuthor() { svnentries(this, _, result, _, _) }
-
-  date getDate() { svnentries(this, _, _, result, _) }
-
-  int getChangeSize() { svnentries(this, _, _, _, result) }
-
-  string getMessage() { svnentrymsg(this, result) }
-
-  string getAnAffectedFilePath(string action) {
-    exists(File rawFile | svnaffectedfiles(this, unresolveElement(rawFile), action) |
-      result = rawFile.getAbsolutePath()
-    )
-  }
-
-  string getAnAffectedFilePath() { result = getAnAffectedFilePath(_) }
-
-  File getAnAffectedFile(string action) {
-    // Workaround for incorrect keys in SVN data
-    exists(File svnFile | svnFile.getAbsolutePath() = result.getAbsolutePath() |
-      svnaffectedfiles(this, unresolveElement(svnFile), action)
-    ) and
-    exists(result.getMetrics().getNumberOfLinesOfCode())
-  }
-
-  File getAnAffectedFile() { exists(string action | result = this.getAnAffectedFile(action)) }
-
-  private predicate churnForFile(File f, int added, int deleted) {
-    // Workaround for incorrect keys in SVN data
-    exists(File svnFile | svnFile.getAbsolutePath() = f.getAbsolutePath() |
-      svnchurn(this, unresolveElement(svnFile), added, deleted)
-    ) and
-    exists(f.getMetrics().getNumberOfLinesOfCode())
-  }
-
-  int getRecentChurnForFile(File f) {
-    exists(int added, int deleted | churnForFile(f, added, deleted) and result = added + deleted)
-  }
-
-  int getRecentAdditionsForFile(File f) { churnForFile(f, result, _) }
-
-  int getRecentDeletionsForFile(File f) { churnForFile(f, _, result) }
-
-  predicate isRecent() { recentCommit(this) }
-
-  int daysToNow() {
-    exists(date now | snapshotDate(now) | result = getDate().daysTo(now) and result >= 0)
-  }
-}
-
-class Author extends string {
-  Author() { exists(Commit e | this = e.getAuthor()) }
-
-  Commit getACommit() { result.getAuthor() = this }
-
-  File getAnEditedFile() { result = this.getACommit().getAnAffectedFile() }
-}
-
-predicate recentCommit(Commit e) {
-  exists(date snapshotDate, date commitDate, int days |
-    snapshotDate(snapshotDate) and
-    e.getDate() = commitDate and
-    days = commitDate.daysTo(snapshotDate) and
-    days >= 0 and
-    days <= 60
-  )
-}
-
-date firstChange(File f) {
-  result = min(Commit e, date toMin | f = e.getAnAffectedFile() and toMin = e.getDate() | toMin)
-}
-
-predicate firstCommit(Commit e) {
-  not exists(File f | f = e.getAnAffectedFile() | firstChange(f) < e.getDate())
-}
-
-predicate artificialChange(Commit e) { firstCommit(e) or e.getChangeSize() >= 50000 }

cpp/ql/src/external/tests/DefectFromSVN.ql

@@ -1,20 +0,0 @@
-/**
- * @name Defect from SVN
- * @description A test case for creating a defect from SVN data.
- * @kind problem
- * @problem.severity warning
- * @tags external-data
- * @deprecated
- */
-
-import cpp
-import external.ExternalArtifact
-import external.VCS
-
-predicate numCommits(File f, int i) { i = count(Commit e | e.getAnAffectedFile() = f) }
-
-predicate maxCommits(int i) { i = max(File f, int j | numCommits(f, j) | j) }
-
-from File f, int i
-where numCommits(f, i) and maxCommits(i)
-select f, "This file has " + i + " commits."

cpp/ql/src/external/tests/MetricFromSVN.ql

@@ -1,17 +0,0 @@
-/**
- * @name Metric from SVN
- * @description Find number of commits for a file
- * @treemap.warnOn lowValues
- * @metricType file
- * @tags external-data
- * @deprecated
- */
-
-import cpp
-import external.VCS
-
-predicate numCommits(File f, int i) { i = count(Commit e | e.getAnAffectedFile() = f) }
-
-from File f, int i
-where numCommits(f, i)
-select f, i

cpp/ql/src/filters/RecentDefects.ql

@@ -1,25 +0,0 @@
-/**
- * @name Filter: exclude results from files that have not recently been
- *               edited
- * @description Use this filter to return results only if they are
- *              located in files that have been modified in the 60 days
- *              before the date of the snapshot.
- * @kind problem
- * @id cpp/recent-defects-filter
- * @tags filter
- *       external-data
- * @deprecated
- */
-
-import cpp
-import external.DefectFilter
-import external.VCS
-
-pragma[noopt]
-private predicate recent(File file) {
-  exists(Commit e | file = e.getAnAffectedFile() | e.isRecent() and not artificialChange(e))
-}
-
-from DefectResult res
-where recent(res.getFile())
-select res, res.getMessage()

cpp/ql/src/filters/RecentDefectsForMetric.ql

@@ -1,25 +0,0 @@
-/**
- * @name Metric filter: exclude results from files that have not
- *       recently been edited
- * @description Use this filter to return results only if they are
- *              located in files that have been modified in the 60 days
- *              before the snapshot.
- * @kind treemap
- * @id cpp/recent-defects-for-metric-filter
- * @tags filter
- *       external-data
- * @deprecated
- */
-
-import cpp
-import external.MetricFilter
-import external.VCS
-
-pragma[noopt]
-private predicate recent(File file) {
-  exists(Commit e | file = e.getAnAffectedFile() | e.isRecent() and not artificialChange(e))
-}
-
-from MetricResult res
-where recent(res.getFile())
-select res, res.getValue()

cpp/ql/src/localDefinitions.ql

@@ -0,0 +1,16 @@
+/**
+ * @name Jump-to-definition links
+ * @description Generates use-definition pairs that provide the data
+ *              for jump-to-definition in the code viewer.
+ * @kind definitions
+ * @id cpp/ide-jump-to-definition
+ * @tags ide-contextual-queries/local-definitions
+ */
+
+import definitions
+
+external string selectedSourceFile();
+
+from Top e, Top def, string kind
+where def = definitionOf(e, kind) and e.getFile() = getEncodedFile(selectedSourceFile())
+select e, def, kind

cpp/ql/src/localReferences.ql

@@ -0,0 +1,16 @@
+/**
+ * @name Find-references links
+ * @description Generates use-definition pairs that provide the data
+ *              for find-references in the code viewer.
+ * @kind definitions
+ * @id cpp/ide-find-references
+ * @tags ide-contextual-queries/local-references
+ */
+
+import definitions
+
+external string selectedSourceFile();
+
+from Top e, Top def, string kind
+where def = definitionOf(e, kind) and def.getFile() = getEncodedFile(selectedSourceFile())
+select e, def, kind

cpp/ql/src/objc.qll

@@ -1 +1,7 @@
+/**
+ * DEPRECATED: Objective C is no longer supported.
+ *
+ * Import `cpp` instead of `objc`.
+ */
+
 import cpp

cpp/ql/src/printAst.ql

@@ -0,0 +1,27 @@
+/**
+ * @name Print AST
+ * @description Outputs a representation of a file's Abstract Syntax Tree. This
+ *              query is used by the VS Code extension.
+ * @id cpp/print-ast
+ * @kind graph
+ * @tags ide-contextual-queries/print-ast
+ */
+
+import cpp
+import semmle.code.cpp.PrintAST
+import definitions
+
+/**
+ * The source file to generate an AST from.
+ */
+external string selectedSourceFile();
+
+class Cfg extends PrintASTConfiguration {
+  /**
+   * Holds if the AST for `func` should be printed.
+   * Print All functions from the selected file.
+   */
+  override predicate shouldPrintFunction(Function func) {
+    func.getFile() = getEncodedFile(selectedSourceFile())
+  }
+}

cpp/ql/src/semmle/code/cpp/ASTConsistency.ql

@@ -0,0 +1,9 @@
+/**
+ * @name AST Consistency Check
+ * @description Performs consistency checks on the Abstract Syntax Tree. This query should have no results.
+ * @kind table
+ * @id cpp/ast-consistency-check
+ */
+
+import cpp
+import CastConsistency

cpp/ql/src/semmle/code/cpp/ASTSanity.ql

@@ -1,9 +0,0 @@
-/**
- * @name AST Sanity Check
- * @description Performs sanity checks on the Abstract Syntax Tree. This query should have no results.
- * @kind table
- * @id cpp/ast-sanity-check
- */
-
-import cpp
-import CastSanity

cpp/ql/src/semmle/code/cpp/AutogeneratedFile.qll

@@ -1,3 +1,8 @@
+/**
+ * Provides a class and predicate for recognizing files that are likely to have been generated
+ * automatically.
+ */
+
 import semmle.code.cpp.Comments
 import semmle.code.cpp.File
 import semmle.code.cpp.Preprocessor

cpp/ql/src/semmle/code/cpp/Class.qll

@@ -1,3 +1,7 @@
+/**
+ * Provides classes representing C++ classes, including structs, unions, and template classes.
+ */
+
 import semmle.code.cpp.Type
 import semmle.code.cpp.UserType
 import semmle.code.cpp.metrics.MetricClass
@@ -29,7 +33,7 @@ private import semmle.code.cpp.internal.ResolveClass
 class Class extends UserType {
   Class() { isClass(underlyingElement(this)) }
 
-  override string getCanonicalQLClass() { result = "Class" }
+  override string getAPrimaryQlClass() { result = "Class" }
 
   /** Gets a child declaration of this class, struct or union. */
   override Declaration getADeclaration() { result = this.getAMember() }
@@ -458,6 +462,15 @@ class Class extends UserType {
     exists(ClassDerivation d | d.getDerivedClass() = this and d = result)
   }
 
+  /**
+   * Gets class derivation number `index` of this class/struct, for example the
+   * `public B` is derivation 1 in the following code:
+   * ```
+   * class D : public A, public B, public C {
+   *   ...
+   * };
+   * ```
+   */
   ClassDerivation getDerivation(int index) {
     exists(ClassDerivation d | d.getDerivedClass() = this and d.getIndex() = index and d = result)
   }
@@ -755,7 +768,7 @@ class ClassDerivation extends Locatable, @derivation {
    */
   Class getBaseClass() { result = getBaseType().getUnderlyingType() }
 
-  override string getCanonicalQLClass() { result = "ClassDerivation" }
+  override string getAPrimaryQlClass() { result = "ClassDerivation" }
 
   /**
    * Gets the type from which we are deriving, without resolving any
@@ -836,9 +849,7 @@ class ClassDerivation extends Locatable, @derivation {
 class LocalClass extends Class {
   LocalClass() { isLocal() }
 
-  override string getCanonicalQLClass() {
-    not this instanceof LocalStruct and result = "LocalClass"
-  }
+  override string getAPrimaryQlClass() { not this instanceof LocalStruct and result = "LocalClass" }
 
   override Function getEnclosingAccessHolder() { result = this.getEnclosingFunction() }
 }
@@ -859,7 +870,7 @@ class LocalClass extends Class {
 class NestedClass extends Class {
   NestedClass() { this.isMember() }
 
-  override string getCanonicalQLClass() {
+  override string getAPrimaryQlClass() {
     not this instanceof NestedStruct and result = "NestedClass"
   }
 
@@ -880,7 +891,7 @@ class NestedClass extends Class {
 class AbstractClass extends Class {
   AbstractClass() { exists(PureVirtualFunction f | this.getAMemberFunction() = f) }
 
-  override string getCanonicalQLClass() { result = "AbstractClass" }
+  override string getAPrimaryQlClass() { result = "AbstractClass" }
 }
 
 /**
@@ -900,12 +911,28 @@ class AbstractClass extends Class {
 class TemplateClass extends Class {
   TemplateClass() { usertypes(underlyingElement(this), _, 6) }
 
+  /**
+   * Gets a class instantiated from this template.
+   *
+   * For example for `MyTemplateClass<T>` in the following code, the results are
+   * `MyTemplateClass<int>` and `MyTemplateClass<long>`:
+   * ```
+   * template<class T>
+   * class MyTemplateClass {
+   *   ...
+   * };
+   *
+   * MyTemplateClass<int> instance;
+   *
+   * MyTemplateClass<long> instance;
+   * ```
+   */
   Class getAnInstantiation() {
     result.isConstructedFrom(this) and
     exists(result.getATemplateArgument())
   }
 
-  override string getCanonicalQLClass() { result = "TemplateClass" }
+  override string getAPrimaryQlClass() { result = "TemplateClass" }
 }
 
 /**
@@ -926,7 +953,7 @@ class ClassTemplateInstantiation extends Class {
 
   ClassTemplateInstantiation() { tc.getAnInstantiation() = this }
 
-  override string getCanonicalQLClass() { result = "ClassTemplateInstantiation" }
+  override string getAPrimaryQlClass() { result = "ClassTemplateInstantiation" }
 
   /**
    * Gets the class template from which this instantiation was instantiated.
@@ -967,7 +994,7 @@ abstract class ClassTemplateSpecialization extends Class {
       count(int i | exists(result.getTemplateArgument(i)))
   }
 
-  override string getCanonicalQLClass() { result = "ClassTemplateSpecialization" }
+  override string getAPrimaryQlClass() { result = "ClassTemplateSpecialization" }
 }
 
 /**
@@ -996,7 +1023,7 @@ class FullClassTemplateSpecialization extends ClassTemplateSpecialization {
     not this instanceof ClassTemplateInstantiation
   }
 
-  override string getCanonicalQLClass() { result = "FullClassTemplateSpecialization" }
+  override string getAPrimaryQlClass() { result = "FullClassTemplateSpecialization" }
 }
 
 /**
@@ -1035,7 +1062,7 @@ class PartialClassTemplateSpecialization extends ClassTemplateSpecialization {
       count(int i | exists(getTemplateArgument(i)))
   }
 
-  override string getCanonicalQLClass() { result = "PartialClassTemplateSpecialization" }
+  override string getAPrimaryQlClass() { result = "PartialClassTemplateSpecialization" }
 }
 
 /**
@@ -1060,7 +1087,7 @@ deprecated class Interface extends Class {
     )
   }
 
-  override string getCanonicalQLClass() { result = "Interface" }
+  override string getAPrimaryQlClass() { result = "Interface" }
 }
 
 /**
@@ -1075,7 +1102,7 @@ deprecated class Interface extends Class {
 class VirtualClassDerivation extends ClassDerivation {
   VirtualClassDerivation() { hasSpecifier("virtual") }
 
-  override string getCanonicalQLClass() { result = "VirtualClassDerivation" }
+  override string getAPrimaryQlClass() { result = "VirtualClassDerivation" }
 }
 
 /**
@@ -1095,7 +1122,7 @@ class VirtualClassDerivation extends ClassDerivation {
 class VirtualBaseClass extends Class {
   VirtualBaseClass() { exists(VirtualClassDerivation cd | cd.getBaseClass() = this) }
 
-  override string getCanonicalQLClass() { result = "VirtualBaseClass" }
+  override string getAPrimaryQlClass() { result = "VirtualBaseClass" }
 
   /** A virtual class derivation of which this class/struct is the base. */
   VirtualClassDerivation getAVirtualDerivation() { result.getBaseClass() = this }
@@ -1117,7 +1144,7 @@ class VirtualBaseClass extends Class {
 class ProxyClass extends UserType {
   ProxyClass() { usertypes(underlyingElement(this), _, 9) }
 
-  override string getCanonicalQLClass() { result = "ProxyClass" }
+  override string getAPrimaryQlClass() { result = "ProxyClass" }
 
   /** Gets the location of the proxy class. */
   override Location getLocation() { result = getTemplateParameter().getDefinitionLocation() }

cpp/ql/src/semmle/code/cpp/Comments.qll

@@ -1,3 +1,7 @@
+/**
+ * Provides classes representing C and C++ comments.
+ */
+
 import semmle.code.cpp.Location
 import semmle.code.cpp.Element
 
@@ -13,8 +17,20 @@ class Comment extends Locatable, @comment {
 
   override Location getLocation() { comments(underlyingElement(this), _, result) }
 
+  /**
+   * Gets the text of this comment, including the opening `//` or `/*`, and the closing `*``/` if
+   * present.
+   */
   string getContents() { comments(underlyingElement(this), result, _) }
 
+  /**
+   * Gets the AST element this comment is associated with. For example, the comment in the
+   * following code is associated with the declaration of `j`.
+   * ```
+   * int i;
+   * int j; // Comment on j
+   * ```
+   */
   Element getCommentedElement() {
     commentbinding(underlyingElement(this), unresolveElement(result))
   }

cpp/ql/src/semmle/code/cpp/Compilation.qll

@@ -1,3 +1,7 @@
+/**
+ * Provides a class representing individual compiler invocations that occurred during the build.
+ */
+
 import semmle.code.cpp.File
 
 /*
@@ -40,6 +44,7 @@ class Compilation extends @compilation {
   /** Gets a file compiled during this invocation. */
   File getAFileCompiled() { result = getFileCompiled(_) }
 
+  /** Gets the `i`th file compiled during this invocation */
   File getFileCompiled(int i) { compilation_compiling_files(this, i, unresolveElement(result)) }
 
   /**

cpp/ql/src/semmle/code/cpp/Declaration.qll

@@ -1,3 +1,7 @@
+/**
+ * Provides classes for working with C and C++ declarations.
+ */
+
 import semmle.code.cpp.Element
 import semmle.code.cpp.Specifier
 import semmle.code.cpp.Namespace
@@ -98,7 +102,12 @@ class Declaration extends Locatable, @declaration {
     this.hasQualifiedName(namespaceQualifier, "", baseName)
   }
 
-  override string toString() { result = this.getName() }
+  /**
+   * Gets a description of this `Declaration` for display purposes.
+   */
+  string getDescription() { result = this.getName() }
+
+  final override string toString() { result = this.getDescription() }
 
   /**
    * Gets the name of this declaration.
@@ -115,7 +124,7 @@ class Declaration extends Locatable, @declaration {
    * To test whether this declaration has a particular name in the global
    * namespace, use `hasGlobalName`.
    */
-  abstract string getName();
+  string getName() { none() } // overridden in subclasses
 
   /** Holds if this declaration has the given name. */
   predicate hasName(string name) { name = this.getName() }
@@ -131,7 +140,7 @@ class Declaration extends Locatable, @declaration {
   }
 
   /** Gets a specifier of this declaration. */
-  abstract Specifier getASpecifier();
+  Specifier getASpecifier() { none() } // overridden in subclasses
 
   /** Holds if this declaration has a specifier with the given name. */
   predicate hasSpecifier(string name) { this.getASpecifier().hasName(name) }
@@ -147,7 +156,7 @@ class Declaration extends Locatable, @declaration {
    * Gets the location of a declaration entry corresponding to this
    * declaration.
    */
-  abstract Location getADeclarationLocation();
+  Location getADeclarationLocation() { none() } // overridden in subclasses
 
   /**
    * Gets the declaration entry corresponding to this declaration that is a
@@ -156,11 +165,12 @@ class Declaration extends Locatable, @declaration {
   DeclarationEntry getDefinition() { none() }
 
   /** Gets the location of the definition, if any. */
-  abstract Location getDefinitionLocation();
+  Location getDefinitionLocation() { none() } // overridden in subclasses
 
   /** Holds if the declaration has a definition. */
   predicate hasDefinition() { exists(this.getDefinition()) }
 
+  /** DEPRECATED: Use `hasDefinition` instead. */
   predicate isDefined() { hasDefinition() }
 
   /** Gets the preferred location of this declaration, if any. */
@@ -279,6 +289,8 @@ class Declaration extends Locatable, @declaration {
   }
 }
 
+private class TDeclarationEntry = @var_decl or @type_decl or @fun_decl;
+
 /**
  * A C/C++ declaration entry. For example the following code contains five
  * declaration entries:
@@ -294,16 +306,16 @@ class Declaration extends Locatable, @declaration {
  * See the comment above `Declaration` for an explanation of the relationship
  * between `Declaration` and `DeclarationEntry`.
  */
-abstract class DeclarationEntry extends Locatable {
+class DeclarationEntry extends Locatable, TDeclarationEntry {
   /** Gets a specifier associated with this declaration entry. */
-  abstract string getASpecifier();
+  string getASpecifier() { none() } // overridden in subclasses
 
   /**
    * Gets the name associated with the corresponding definition (where
    * available), or the name declared by this entry otherwise.
    */
   string getCanonicalName() {
-    if getDeclaration().isDefined()
+    if getDeclaration().hasDefinition()
     then result = getDeclaration().getDefinition().getName()
     else result = getName()
   }
@@ -319,10 +331,10 @@ abstract class DeclarationEntry extends Locatable {
    *  `I.getADeclarationEntry()` returns `D`
    *  but `D.getDeclaration()` only returns `C`
    */
-  abstract Declaration getDeclaration();
+  Declaration getDeclaration() { none() } // overridden in subclasses
 
   /** Gets the name associated with this declaration entry, if any. */
-  abstract string getName();
+  string getName() { none() } // overridden in subclasses
 
   /**
    * Gets the type associated with this declaration entry.
@@ -331,7 +343,7 @@ abstract class DeclarationEntry extends Locatable {
    * For function declarations, get the return type of the function.
    * For type declarations, get the type being declared.
    */
-  abstract Type getType();
+  Type getType() { none() } // overridden in subclasses
 
   /**
    * Gets the type associated with this declaration entry after specifiers
@@ -349,7 +361,7 @@ abstract class DeclarationEntry extends Locatable {
   predicate hasSpecifier(string specifier) { getASpecifier() = specifier }
 
   /** Holds if this declaration entry is a definition. */
-  abstract predicate isDefinition();
+  predicate isDefinition() { none() } // overridden in subclasses
 
   override string toString() {
     if isDefinition()
@@ -361,6 +373,8 @@ abstract class DeclarationEntry extends Locatable {
   }
 }
 
+private class TAccessHolder = @function or @usertype;
+
 /**
  * A declaration that can potentially have more C++ access rights than its
  * enclosing element. This comprises `Class` (they have access to their own
@@ -382,7 +396,7 @@ abstract class DeclarationEntry extends Locatable {
  * the informal phrase "_R_ occurs in a member or friend of class C", where
  * `AccessHolder` corresponds to this _R_.
  */
-abstract class AccessHolder extends Declaration {
+class AccessHolder extends Declaration, TAccessHolder {
   /**
    * Holds if `this` can access private members of class `c`.
    *
@@ -400,7 +414,7 @@ abstract class AccessHolder extends Declaration {
   /**
    * Gets the nearest enclosing `AccessHolder`.
    */
-  abstract AccessHolder getEnclosingAccessHolder();
+  AccessHolder getEnclosingAccessHolder() { none() } // overridden in subclasses
 
   /**
    * Holds if a base class `base` of `derived` _is accessible at_ `this` (N4140

cpp/ql/src/semmle/code/cpp/Diagnostics.qll

@@ -1,3 +1,7 @@
+/**
+ * Provides classes representing warnings generated during compilation.
+ */
+
 import semmle.code.cpp.Location
 
 /** A compiler-generated error, warning or remark. */
@@ -11,6 +15,7 @@ class Diagnostic extends Locatable, @diagnostic {
   /** Gets the error code for this compiler message. */
   string getTag() { diagnostics(underlyingElement(this), _, result, _, _, _) }
 
+  /** Holds if `s` is the error code for this compiler message. */
   predicate hasTag(string s) { this.getTag() = s }
 
   /**

cpp/ql/src/semmle/code/cpp/Element.qll

@@ -1,3 +1,8 @@
+/**
+ * Provides the `Element` class, which is the base class for all classes representing C or C++
+ * program elements.
+ */
+
 import semmle.code.cpp.Location
 private import semmle.code.cpp.Enclosing
 private import semmle.code.cpp.internal.ResolveClass
@@ -50,12 +55,21 @@ class ElementBase extends @element {
   cached
   string toString() { none() }
 
+  /** DEPRECATED: use `getAPrimaryQlClass` instead. */
+  deprecated string getCanonicalQLClass() { result = this.getAPrimaryQlClass() }
+
   /**
-   * Canonical QL class corresponding to this element.
+   * Gets the name of a primary CodeQL class to which this element belongs.
    *
-   * ElementBase is the root class for this predicate.
+   * For most elements, this is simply the most precise syntactic category to
+   * which they belong; for example, `AddExpr` is a primary class, but
+   * `BinaryOperation` is not.
+   *
+   * This predicate always has a result. If no primary class can be
+   * determined, the result is `"???"`. If multiple primary classes match,
+   * this predicate can have multiple results.
    */
-  string getCanonicalQLClass() { result = "???" }
+  string getAPrimaryQlClass() { result = "???" }
 }
 
 /**
@@ -183,7 +197,8 @@ class Element extends ElementBase {
     initialisers(underlyingElement(this), unresolveElement(result), _, _) or
     exprconv(unresolveElement(result), underlyingElement(this)) or
     param_decl_bind(underlyingElement(this), _, unresolveElement(result)) or
-    using_container(unresolveElement(result), underlyingElement(this))
+    using_container(unresolveElement(result), underlyingElement(this)) or
+    static_asserts(unresolveElement(this), _, _, _, underlyingElement(result))
   }
 
   /** Gets the closest `Element` enclosing this one. */
@@ -261,9 +276,15 @@ private predicate isFromUninstantiatedTemplateRec(Element e, Element template) {
 class StaticAssert extends Locatable, @static_assert {
   override string toString() { result = "static_assert(..., \"" + getMessage() + "\")" }
 
-  Expr getCondition() { static_asserts(underlyingElement(this), unresolveElement(result), _, _) }
+  /**
+   * Gets the expression which this static assertion ensures is true.
+   */
+  Expr getCondition() { static_asserts(underlyingElement(this), unresolveElement(result), _, _, _) }
 
-  string getMessage() { static_asserts(underlyingElement(this), _, result, _) }
+  /**
+   * Gets the message which will be reported by the compiler if this static assertion fails.
+   */
+  string getMessage() { static_asserts(underlyingElement(this), _, result, _, _) }
 
-  override Location getLocation() { static_asserts(underlyingElement(this), _, _, result) }
+  override Location getLocation() { static_asserts(underlyingElement(this), _, _, result, _) }
 }

cpp/ql/src/semmle/code/cpp/Enclosing.qll

@@ -1,3 +1,7 @@
+/**
+ * Provides predicates for finding the smallest element that encloses an expression or statement.
+ */
+
 import cpp
 
 /**

cpp/ql/src/semmle/code/cpp/Enum.qll

@@ -1,3 +1,7 @@
+/**
+ * Provides classes representing C/C++ enums and enum constants.
+ */
+
 import semmle.code.cpp.Type
 private import semmle.code.cpp.internal.ResolveClass
 
@@ -19,11 +23,22 @@ class Enum extends UserType, IntegralOrEnumType {
   /** Gets an enumerator of this enumeration. */
   EnumConstant getAnEnumConstant() { result.getDeclaringEnum() = this }
 
+  /**
+   * Gets the enumerator of this enumeration that was declared at the zero-based position `index`.
+   * For example, `zero` is at index 2 in the following declaration:
+   * ```
+   * enum ReversedOrder {
+   *   two = 2,
+   *   one = 1,
+   *   zero = 0
+   * };
+   * ```
+   */
   EnumConstant getEnumConstant(int index) {
     enumconstants(unresolveElement(result), underlyingElement(this), index, _, _, _)
   }
 
-  override string getCanonicalQLClass() { result = "Enum" }
+  override string getAPrimaryQlClass() { result = "Enum" }
 
   /**
    * Gets a descriptive string for the enum. This method is only intended to
@@ -72,7 +87,7 @@ class Enum extends UserType, IntegralOrEnumType {
 class LocalEnum extends Enum {
   LocalEnum() { isLocal() }
 
-  override string getCanonicalQLClass() { result = "LocalEnum" }
+  override string getAPrimaryQlClass() { result = "LocalEnum" }
 }
 
 /**
@@ -90,7 +105,7 @@ class LocalEnum extends Enum {
 class NestedEnum extends Enum {
   NestedEnum() { this.isMember() }
 
-  override string getCanonicalQLClass() { result = "NestedEnum" }
+  override string getAPrimaryQlClass() { result = "NestedEnum" }
 
   /** Holds if this member is private. */
   predicate isPrivate() { this.hasSpecifier("private") }
@@ -115,7 +130,7 @@ class NestedEnum extends Enum {
 class ScopedEnum extends Enum {
   ScopedEnum() { usertypes(underlyingElement(this), _, 13) }
 
-  override string getCanonicalQLClass() { result = "ScopedEnum" }
+  override string getAPrimaryQlClass() { result = "ScopedEnum" }
 }
 
 /**
@@ -138,7 +153,7 @@ class EnumConstant extends Declaration, @enumconstant {
     enumconstants(underlyingElement(this), unresolveElement(result), _, _, _, _)
   }
 
-  override string getCanonicalQLClass() { result = "EnumConstant" }
+  override string getAPrimaryQlClass() { result = "EnumConstant" }
 
   override Class getDeclaringType() { result = this.getDeclaringEnum().getDeclaringType() }
 

cpp/ql/src/semmle/code/cpp/Field.qll

@@ -1,3 +1,7 @@
+/**
+ * Provides classes representing C structure members and C++ non-static member variables.
+ */
+
 import semmle.code.cpp.Variable
 import semmle.code.cpp.Enum
 import semmle.code.cpp.exprs.Access
@@ -19,7 +23,7 @@ import semmle.code.cpp.exprs.Access
 class Field extends MemberVariable {
   Field() { fieldoffsets(underlyingElement(this), _, _) }
 
-  override string getCanonicalQLClass() { result = "Field" }
+  override string getAPrimaryQlClass() { result = "Field" }
 
   /**
    * Gets the offset of this field in bytes from the start of its declaring
@@ -86,7 +90,7 @@ class Field extends MemberVariable {
 class BitField extends Field {
   BitField() { bitfield(underlyingElement(this), _, _) }
 
-  override string getCanonicalQLClass() { result = "BitField" }
+  override string getAPrimaryQlClass() { result = "BitField" }
 
   /**
    * Gets the size of this bitfield in bits (on the machine where facts

cpp/ql/src/semmle/code/cpp/File.qll

@@ -1,9 +1,13 @@
+/**
+ * Provides classes representing files and folders.
+ */
+
 import semmle.code.cpp.Element
 import semmle.code.cpp.Declaration
 import semmle.code.cpp.metrics.MetricFile
 
 /** A file or folder. */
-abstract class Container extends Locatable, @container {
+class Container extends Locatable, @container {
   /**
    * Gets the absolute, canonical path of this container, using forward slashes
    * as path separator.
@@ -28,7 +32,7 @@ abstract class Container extends Locatable, @container {
    * a bare root prefix, that is, the path has no path segments. A container
    * whose absolute path has no segments is always a `Folder`, not a `File`.
    */
-  abstract string getAbsolutePath();
+  string getAbsolutePath() { none() } // overridden by subclasses
 
   /**
    * DEPRECATED: Use `getLocation` instead.
@@ -36,7 +40,7 @@ abstract class Container extends Locatable, @container {
    *
    * For more information see [Providing URLs](https://help.semmle.com/QL/learn-ql/ql/locations.html#providing-urls).
    */
-  abstract deprecated string getURL();
+  deprecated string getURL() { none() } // overridden by subclasses
 
   /**
    * Gets the relative path of this file or folder from the root folder of the
@@ -174,7 +178,7 @@ class Folder extends Container, @folder {
     result.hasLocationInfo(_, 0, 0, 0, 0)
   }
 
-  override string getCanonicalQLClass() { result = "Folder" }
+  override string getAPrimaryQlClass() { result = "Folder" }
 
   /**
    * DEPRECATED: Use `getLocation` instead.
@@ -242,7 +246,7 @@ class File extends Container, @file {
 
   override string toString() { result = Container.super.toString() }
 
-  override string getCanonicalQLClass() { result = "File" }
+  override string getAPrimaryQlClass() { result = "File" }
 
   override Location getLocation() {
     result.getContainer() = this and
@@ -261,18 +265,6 @@ class File extends Container, @file {
   /** Holds if this file was compiled as C++ (at any point). */
   predicate compiledAsCpp() { fileannotations(underlyingElement(this), 1, "compiled as c++", "1") }
 
-  /**
-   * DEPRECATED: Objective-C is no longer supported.
-   * Holds if this file was compiled as Objective C (at any point).
-   */
-  deprecated predicate compiledAsObjC() { none() }
-
-  /**
-   * DEPRECATED: Objective-C is no longer supported.
-   * Holds if this file was compiled as Objective C++ (at any point).
-   */
-  deprecated predicate compiledAsObjCpp() { none() }
-
   /**
    * Holds if this file was compiled by a Microsoft compiler (at any point).
    *
@@ -316,14 +308,6 @@ class File extends Container, @file {
     exists(Include i | i.getFile() = this and i.getIncludedFile() = result)
   }
 
-  /**
-   * DEPRECATED: use `getParentContainer` instead.
-   * Gets the folder which contains this file.
-   */
-  deprecated Folder getParent() {
-    containerparent(unresolveElement(result), underlyingElement(this))
-  }
-
   /**
    * Holds if this file may be from source. This predicate holds for all files
    * except the dummy file, whose name is the empty string, which contains
@@ -341,28 +325,6 @@ class File extends Container, @file {
   /** Gets the metric file. */
   MetricFile getMetrics() { result = this }
 
-  /**
-   * DEPRECATED: Use `getAbsolutePath` instead.
-   * Gets the full name of this file, for example:
-   * "/usr/home/me/myprogram.c".
-   */
-  deprecated string getName() { files(underlyingElement(this), result, _, _, _) }
-
-  /**
-   * DEPRECATED: Use `getAbsolutePath` instead.
-   * Holds if this file has the specified full name.
-   *
-   * Example usage: `f.hasName("/usr/home/me/myprogram.c")`.
-   */
-  deprecated predicate hasName(string name) { name = this.getName() }
-
-  /**
-   * DEPRECATED: Use `getAbsolutePath` instead.
-   * Gets the full name of this file, for example
-   * "/usr/home/me/myprogram.c".
-   */
-  deprecated string getFullName() { result = this.getName() }
-
   /**
    * Gets the remainder of the base name after the first dot character. Note
    * that the name of this predicate is in plural form, unlike `getExtension`,
@@ -377,22 +339,6 @@ class File extends Container, @file {
    */
   string getExtensions() { files(underlyingElement(this), _, _, result, _) }
 
-  /**
-   * DEPRECATED: Use `getBaseName` instead.
-   * Gets the name and extension(s), but not path, of a file. For example,
-   * if the full name is "/path/to/filename.a.bcd" then the filename is
-   * "filename.a.bcd".
-   */
-  deprecated string getFileName() {
-    // [a/b.c/d/]fileName
-    //         ^ beginAfter
-    exists(string fullName, int beginAfter |
-      fullName = this.getName() and
-      beginAfter = max(int i | i = -1 or fullName.charAt(i) = "/" | i) and
-      result = fullName.suffix(beginAfter + 1)
-    )
-  }
-
   /**
    * Gets the short name of this file, that is, the prefix of its base name up
    * to (but not including) the first dot character if there is one, or the
@@ -436,7 +382,7 @@ class HeaderFile extends File {
     exists(Include i | i.getIncludedFile() = this)
   }
 
-  override string getCanonicalQLClass() { result = "HeaderFile" }
+  override string getAPrimaryQlClass() { result = "HeaderFile" }
 
   /**
    * Holds if this header file does not contain any declaration entries or top level
@@ -462,7 +408,7 @@ class HeaderFile extends File {
 class CFile extends File {
   CFile() { exists(string ext | ext = this.getExtension().toLowerCase() | ext = "c" or ext = "i") }
 
-  override string getCanonicalQLClass() { result = "CFile" }
+  override string getAPrimaryQlClass() { result = "CFile" }
 }
 
 /**
@@ -490,7 +436,7 @@ class CppFile extends File {
     )
   }
 
-  override string getCanonicalQLClass() { result = "CppFile" }
+  override string getAPrimaryQlClass() { result = "CppFile" }
 }
 
 /**

cpp/ql/src/semmle/code/cpp/FriendDecl.qll

@@ -1,3 +1,7 @@
+/**
+ * Provides a class representing C++ `friend` declarations.
+ */
+
 import semmle.code.cpp.Declaration
 private import semmle.code.cpp.internal.ResolveClass
 
@@ -23,7 +27,7 @@ class FriendDecl extends Declaration, @frienddecl {
    */
   override Location getADeclarationLocation() { result = this.getLocation() }
 
-  override string getCanonicalQLClass() { result = "FriendDecl" }
+  override string getAPrimaryQlClass() { result = "FriendDecl" }
 
   /**
    * Implements the abstract method `Declaration.getDefinitionLocation`. A

cpp/ql/src/semmle/code/cpp/Function.qll

@@ -1,5 +1,8 @@
+/**
+ * Provides classes for working with functions, including template functions.
+ */
+
 import semmle.code.cpp.Location
-import semmle.code.cpp.Member
 import semmle.code.cpp.Class
 import semmle.code.cpp.Parameter
 import semmle.code.cpp.exprs.Call
@@ -103,6 +106,9 @@ class Function extends Declaration, ControlFlowNode, AccessHolder, @function {
 
   /**
    * Holds if this function is declared to be `constexpr`.
+   *
+   * Note that this does not hold if the function has been declared
+   * `consteval`.
    */
   predicate isDeclaredConstexpr() { this.hasSpecifier("declared_constexpr") }
 
@@ -115,9 +121,16 @@ class Function extends Declaration, ControlFlowNode, AccessHolder, @function {
    * template <typename T> constexpr int g(T x) { return f(x); }
    * ```
    * `g<int>` is declared constexpr, but is not constexpr.
+   *
+   * Will also hold if this function is `consteval`.
    */
   predicate isConstexpr() { this.hasSpecifier("is_constexpr") }
 
+  /**
+   * Holds if this function is declared to be `consteval`.
+   */
+  predicate isConsteval() { this.hasSpecifier("is_consteval") }
+
   /**
    * Holds if this function is declared with `__attribute__((naked))` or
    * `__declspec(naked)`.
@@ -174,17 +187,8 @@ class Function extends Declaration, ControlFlowNode, AccessHolder, @function {
    * For example: for a function `int Foo(int p1, int p2)` this would
    * return `int p1, int p2`.
    */
-  string getParameterString() { result = getParameterStringFrom(0) }
-
-  private string getParameterStringFrom(int index) {
-    index = getNumberOfParameters() and
-    result = ""
-    or
-    index = getNumberOfParameters() - 1 and
-    result = getParameter(index).getTypedName()
-    or
-    index < getNumberOfParameters() - 1 and
-    result = getParameter(index).getTypedName() + ", " + getParameterStringFrom(index + 1)
+  string getParameterString() {
+    result = concat(int i | | min(getParameter(i).getTypedName()), ", " order by i)
   }
 
   /** Gets a call to this function. */
@@ -509,7 +513,7 @@ class FunctionDeclarationEntry extends DeclarationEntry, @fun_decl {
   /** Gets the function which is being declared or defined. */
   override Function getDeclaration() { result = getFunction() }
 
-  override string getCanonicalQLClass() { result = "FunctionDeclarationEntry" }
+  override string getAPrimaryQlClass() { result = "FunctionDeclarationEntry" }
 
   /** Gets the function which is being declared or defined. */
   Function getFunction() { fun_decls(underlyingElement(this), unresolveElement(result), _, _, _) }
@@ -606,18 +610,8 @@ class FunctionDeclarationEntry extends DeclarationEntry, @fun_decl {
    * For example: for a function 'int Foo(int p1, int p2)' this would
    * return 'int p1, int p2'.
    */
-  string getParameterString() { result = getParameterStringFrom(0) }
-
-  private string getParameterStringFrom(int index) {
-    index = getNumberOfParameters() and
-    result = ""
-    or
-    index = getNumberOfParameters() - 1 and
-    result = getParameterDeclarationEntry(index).getTypedName()
-    or
-    index < getNumberOfParameters() - 1 and
-    result =
-      getParameterDeclarationEntry(index).getTypedName() + ", " + getParameterStringFrom(index + 1)
+  string getParameterString() {
+    result = concat(int i | | min(getParameterDeclarationEntry(i).getTypedName()), ", " order by i)
   }
 
   /**
@@ -704,428 +698,7 @@ class FunctionDeclarationEntry extends DeclarationEntry, @fun_decl {
 class TopLevelFunction extends Function {
   TopLevelFunction() { not this.isMember() }
 
-  override string getCanonicalQLClass() { result = "TopLevelFunction" }
-}
-
-/**
- * A C++ function declared as a member of a class [N4140 9.3]. This includes
- * static member functions. For example the functions `MyStaticMemberFunction`
- * and `MyMemberFunction` in:
- * ```
- * class MyClass {
- * public:
- *   void MyMemberFunction() {
- *     DoSomething();
- *   }
- *
- *   static void MyStaticMemberFunction() {
- *     DoSomething();
- *   }
- * };
- * ```
- */
-class MemberFunction extends Function {
-  MemberFunction() { this.isMember() }
-
-  override string getCanonicalQLClass() {
-    not this instanceof CopyAssignmentOperator and
-    not this instanceof MoveAssignmentOperator and
-    result = "MemberFunction"
-  }
-
-  /**
-   * Gets the number of parameters of this function, including any implicit
-   * `this` parameter.
-   */
-  override int getEffectiveNumberOfParameters() {
-    if isStatic() then result = getNumberOfParameters() else result = getNumberOfParameters() + 1
-  }
-
-  /** Holds if this member is private. */
-  predicate isPrivate() { this.hasSpecifier("private") }
-
-  /** Holds if this member is protected. */
-  predicate isProtected() { this.hasSpecifier("protected") }
-
-  /** Holds if this member is public. */
-  predicate isPublic() { this.hasSpecifier("public") }
-
-  /** Holds if this function overrides that function. */
-  predicate overrides(MemberFunction that) {
-    overrides(underlyingElement(this), unresolveElement(that))
-  }
-
-  /** Gets a directly overridden function. */
-  MemberFunction getAnOverriddenFunction() { this.overrides(result) }
-
-  /** Gets a directly overriding function. */
-  MemberFunction getAnOverridingFunction() { result.overrides(this) }
-
-  /**
-   * Gets the declaration entry for this member function that is within the
-   * class body.
-   */
-  FunctionDeclarationEntry getClassBodyDeclarationEntry() {
-    if strictcount(getADeclarationEntry()) = 1
-    then result = getDefinition()
-    else (
-      result = getADeclarationEntry() and result != getDefinition()
-    )
-  }
-}
-
-/**
- * A C++ virtual function. For example the two functions called
- * `myVirtualFunction` in the following code are each a
- * `VirtualFunction`:
- * ```
- * class A {
- * public:
- *   virtual void myVirtualFunction() = 0;
- * };
- *
- * class B: public A {
- * public:
- *   virtual void myVirtualFunction() {
- *     doSomething();
- *   }
- * };
- * ```
- */
-class VirtualFunction extends MemberFunction {
-  VirtualFunction() { this.hasSpecifier("virtual") or purefunctions(underlyingElement(this)) }
-
-  override string getCanonicalQLClass() { result = "VirtualFunction" }
-
-  /** Holds if this virtual function is pure. */
-  predicate isPure() { this instanceof PureVirtualFunction }
-
-  /**
-   * Holds if this function was declared with the `override` specifier
-   * [N4140 10.3].
-   */
-  predicate isOverrideExplicit() { this.hasSpecifier("override") }
-}
-
-/**
- * A C++ pure virtual function [N4140 10.4]. For example the first function
- * called `myVirtualFunction` in the following code:
- * ```
- * class A {
- * public:
- *   virtual void myVirtualFunction() = 0;
- * };
- *
- * class B: public A {
- * public:
- *   virtual void myVirtualFunction() {
- *     doSomething();
- *   }
- * };
- * ```
- */
-class PureVirtualFunction extends VirtualFunction {
-  PureVirtualFunction() { purefunctions(underlyingElement(this)) }
-
-  override string getCanonicalQLClass() { result = "PureVirtualFunction" }
-}
-
-/**
- * A const C++ member function [N4140 9.3.1/4]. A const function has the
- * `const` specifier and does not modify the state of its class. For example
- * the member function `day` in the following code:
- * ```
- * class MyClass {
- *   ...
- *
- *   int day() const {
- *     return d;
- *   }
- *
- *   ...
- * };
- * ```
- */
-class ConstMemberFunction extends MemberFunction {
-  ConstMemberFunction() { this.hasSpecifier("const") }
-
-  override string getCanonicalQLClass() { result = "ConstMemberFunction" }
-}
-
-/**
- * A C++ constructor [N4140 12.1]. For example the function `MyClass` in the
- * following code is a constructor:
- * ```
- * class MyClass {
- * public:
- *   MyClass() {
- *     ...
- *   }
- * };
- * ```
- */
-class Constructor extends MemberFunction {
-  Constructor() { functions(underlyingElement(this), _, 2) }
-
-  override string getCanonicalQLClass() { result = "Constructor" }
-
-  /**
-   * Holds if this constructor serves as a default constructor.
-   *
-   * This holds for constructors with zero formal parameters. It also holds
-   * for constructors which have a non-zero number of formal parameters,
-   * provided that every parameter has a default value.
-   */
-  predicate isDefault() { forall(Parameter p | p = this.getAParameter() | p.hasInitializer()) }
-
-  /**
-   * Gets an entry in the constructor's initializer list, or a
-   * compiler-generated action which initializes a base class or member
-   * variable.
-   */
-  ConstructorInit getAnInitializer() { result = getInitializer(_) }
-
-  /**
-   * Gets an entry in the constructor's initializer list, or a
-   * compiler-generated action which initializes a base class or member
-   * variable. The index specifies the order in which the initializer is
-   * to be evaluated.
-   */
-  ConstructorInit getInitializer(int i) {
-    exprparents(unresolveElement(result), i, underlyingElement(this))
-  }
-}
-
-/**
- * A function that defines an implicit conversion.
- */
-abstract class ImplicitConversionFunction extends MemberFunction {
-  abstract Type getSourceType();
-
-  abstract Type getDestType();
-}
-
-/**
- * A C++ constructor that also defines an implicit conversion. For example the
- * function `MyClass` in the following code is a `ConversionConstructor`:
- * ```
- * class MyClass {
- * public:
- *   MyClass(const MyOtherClass &from) {
- *     ...
- *   }
- * };
- * ```
- */
-class ConversionConstructor extends Constructor, ImplicitConversionFunction {
-  ConversionConstructor() {
-    strictcount(Parameter p | p = getAParameter() and not p.hasInitializer()) = 1 and
-    not hasSpecifier("explicit") and
-    not this instanceof CopyConstructor
-  }
-
-  override string getCanonicalQLClass() {
-    not this instanceof MoveConstructor and result = "ConversionConstructor"
-  }
-
-  /** Gets the type this `ConversionConstructor` takes as input. */
-  override Type getSourceType() { result = this.getParameter(0).getType() }
-
-  /** Gets the type this `ConversionConstructor` is a constructor of. */
-  override Type getDestType() { result = this.getDeclaringType() }
-}
-
-private predicate hasCopySignature(MemberFunction f) {
-  f.getParameter(0).getUnspecifiedType().(LValueReferenceType).getBaseType() = f.getDeclaringType()
-}
-
-private predicate hasMoveSignature(MemberFunction f) {
-  f.getParameter(0).getUnspecifiedType().(RValueReferenceType).getBaseType() = f.getDeclaringType()
-}
-
-/**
- * A C++ copy constructor [N4140 12.8]. For example the function `MyClass` in
- * the following code is a `CopyConstructor`:
- * ```
- * class MyClass {
- * public:
- *   MyClass(const MyClass &from) {
- *     ...
- *   }
- * };
- * ```
- *
- * As per the standard, a copy constructor of class `T` is a non-template
- * constructor whose first parameter has type `T&`, `const T&`, `volatile
- * T&`, or `const volatile T&`, and either there are no other parameters,
- * or the rest of the parameters all have default values.
- *
- * For template classes, it can generally not be determined until instantiation
- * whether a constructor is a copy constructor. For such classes, `CopyConstructor`
- * over-approximates the set of copy constructors; if an under-approximation is
- * desired instead, see the member predicate
- * `mayNotBeCopyConstructorInInstantiation`.
- */
-class CopyConstructor extends Constructor {
-  CopyConstructor() {
-    hasCopySignature(this) and
-    (
-      // The rest of the parameters all have default values
-      forall(int i | i > 0 and exists(getParameter(i)) | getParameter(i).hasInitializer())
-      or
-      // or this is a template class, in which case the default values have
-      // not been extracted even if they exist. In that case, we assume that
-      // there are default values present since that is the most common case
-      // in real-world code.
-      getDeclaringType() instanceof TemplateClass
-    ) and
-    not exists(getATemplateArgument())
-  }
-
-  override string getCanonicalQLClass() { result = "CopyConstructor" }
-
-  /**
-   * Holds if we cannot determine that this constructor will become a copy
-   * constructor in all instantiations. Depending on template parameters of the
-   * enclosing class, this may become an ordinary constructor or a copy
-   * constructor.
-   */
-  predicate mayNotBeCopyConstructorInInstantiation() {
-    // In general, default arguments of template classes can only be
-    // type-checked for each template instantiation; if an argument in an
-    // instantiation fails to type-check then the corresponding parameter has
-    // no default argument in the instantiation.
-    getDeclaringType() instanceof TemplateClass and
-    getNumberOfParameters() > 1
-  }
-}
-
-/**
- * A C++ move constructor [N4140 12.8]. For example the function `MyClass` in
- * the following code is a `MoveConstructor`:
- * ```
- * class MyClass {
- * public:
- *   MyClass(MyClass &&from) {
- *     ...
- *   }
- * };
- * ```
- *
- * As per the standard, a move constructor of class `T` is a non-template
- * constructor whose first parameter is `T&&`, `const T&&`, `volatile T&&`,
- * or `const volatile T&&`, and either there are no other parameters, or
- * the rest of the parameters all have default values.
- *
- * For template classes, it can generally not be determined until instantiation
- * whether a constructor is a move constructor. For such classes, `MoveConstructor`
- * over-approximates the set of move constructors; if an under-approximation is
- * desired instead, see the member predicate
- * `mayNotBeMoveConstructorInInstantiation`.
- */
-class MoveConstructor extends Constructor {
-  MoveConstructor() {
-    hasMoveSignature(this) and
-    (
-      // The rest of the parameters all have default values
-      forall(int i | i > 0 and exists(getParameter(i)) | getParameter(i).hasInitializer())
-      or
-      // or this is a template class, in which case the default values have
-      // not been extracted even if they exist. In that case, we assume that
-      // there are default values present since that is the most common case
-      // in real-world code.
-      getDeclaringType() instanceof TemplateClass
-    ) and
-    not exists(getATemplateArgument())
-  }
-
-  override string getCanonicalQLClass() { result = "MoveConstructor" }
-
-  /**
-   * Holds if we cannot determine that this constructor will become a move
-   * constructor in all instantiations. Depending on template parameters of the
-   * enclosing class, this may become an ordinary constructor or a move
-   * constructor.
-   */
-  predicate mayNotBeMoveConstructorInInstantiation() {
-    // In general, default arguments of template classes can only be
-    // type-checked for each template instantiation; if an argument in an
-    // instantiation fails to type-check then the corresponding parameter has
-    // no default argument in the instantiation.
-    getDeclaringType() instanceof TemplateClass and
-    getNumberOfParameters() > 1
-  }
-}
-
-/**
- * A C++ constructor that takes no arguments ('default' constructor). This
- * is the constructor that is invoked when no initializer is given. For
- * example the function `MyClass` in the following code is a
- * `NoArgConstructor`:
- * ```
- * class MyClass {
- * public:
- *   MyClass() {
- *     ...
- *   }
- * };
- * ```
- */
-class NoArgConstructor extends Constructor {
-  NoArgConstructor() { this.getNumberOfParameters() = 0 }
-}
-
-/**
- * A C++ destructor [N4140 12.4]. For example the function `~MyClass` in the
- * following code is a destructor:
- * ```
- * class MyClass {
- * public:
- *   ~MyClass() {
- *     ...
- *   }
- * };
- * ```
- */
-class Destructor extends MemberFunction {
-  Destructor() { functions(underlyingElement(this), _, 3) }
-
-  override string getCanonicalQLClass() { result = "Destructor" }
-
-  /**
-   * Gets a compiler-generated action which destructs a base class or member
-   * variable.
-   */
-  DestructorDestruction getADestruction() { result = getDestruction(_) }
-
-  /**
-   * Gets a compiler-generated action which destructs a base class or member
-   * variable. The index specifies the order in which the destruction should
-   * be evaluated.
-   */
-  DestructorDestruction getDestruction(int i) {
-    exprparents(unresolveElement(result), i, underlyingElement(this))
-  }
-}
-
-/**
- * A C++ conversion operator [N4140 12.3.2]. For example the function
- * `operator int` in the following code is a `ConversionOperator`:
- * ```
- * class MyClass {
- * public:
- *   operator int();
- * };
- * ```
- */
-class ConversionOperator extends MemberFunction, ImplicitConversionFunction {
-  ConversionOperator() { functions(underlyingElement(this), _, 4) }
-
-  override string getCanonicalQLClass() { result = "ConversionOperator" }
-
-  override Type getSourceType() { result = this.getDeclaringType() }
-
-  override Type getDestType() { result = this.getType() }
+  override string getAPrimaryQlClass() { result = "TopLevelFunction" }
 }
 
 /**
@@ -1134,69 +707,11 @@ class ConversionOperator extends MemberFunction, ImplicitConversionFunction {
 class Operator extends Function {
   Operator() { functions(underlyingElement(this), _, 5) }
 
-  override string getCanonicalQLClass() {
+  override string getAPrimaryQlClass() {
     not this instanceof MemberFunction and result = "Operator"
   }
 }
 
-/**
- * A C++ copy assignment operator [N4140 12.8]. For example the function
- * `operator=` in the following code is a `CopyAssignmentOperator`:
- * ```
- * class MyClass {
- * public:
- *   MyClass &operator=(const MyClass &other);
- * };
- * ```
- *
- * As per the standard, a copy assignment operator of class `T` is a
- * non-template non-static member function with the name `operator=` that
- * takes exactly one parameter of type `T`, `T&`, `const T&`, `volatile
- * T&`, or `const volatile T&`.
- */
-class CopyAssignmentOperator extends Operator {
-  CopyAssignmentOperator() {
-    hasName("operator=") and
-    (
-      hasCopySignature(this)
-      or
-      // Unlike CopyConstructor, this member allows a non-reference
-      // parameter.
-      getParameter(0).getUnspecifiedType() = getDeclaringType()
-    ) and
-    not exists(this.getParameter(1)) and
-    not exists(getATemplateArgument())
-  }
-
-  override string getCanonicalQLClass() { result = "CopyAssignmentOperator" }
-}
-
-/**
- * A C++ move assignment operator [N4140 12.8]. For example the function
- * `operator=` in the following code is a `MoveAssignmentOperator`:
- * ```
- * class MyClass {
- * public:
- *   MyClass &operator=(MyClass &&other);
- * };
- * ```
- *
- * As per the standard, a move assignment operator of class `T` is a
- * non-template non-static member function with the name `operator=` that
- * takes exactly one parameter of type `T&&`, `const T&&`, `volatile T&&`,
- * or `const volatile T&&`.
- */
-class MoveAssignmentOperator extends Operator {
-  MoveAssignmentOperator() {
-    hasName("operator=") and
-    hasMoveSignature(this) and
-    not exists(this.getParameter(1)) and
-    not exists(getATemplateArgument())
-  }
-
-  override string getCanonicalQLClass() { result = "MoveAssignmentOperator" }
-}
-
 /**
  * A C++ function which has a non-empty template argument list. For example
  * the function `myTemplateFunction` in the following code:
@@ -1223,7 +738,7 @@ class TemplateFunction extends Function {
     is_function_template(underlyingElement(this)) and exists(getATemplateArgument())
   }
 
-  override string getCanonicalQLClass() { result = "TemplateFunction" }
+  override string getAPrimaryQlClass() { result = "TemplateFunction" }
 
   /**
    * Gets a compiler-generated instantiation of this function template.
@@ -1263,7 +778,7 @@ class FunctionTemplateInstantiation extends Function {
 
   FunctionTemplateInstantiation() { tf.getAnInstantiation() = this }
 
-  override string getCanonicalQLClass() { result = "FunctionTemplateInstantiation" }
+  override string getAPrimaryQlClass() { result = "FunctionTemplateInstantiation" }
 
   /**
    * Gets the function template from which this instantiation was instantiated.
@@ -1308,7 +823,7 @@ class FunctionTemplateInstantiation extends Function {
 class FunctionTemplateSpecialization extends Function {
   FunctionTemplateSpecialization() { this.isSpecialization() }
 
-  override string getCanonicalQLClass() { result = "FunctionTemplateSpecialization" }
+  override string getAPrimaryQlClass() { result = "FunctionTemplateSpecialization" }
 
   /**
    * Gets the primary template for the specialization (the function template

cpp/ql/src/semmle/code/cpp/Include.qll

@@ -1,3 +1,8 @@
+/**
+ * Provides classes representing C/C++ `#include`, `#include_next`, and `#import` preprocessor
+ * directives.
+ */
+
 import semmle.code.cpp.Preprocessor
 
 /**

cpp/ql/src/semmle/code/cpp/Initializer.qll

@@ -1,3 +1,7 @@
+/**
+ * Provides the `Initializer` class, representing C/C++ declaration initializers.
+ */
+
 import semmle.code.cpp.controlflow.ControlFlowGraph
 
 /**
@@ -18,7 +22,7 @@ import semmle.code.cpp.controlflow.ControlFlowGraph
 class Initializer extends ControlFlowNode, @initialiser {
   override Location getLocation() { initialisers(underlyingElement(this), _, _, result) }
 
-  override string getCanonicalQLClass() { result = "Initializer" }
+  override string getAPrimaryQlClass() { result = "Initializer" }
 
   /** Holds if this initializer is explicit in the source. */
   override predicate fromSource() { not this.getLocation() instanceof UnknownLocation }