Compare commits

..

15 Commits

Author SHA1 Message Date
Taus
cdd557f877 Python: hotfix - disable instanceFieldStep to avoid type-tracker blowup
The `instanceFieldStep` disjunct of `TypeTrackingInput::levelStepCall`
that was added in 7.2.0 uses `classInstanceTracker(cls)` -- which is
itself a type-tracker -- inside `levelStepCall`. That creates a
structural mutual recursion between the main type-tracker fixpoint and
`classInstanceTracker`, causing the type-tracker delta to blow up to
~100M tuples per iteration on some OOP-heavy Python codebases.
Verified on the python/mypy database: SSRF query wall time goes from
~12s before the offending commit to >40 minutes after it.

This hotfix temporarily drops the `instanceFieldStep` disjunct and
keeps only `inheritedFieldStep`, which does not pull on the call
graph and is well-behaved (verified at ~12s on mypy). The
`instanceFieldStep` helper predicate itself is kept in place, and
the `levelStepCall` body has a commented-out call to it so the
change is trivial to re-enable once the recursion issue is properly
addressed.
2026-07-01 14:31:00 +01:00
Tom Hvitved
2bf6031c0f Python: Update inline test expectations 2026-07-01 13:10:41 +02:00
Tom Hvitved
a5444b573a Python: Improve some flow summaries 2026-07-01 12:05:53 +02:00
Asger F
2ef06c9f96 Merge pull request #22080 from asgerf/unified/commonast-followups
unified: Add or_pattern and fix 'if case let' translation
2026-06-29 12:05:08 +02:00
Asger F
1842382e23 unified: regenerate QL 2026-06-29 11:06:14 +02:00
Asger F
db449dca6a unified: Fix handling of 'if case let' 2026-06-29 11:03:20 +02:00
Asger F
7216d12b9a unified: Avoid singleton or_pattern in Swift switch case mapping 2026-06-29 11:03:20 +02:00
Asger F
c4b4fde0d7 unified: Make switch_case pattern optional; add or_pattern disjunction node 2026-06-29 11:03:00 +02:00
Mario Campos
da3d0cf977 Merge pull request #22062 from github/mario-campos/mirror-maven-central/gradle
Replace `jcenter()` and `mavenCentral()` with Maven Central mirror URL
2026-06-26 11:35:10 -05:00
Mario Campos
1b6ff24642 Fix buildless-fetches.expected for buildless-sibling-projects 2026-06-25 22:57:35 -05:00
Mario Campos
221a54d22e Add Maven Central mirror settings for Maven test project buildless-sibling-projects 2026-06-25 21:44:20 +00:00
Mario Campos
cc215858e4 Fix expected URL fetches for buildless-sibling-projects 2026-06-25 21:12:33 +00:00
Mario Campos
56a1b12c9e Delete extra blank line
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
2026-06-25 15:01:20 -05:00
Mario Campos
688213056c Replace deprecated jcenter() with Maven Central mirror URL for dependency resolution in Gradle build scripts 2026-06-25 19:02:43 +00:00
Mario Campos
1c37688ec1 Replace mavenCentral() with Maven Central mirror URL for dependency resolution in Gradle build scripts 2026-06-25 19:02:37 +00:00
63 changed files with 1086 additions and 757 deletions

View File

@@ -14,7 +14,9 @@ pluginManagement {
repositories {
gradlePluginPortal()
google()
mavenCentral()
maven {
url = 'https://maven-central.storage-download.googleapis.com/maven2/'
}
}
}
dependencyResolutionManagement {
@@ -33,7 +35,9 @@ dependencyResolutionManagement {
repositoriesMode.set(RepositoriesMode.FAIL_ON_PROJECT_REPOS)
repositories {
google()
mavenCentral()
maven {
url = 'https://maven-central.storage-download.googleapis.com/maven2/'
}
}
}
rootProject.name = "Android Sample"

View File

@@ -14,7 +14,9 @@ pluginManagement {
repositories {
gradlePluginPortal()
google()
mavenCentral()
maven {
url = uri("https://maven-central.storage-download.googleapis.com/maven2/")
}
}
}
dependencyResolutionManagement {
@@ -33,7 +35,9 @@ dependencyResolutionManagement {
repositoriesMode.set(RepositoriesMode.FAIL_ON_PROJECT_REPOS)
repositories {
google()
mavenCentral()
maven {
url = uri("https://maven-central.storage-download.googleapis.com/maven2/")
}
}
}
rootProject.name = "Android Sample"

View File

@@ -14,7 +14,9 @@ pluginManagement {
repositories {
gradlePluginPortal()
google()
mavenCentral()
maven {
url = uri("https://maven-central.storage-download.googleapis.com/maven2/")
}
}
}
dependencyResolutionManagement {
@@ -33,7 +35,9 @@ dependencyResolutionManagement {
repositoriesMode.set(RepositoriesMode.FAIL_ON_PROJECT_REPOS)
repositories {
google()
mavenCentral()
maven {
url = uri("https://maven-central.storage-download.googleapis.com/maven2/")
}
}
}
rootProject.name = "Android Sample"

View File

@@ -14,7 +14,9 @@ pluginManagement {
repositories {
gradlePluginPortal()
google()
mavenCentral()
maven {
url = 'https://maven-central.storage-download.googleapis.com/maven2/'
}
}
}
dependencyResolutionManagement {
@@ -33,7 +35,9 @@ dependencyResolutionManagement {
repositoriesMode.set(RepositoriesMode.FAIL_ON_PROJECT_REPOS)
repositories {
google()
mavenCentral()
maven {
url = 'https://maven-central.storage-download.googleapis.com/maven2/'
}
}
}
rootProject.name = "Android Sample"

View File

@@ -13,7 +13,9 @@ buildscript {
repositories {
google()
jcenter()
maven {
url = uri("https://maven-central.storage-download.googleapis.com/maven2/")
}
}
/**
@@ -39,6 +41,8 @@ buildscript {
allprojects {
repositories {
google()
jcenter()
maven {
url = uri("https://maven-central.storage-download.googleapis.com/maven2/")
}
}
}

View File

@@ -13,7 +13,9 @@ buildscript {
repositories {
google()
jcenter()
maven {
url = uri("https://maven-central.storage-download.googleapis.com/maven2/")
}
}
/**
@@ -39,6 +41,8 @@ buildscript {
allprojects {
repositories {
google()
jcenter()
maven {
url = uri("https://maven-central.storage-download.googleapis.com/maven2/")
}
}
}

View File

@@ -13,7 +13,9 @@ buildscript {
repositories {
google()
jcenter()
maven {
url = 'https://maven-central.storage-download.googleapis.com/maven2/'
}
}
/**
@@ -39,6 +41,8 @@ buildscript {
allprojects {
repositories {
google()
jcenter()
maven {
url = 'https://maven-central.storage-download.googleapis.com/maven2/'
}
}
}

View File

@@ -13,7 +13,9 @@ buildscript {
repositories {
google()
jcenter()
maven {
url = 'https://maven-central.storage-download.googleapis.com/maven2/'
}
}
/**
@@ -32,13 +34,15 @@ buildscript {
* dependencies used by all modules in your project, such as third-party plugins
* or libraries. However, you should configure module-specific dependencies in
* each module-level build.gradle file. For new projects, Android Studio
* includes JCenter and Google's Maven repository by default, but it does not
* includes Maven Central and Google's Maven repository by default, but it does not
* configure any dependencies (unless you select a template that requires some).
*/
allprojects {
repositories {
google()
jcenter()
maven {
url = 'https://maven-central.storage-download.googleapis.com/maven2/'
}
}
}

View File

@@ -14,7 +14,9 @@ pluginManagement {
repositories {
gradlePluginPortal()
google()
mavenCentral()
maven {
url = 'https://maven-central.storage-download.googleapis.com/maven2/'
}
}
}
dependencyResolutionManagement {
@@ -33,7 +35,9 @@ dependencyResolutionManagement {
repositoriesMode.set(RepositoriesMode.FAIL_ON_PROJECT_REPOS)
repositories {
google()
mavenCentral()
maven {
url = 'https://maven-central.storage-download.googleapis.com/maven2/'
}
}
}
rootProject.name = "Android Sample"

View File

@@ -8,7 +8,9 @@
apply plugin: 'java-library'
repositories {
mavenCentral()
maven {
url = 'https://maven-central.storage-download.googleapis.com/maven2/'
}
}
dependencies {

View File

@@ -1,5 +1,5 @@
https://repo.maven.apache.org/maven2/org/apache/commons/commons-math3/3.6.1/commons-math3-3.6.1.jar
https://repo.maven.apache.org/maven2/org/apiguardian/apiguardian-api/1.1.2/apiguardian-api-1.1.2.jar
https://repo.maven.apache.org/maven2/org/junit/jupiter/junit-jupiter-api/5.12.1/junit-jupiter-api-5.12.1.jar
https://repo.maven.apache.org/maven2/org/junit/platform/junit-platform-commons/1.12.1/junit-platform-commons-1.12.1.jar
https://repo.maven.apache.org/maven2/org/opentest4j/opentest4j/1.3.0/opentest4j-1.3.0.jar
https://maven-central.storage-download.googleapis.com/maven2/org/apache/commons/commons-math3/3.6.1/commons-math3-3.6.1.jar
https://maven-central.storage-download.googleapis.com/maven2/org/apiguardian/apiguardian-api/1.1.2/apiguardian-api-1.1.2.jar
https://maven-central.storage-download.googleapis.com/maven2/org/junit/jupiter/junit-jupiter-api/5.12.1/junit-jupiter-api-5.12.1.jar
https://maven-central.storage-download.googleapis.com/maven2/org/junit/platform/junit-platform-commons/1.12.1/junit-platform-commons-1.12.1.jar
https://maven-central.storage-download.googleapis.com/maven2/org/opentest4j/opentest4j/1.3.0/opentest4j-1.3.0.jar

View File

@@ -8,7 +8,9 @@
apply plugin: 'java-library'
repositories {
mavenCentral()
maven {
url = 'https://maven-central.storage-download.googleapis.com/maven2/'
}
}
dependencies {

View File

@@ -1,2 +1,2 @@
https://repo.maven.apache.org/maven2/joda-time/joda-time/2.12.7/joda-time-2.12.7-no-tzdb.jar
https://repo.maven.apache.org/maven2/org/apache/commons/commons-math3/3.6.1/commons-math3-3.6.1.jar
https://maven-central.storage-download.googleapis.com/maven2/joda-time/joda-time/2.12.7/joda-time-2.12.7-no-tzdb.jar
https://maven-central.storage-download.googleapis.com/maven2/org/apache/commons/commons-math3/3.6.1/commons-math3-3.6.1.jar

View File

@@ -12,9 +12,9 @@ apply plugin: 'java'
// In this section you declare where to find the dependencies of your project
repositories {
// Use 'jcenter' for resolving your dependencies.
// You can declare any Maven/Ivy/file repository here.
jcenter()
maven {
url = 'https://maven-central.storage-download.googleapis.com/maven2/'
}
}
// In this section you declare the dependencies for your production and test code

View File

@@ -8,7 +8,9 @@
apply plugin: 'java-library'
repositories {
mavenCentral()
maven {
url = 'https://maven-central.storage-download.googleapis.com/maven2/'
}
}
dependencies {

View File

@@ -1 +1 @@
https://repo.maven.apache.org/maven2/org/apache/commons/commons-math3/3.6.1/commons-math3-3.6.1.jar
https://maven-central.storage-download.googleapis.com/maven2/org/apache/commons/commons-math3/3.6.1/commons-math3-3.6.1.jar

View File

@@ -8,7 +8,9 @@
apply plugin: 'java-library'
repositories {
mavenCentral()
maven {
url = 'https://maven-central.storage-download.googleapis.com/maven2/'
}
}
dependencies {

View File

@@ -1 +1 @@
https://repo.maven.apache.org/maven2/org/apache/commons/commons-math3/3.6.1/commons-math3-3.6.1.jar
https://maven-central.storage-download.googleapis.com/maven2/org/apache/commons/commons-math3/3.6.1/commons-math3-3.6.1.jar

View File

@@ -1,6 +1,7 @@
https://jcenter.bintray.com/junit/junit/4.12/junit-4.12.jar
https://jcenter.bintray.com/org/hamcrest/hamcrest-core/1.3/hamcrest-core-1.3.jar
https://jcenter.bintray.com/org/slf4j/slf4j-api/1.7.21/slf4j-api-1.7.21.jar
https://maven-central.storage-download.googleapis.com/maven2/junit/junit/4.11/junit-4.11.jar
https://maven-central.storage-download.googleapis.com/maven2/junit/junit/4.12/junit-4.12.jar
https://maven-central.storage-download.googleapis.com/maven2/org/hamcrest/hamcrest-core/1.3/hamcrest-core-1.3.jar
https://maven-central.storage-download.googleapis.com/maven2/org/slf4j/slf4j-api/1.7.21/slf4j-api-1.7.21.jar
https://repo.maven.apache.org/maven2/com/feiniaojin/naaf/naaf-graceful-response-example/1.0/naaf-graceful-response-example-1.0.jar
https://repo.maven.apache.org/maven2/com/github/MoebiusSolutions/avro-registry-in-source/avro-registry-in-source-tests/1.8/avro-registry-in-source-tests-1.8.jar
https://repo.maven.apache.org/maven2/com/github/MoebiusSolutions/avro-registry-in-source/example-project/1.5/example-project-1.5.jar
@@ -12,7 +13,6 @@ https://repo.maven.apache.org/maven2/de/knutwalker/rx-redis-example_2.11/0.1.2/r
https://repo.maven.apache.org/maven2/de/knutwalker/rx-redis-java-example_2.11/0.1.2/rx-redis-java-example_2.11-0.1.2.jar
https://repo.maven.apache.org/maven2/io/github/scrollsyou/example-spring-boot-starter/1.0.0/example-spring-boot-starter-1.0.0.jar
https://repo.maven.apache.org/maven2/io/streamnative/com/example/maven-central-template/server/3.0.0/server-3.0.0.jar
https://repo.maven.apache.org/maven2/junit/junit/4.11/junit-4.11.jar
https://repo.maven.apache.org/maven2/no/nav/security/token-validation-ktor-demo/3.1.0/token-validation-ktor-demo-3.1.0.jar
https://repo.maven.apache.org/maven2/org/minijax/minijax-example-fileupload/0.5.10/minijax-example-fileupload-0.5.10.jar
https://repo.maven.apache.org/maven2/org/minijax/minijax-example-inject/0.5.10/minijax-example-inject-0.5.10.jar

View File

@@ -12,9 +12,9 @@ apply plugin: 'java'
// In this section you declare where to find the dependencies of your project
repositories {
// Use 'jcenter' for resolving your dependencies.
// You can declare any Maven/Ivy/file repository here.
jcenter()
maven {
url = 'https://maven-central.storage-download.googleapis.com/maven2/'
}
}
// In this section you declare the dependencies for your production and test code

View File

@@ -12,9 +12,9 @@ apply plugin: 'java'
// In this section you declare where to find the dependencies of your project
repositories {
// Use 'jcenter' for resolving your dependencies.
// You can declare any Maven/Ivy/file repository here.
jcenter()
maven {
url = 'https://maven-central.storage-download.googleapis.com/maven2/'
}
}
// In this section you declare the dependencies for your production and test code

View File

@@ -0,0 +1,10 @@
<settings>
<mirrors>
<mirror>
<id>google-maven-central</id>
<name>GCS Maven Central mirror</name>
<url>https://maven-central.storage-download.googleapis.com/maven2/</url>
<mirrorOf>central</mirrorOf>
</mirror>
</mirrors>
</settings>

View File

@@ -26,4 +26,5 @@ maven-project-2/src/main/resources/my-app.properties
maven-project-2/src/main/resources/page.xml
maven-project-2/src/main/resources/struts.xml
maven-project-2/src/test/java/com/example/AppTest4.java
settings.xml
test-db/working/settings.xml

View File

@@ -1,3 +1,5 @@
import os
def test(codeql, use_java_11, java, actions_toolchains_file, check_diagnostics_java):
# The version of gradle used doesn't work on java 17
codeql.database.create(
@@ -5,5 +7,6 @@ def test(codeql, use_java_11, java, actions_toolchains_file, check_diagnostics_j
"CODEQL_EXTRACTOR_JAVA_OPTION_BUILDLESS": "true",
"CODEQL_EXTRACTOR_JAVA_OPTION_BUILDLESS_CLASSPATH_FROM_BUILD_FILES": "true",
"LGTM_INDEX_MAVEN_TOOLCHAINS_FILE": str(actions_toolchains_file),
"LGTM_INDEX_MAVEN_SETTINGS_FILE": os.path.join(os.path.dirname(os.path.realpath(__file__)), "settings.xml"),
}
)

View File

@@ -14,7 +14,9 @@ pluginManagement {
repositories {
gradlePluginPortal()
google()
mavenCentral()
maven {
url = 'https://maven-central.storage-download.googleapis.com/maven2/'
}
}
}
dependencyResolutionManagement {
@@ -33,7 +35,9 @@ dependencyResolutionManagement {
repositoriesMode.set(RepositoriesMode.FAIL_ON_PROJECT_REPOS)
repositories {
google()
mavenCentral()
maven {
url = 'https://maven-central.storage-download.googleapis.com/maven2/'
}
}
}
rootProject.name = "Android Sample"

View File

@@ -12,9 +12,9 @@ apply plugin: 'java'
// In this section you declare where to find the dependencies of your project
repositories {
// Use 'jcenter' for resolving your dependencies.
// You can declare any Maven/Ivy/file repository here.
jcenter()
maven {
url = 'https://maven-central.storage-download.googleapis.com/maven2/'
}
}
// In this section you declare the dependencies for your production and test code

View File

@@ -12,9 +12,9 @@ apply plugin: 'java'
// In this section you declare where to find the dependencies of your project
repositories {
// Use 'jcenter' for resolving your dependencies.
// You can declare any Maven/Ivy/file repository here.
jcenter()
maven {
url = 'https://maven-central.storage-download.googleapis.com/maven2/'
}
}
// In this section you declare the dependencies for your production and test code

View File

@@ -12,8 +12,9 @@ plugins {
}
repositories {
// Use Maven Central for resolving dependencies.
mavenCentral()
maven {
url = uri("https://maven-central.storage-download.googleapis.com/maven2/")
}
}
dependencies {

View File

@@ -12,9 +12,9 @@ apply plugin: 'java'
// In this section you declare where to find the dependencies of your project
repositories {
// Use 'jcenter' for resolving your dependencies.
// You can declare any Maven/Ivy/file repository here.
jcenter()
maven {
url = 'https://maven-central.storage-download.googleapis.com/maven2/'
}
}
// In this section you declare the dependencies for your production and test code

View File

@@ -12,9 +12,9 @@ apply plugin: 'java'
// In this section you declare where to find the dependencies of your project
repositories {
// Use 'jcenter' for resolving your dependencies.
// You can declare any Maven/Ivy/file repository here.
jcenter()
maven {
url = 'https://maven-central.storage-download.googleapis.com/maven2/'
}
}
// In this section you declare the dependencies for your production and test code

View File

@@ -12,9 +12,9 @@ apply plugin: 'java'
// In this section you declare where to find the dependencies of your project
repositories {
// Use 'jcenter' for resolving your dependencies.
// You can declare any Maven/Ivy/file repository here.
jcenter()
maven {
url = 'https://maven-central.storage-download.googleapis.com/maven2/'
}
}
// In this section you declare the dependencies for your production and test code

View File

@@ -12,9 +12,9 @@ apply plugin: 'java'
// In this section you declare where to find the dependencies of your project
repositories {
// Use 'jcenter' for resolving your dependencies.
// You can declare any Maven/Ivy/file repository here.
jcenter()
maven {
url = 'https://maven-central.storage-download.googleapis.com/maven2/'
}
}
// In this section you declare the dependencies for your production and test code

View File

@@ -11,7 +11,9 @@ version = '0.0.1-SNAPSHOT'
// but I omit it to test we recognise the Spring Boot plugin version.
repositories {
mavenCentral()
maven {
url = 'https://maven-central.storage-download.googleapis.com/maven2/'
}
}
dependencies {

View File

@@ -15,8 +15,9 @@ plugins {
}
repositories {
// Use Maven Central for resolving dependencies.
mavenCentral()
maven {
url = 'https://maven-central.storage-download.googleapis.com/maven2/'
}
}
application {

View File

@@ -15,8 +15,9 @@ plugins {
}
repositories {
// Use Maven Central for resolving dependencies.
mavenCentral()
maven {
url = 'https://maven-central.storage-download.googleapis.com/maven2/'
}
}
application {

View File

@@ -4,7 +4,9 @@ plugins {
}
repositories {
mavenCentral()
maven {
url = 'https://maven-central.storage-download.googleapis.com/maven2/'
}
}
dependencies {

View File

@@ -15,8 +15,9 @@ plugins {
}
repositories {
// Use Maven Central for resolving dependencies.
mavenCentral()
maven {
url = 'https://maven-central.storage-download.googleapis.com/maven2/'
}
}
application {

View File

@@ -0,0 +1,5 @@
---
category: minorAnalysis
---
- Temporarily disabled the `instanceFieldStep` disjunct of the internal `TypeTrackingInput::levelStepCall` predicate, which was introduced in 7.2.0 and caused catastrophic query slowdowns on some OOP-heavy Python codebases (e.g. `mypy` and `dask`).

View File

@@ -1138,7 +1138,9 @@ predicate clearsContent(Node n, ContentSet cs) {
* Holds if the value that is being tracked is expected to be stored inside content `c`
* at node `n`.
*/
predicate expectsContent(Node n, ContentSet c) { none() }
predicate expectsContent(Node n, ContentSet c) {
FlowSummaryImpl::Private::Steps::summaryExpectsContent(n.(FlowSummaryNode).getSummaryNode(), c)
}
/**
* Holds if values stored inside attribute `c` are cleared at node `n`.

View File

@@ -91,6 +91,8 @@ module Input implements InputSig<Location, DataFlowImplSpecific::PythonDataFlow>
cs.isAnyTupleOrDictionaryElement() and result = "AnyTupleOrDictionaryElement" and arg = ""
}
string encodeWithContent(ContentSet c, string arg) { result = "With" + encodeContent(c, arg) }
bindingset[token]
ParameterPosition decodeUnknownParameterPosition(AccessPath::AccessPathTokenBase token) {
// needed to support `Argument[x..y]` ranges

View File

@@ -170,7 +170,13 @@ module TypeTrackingInput implements Shared::TypeTrackingInput<Location> {
/** Holds if there is a level step from `nodeFrom` to `nodeTo`, which may depend on the call graph. */
predicate levelStepCall(Node nodeFrom, LocalSourceNode nodeTo) {
instanceFieldStep(nodeFrom, nodeTo)
// HOTFIX: `instanceFieldStep` is temporarily disabled (via `and none()`).
// It uses `classInstanceTracker(cls)` -- itself a type-tracker run --
// from inside `levelStepCall`, creating a structural mutual recursion
// that causes catastrophic query slowdowns on some OOP-heavy Python
// codebases (e.g. mypy and dask). The `and none()` should be removed
// once that recursion is redesigned.
instanceFieldStep(nodeFrom, nodeTo) and none()
or
inheritedFieldStep(nodeFrom, nodeTo)
}

View File

@@ -4199,11 +4199,9 @@ module StdlibPrivate {
// The positional argument contains a mapping.
// TODO: these values can be overwritten by keyword arguments
// - dict mapping
exists(DataFlow::DictionaryElementContent dc, string key | key = dc.getKey() |
input = "Argument[0].DictionaryElement[" + key + "]" and
output = "ReturnValue.DictionaryElement[" + key + "]" and
preservesValue = true
)
input = "Argument[0].WithAnyDictionaryElement" and
output = "ReturnValue" and
preservesValue = true
or
// - list-of-pairs mapping
input = "Argument[0].ListElement.TupleElement[1]" and
@@ -4240,9 +4238,7 @@ module StdlibPrivate {
or
input = "Argument[0].SetElement"
or
exists(DataFlow::TupleElementContent tc, int i | i = tc.getIndex() |
input = "Argument[0].TupleElement[" + i.toString() + "]"
)
input = "Argument[0].AnyTupleElement"
// TODO: Once we have DictKeyContent, we need to transform that into ListElementContent
) and
// Element content is mutated into list element content
@@ -4266,11 +4262,9 @@ module StdlibPrivate {
}
override predicate propagatesFlow(string input, string output, boolean preservesValue) {
exists(DataFlow::TupleElementContent tc, int i | i = tc.getIndex() |
input = "Argument[0].TupleElement[" + i.toString() + "]" and
output = "ReturnValue.TupleElement[" + i.toString() + "]" and
preservesValue = true
)
input = "Argument[0].WithAnyTupleElement" and
output = "ReturnValue" and
preservesValue = true
or
input = "Argument[0].ListElement" and
output = "ReturnValue" and
@@ -4294,9 +4288,7 @@ module StdlibPrivate {
or
input = "Argument[0].SetElement"
or
exists(DataFlow::TupleElementContent tc, int i | i = tc.getIndex() |
input = "Argument[0].TupleElement[" + i.toString() + "]"
)
input = "Argument[0].AnyTupleElement"
// TODO: Once we have DictKeyContent, we need to transform that into ListElementContent
) and
output = "ReturnValue.SetElement" and
@@ -4342,9 +4334,7 @@ module StdlibPrivate {
or
input = "Argument[0].SetElement"
or
exists(DataFlow::TupleElementContent tc, int i | i = tc.getIndex() |
input = "Argument[0].TupleElement[" + i.toString() + "]"
)
input = "Argument[0].AnyTupleElement"
// TODO: Once we have DictKeyContent, we need to transform that into ListElementContent
) and
output = "ReturnValue.ListElement" and
@@ -4372,9 +4362,7 @@ module StdlibPrivate {
or
content = "SetElement"
or
exists(DataFlow::TupleElementContent tc, int i | i = tc.getIndex() |
content = "TupleElement[" + i.toString() + "]"
)
content = "AnyTupleElement"
|
// TODO: Once we have DictKeyContent, we need to transform that into ListElementContent
input = "Argument[0]." + content and
@@ -4404,9 +4392,7 @@ module StdlibPrivate {
or
input = "Argument[0].SetElement"
or
exists(DataFlow::TupleElementContent tc, int i | i = tc.getIndex() |
input = "Argument[0].TupleElement[" + i.toString() + "]"
)
input = "Argument[0].AnyTupleElement"
// TODO: Once we have DictKeyContent, we need to transform that into ListElementContent
) and
output = "ReturnValue.ListElement" and
@@ -4434,9 +4420,7 @@ module StdlibPrivate {
or
input = "Argument[0].SetElement"
or
exists(DataFlow::TupleElementContent tc, int i | i = tc.getIndex() |
input = "Argument[0].TupleElement[" + i.toString() + "]"
)
input = "Argument[0].AnyTupleElement"
// TODO: Once we have DictKeyContent, we need to transform that into ListElementContent
) and
output = "ReturnValue" and
@@ -4468,9 +4452,7 @@ module StdlibPrivate {
// We reduce generality slightly by not tracking tuple contents on list arguments beyond the first, for performance.
// TODO: Once we have TupleElementAny, this generality can be increased.
i = 0 and
exists(DataFlow::TupleElementContent tc, int j | j = tc.getIndex() |
input = "Argument[1].TupleElement[" + j.toString() + "]"
)
input = "Argument[1].AnyTupleElement"
// TODO: Once we have DictKeyContent, we need to transform that into ListElementContent
) and
output = "Argument[0].Parameter[" + i.toString() + "]" and
@@ -4499,9 +4481,7 @@ module StdlibPrivate {
or
input = "Argument[1].SetElement"
or
exists(DataFlow::TupleElementContent tc, int i | i = tc.getIndex() |
input = "Argument[1].TupleElement[" + i.toString() + "]"
)
input = "Argument[1].AnyTupleElement"
// TODO: Once we have DictKeyContent, we need to transform that into ListElementContent
) and
(output = "Argument[0].Parameter[0]" or output = "ReturnValue.ListElement") and
@@ -4525,9 +4505,7 @@ module StdlibPrivate {
or
input = "Argument[0].SetElement"
or
exists(DataFlow::TupleElementContent tc, int i | i = tc.getIndex() |
input = "Argument[0].TupleElement[" + i.toString() + "]"
)
input = "Argument[0].AnyTupleElement"
// TODO: Once we have DictKeyContent, we need to transform that into ListElementContent
) and
output = "ReturnValue.ListElement.TupleElement[1]" and
@@ -4552,12 +4530,7 @@ module StdlibPrivate {
or
input = "Argument[" + i.toString() + "].SetElement"
or
// We reduce generality slightly by not tracking tuple contents on arguments beyond the first two, for performance.
// TODO: Once we have TupleElementAny, this generality can be increased.
i in [0 .. 1] and
exists(DataFlow::TupleElementContent tc, int j | j = tc.getIndex() |
input = "Argument[" + i.toString() + "].TupleElement[" + j.toString() + "]"
)
input = "Argument[" + i.toString() + "].AnyTupleElement"
// TODO: Once we have DictKeyContent, we need to transform that into ListElementContent
) and
output = "ReturnValue.ListElement.TupleElement[" + i.toString() + "]" and
@@ -4580,12 +4553,6 @@ module StdlibPrivate {
override DataFlow::ArgumentNode getACallback() { none() }
override predicate propagatesFlow(string input, string output, boolean preservesValue) {
exists(DataFlow::Content c |
input = "Argument[self]." + c.getMaDRepresentation() and
output = "ReturnValue." + c.getMaDRepresentation() and
preservesValue = true
)
or
input = "Argument[self]" and
output = "ReturnValue" and
preservesValue = true
@@ -4741,12 +4708,10 @@ module StdlibPrivate {
override DataFlow::ArgumentNode getACallback() { none() }
override predicate propagatesFlow(string input, string output, boolean preservesValue) {
exists(DataFlow::DictionaryElementContent dc, string key | key = dc.getKey() |
input = "Argument[self].DictionaryElement[" + key + "]" and
output = "ReturnValue.TupleElement[1]" and
preservesValue = true
// TODO: put `key` into "ReturnValue.TupleElement[0]"
)
input = "Argument[self].AnyDictionaryElement" and
output = "ReturnValue.TupleElement[1]" and
preservesValue = true
// TODO: put `key` into "ReturnValue.TupleElement[0]"
}
}
@@ -4825,11 +4790,9 @@ module StdlibPrivate {
}
override predicate propagatesFlow(string input, string output, boolean preservesValue) {
exists(DataFlow::DictionaryElementContent dc, string key | key = dc.getKey() |
input = "Argument[self].DictionaryElement[" + key + "]" and
output = "ReturnValue.ListElement" and
preservesValue = true
)
input = "Argument[self].AnyDictionaryElement" and
output = "ReturnValue.ListElement" and
preservesValue = true
or
input = "Argument[self]" and
output = "ReturnValue" and
@@ -4876,11 +4839,9 @@ module StdlibPrivate {
}
override predicate propagatesFlow(string input, string output, boolean preservesValue) {
exists(DataFlow::DictionaryElementContent dc, string key | key = dc.getKey() |
input = "Argument[self].DictionaryElement[" + key + "]" and
output = "ReturnValue.ListElement.TupleElement[1]" and
preservesValue = true
)
input = "Argument[self].AnyDictionaryElement" and
output = "ReturnValue.ListElement.TupleElement[1]" and
preservesValue = true
or
// TODO: Add the keys to output list
input = "Argument[self]" and

View File

@@ -589,11 +589,11 @@ def test_zip_tuple():
SINK(z[0][0]) # $ flow="SOURCE, l:-7 -> z[0][0]"
SINK(z[0][1]) # $ flow="SOURCE, l:-7 -> z[0][1]"
SINK_F(z[0][2])
SINK_F(z[0][2]) # $ SPURIOUS: flow="SOURCE, l:-7 -> z[0][2]"
SINK_F(z[0][3])
SINK(z[1][0]) # $ flow="SOURCE, l:-11 -> z[1][0]"
SINK_F(z[1][1]) # $ SPURIOUS: flow="SOURCE, l:-11 -> z[1][1]"
SINK(z[1][2]) # $ MISSING: flow="SOURCE, l:-11 -> z[1][2]" # Tuple contents are not tracked beyond the first two arguments for performance.
SINK(z[1][2]) # $ flow="SOURCE, l:-11 -> z[1][2]"
SINK_F(z[1][3])
@expects(4)

View File

@@ -157,7 +157,7 @@ class MyClass2(object):
print(self.foo) # $ tracked MISSING: tracked=foo
instance = MyClass2()
print(instance.foo) # $ tracked MISSING: tracked=foo
print(instance.foo) # $ MISSING: tracked=foo tracked
instance.print_foo() # $ MISSING: tracked=foo
@@ -195,7 +195,7 @@ class Sub1(Base1):
sub1 = Sub1()
sub1.read_foo()
print(sub1.foo) # $ tracked MISSING: tracked=foo
print(sub1.foo) # $ MISSING: tracked=foo tracked
# attribute written in a subclass method, read in an inherited base class method
@@ -210,7 +210,7 @@ class Sub2(Base2):
sub2 = Sub2()
sub2.read_bar()
print(sub2.bar) # $ tracked MISSING: tracked=bar
print(sub2.bar) # $ MISSING: tracked=bar tracked
# attribute written in a base class method, read on an instance of the subclass
@@ -223,4 +223,4 @@ class Sub3(Base3):
pass
sub3 = Sub3()
print(sub3.baz) # $ tracked MISSING: tracked=baz
print(sub3.baz) # $ MISSING: tracked=baz tracked

View File

@@ -362,7 +362,7 @@ def test_load_in_bulk():
# see https://docs.djangoproject.com/en/4.0/ref/models/querysets/#in-bulk
d = TestLoad.objects.in_bulk([1])
for val in d.values():
SINK(val.text) # $ MISSING: flow
SINK(val.text) # $ flow="SOURCE, l:-65 -> val.text"
SINK(d[1].text) # $ flow="SOURCE, l:-66 -> d[1].text"

View File

@@ -1,7 +1,6 @@
#select
| app.py:23:20:23:24 | ControlFlowNode for query | app.py:20:18:20:21 | ControlFlowNode for name | app.py:23:20:23:24 | ControlFlowNode for query | This SQL query depends on a $@. | app.py:20:18:20:21 | ControlFlowNode for name | user-provided value |
| app.py:30:20:30:24 | ControlFlowNode for query | app.py:27:19:27:22 | ControlFlowNode for name | app.py:30:20:30:24 | ControlFlowNode for query | This SQL query depends on a $@. | app.py:27:19:27:22 | ControlFlowNode for name | user-provided value |
| app.py:37:20:37:24 | ControlFlowNode for query | app.py:34:19:34:22 | ControlFlowNode for name | app.py:37:20:37:24 | ControlFlowNode for query | This SQL query depends on a $@. | app.py:34:19:34:22 | ControlFlowNode for name | user-provided value |
| app.py:44:20:44:24 | ControlFlowNode for query | app.py:41:19:41:22 | ControlFlowNode for name | app.py:44:20:44:24 | ControlFlowNode for query | This SQL query depends on a $@. | app.py:41:19:41:22 | ControlFlowNode for name | user-provided value |
| app.py:51:20:51:24 | ControlFlowNode for query | app.py:48:19:48:22 | ControlFlowNode for name | app.py:51:20:51:24 | ControlFlowNode for query | This SQL query depends on a $@. | app.py:48:19:48:22 | ControlFlowNode for name | user-provided value |
| sql_injection.py:21:24:21:77 | ControlFlowNode for BinaryExpr | sql_injection.py:14:15:14:22 | ControlFlowNode for username | sql_injection.py:21:24:21:77 | ControlFlowNode for BinaryExpr | This SQL query depends on a $@. | sql_injection.py:14:15:14:22 | ControlFlowNode for username | user-provided value |
@@ -25,8 +24,6 @@ edges
| app.py:21:5:21:9 | ControlFlowNode for query | app.py:23:20:23:24 | ControlFlowNode for query | provenance | |
| app.py:27:19:27:22 | ControlFlowNode for name | app.py:28:5:28:9 | ControlFlowNode for query | provenance | |
| app.py:28:5:28:9 | ControlFlowNode for query | app.py:30:20:30:24 | ControlFlowNode for query | provenance | |
| app.py:34:19:34:22 | ControlFlowNode for name | app.py:35:5:35:9 | ControlFlowNode for query | provenance | |
| app.py:35:5:35:9 | ControlFlowNode for query | app.py:37:20:37:24 | ControlFlowNode for query | provenance | |
| app.py:41:19:41:22 | ControlFlowNode for name | app.py:42:5:42:9 | ControlFlowNode for query | provenance | |
| app.py:42:5:42:9 | ControlFlowNode for query | app.py:44:20:44:24 | ControlFlowNode for query | provenance | |
| app.py:48:19:48:22 | ControlFlowNode for name | app.py:49:5:49:9 | ControlFlowNode for query | provenance | |
@@ -54,9 +51,6 @@ nodes
| app.py:27:19:27:22 | ControlFlowNode for name | semmle.label | ControlFlowNode for name |
| app.py:28:5:28:9 | ControlFlowNode for query | semmle.label | ControlFlowNode for query |
| app.py:30:20:30:24 | ControlFlowNode for query | semmle.label | ControlFlowNode for query |
| app.py:34:19:34:22 | ControlFlowNode for name | semmle.label | ControlFlowNode for name |
| app.py:35:5:35:9 | ControlFlowNode for query | semmle.label | ControlFlowNode for query |
| app.py:37:20:37:24 | ControlFlowNode for query | semmle.label | ControlFlowNode for query |
| app.py:41:19:41:22 | ControlFlowNode for name | semmle.label | ControlFlowNode for name |
| app.py:42:5:42:9 | ControlFlowNode for query | semmle.label | ControlFlowNode for query |
| app.py:44:20:44:24 | ControlFlowNode for query | semmle.label | ControlFlowNode for query |

View File

@@ -31,10 +31,10 @@ async def unsafe2(name: str): # $ Source
cursor.close()
@app.get("/unsafe3/")
async def unsafe3(name: str): # $ Source
async def unsafe3(name: str): # $ MISSING: Source
query = "select * from users where name=" + name
cursor = hdb_con3.cursor()
cursor.execute(query) # $ Alert
cursor.execute(query) # $ MISSING: Alert
cursor.close()
@app.get("/unsafe4/")

View File

@@ -66,7 +66,7 @@ impl<'a> AstNode for Node<'a> {
impl AstNode for yeast::Node {
fn kind(&self) -> &str {
yeast::Node::kind_name(self)
yeast::Node::kind(self)
}
fn is_named(&self) -> bool {
yeast::Node::is_named(self)
@@ -882,6 +882,7 @@ fn emit_extras_in(visitor: &mut Visitor, node: Node<'_>) {
}
fn traverse_yeast(tree: &yeast::Ast, visitor: &mut Visitor) {
use yeast::Cursor;
let mut cursor = tree.walk();
visitor.enter_node(cursor.node());
let mut recurse = true;

View File

@@ -41,14 +41,22 @@ pub fn query(input: TokenStream) -> TokenStream {
/// (kind "literal") - leaf with static content
/// (kind #{expr}) - leaf with computed content (expr.to_string())
/// (kind $fresh) - leaf with auto-generated unique name
/// {expr} - embed a Rust expression, dispatched via
/// the `IntoFieldIds` trait: `Id` pushes a
/// single id; iterables (`Vec<Id>`,
/// `Option<Id>`, iterator chains) splice
/// their elements
/// field: {expr} - extend a named field with `{expr}`'s ids
/// {expr} - embed a Rust expression returning Id
/// {..expr} - splice an iterable of Id (in child/field position)
/// field: {..expr} - splice into a named field
/// {expr}.map(p -> tpl) - apply tpl to each element; splice result
/// {expr}.reduce_left(f -> init, acc, e -> fold)
/// - fold with per-element init; splice 0 or 1 result
/// ```
///
/// Chain syntax after `{expr}` or `{..expr}`:
/// - `.map(param -> template)` — one output node per input element.
/// - `.reduce_left(first -> init, acc, elem -> fold)` — fold left; the first
/// element is converted by `init`, subsequent elements are folded by `fold`
/// with the accumulator bound to `acc`. An empty iterable yields nothing.
/// - Chains always splice (the result is iterable).
/// - Multiple chains can be chained, e.g. `.map(...).reduce_left(...)`.
///
/// Can be called with an explicit context or using the implicit context
/// from an enclosing `rule!`:
///
@@ -92,7 +100,7 @@ pub fn trees(input: TokenStream) -> TokenStream {
/// rule!(
/// (query_pattern field: (_) @name (kind)* @repeated (_)? @optional)
/// =>
/// (output_template field: {name} {repeated})
/// (output_template field: {name} {..repeated})
/// )
///
/// // Shorthand: captures become fields on the output node
@@ -113,3 +121,37 @@ pub fn rule(input: TokenStream) -> TokenStream {
Err(err) => err.to_compile_error().into(),
}
}
/// Define a desugaring rule whose transform is a hand-written Rust block.
///
/// Use `manual_rule!` when the transform needs control over capture
/// translation timing — for example, when an outer rule needs to set
/// state in `ctx` (the `BuildCtx`'s user context) before recursive
/// translation reaches inner rules that read that state.
///
/// ```text
/// manual_rule!(
/// (query_pattern field: (_) @name)
/// {
/// // `ctx` is a `&mut BuildCtx<'_, C>`; capture variables
/// // (`name: NodeRef`, etc.) are bound from the query.
/// let translated = ctx.translate(name)?;
/// Ok(translated)
/// }
/// )
/// ```
///
/// Differences from [`rule!`]:
/// - Captures are **not** auto-translated before the body runs; they
/// refer to raw input-schema nodes. Use [`BuildCtx::translate`] (or
/// [`BuildCtx::translate_opt`]) to translate them when you choose.
/// - The body is plain Rust returning `Result<Vec<Id>, String>` — no
/// tree template, no `Ok(...)` wrap.
#[proc_macro]
pub fn manual_rule(input: TokenStream) -> TokenStream {
let input2: TokenStream2 = input.into();
match parse::parse_manual_rule_top(input2) {
Ok(output) => output.into(),
Err(err) => err.to_compile_error().into(),
}
}

View File

@@ -22,9 +22,10 @@ pub fn parse_query_top(input: TokenStream) -> Result<TokenStream> {
/// Parse a single query node (possibly with a trailing `@capture`).
fn parse_query_node(tokens: &mut Tokens) -> Result<TokenStream> {
let base = parse_query_atom(tokens)?;
// Check for trailing @capture or @@capture
// Check for trailing @capture
if peek_is_at(tokens) {
let capture_name = consume_capture_marker(tokens)?;
tokens.next(); // consume @
let capture_name = expect_ident(tokens, "expected capture name after @")?;
let name_str = capture_name.to_string();
Ok(quote! {
yeast::query::QueryNode::Capture {
@@ -158,7 +159,8 @@ fn parse_query_fields(tokens: &mut Tokens) -> Result<Vec<TokenStream>> {
push_field_elem(&mut field_order, &mut field_elems, field_str, elem);
} else {
let child = if peek_is_at(tokens) {
let capture_name = consume_capture_marker(tokens)?;
tokens.next();
let capture_name = expect_ident(tokens, "expected capture name after @")?;
let name_str = capture_name.to_string();
quote! {
yeast::query::QueryNode::Capture {
@@ -304,8 +306,7 @@ fn parse_ctx_or_implicit(tokens: &mut Tokens) -> Ident {
&& matches!(lookahead.next(), Some(TokenTree::Punct(p)) if p.as_char() == ',');
if is_explicit {
let ctx = expect_ident(tokens, "unreachable: ident was just peeked")
.expect("unreachable: ident was just peeked");
let ctx = expect_ident(tokens, "").unwrap();
let _ = tokens.next(); // consume comma
ctx
} else {
@@ -343,7 +344,7 @@ pub fn parse_trees_top(input: TokenStream) -> Result<TokenStream> {
}
Ok(quote! {
{
let mut __nodes: Vec<yeast::Id> = Vec::new();
let mut __nodes: Vec<usize> = Vec::new();
#(#items)*
__nodes
}
@@ -357,7 +358,7 @@ fn parse_direct_node(tokens: &mut Tokens, ctx: &Ident) -> Result<TokenStream> {
Some(TokenTree::Group(g)) if g.delimiter() == Delimiter::Brace => {
let group = expect_group(tokens, Delimiter::Brace)?;
let expr = group.stream();
Ok(quote! { ::std::convert::Into::<yeast::Id>::into({ #expr }) })
Ok(quote! { ::std::convert::Into::<usize>::into({ #expr }) })
}
Some(TokenTree::Group(g)) if g.delimiter() == Delimiter::Parenthesis => {
let group = expect_group(tokens, Delimiter::Parenthesis)?;
@@ -430,24 +431,49 @@ fn parse_direct_node_inner(tokens: &mut Tokens, ctx: &Ident) -> Result<TokenStre
);
field_counter += 1;
// Plain `field: {expr}` — trait-dispatched extend.
// Check for field: {..expr}.chain or field: {expr}.chain — splice a Vec<Id> into the field
if peek_is_group(tokens, Delimiter::Brace) {
let group = expect_group(tokens, Delimiter::Brace)?;
let expr = group.stream();
stmts.push(quote! {
let mut #temp: Vec<yeast::Id> = Vec::new();
yeast::IntoFieldIds::extend_into({ #expr }, &mut #temp);
});
// An empty `{expr}` means the field is absent — skip it
// entirely rather than emitting an empty named field.
field_args.push(quote! {
if !#temp.is_empty() { __fields.push((#field_str, #temp)); }
});
continue;
let group_clone = tokens.clone().next().unwrap();
if let TokenTree::Group(g) = &group_clone {
let mut inner_check = g.stream().into_iter();
let is_splice = matches!(inner_check.next(), Some(TokenTree::Punct(p)) if p.as_char() == '.')
&& matches!(inner_check.next(), Some(TokenTree::Punct(p)) if p.as_char() == '.');
// Determine if a chain (.map(..)) follows the `{}` group.
let mut after = tokens.clone();
after.next(); // skip the brace group
let has_chain =
matches!(after.peek(), Some(TokenTree::Punct(p)) if p.as_char() == '.');
if is_splice || has_chain {
let group = expect_group(tokens, Delimiter::Brace)?;
let base: TokenStream = if is_splice {
let mut inner = group.stream().into_iter().peekable();
inner.next(); // consume first .
inner.next(); // consume second .
let expr: TokenStream = inner.collect();
quote! {
{ #expr }.into_iter().map(::std::convert::Into::<usize>::into)
}
} else {
let expr = group.stream();
quote! { { #expr }.into_iter() }
};
let chained = parse_chain_suffix(tokens, ctx, base)?;
stmts.push(quote! {
let #temp: Vec<usize> = #chained.collect();
});
// An empty splice means the field is absent — skip it
// entirely rather than emitting an empty named field.
field_args.push(quote! {
if !#temp.is_empty() { __fields.push((#field_str, #temp)); }
});
continue;
}
}
}
let value = parse_direct_node(tokens, ctx)?;
stmts.push(quote! { let #temp: yeast::Id = #value; });
stmts.push(quote! { let #temp: usize = #value; });
field_args.push(quote! { __fields.push((#field_str, vec![#temp])); });
}
@@ -464,13 +490,101 @@ fn parse_direct_node_inner(tokens: &mut Tokens, ctx: &Ident) -> Result<TokenStre
Ok(quote! {
{
#(#stmts)*
let mut __fields: Vec<(&str, Vec<yeast::Id>)> = Vec::new();
let mut __fields: Vec<(&str, Vec<usize>)> = Vec::new();
#(#field_args)*
#ctx.node(#kind_str, __fields)
}
})
}
/// Parse a chain of `.method(args)` suffixes after a `{expr}` or `{..expr}`
/// placeholder in tree templates. Currently supports:
///
/// ```text
/// .map(param -> template) -- iterator map: produces Vec<usize>
/// ```
///
/// The chain may be empty (returns `base` unchanged). Multiple chained calls
/// are supported, e.g. `.map(p -> ...).map(q -> ...)`.
///
/// Each call expects the receiver to be an iterator. The `base` argument
/// should therefore already be an iterator (use `.into_iter()` on it before
/// calling this function).
fn parse_chain_suffix(tokens: &mut Tokens, ctx: &Ident, base: TokenStream) -> Result<TokenStream> {
let mut current = base;
while matches!(tokens.peek(), Some(TokenTree::Punct(p)) if p.as_char() == '.') {
tokens.next(); // consume .
let method = expect_ident(tokens, "expected method name after `.`")?;
let method_str = method.to_string();
let args_group = expect_group(tokens, Delimiter::Parenthesis)?;
match method_str.as_str() {
"map" => {
let mut inner = args_group.stream().into_iter().peekable();
let param = expect_ident(&mut inner, "expected lambda parameter name")?;
expect_punct(&mut inner, '-', "expected `->` after lambda parameter")?;
expect_punct(&mut inner, '>', "expected `->` after lambda parameter")?;
let body = parse_direct_node(&mut inner, ctx)?;
if let Some(tok) = inner.next() {
return Err(syn::Error::new_spanned(
tok,
"unexpected token after lambda body",
));
}
current = quote! {
#current.map(|#param| #body)
};
}
"reduce_left" => {
// Syntax: reduce_left(first -> init_tpl, acc, elem -> fold_tpl)
// - first -> init_tpl : converts the first element to the initial accumulator
// - acc, elem -> fold_tpl : fold step (acc = current accumulator, elem = next element)
// Empty iterator produces an empty iterator; non-empty produces a single-element iterator.
let mut inner = args_group.stream().into_iter().peekable();
let init_param = expect_ident(&mut inner, "expected initial lambda parameter")?;
expect_punct(&mut inner, '-', "expected `->` after init parameter")?;
expect_punct(&mut inner, '>', "expected `->` after init parameter")?;
let init_body = parse_direct_node(&mut inner, ctx)?;
expect_punct(&mut inner, ',', "expected `,` after init template")?;
let acc_param = expect_ident(&mut inner, "expected accumulator parameter")?;
expect_punct(&mut inner, ',', "expected `,` after accumulator parameter")?;
let elem_param = expect_ident(&mut inner, "expected element parameter")?;
expect_punct(&mut inner, '-', "expected `->` after element parameter")?;
expect_punct(&mut inner, '>', "expected `->` after element parameter")?;
let fold_body = parse_direct_node(&mut inner, ctx)?;
if let Some(tok) = inner.next() {
return Err(syn::Error::new_spanned(
tok,
"unexpected token after fold template",
));
}
current = quote! {
{
let mut __iter = #current;
let __result: Option<usize> = if let Some(#init_param) = __iter.next() {
let mut __acc: usize = #init_body;
for #elem_param in __iter {
let #acc_param: usize = __acc;
__acc = #fold_body;
}
Some(__acc)
} else {
None
};
__result.into_iter()
}
};
}
_ => {
return Err(syn::Error::new_spanned(
method,
format!("unknown builtin method `.{method_str}()`"),
));
}
}
}
Ok(current)
}
/// Parse the top-level list of a `trees!` template.
/// Each item is a node template or `{expr}` splice.
fn parse_direct_list(tokens: &mut Tokens, ctx: &Ident) -> Result<Vec<TokenStream>> {
@@ -491,14 +605,35 @@ fn parse_direct_list(tokens: &mut Tokens, ctx: &Ident) -> Result<Vec<TokenStream
continue;
}
// `{expr}` — extend `__nodes` via `IntoFieldIds`, which handles
// single ids and iterables uniformly.
// {expr} or {..expr} (with optional .chain) — single node or splice
if peek_is_group(tokens, Delimiter::Brace) {
let group = expect_group(tokens, Delimiter::Brace)?;
let expr = group.stream();
items.push(quote! {
yeast::IntoFieldIds::extend_into({ #expr }, &mut __nodes);
});
let has_chain =
matches!(tokens.peek(), Some(TokenTree::Punct(p)) if p.as_char() == '.');
let mut inner = group.stream().into_iter().peekable();
let is_splice = peek_is_dotdot(&inner);
if is_splice || has_chain {
let base: TokenStream = if is_splice {
inner.next(); // consume first .
inner.next(); // consume second .
let expr: TokenStream = inner.collect();
quote! {
{ #expr }.into_iter().map(::std::convert::Into::<usize>::into)
}
} else {
let expr = group.stream();
quote! { { #expr }.into_iter() }
};
let chained = parse_chain_suffix(tokens, ctx, base)?;
items.push(quote! {
__nodes.extend(#chained);
});
} else {
let expr = group.stream();
items.push(quote! {
__nodes.push(::std::convert::Into::<usize>::into({ #expr }));
});
}
continue;
}
@@ -515,9 +650,6 @@ fn parse_direct_list(tokens: &mut Tokens, ctx: &Ident) -> Result<Vec<TokenStream
struct CaptureInfo {
name: String,
multiplicity: CaptureMultiplicity,
/// `true` for `@@name` captures: the auto-translate prefix skips them,
/// so the bound `Id` refers to the raw (input-schema) node.
raw: bool,
}
#[derive(Clone, Copy, PartialEq)]
@@ -576,14 +708,6 @@ fn extract_captures_inner(
extract_captures_inner(&mut inner, captures, child_mult);
}
TokenTree::Punct(p) if p.as_char() == '@' => {
// `@@name` marks the capture as raw (skip auto-translate).
let raw = matches!(
tokens.peek(),
Some(TokenTree::Punct(p)) if p.as_char() == '@'
);
if raw {
tokens.next(); // consume the second `@`
}
if let Some(TokenTree::Ident(name)) = tokens.next() {
let mult = if parent_mult == CaptureMultiplicity::Repeated
|| last_mult == CaptureMultiplicity::Repeated
@@ -599,7 +723,6 @@ fn extract_captures_inner(
captures.push(CaptureInfo {
name: name.to_string(),
multiplicity: mult,
raw,
});
}
last_mult = CaptureMultiplicity::Single;
@@ -653,14 +776,6 @@ pub fn parse_rule_top(input: TokenStream) -> Result<TokenStream> {
// Parse query
let query_code = parse_query_top(query_stream.clone())?;
// Capture names marked `@@name` (raw) — passed to the auto-translate
// prefix as a skip list so those captures keep their input-schema ids.
let raw_capture_names: Vec<&str> = captures
.iter()
.filter(|c| c.raw)
.map(|c| c.name.as_str())
.collect();
// Generate capture bindings
let ctx_ident = Ident::new(IMPLICIT_CTX, Span::call_site());
let bindings: Vec<TokenStream> = captures
@@ -671,17 +786,22 @@ pub fn parse_rule_top(input: TokenStream) -> Result<TokenStream> {
match cap.multiplicity {
CaptureMultiplicity::Repeated => {
quote! {
let #name: Vec<yeast::Id> = __captures.get_all(#name_str);
let #name: Vec<yeast::NodeRef> = __captures.get_all(#name_str)
.into_iter()
.map(yeast::NodeRef)
.collect();
}
}
CaptureMultiplicity::Optional => {
quote! {
let #name: Option<yeast::Id> = __captures.get_opt(#name_str);
let #name: Option<yeast::NodeRef> =
__captures.get_opt(#name_str).map(yeast::NodeRef);
}
}
CaptureMultiplicity::Single => {
quote! {
let #name: yeast::Id = __captures.get_var(#name_str).unwrap();
let #name: yeast::NodeRef =
yeast::NodeRef(__captures.get_var(#name_str).unwrap());
}
}
}
@@ -712,7 +832,7 @@ pub fn parse_rule_top(input: TokenStream) -> Result<TokenStream> {
__fields.insert(
__field_id,
#name.into_iter()
.map(::std::convert::Into::<yeast::Id>::into)
.map(::std::convert::Into::<usize>::into)
.collect(),
);
},
@@ -721,14 +841,14 @@ pub fn parse_rule_top(input: TokenStream) -> Result<TokenStream> {
.unwrap_or_else(|| panic!("field '{}' not found", #name_str));
if let Some(__id) = #name {
__fields.entry(__field_id).or_insert_with(Vec::new)
.push(::std::convert::Into::<yeast::Id>::into(__id));
.push(::std::convert::Into::<usize>::into(__id));
}
},
CaptureMultiplicity::Single => quote! {
let __field_id = #ctx_ident.ast.field_id_for_name(#name_str)
.unwrap_or_else(|| panic!("field '{}' not found", #name_str));
__fields.entry(__field_id).or_insert_with(Vec::new)
.push(::std::convert::Into::<yeast::Id>::into(#name));
.push(::std::convert::Into::<usize>::into(#name));
},
}
})
@@ -760,7 +880,7 @@ pub fn parse_rule_top(input: TokenStream) -> Result<TokenStream> {
}
quote! {
let mut __nodes: Vec<yeast::Id> = Vec::new();
let mut __nodes: Vec<usize> = Vec::new();
#(#transform_items)*
__nodes
}
@@ -771,23 +891,120 @@ pub fn parse_rule_top(input: TokenStream) -> Result<TokenStream> {
let __query = #query_code;
yeast::Rule::new(__query, Box::new(|__ast: &mut yeast::Ast, mut __captures: yeast::captures::Captures, __fresh: &yeast::tree_builder::FreshScope, __source_range: Option<tree_sitter::Range>, __user_ctx: &mut _, __translator: yeast::TranslatorHandle<'_, _>| {
// Auto-translation prefix: recursively translate every
// captured node before invoking the user's transform body,
// except for `@@name` captures listed in `__skip` which the
// body consumes raw.
// captured node before invoking the user's transform body.
// For OneShot rules this preserves the legacy behaviour
// (input-schema captures translated to output-schema
// nodes); for Repeating rules it is a no-op.
let __skip: &[&str] = &[#(#raw_capture_names),*];
__translator.auto_translate_captures(&mut __captures, __ast, __user_ctx, __skip)?;
__translator.auto_translate_captures(&mut __captures, __ast, __user_ctx)?;
#(#bindings)*
let mut #ctx_ident = yeast::build::BuildCtx::with_translator(__ast, &__captures, __fresh, __source_range, __user_ctx, __translator);
let __result: Vec<yeast::Id> = { #transform_body };
let __result: Vec<usize> = { #transform_body };
Ok(__result)
}))
}
})
}
/// Parse `manual_rule!( query { body } )`.
///
/// Like [`parse_rule_top`] but:
/// - Expects a Rust block `{ ... }` after the query (no `=>` arrow).
/// - Generates code that does NOT auto-translate captures before
/// running the body. Capture variables refer to raw (input-schema)
/// nodes; the body is responsible for explicit translation via
/// `ctx.translate(...)`.
/// - The body is included verbatim and must evaluate to
/// `Result<Vec<usize>, String>`.
pub fn parse_manual_rule_top(input: TokenStream) -> Result<TokenStream> {
let mut tokens = input.into_iter().peekable();
// Collect query tokens up to the body block `{ ... }`.
let mut query_tokens = Vec::new();
loop {
match tokens.peek() {
None => {
return Err(syn::Error::new(
Span::call_site(),
"expected a Rust block `{ ... }` after the query in manual_rule!",
))
}
Some(TokenTree::Group(g)) if g.delimiter() == Delimiter::Brace => break,
_ => {
query_tokens.push(tokens.next().unwrap());
}
}
}
let query_stream: TokenStream = query_tokens.into_iter().collect();
// Extract captures from the query (same as in `rule!`).
let captures = extract_captures(&query_stream);
// Parse the query into the QueryNode-building expression.
let query_code = parse_query_top(query_stream)?;
// Generate capture bindings (same as in `rule!`).
let ctx_ident = Ident::new(IMPLICIT_CTX, Span::call_site());
let bindings: Vec<TokenStream> = captures
.iter()
.map(|cap| {
let name = Ident::new(&cap.name, Span::call_site());
let name_str = &cap.name;
match cap.multiplicity {
CaptureMultiplicity::Repeated => quote! {
let #name: Vec<yeast::NodeRef> = __captures.get_all(#name_str)
.into_iter()
.map(yeast::NodeRef)
.collect();
},
CaptureMultiplicity::Optional => quote! {
let #name: Option<yeast::NodeRef> =
__captures.get_opt(#name_str).map(yeast::NodeRef);
},
CaptureMultiplicity::Single => quote! {
let #name: yeast::NodeRef =
yeast::NodeRef(__captures.get_var(#name_str).unwrap());
},
}
})
.collect();
// Consume the body block.
let body_group = match tokens.next() {
Some(TokenTree::Group(g)) if g.delimiter() == Delimiter::Brace => g,
other => {
return Err(syn::Error::new(
Span::call_site(),
format!(
"expected a Rust block `{{ ... }}` after the query in manual_rule!, found: {other:?}"
),
))
}
};
let body_stream = body_group.stream();
// No tokens should follow the body.
if let Some(tok) = tokens.next() {
return Err(syn::Error::new_spanned(
tok,
"unexpected token after manual_rule! body",
));
}
Ok(quote! {
{
let __query = #query_code;
yeast::Rule::new(__query, Box::new(|__ast: &mut yeast::Ast, __captures: yeast::captures::Captures, __fresh: &yeast::tree_builder::FreshScope, __source_range: Option<tree_sitter::Range>, __user_ctx: &mut _, __translator: yeast::TranslatorHandle<'_, _>| {
// No auto-translate prefix for manual rules — the body
// is responsible for translating captures explicitly.
#(#bindings)*
let mut #ctx_ident = yeast::build::BuildCtx::with_translator(__ast, &__captures, __fresh, __source_range, __user_ctx, __translator);
#body_stream
}))
}
})
}
// ---------------------------------------------------------------------------
// Token utilities
// ---------------------------------------------------------------------------
@@ -796,16 +1013,6 @@ fn peek_is_at(tokens: &mut Tokens) -> bool {
matches!(tokens.peek(), Some(TokenTree::Punct(p)) if p.as_char() == '@')
}
/// Consume an `@` or `@@` capture marker and the following name ident.
/// Caller has already verified `peek_is_at(tokens)`.
fn consume_capture_marker(tokens: &mut Tokens) -> Result<Ident> {
tokens.next(); // consume the first `@`
if peek_is_at(tokens) {
tokens.next(); // consume the second `@` of `@@`
}
expect_ident(tokens, "expected capture name after `@` or `@@`")
}
fn peek_is_literal(tokens: &mut Tokens) -> bool {
matches!(tokens.peek(), Some(TokenTree::Literal(_)))
}
@@ -818,6 +1025,13 @@ fn peek_is_hash(tokens: &mut Tokens) -> bool {
matches!(tokens.peek(), Some(TokenTree::Punct(p)) if p.as_char() == '#')
}
/// Check for `..` (two consecutive dot punctuation tokens).
fn peek_is_dotdot(tokens: &Tokens) -> bool {
let mut lookahead = tokens.clone();
matches!(lookahead.next(), Some(TokenTree::Punct(p)) if p.as_char() == '.')
&& matches!(lookahead.next(), Some(TokenTree::Punct(p)) if p.as_char() == '.')
}
fn peek_is_underscore(tokens: &mut Tokens) -> bool {
matches!(tokens.peek(), Some(TokenTree::Ident(id)) if *id == "_")
}
@@ -899,7 +1113,8 @@ fn expect_repetition(tokens: &mut Tokens) -> Result<TokenStream> {
fn maybe_wrap_capture(tokens: &mut Tokens, base: TokenStream) -> Result<TokenStream> {
if peek_is_at(tokens) {
let name = consume_capture_marker(tokens)?;
tokens.next(); // consume @
let name = expect_ident(tokens, "expected capture name after @")?;
let name_str = name.to_string();
Ok(quote! {
yeast::query::QueryNode::Capture {
@@ -926,12 +1141,13 @@ fn maybe_wrap_repetition(tokens: &mut Tokens, single: TokenStream) -> Result<Tok
}
}
/// If `@name` (or `@@name`) follows a Repeated list element, wrap each
/// child SingleNode inside the repetition with a Capture. This matches
/// tree-sitter semantics where `(_)* @name` captures each matched node.
/// If `@name` follows a Repeated list element, wrap each child SingleNode
/// inside the repetition with a Capture. This matches tree-sitter semantics
/// where `(_)* @name` captures each matched node.
fn maybe_wrap_list_capture(tokens: &mut Tokens, elem: TokenStream) -> Result<TokenStream> {
if peek_is_at(tokens) {
let name = consume_capture_marker(tokens)?;
tokens.next();
let name = expect_ident(tokens, "expected capture name after @")?;
let name_str = name.to_string();
// Re-parse the element isn't practical, so we generate a wrapper
// that creates a new Repeated with each child wrapped in a capture.

View File

@@ -214,7 +214,7 @@ yeast::tree!(ctx,
```rust
yeast::trees!(ctx,
(assignment left: {tmp} right: {right})
{body}
{..body}
)
```
@@ -256,26 +256,12 @@ occurrences of the same `$name` within one `BuildCtx` share the same value:
### Embedded Rust expressions
`{expr}` embeds a Rust expression whose value is appended to the
enclosing field (or to the rule body's id list). Dispatch happens via
the [`IntoFieldIds`] trait, which is implemented for:
- `Id` — pushes the single id.
- Any `IntoIterator<Item: Into<Id>>` — extends with all yielded ids
(covers `Vec<Id>`, `Option<Id>`, iterator chains, etc.).
So the same `{expr}` syntax handles single ids, splices, and zero-or-many
options uniformly:
`{expr}` embeds a Rust expression that returns a single node `Id`:
```rust
(assignment
left: {some_node_id} // a single Id
right: {rhs} // a captured value (inside rule!)
)
yeast::trees!(ctx,
(assignment left: {tmp} right: {right})
{extra_nodes} // splices a Vec<Id>
left: {some_node_id} // insert a pre-built node
right: {rhs} // insert a captured value (inside rule!)
)
```
@@ -291,47 +277,20 @@ expressions (with `let` bindings) work too:
})
```
Inside `rule!`, captures are Rust variables — `{name}` works for
single, optional, and repeated captures alike:
`{..expr}` splices a `Vec<Id>` (or any iterable of `Id`); the contents
are likewise a Rust block, so the splice can be the result of arbitrary
computation:
```rust
rule!(
(assignment left: @lhs right: _* @parts)
=>
(assignment left: {lhs} right: (block stmt: {parts}))
yeast::trees!(ctx,
(assignment left: {tmp} right: {right})
{..extra_nodes} // splice a Vec<Id>
)
```
### Raw captures (`@@name`)
The default `@name` capture marker is *auto-translated*: in OneShot
phases the macro recursively translates the captured node before
binding it, so `{name}` in the output template splices a node that
already conforms to the output schema.
For rules that need the raw (input-schema) capture — typically to read
its source text or to translate it explicitly with mutable context
state between calls — use `@@name` instead. The body sees the original
input-schema `Id`:
```rust
yeast::rule!(
(assignment left: (_) @@raw_lhs right: (_) @rhs)
=>
{
// raw_lhs is untranslated: read its original source text.
let text = ctx.ast.source_text(raw_lhs.into());
// rhs is already translated by the auto-translate prefix.
tree!((call
method: (identifier #{text.as_str()})
receiver: {rhs}))
}
);
```
Mix `@` and `@@` freely in the same rule. In a Repeating phase both
markers are equivalent (auto-translation is a no-op for repeating
rules).
Inside `rule!`, captures are Rust variables, so `{name}` inserts a
single capture (`Id`) and `{..name}` splices a repeated capture
(`Vec<Id>`).
## Complete example: for-loop desugaring

View File

@@ -158,6 +158,15 @@ impl<'a, C> BuildCtx<'a, C> {
self.ast
.create_named_token_with_range(kind, generated, self.source_range)
}
/// Prepend a value to a field of an existing node.
pub fn prepend_field(&mut self, node_id: Id, field_name: &str, value_id: Id) {
let field_id = self
.ast
.field_id_for_name(field_name)
.unwrap_or_else(|| panic!("build: field '{field_name}' not found"));
self.ast.prepend_field_child(node_id, field_id, value_id);
}
}
impl<C: Clone> BuildCtx<'_, C> {
@@ -167,6 +176,9 @@ impl<C: Clone> BuildCtx<'_, C> {
/// (translation is not meaningful when input and output share a
/// schema).
///
/// Accepts any value convertible to [`Id`] (including [`crate::NodeRef`]),
/// so manual rules can pass capture bindings directly without unwrapping.
///
/// Errors if this `BuildCtx` was constructed by hand (without a
/// translator handle) — for example, in unit tests that don't go
/// through the rule driver.
@@ -177,6 +189,20 @@ impl<C: Clone> BuildCtx<'_, C> {
None => Err("translate() called on a BuildCtx without a translator handle".into()),
}
}
/// Translate an optional capture, returning the first translated id or
/// `None`. Convenience for `?`-quantifier captures (`Option<NodeRef>`).
///
/// If the underlying translation produces multiple ids for a single
/// input, only the first is returned. For most use cases (e.g.
/// translating a single type annotation) this is what you want; if
/// you need all ids, use [`translate`] directly.
pub fn translate_opt<I: Into<Id>>(&mut self, id: Option<I>) -> Result<Option<Id>, String> {
match id {
Some(id) => Ok(self.translate(id)?.into_iter().next()),
None => Ok(None),
}
}
}
impl<C> std::ops::Deref for BuildCtx<'_, C> {

View File

@@ -54,24 +54,24 @@ impl Captures {
self.captures.entry(key).or_default().push(id);
}
/// Apply a fallible function to every captured id, replacing each id
/// with the results. A function returning an empty vector removes
/// the capture; returning multiple ids splices them into the
/// capture's value list (suitable for `*`/`+` captures). Captures
/// whose name appears in `skip` are left untouched. Stops and
/// returns the error on the first failure.
///
/// Used by the `rule!` macro's auto-translate prefix to translate
/// every capture except those marked `@@name` (raw).
pub fn try_map_captures_except<E>(
pub fn map_captures(&mut self, kind: &str, f: &mut impl FnMut(Id) -> Id) {
if let Some(ids) = self.captures.get_mut(kind) {
for id in ids {
*id = f(*id);
}
}
}
/// Apply a fallible function to every captured id (across all keys),
/// replacing each id with the results. A function returning an empty
/// vector removes the capture; returning multiple ids splices them
/// into the capture's value list (suitable for `*`/`+` captures).
/// Stops and returns the error on the first failure.
pub fn try_map_all_captures<E>(
&mut self,
skip: &[&str],
mut f: impl FnMut(Id) -> Result<Vec<Id>, E>,
) -> Result<(), E> {
for (name, ids) in self.captures.iter_mut() {
if skip.contains(name) {
continue;
}
for ids in self.captures.values_mut() {
let mut new_ids = Vec::with_capacity(ids.len());
for &id in ids.iter() {
new_ids.extend(f(id)?);
@@ -80,6 +80,12 @@ impl Captures {
}
Ok(())
}
pub fn map_captures_to(&mut self, from: &str, to: &'static str, f: &mut impl FnMut(Id) -> Id) {
if let Some(from_ids) = self.captures.get(from) {
let new_values = from_ids.iter().copied().map(f).collect();
self.captures.insert(to, new_values);
}
}
pub fn merge(&mut self, other: &Captures) {
for (key, ids) in &other.captures {

View File

@@ -0,0 +1,8 @@
pub trait Cursor<'a, T, N, F> {
fn node(&self) -> &'a N;
fn field_id(&self) -> Option<F>;
fn field_name(&self) -> Option<&'static str>;
fn goto_first_child(&mut self) -> bool;
fn goto_next_sibling(&mut self) -> bool;
fn goto_parent(&mut self) -> bool;
}

View File

@@ -1,6 +1,6 @@
use std::fmt::Write;
use crate::{schema::Schema, Ast, Id, Node, NodeContent, CHILD_FIELD};
use crate::{schema::Schema, Ast, Node, NodeContent, CHILD_FIELD};
/// Options for controlling AST dump output.
pub struct DumpOptions {
@@ -34,11 +34,16 @@ impl Default for DumpOptions {
/// method:
/// identifier "foo"
/// ```
pub fn dump_ast(ast: &Ast, root: Id, source: &str) -> String {
pub fn dump_ast(ast: &Ast, root: usize, source: &str) -> String {
dump_ast_with_options(ast, root, source, &DumpOptions::default())
}
pub fn dump_ast_with_options(ast: &Ast, root: Id, source: &str, options: &DumpOptions) -> String {
pub fn dump_ast_with_options(
ast: &Ast,
root: usize,
source: &str,
options: &DumpOptions,
) -> String {
let mut out = String::new();
dump_node(ast, root, source, options, 0, None, &mut out);
out
@@ -48,7 +53,7 @@ pub fn dump_ast_with_options(ast: &Ast, root: Id, source: &str, options: &DumpOp
///
/// Any node that does not match the expected type set for its parent field is
/// rendered with a trailing `" <-- ERROR: ..."` annotation on the same line.
pub fn dump_ast_with_type_errors(ast: &Ast, root: Id, source: &str, schema: &Schema) -> String {
pub fn dump_ast_with_type_errors(ast: &Ast, root: usize, source: &str, schema: &Schema) -> String {
dump_ast_with_type_errors_and_options(ast, root, source, schema, &DumpOptions::default())
}
@@ -58,7 +63,7 @@ pub fn dump_ast_with_type_errors(ast: &Ast, root: Id, source: &str, schema: &Sch
/// rendered with a trailing `" <-- ERROR: ..."` annotation on the same line.
pub fn dump_ast_with_type_errors_and_options(
ast: &Ast,
root: Id,
root: usize,
source: &str,
schema: &Schema,
options: &DumpOptions,
@@ -171,7 +176,7 @@ fn expected_for_field<'a>(
fn dump_node(
ast: &Ast,
id: Id,
id: usize,
source: &str,
options: &DumpOptions,
indent: usize,
@@ -310,7 +315,7 @@ fn dump_node(
/// Dump a leaf node inline (no newline prefix, caller provides context).
fn dump_node_inline(
ast: &Ast,
id: Id,
id: usize,
source: &str,
options: &DumpOptions,
type_check: Option<(

View File

@@ -7,6 +7,7 @@ use serde_json::{json, Value};
pub mod build;
pub mod captures;
pub mod cursor;
pub mod dump;
pub mod node_types_yaml;
pub mod query;
@@ -15,64 +16,35 @@ pub mod schema;
pub mod tree_builder;
mod visitor;
pub use yeast_macros::{query, rule, tree, trees};
pub use yeast_macros::{manual_rule, query, rule, tree, trees};
use captures::Captures;
pub use cursor::Cursor;
use query::QueryNode;
/// Node id: an index into the [`Ast`] arena. A newtype around `usize`
/// rather than a bare alias so that it can carry its own
/// [`YeastDisplay`] / [`YeastSourceRange`] / [`IntoFieldIds`] impls
/// without colliding with the impls for plain integers.
///
/// Use `id.0` (or `id.into()`) to obtain the raw arena index.
#[repr(transparent)]
#[derive(Copy, Clone, Eq, PartialEq, Ord, PartialOrd, Debug, Hash, Serialize)]
pub struct Id(pub usize);
impl From<usize> for Id {
fn from(value: usize) -> Self {
Id(value)
}
}
impl From<Id> for usize {
fn from(value: Id) -> Self {
value.0
}
}
/// Node ids are indexes into the arena
pub type Id = usize;
/// Field and Kind ids are provided by tree-sitter
type FieldId = u16;
type KindId = u16;
/// Trait for values that can be appended to a field's id list inside a
/// `tree!`/`trees!`/`rule!` template (in `{expr}` placeholders).
///
/// `Id` pushes a single id; the blanket impl for
/// `IntoIterator<Item: Into<Id>>` handles `Vec<Id>`, `Option<Id>`,
/// arbitrary iterators yielding `Id`, etc.
///
/// This lets `{expr}` interpolate any of these shapes without a
/// dedicated splice syntax — the macro emits the same trait-dispatched
/// call regardless of the value's type.
pub trait IntoFieldIds {
fn extend_into(self, out: &mut Vec<Id>);
}
/// A typed reference to a node in an [`Ast`] arena. Wraps an [`Id`] but
/// deliberately does not implement [`std::fmt::Display`]: rendering a node
/// requires the [`Ast`] it lives in (to resolve [`NodeContent::Range`] back
/// to source text). Use [`YeastDisplay::yeast_to_string`] to format it.
#[derive(Copy, Clone, Eq, PartialEq, Debug, Hash)]
pub struct NodeRef(pub Id);
impl IntoFieldIds for Id {
fn extend_into(self, out: &mut Vec<Id>) {
out.push(self);
impl NodeRef {
pub fn id(self) -> Id {
self.0
}
}
impl<I, T> IntoFieldIds for I
where
I: IntoIterator<Item = T>,
T: Into<Id>,
{
fn extend_into(self, out: &mut Vec<Id>) {
out.extend(self.into_iter().map(Into::into));
impl From<NodeRef> for Id {
fn from(value: NodeRef) -> Self {
value.0
}
}
@@ -89,21 +61,21 @@ pub trait YeastDisplay {
/// Optional source range for values used in `#{expr}` interpolations.
///
/// By default this returns `None`, so synthesized leaves inherit the matched
/// rule's source range. `Id` returns the referenced node's range, letting
/// rule's source range. `NodeRef` returns the referenced node's range, letting
/// `(kind #{capture})` carry the captured node's location.
pub trait YeastSourceRange {
fn yeast_source_range(&self, ast: &Ast) -> Option<tree_sitter::Range>;
}
impl YeastDisplay for Id {
impl YeastDisplay for NodeRef {
fn yeast_to_string(&self, ast: &Ast) -> String {
ast.source_text(*self)
ast.source_text(self.0)
}
}
impl YeastSourceRange for Id {
impl YeastSourceRange for NodeRef {
fn yeast_source_range(&self, ast: &Ast) -> Option<tree_sitter::Range> {
ast.get_node(*self).and_then(|n| match &n.content {
ast.get_node(self.0).and_then(|n| match &n.content {
NodeContent::Range(r) => Some(r.clone()),
_ => n.source_range,
})
@@ -172,36 +144,6 @@ impl<'a> AstCursor<'a> {
self.node_id
}
pub fn node(&self) -> &'a Node {
&self.ast.nodes[self.node_id.0]
}
pub fn field_id(&self) -> Option<FieldId> {
let (_, children) = self.parents.last()?;
children.current_field()
}
pub fn field_name(&self) -> Option<&'static str> {
if self.field_id() == Some(CHILD_FIELD) {
None
} else {
self.field_id()
.and_then(|id| self.ast.field_name_for_id(id))
}
}
pub fn goto_first_child(&mut self) -> bool {
self.goto_first_child_opt().is_some()
}
pub fn goto_next_sibling(&mut self) -> bool {
self.goto_next_sibling_opt().is_some()
}
pub fn goto_parent(&mut self) -> bool {
self.goto_parent_opt().is_some()
}
fn goto_next_sibling_opt(&mut self) -> Option<()> {
self.node_id = self.parents.last_mut()?.1.next()?;
Some(())
@@ -222,6 +164,37 @@ impl<'a> AstCursor<'a> {
Some(())
}
}
impl<'a> Cursor<'a, Ast, Node, FieldId> for AstCursor<'a> {
fn node(&self) -> &'a Node {
&self.ast.nodes[self.node_id]
}
fn field_id(&self) -> Option<FieldId> {
let (_, children) = self.parents.last()?;
children.current_field()
}
fn field_name(&self) -> Option<&'static str> {
if self.field_id() == Some(CHILD_FIELD) {
None
} else {
self.field_id()
.and_then(|id| self.ast.field_name_for_id(id))
}
}
fn goto_first_child(&mut self) -> bool {
self.goto_first_child_opt().is_some()
}
fn goto_next_sibling(&mut self) -> bool {
self.goto_next_sibling_opt().is_some()
}
fn goto_parent(&mut self) -> bool {
self.goto_parent_opt().is_some()
}
}
/// An iterator over the child Ids of a node.
#[derive(Debug)]
@@ -368,16 +341,16 @@ impl Ast {
///
/// This reflects the effective AST after desugaring and excludes orphaned
/// arena nodes left behind by rewrite operations.
pub fn reachable_node_ids(&self) -> Vec<Id> {
pub fn reachable_node_ids(&self) -> Vec<usize> {
let mut reachable = Vec::new();
let mut stack = vec![self.root];
let mut seen = vec![false; self.nodes.len()];
while let Some(id) = stack.pop() {
if id.0 >= self.nodes.len() || seen[id.0] {
if id >= self.nodes.len() || seen[id] {
continue;
}
seen[id.0] = true;
seen[id] = true;
reachable.push(id);
if let Some(node) = self.get_node(id) {
@@ -401,11 +374,11 @@ impl Ast {
}
pub fn get_node(&self, id: Id) -> Option<&Node> {
self.nodes.get(id.0)
self.nodes.get(id)
}
pub fn print(&self, source: &str, root_id: Id) -> Value {
let root = &self.nodes()[root_id.0];
let root = &self.nodes()[root_id];
self.print_node(root, source)
}
@@ -448,7 +421,7 @@ impl Ast {
is_named,
source_range,
});
Id(id)
id
}
fn union_source_range_of_children(
@@ -515,6 +488,15 @@ impl Ast {
self.create_named_token_with_range(kind, content, None)
}
/// Prepend a child id to the given field of the given node.
pub fn prepend_field_child(&mut self, node_id: Id, field_id: FieldId, value_id: Id) {
let node = self
.nodes
.get_mut(node_id)
.expect("prepend_field_child: invalid node id");
node.fields.entry(field_id).or_default().insert(0, value_id);
}
pub fn create_named_token_with_range(
&mut self,
kind: &'static str,
@@ -536,7 +518,7 @@ impl Ast {
fields: BTreeMap::new(),
content: NodeContent::DynamicString(content),
});
Id(id)
id
}
pub fn field_name_for_id(&self, id: FieldId) -> Option<&'static str> {
@@ -620,6 +602,10 @@ pub struct Node {
}
impl Node {
pub fn kind(&self) -> &'static str {
self.kind_name
}
pub fn kind_name(&self) -> &'static str {
self.kind_name
}
@@ -771,14 +757,13 @@ impl<'a, C: Clone> TranslatorHandle<'a, C> {
}
/// Translate every captured node in `captures` in place (OneShot phase
/// only), except for captures whose name appears in `skip` — those are
/// left as raw (input-schema) ids for the rule body to consume
/// directly. In a Repeating phase this is a no-op — Repeating rules
/// receive raw captures regardless of `skip`.
/// only). In a Repeating phase this is a no-op — Repeating rules
/// receive raw captures.
///
/// Used by the `rule!` macro's generated prefix. `skip` is populated
/// from the macro's `@@name` capture markers; for plain `@name`
/// captures (and rules with no `@@` markers) it is empty.
/// Used by the `rule!` macro's generated prefix to preserve the
/// pre-existing "auto-translate captures before running the transform
/// body" behavior. Manually-written transforms typically translate
/// captures selectively via [`translate`] instead.
///
/// To avoid infinite recursion, a capture whose id matches the rule's
/// matched root (e.g. from a `(_) @_` pattern) is left unchanged.
@@ -787,12 +772,11 @@ impl<'a, C: Clone> TranslatorHandle<'a, C> {
captures: &mut Captures,
ast: &mut Ast,
user_ctx: &mut C,
skip: &[&str],
) -> Result<(), String> {
match &self.inner {
TranslatorImpl::OneShot { matched_root, .. } => {
let root = *matched_root;
captures.try_map_captures_except(skip, |cid| {
captures.try_map_all_captures(|cid| {
if cid == root {
Ok(vec![cid])
} else {
@@ -964,7 +948,7 @@ fn apply_repeating_rules_inner<C: Clone>(
));
}
let node_kind = ast.get_node(id).map(|n| n.kind_name()).unwrap_or("");
let node_kind = ast.get_node(id).map(|n| n.kind()).unwrap_or("");
for rule in index.rules_for_kind(node_kind) {
let rule_ptr = *rule as *const Rule<C>;
if Some(rule_ptr) == skip_rule {
@@ -1016,7 +1000,7 @@ fn apply_repeating_rules_inner<C: Clone>(
//
// Child traversal does not increment rewrite depth and starts fresh
// (no rule is skipped on child subtrees).
let mut fields = std::mem::take(&mut ast.nodes[id.0].fields);
let mut fields = std::mem::take(&mut ast.nodes[id].fields);
for children in fields.values_mut() {
let mut new_children: Option<Vec<Id>> = None;
for (i, &child_id) in children.iter().enumerate() {
@@ -1049,7 +1033,7 @@ fn apply_repeating_rules_inner<C: Clone>(
*children = new;
}
}
ast.nodes[id.0].fields = fields;
ast.nodes[id].fields = fields;
Ok(vec![id])
}
@@ -1083,7 +1067,7 @@ fn apply_one_shot_rules_inner<C: Clone>(
));
}
let node_kind = ast.get_node(id).map(|n| n.kind_name()).unwrap_or("");
let node_kind = ast.get_node(id).map(|n| n.kind()).unwrap_or("");
for rule in index.rules_for_kind(node_kind) {
if let Some(captures) = rule.try_match(ast, id)? {

View File

@@ -49,7 +49,7 @@ impl Visitor {
pub fn build_with_schema(self, schema: crate::schema::Schema) -> Ast {
Ast {
root: Id(0),
root: 0,
schema,
nodes: self.nodes.into_iter().map(|n| n.inner).collect(),
source: Vec::new(),
@@ -72,7 +72,7 @@ impl Visitor {
},
parent: self.current,
});
Id(id)
id
}
fn enter_node(&mut self, node: tree_sitter::Node<'_>) -> bool {
@@ -83,10 +83,10 @@ impl Visitor {
fn leave_node(&mut self, field_name: Option<&'static str>, _node: tree_sitter::Node<'_>) {
let node_id = self.current.unwrap();
let node_parent = self.nodes[node_id.0].parent;
let node_parent = self.nodes[node_id].parent;
if let Some(parent_id) = node_parent {
let parent = self.nodes.get_mut(parent_id.0).unwrap();
let parent = self.nodes.get_mut(parent_id).unwrap();
if let Some(field) = field_name {
let field_id = self.language.field_id_for_name(field).unwrap().get();
parent

View File

@@ -300,7 +300,7 @@ fn test_query_skips_extras_in_positional_match() {
let mut cursor = AstCursor::new(&ast);
cursor.goto_first_child();
let array_id = cursor.node_id();
assert_eq!(ast.get_node(array_id).unwrap().kind_name(), "array");
assert_eq!(ast.get_node(array_id).unwrap().kind(), "array");
// Two positional wildcards should bind to the two integers, skipping
// the comment that sits between them.
@@ -309,15 +309,11 @@ fn test_query_skips_extras_in_positional_match() {
let matched = query.do_match(&ast, array_id, &mut captures).unwrap();
assert!(matched);
assert_eq!(
ast.get_node(captures.get_var("a").unwrap())
.unwrap()
.kind_name(),
ast.get_node(captures.get_var("a").unwrap()).unwrap().kind(),
"integer"
);
assert_eq!(
ast.get_node(captures.get_var("b").unwrap())
.unwrap()
.kind_name(),
ast.get_node(captures.get_var("b").unwrap()).unwrap().kind(),
"integer"
);
}
@@ -395,7 +391,7 @@ fn test_capture_unnamed_node_parenthesized() {
assert!(matched);
let op_id = captures.get_var("op").unwrap();
let op_node = ast.get_node(op_id).unwrap();
assert_eq!(op_node.kind_name(), "=");
assert_eq!(op_node.kind(), "=");
assert!(!op_node.is_named());
}
@@ -418,7 +414,7 @@ fn test_capture_bare_underscore_repeated() {
let all = captures.get_all("all");
assert_eq!(all.len(), 1);
assert_eq!(ast.get_node(all[0]).unwrap().kind_name(), "=");
assert_eq!(ast.get_node(all[0]).unwrap().kind(), "=");
assert!(!ast.get_node(all[0]).unwrap().is_named());
}
@@ -445,7 +441,7 @@ fn test_capture_unnamed_node_bare_literal() {
assert!(matched);
let op_id = captures.get_var("op").unwrap();
let op_node = ast.get_node(op_id).unwrap();
assert_eq!(op_node.kind_name(), "=");
assert_eq!(op_node.kind(), "=");
assert!(!op_node.is_named());
}
@@ -483,7 +479,7 @@ fn test_bare_underscore_matches_unnamed() {
.unwrap();
assert!(matched, "_ should match the unnamed `=`");
let any_node = ast.get_node(captures.get_var("any").unwrap()).unwrap();
assert_eq!(any_node.kind_name(), "=");
assert_eq!(any_node.kind(), "=");
assert!(!any_node.is_named());
}
@@ -510,7 +506,7 @@ fn test_bare_forms_in_field_position() {
assert_eq!(
ast.get_node(captures.get_var("lhs").unwrap())
.unwrap()
.kind_name(),
.kind(),
"identifier"
);
@@ -520,7 +516,7 @@ fn test_bare_forms_in_field_position() {
let matched = query.do_match(&ast, assignment_id, &mut captures).unwrap();
assert!(matched);
let op = ast.get_node(captures.get_var("op").unwrap()).unwrap();
assert_eq!(op.kind_name(), "=");
assert_eq!(op.kind(), "=");
assert!(!op.is_named());
}
@@ -539,7 +535,7 @@ fn test_forward_scan_finds_unnamed_token_late() {
let mut cursor = AstCursor::new(&ast);
cursor.goto_first_child(); // for
cursor.goto_first_child(); // do (the body)
while cursor.node().kind_name() != "do" || !cursor.node().is_named() {
while cursor.node().kind() != "do" || !cursor.node().is_named() {
assert!(cursor.goto_next_sibling(), "expected to find named `do`");
}
let do_id = cursor.node_id();
@@ -549,7 +545,7 @@ fn test_forward_scan_finds_unnamed_token_late() {
let matched = query.do_match(&ast, do_id, &mut captures).unwrap();
assert!(matched, "forward-scan should find the `end` keyword");
let kw = ast.get_node(captures.get_var("kw").unwrap()).unwrap();
assert_eq!(kw.kind_name(), "end");
assert_eq!(kw.kind(), "end");
assert!(!kw.is_named());
}
@@ -565,7 +561,7 @@ fn test_forward_scan_preserves_order() {
let mut cursor = AstCursor::new(&ast);
cursor.goto_first_child();
cursor.goto_first_child();
while cursor.node().kind_name() != "do" || !cursor.node().is_named() {
while cursor.node().kind() != "do" || !cursor.node().is_named() {
assert!(cursor.goto_next_sibling(), "expected to find named `do`");
}
let do_id = cursor.node_id();
@@ -639,7 +635,7 @@ fn ruby_rules() -> Vec<Rule> {
left: (identifier $tmp)
right: {right}
)
{left.iter().enumerate().map(|(i, &lhs)|
{..left.iter().enumerate().map(|(i, &lhs)|
yeast::tree!(
(assignment
left: {lhs}
@@ -671,7 +667,7 @@ fn ruby_rules() -> Vec<Rule> {
left: {pat}
right: (identifier $tmp)
)
stmt: {body}
stmt: {..body}
)
)
)
@@ -907,7 +903,7 @@ fn one_shot_xeq1_rules() -> Vec<Rule> {
yeast::rule!(
(program (_)* @stmts)
=>
(program stmt: {stmts})
(program stmt: {..stmts})
),
yeast::rule!(
(assignment left: (_) @left right: (_) @right)
@@ -983,7 +979,7 @@ fn test_one_shot_recurses_into_returned_capture() {
yeast::rule!(
(program (_)* @stmts)
=>
(program stmt: {stmts})
(program stmt: {..stmts})
),
// Returns the captured `left` verbatim, discarding `right`.
yeast::rule!(
@@ -1025,7 +1021,7 @@ fn test_one_shot_does_not_recurse_into_wrapper_output() {
yeast::rule!(
(program (_)* @stmts)
=>
(program stmt: {stmts})
(program stmt: {..stmts})
),
// Wraps `left` in nested `first_node`/`second_node` output kinds.
// Neither wrapper kind has a matching rule, so a buggy implementation
@@ -1062,111 +1058,6 @@ fn test_one_shot_does_not_recurse_into_wrapper_output() {
);
}
/// Verify that `@@name` capture markers skip the auto-translate prefix:
/// the body sees the *raw* (input-schema) `Id` and can read its
/// source text or call `ctx.translate(...)` explicitly. Compare with
/// the bare `@name` form, where the auto-translate prefix runs the
/// same translation up front and the body sees the post-translate id.
#[test]
fn test_raw_capture_marker() {
let lang: tree_sitter::Language = tree_sitter_ruby::LANGUAGE.into();
let schema =
yeast::node_types_yaml::schema_from_yaml_with_language(OUTPUT_SCHEMA_YAML, &lang).unwrap();
let rules: Vec<Rule> = vec![
yeast::rule!(
(program (_)* @stmts)
=>
(program stmt: {stmts})
),
// `@@raw_lhs` is untranslated: the body reads its source text
// ("x") and embeds it directly as the identifier content. `@rhs`
// is auto-translated (rhs already points to (integer "INT")).
yeast::rule!(
(assignment left: (_) @@raw_lhs right: (_) @rhs)
=>
{
let text = ctx.ast.source_text(raw_lhs);
tree!((call
method: (identifier #{text.as_str()})
receiver: {rhs}))
}
),
yeast::rule!((identifier) => (identifier "ID")),
yeast::rule!((integer) => (integer "INT")),
];
let phases = vec![Phase::new("translate", PhaseKind::OneShot, rules)];
let runner: Runner = Runner::with_schema(lang, &schema, &phases);
let input = "x = 1";
let ast = runner.run(input).unwrap();
let dump = dump_ast(&ast, ast.get_root(), input);
// `method:` uses the raw source text ("x"); if `@@` were broken and
// auto-translation ran on `raw_lhs`, it would still produce the
// string "x" (source_text inherits the input range), so the dump
// wouldn't change here. The companion test
// `test_raw_capture_marker_explicit_translate` exercises the
// stronger property that `ctx.translate(raw_lhs)?` succeeds and
// produces the translated `(identifier "ID")`.
assert_dump_eq(
&dump,
r#"
program
stmt:
call
method: identifier "x"
receiver: integer "INT"
"#,
);
}
/// Companion to `test_raw_capture_marker`: confirms that calling
/// `ctx.translate(raw)` on a `@@`-captured `Id` from the rule body
/// produces the correctly-translated output-schema node. With `@`, the
/// translation has already happened, so `ctx.translate(...)` inside the
/// body would attempt to re-translate an output node (which has no
/// matching rule and would error).
#[test]
fn test_raw_capture_marker_explicit_translate() {
let lang: tree_sitter::Language = tree_sitter_ruby::LANGUAGE.into();
let schema =
yeast::node_types_yaml::schema_from_yaml_with_language(OUTPUT_SCHEMA_YAML, &lang).unwrap();
let rules: Vec<Rule> = vec![
yeast::rule!(
(program (_)* @stmts)
=>
(program stmt: {stmts})
),
yeast::rule!(
(assignment left: (_) @@raw_lhs right: (_) @rhs)
=>
{
let translated_lhs = ctx.translate(raw_lhs)?;
tree!((call
method: {translated_lhs}
receiver: {rhs}))
}
),
yeast::rule!((identifier) => (identifier "ID")),
yeast::rule!((integer) => (integer "INT")),
];
let phases = vec![Phase::new("translate", PhaseKind::OneShot, rules)];
let runner: Runner = Runner::with_schema(lang, &schema, &phases);
let input = "x = 1";
let ast = runner.run(input).unwrap();
let dump = dump_ast(&ast, ast.get_root(), input);
assert_dump_eq(
&dump,
r#"
program
stmt:
call
method: identifier "ID"
receiver: integer "INT"
"#,
);
}
// ---- Cursor tests ----
#[test]
@@ -1176,11 +1067,11 @@ fn test_cursor_navigation() {
let mut cursor = AstCursor::new(&ast);
// Start at root
assert_eq!(cursor.node().kind_name(), "program");
assert_eq!(cursor.node().kind(), "program");
// Go to first child (assignment)
assert!(cursor.goto_first_child());
assert_eq!(cursor.node().kind_name(), "assignment");
assert_eq!(cursor.node().kind(), "assignment");
// No sibling
assert!(!cursor.goto_next_sibling());
@@ -1191,10 +1082,10 @@ fn test_cursor_navigation() {
// Go back up
assert!(cursor.goto_parent());
assert_eq!(cursor.node().kind_name(), "assignment");
assert_eq!(cursor.node().kind(), "assignment");
assert!(cursor.goto_parent());
assert_eq!(cursor.node().kind_name(), "program");
assert_eq!(cursor.node().kind(), "program");
// Can't go further up
assert!(!cursor.goto_parent());
@@ -1239,8 +1130,10 @@ fn test_desugar_for_with_multiple_assignment() {
}
/// Regression test: `#{capture}` in a template must render the *source text*
/// of the captured node, not its arena `Id`. Captures are bound as `Id`,
/// whose `YeastDisplay` impl resolves to the captured node's source text.
/// of the captured node, not its arena `Id`. Previously, captures were bound
/// as `usize`, so `#{cap}` printed the integer id (e.g. `"3"`) via `Display`.
/// Captures are now bound as `NodeRef`, which has no `Display` impl and
/// resolves to the captured node's source text via `YeastDisplay`.
#[test]
fn test_hash_brace_renders_capture_source_text() {
let rule: Rule = rule!(
@@ -1268,7 +1161,7 @@ fn test_hash_brace_renders_capture_source_text() {
);
}
/// Regression test: non-`Id` values in `#{expr}` still render via their
/// Regression test: non-`NodeRef` values in `#{expr}` still render via their
/// `Display` impl (covered by `YeastDisplay`'s blanket impls for primitives).
#[test]
fn test_hash_brace_renders_integer_expression() {
@@ -1306,12 +1199,12 @@ fn test_hash_brace_uses_capture_location_for_leaf() {
let ast = run_and_ast("foo.bar()", vec![rule]);
let mut bar_ids: Vec<yeast::Id> = Vec::new();
let mut bar_ids: Vec<usize> = Vec::new();
for id in ast.reachable_node_ids() {
let Some(node) = ast.get_node(id) else {
continue;
};
if node.kind_name() == "identifier" && ast.source_text(id) == "bar" {
if node.kind() == "identifier" && ast.source_text(id) == "bar" {
bar_ids.push(id);
}
}

View File

@@ -42,6 +42,7 @@ supertypes:
- name_pattern
- tuple_pattern
- constructor_pattern
- or_pattern
- ignore_pattern
- expr_equality_pattern
- bulk_importing_pattern
@@ -359,12 +360,12 @@ named:
case*: switch_case
# A single `case ...:` (or `default:`) entry in a switch.
# An entry with multiple `case p1, p2:` patterns has multiple `pattern`s.
# A `default:` entry has no patterns.
# An entry with multiple `case p1, p2:` patterns uses an `or_pattern`.
# A `default:` entry has no pattern.
# An optional `guard` corresponds to a `where`-clause on the case.
switch_case:
modifier*: modifier
pattern*: pattern
pattern?: pattern
guard?: expr
body: block
@@ -421,6 +422,11 @@ named:
constructor: expr_or_type
element*: pattern_element
# A disjunction pattern that matches if any of its sub-patterns match.
or_pattern:
modifier*: modifier
pattern*: pattern
# A pattern with an optional associated name.
pattern_element:
modifier*: modifier

View File

@@ -1,5 +1,5 @@
use codeql_extractor::extractor::simple;
use yeast::{ConcreteDesugarer, DesugaringConfig, PhaseKind, Rule, rule, tree};
use yeast::{ConcreteDesugarer, DesugaringConfig, PhaseKind, Rule, manual_rule, rule, tree};
/// User context propagated from outer rules down to the inner rules that
/// emit the corresponding output declarations, so that each emitted node
@@ -45,7 +45,7 @@ struct SwiftContext {
/// Build a freshly-created `chained_declaration` modifier node if
/// `ctx.is_chained`, else `None`. Used by inner declaration rules to
/// emit the chained tag for non-first children of a flattening outer
/// rule. Returns `Option<Id>` so it splices via `{…}` to 0 or 1 ids.
/// rule. Returns `Option<Id>` so it splices via `{..…}` to 0 or 1 ids.
fn chained_modifier(ctx: &mut yeast::build::BuildCtx<'_, SwiftContext>) -> Option<yeast::Id> {
if ctx.is_chained {
Some(ctx.literal("modifier", "chained_declaration"))
@@ -63,10 +63,10 @@ fn chained_modifier(ctx: &mut yeast::build::BuildCtx<'_, SwiftContext>) -> Optio
/// condition.
fn and_chain(
ctx: &mut yeast::build::BuildCtx<'_, SwiftContext>,
conds: Vec<yeast::Id>,
conds: Vec<yeast::NodeRef>,
) -> yeast::Id {
conds
.into_iter()
conds.into_iter()
.map(yeast::Id::from)
.reduce(|acc, elem| {
tree!((binary_expr operator: (infix_operator "&&") left: {acc} right: {elem}))
})
@@ -79,7 +79,7 @@ fn and_chain(
/// guarantees at least one part.
fn member_chain(
ctx: &mut yeast::build::BuildCtx<'_, SwiftContext>,
parts: Vec<yeast::Id>,
parts: Vec<yeast::NodeRef>,
) -> yeast::Id {
let mut iter = parts.into_iter();
let first = iter
@@ -100,7 +100,7 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
(source_file statement: _* @children)
=>
(top_level
body: (block stmt: {children})
body: (block stmt: {..children})
)
),
// Declarations may be wrapped in local/global wrapper nodes.
@@ -144,12 +144,12 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
rule!(
(operator_declaration "prefix" (referenceable_operator _ @op) (simple_identifier)? @prec)
=>
(operator_syntax_declaration name: (identifier #{op}) fixity: (fixity "prefix") precedence: {prec})
(operator_syntax_declaration name: (identifier #{op}) fixity: (fixity "prefix") precedence: {..prec})
),
rule!(
(operator_declaration "postfix" (referenceable_operator _ @op) (simple_identifier)? @prec)
=>
(operator_syntax_declaration name: (identifier #{op}) fixity: (fixity "postfix") precedence: {prec})
(operator_syntax_declaration name: (identifier #{op}) fixity: (fixity "postfix") precedence: {..prec})
),
rule!(
(operator_declaration "infix" (referenceable_operator _ @op) (simple_identifier)? @prec)
@@ -157,7 +157,7 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
(operator_syntax_declaration
name: (identifier #{op})
fixity: (fixity "infix")
precedence: {prec})
precedence: {..prec})
),
rule!((bitwise_operation lhs: @l op: @op rhs: @r) => (binary_expr left: {l} operator: (infix_operator #{op}) right: {r})),
rule!((nil_coalescing_expression value: @l if_nil: @r) => (binary_expr left: {l} operator: (infix_operator "??") right: {r})),
@@ -170,9 +170,9 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
rule!((postfix_expression operation: @op target: @operand) => (unary_expr operator: (postfix_operator #{op}) operand: {operand})),
// TODO: Parenthesised single-value tuple is a grouping expression and should pass through.
// Multi-value tuples become tuple_expr.
rule!((tuple_expression value: _* @v) => (tuple_expr element: {v})),
rule!((tuple_expression value: _* @v) => (tuple_expr element: {..v})),
// Blocks contain statement* directly.
rule!((block statement: _+ @stmts) => (block stmt: {stmts})),
rule!((block statement: _+ @stmts) => (block stmt: {..stmts})),
rule!((block) => (block)),
// ---- Variables ----
// property_binding rules — these produce variable_declaration and/or accessor_declaration
@@ -192,15 +192,21 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
// this whole property_binding is itself a non-first declarator
// of a containing property_declaration); subsequent accessors
// always emit `chained_declaration`.
rule!(
manual_rule!(
(property_binding
name: @pattern
type: _? @ty
computed_value: (computed_property accessor: _+ @@accessors))
=>
{{
ctx.property_name = Some(tree!((identifier #{pattern})));
ctx.property_type = ty;
computed_value: (computed_property accessor: _+ @accessors))
{
// Translate `ty` first so the context holds an
// output-schema node id.
let translated_ty = ctx.translate_opt(ty)?;
// Build the property-name identifier from the
// (untranslated) pattern leaf.
let name_id = tree!((identifier #{pattern}));
ctx.property_name = Some(name_id);
ctx.property_type = translated_ty;
let mut result = Vec::new();
for (i, acc) in accessors.into_iter().enumerate() {
@@ -209,8 +215,8 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
}
result.extend(ctx.translate(acc)?);
}
result
}}
Ok(result)
}
),
// Computed property: shorthand getter (no explicit get/set, just
// statements) → a single accessor_declaration with kind "get".
@@ -223,13 +229,13 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
computed_value: (computed_property statement: _* @body))
=>
(accessor_declaration
modifier: {ctx.binding_modifier}
modifier: {ctx.outer_modifiers.clone()}
modifier: {chained_modifier(&mut ctx)}
modifier: {..ctx.binding_modifier}
modifier: {..ctx.outer_modifiers.clone()}
modifier: {..chained_modifier(&mut ctx)}
name: (identifier #{name})
type: {ty}
type: {..ty}
accessor_kind: (accessor_kind "get")
body: (block stmt: {body}))
body: (block stmt: {..body}))
),
// Stored property with willSet/didSet observers (initializer
// optional) → a `variable_declaration` followed by one
@@ -242,22 +248,26 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
// The `variable_declaration` itself inherits the outer rule's
// chained state; observers always get `chained_declaration`
// because they're subsequent outputs of this flattening rule.
rule!(
manual_rule!(
(property_binding
name: (pattern bound_identifier: @name)
type: _? @ty
value: _? @val
observers: (willset_didset_block willset: _? @@ws didset: _? @@ds))
=>
{{
observers: (willset_didset_block willset: _? @ws didset: _? @ds))
{
// Translate ty and val so the variable_declaration
// below contains output-schema nodes.
let translated_ty = ctx.translate_opt(ty)?;
let translated_val = ctx.translate_opt(val)?;
let var_decl = tree!(
(variable_declaration
modifier: {ctx.binding_modifier}
modifier: {ctx.outer_modifiers.clone()}
modifier: {chained_modifier(&mut ctx)}
modifier: {..ctx.binding_modifier}
modifier: {..ctx.outer_modifiers.clone()}
modifier: {..chained_modifier(&mut ctx)}
pattern: (name_pattern identifier: (identifier #{name}))
type: {ty}
value: {val})
type: {..translated_ty}
value: {..translated_val})
);
// Publish the property name for the observer rules.
@@ -270,8 +280,8 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
for obs in ws.into_iter().chain(ds) {
result.extend(ctx.translate(obs)?);
}
result
}}
Ok(result)
}
),
// property_binding with any pattern name (identifier or
// destructuring). Reads outer modifiers / chained tag from `ctx`.
@@ -282,12 +292,12 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
value: _? @val)
=>
(variable_declaration
modifier: {ctx.binding_modifier}
modifier: {ctx.outer_modifiers.clone()}
modifier: {chained_modifier(&mut ctx)}
modifier: {..ctx.binding_modifier}
modifier: {..ctx.outer_modifiers.clone()}
modifier: {..chained_modifier(&mut ctx)}
pattern: {pattern}
type: {ty}
value: {val})
type: {..ty}
value: {..val})
),
// property_declaration: flatten declarators (each may translate
// to multiple nodes — variable_declaration and/or
@@ -299,24 +309,27 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
// inner declaration rules (`property_binding` variants,
// accessor inner rules) read these fields and emit complete
// `modifier:` lists from the start.
rule!(
manual_rule!(
(property_declaration
binding: (value_binding_pattern mutability: @@binding_kind)
declarator: _* @@decls
binding: (value_binding_pattern mutability: @binding_kind)
declarator: _* @decls
(modifiers)* @mods)
=>
{{
let binding_text = ctx.ast.source_text(binding_kind);
{
let binding_text = ctx.ast.source_text(binding_kind.0);
ctx.binding_modifier = Some(ctx.literal("modifier", &binding_text));
ctx.outer_modifiers = mods;
let mut modifiers = Vec::new();
for m in mods {
modifiers.extend(ctx.translate(m)?);
}
ctx.outer_modifiers = modifiers;
let mut result = Vec::new();
for (i, decl) in decls.into_iter().enumerate() {
ctx.is_chained = i > 0;
result.extend(ctx.translate(decl)?);
}
result
}}
Ok(result)
}
),
// ---- Enums ----
// enum_type_parameter → parameter (with optional name as pattern).
@@ -342,19 +355,19 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
data_contents: (enum_type_parameters parameter: _* @params))
=>
(class_like_declaration
modifier: {ctx.outer_modifiers.clone()}
modifier: {chained_modifier(&mut ctx)}
modifier: {..ctx.outer_modifiers.clone()}
modifier: {..chained_modifier(&mut ctx)}
modifier: (modifier "enum_case")
name: (identifier #{name})
member: (constructor_declaration parameter: {params} body: (block)))
member: (constructor_declaration parameter: {..params} body: (block)))
),
// enum_case_entry with explicit raw value → variable_declaration with that value.
rule!(
(enum_case_entry name: @name raw_value: @val)
=>
(variable_declaration
modifier: {ctx.outer_modifiers.clone()}
modifier: {chained_modifier(&mut ctx)}
modifier: {..ctx.outer_modifiers.clone()}
modifier: {..chained_modifier(&mut ctx)}
modifier: (modifier "enum_case")
pattern: (name_pattern identifier: (identifier #{name}))
value: {val})
@@ -364,8 +377,8 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
(enum_case_entry name: @name)
=>
(variable_declaration
modifier: {ctx.outer_modifiers.clone()}
modifier: {chained_modifier(&mut ctx)}
modifier: {..ctx.outer_modifiers.clone()}
modifier: {..chained_modifier(&mut ctx)}
modifier: (modifier "enum_case")
pattern: (name_pattern identifier: (identifier #{name})))
),
@@ -373,19 +386,22 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
// into `ctx` and translate each case with `ctx.is_chained`
// toggled per iteration so the inner `enum_case_entry` rules
// emit complete `modifier:` lists from the start.
rule!(
(enum_entry case: _+ @@cases (modifiers)* @mods)
=>
{{
ctx.outer_modifiers = mods;
manual_rule!(
(enum_entry case: _+ @cases (modifiers)* @mods)
{
let mut modifiers = Vec::new();
for m in mods {
modifiers.extend(ctx.translate(m)?);
}
ctx.outer_modifiers = modifiers;
let mut result = Vec::new();
for (i, case) in cases.into_iter().enumerate() {
ctx.is_chained = i > 0;
result.extend(ctx.translate(case)?);
}
result
}}
Ok(result)
}
),
// Plain assignment: `x = expr`
rule!(
@@ -418,7 +434,7 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
=>
(constructor_pattern
constructor: (member_access_expr base: {typ} member: (identifier #{name}))
element: {items})
element: {..items})
),
// case .foo(x,y) pattern
rule!(
@@ -426,10 +442,10 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
=>
(constructor_pattern
constructor: (member_access_expr base: (inferred_type_expr #{dot}) member: (identifier #{name}))
element: {items})
element: {..items})
),
// Tuple pattern and its (optionally named) items
rule!((pattern kind: (tuple_pattern item: _* @elems)) => (tuple_pattern element: {elems})),
rule!((pattern kind: (tuple_pattern item: _* @elems)) => (tuple_pattern element: {..elems})),
rule!((tuple_pattern_item name: @key pattern: @pat) => (pattern_element key: (identifier #{key}) pattern: {pat})),
rule!((tuple_pattern_item pattern: @pat) => (pattern_element pattern: {pat})),
// Type casting pattern (TODO)
@@ -452,21 +468,20 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
=>
(function_declaration
name: (identifier #{name})
parameter: {params}
return_type: {ret}
body: (block stmt: {body_stmts}))
parameter: {..params}
return_type: {..ret}
body: (block stmt: {..body_stmts}))
),
// Parameters are wrapped in function_parameter, which also carries
// optional default values. Publishes the default value into `ctx`
// before translating the inner `parameter` so the `parameter`
// rules can include it as a `default:` field directly.
rule!(
(function_parameter parameter: @@p default_value: _? @def)
=>
{{
ctx.default_value = def;
ctx.translate(p)?
}}
manual_rule!(
(function_parameter parameter: @p default_value: _? @def)
{
ctx.default_value = ctx.translate_opt(def)?;
ctx.translate(p)
}
),
// Parameter with external name and type
rule!(
@@ -475,7 +490,7 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
(parameter
external_name: (identifier #{ext})
pattern: (name_pattern identifier: (identifier #{name}))
default: {ctx.default_value})
default: {..ctx.default_value})
),
rule!(
(parameter external_name: @ext name: @name type: @ty)
@@ -484,7 +499,7 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
external_name: (identifier #{ext})
pattern: (name_pattern identifier: (identifier #{name}))
type: {ty}
default: {ctx.default_value})
default: {..ctx.default_value})
),
// Parameter with just name and type (no external name)
rule!(
@@ -492,7 +507,7 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
=>
(parameter
pattern: (name_pattern identifier: (identifier #{name}))
default: {ctx.default_value})
default: {..ctx.default_value})
),
rule!(
(parameter name: @name type: @ty)
@@ -500,7 +515,7 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
(parameter
pattern: (name_pattern identifier: (identifier #{name}))
type: {ty}
default: {ctx.default_value})
default: {..ctx.default_value})
),
// Reference to a function, f(x:y:z:). This is parsed as a call with a single argument with multiple reference_specifier labels.
// We don't want downstream QL to try to handle this as a call_expr with a weird argument, so explicitly mark it as unsupported for now.
@@ -514,7 +529,7 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
rule!(
(call_expression function: @func suffix: (call_suffix arguments: (value_arguments argument: (value_argument)* @args)))
=>
(call_expr callee: {func} argument: {args})
(call_expr callee: {func} argument: {..args})
),
// Value argument with label (value: _ matches both named nodes and anonymous tokens like nil)
rule!(
@@ -537,7 +552,7 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
// Return / break / continue, one rule per keyword.
// The anonymous "return"/"break"/"continue" keywords are matched as
// string literals.
rule!((control_transfer_statement kind: "return" result: _? @val) => (return_expr value: {val})),
rule!((control_transfer_statement kind: "return" result: _? @val) => (return_expr value: {..val})),
rule!((control_transfer_statement kind: "break" result: @lbl) => (break_expr label: (identifier #{lbl}))),
rule!((control_transfer_statement kind: "break") => (break_expr)),
rule!((control_transfer_statement kind: "continue" result: @lbl) => (continue_expr label: (identifier #{lbl}))),
@@ -556,20 +571,20 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
statement: _* @body)
=>
(function_expr
modifier: {attrs}
capture_declaration: {captures}
parameter: {params}
return_type: {ret}
body: (block stmt: {body}))
modifier: {..attrs}
capture_declaration: {..captures}
parameter: {..params}
return_type: {..ret}
body: (block stmt: {..body}))
),
// capture_list_item with ownership modifier (e.g. [weak self], [unowned x])
rule!(
(capture_list_item ownership: _? @ownership name: @name value: _? @val)
=>
(variable_declaration
modifier: {ownership}
modifier: {..ownership}
pattern: (name_pattern identifier: (identifier #{name}))
value: {val})
value: {..val})
),
// Lambda parameter with type and optional external name
rule!(
@@ -615,7 +630,7 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
(if_expr
condition: {and_chain(&mut ctx, cond)}
then: {then_body}
else: {else_stmts})
else: {..else_stmts})
),
// Guard statement
rule!(
@@ -623,7 +638,7 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
=>
(guard_if_stmt
condition: {and_chain(&mut ctx, cond)}
else: (block stmt: {else_stmts}))
else: (block stmt: {..else_stmts}))
),
// Ternary expression → if_expr
rule!(
@@ -635,27 +650,36 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
rule!(
(switch_statement expr: @val entry: (switch_entry)* @cases)
=>
(switch_expr value: {val} case: {cases})
(switch_expr value: {val} case: {..cases})
),
// Switch entry with patterns and body
// Switch entry with multiple patterns and body
rule!(
(switch_entry pattern: (switch_pattern pattern: @pats)* statement: _* @body)
(switch_entry
pattern: (switch_pattern pattern: @first)
pattern: (switch_pattern pattern: @rest)+
statement: _* @body)
=>
(switch_case pattern: {pats} body: (block stmt: {body}))
(switch_case pattern: (or_pattern pattern: {first} pattern: {..rest}) body: (block stmt: {..body}))
),
// Switch entry with exactly one pattern and body
rule!(
(switch_entry pattern: (switch_pattern pattern: @pat) statement: _* @body)
=>
(switch_case pattern: {pat} body: (block stmt: {..body}))
),
// Switch entry: default case (no patterns)
rule!(
(switch_entry default: (default_keyword) statement: _* @body)
=>
(switch_case body: (block stmt: {body}))
(switch_case body: (block stmt: {..body}))
),
// if case let x = expr — the pattern is taken as-is (no Optional wrapping)
// if case PATTERN = expr — preserve the pattern directly (no Optional wrapping)
rule!(
(if_let_binding "case" (value_binding_pattern) bound_identifier: @name _ @val)
(if_let_binding "case" pattern: @pat value: @val)
=>
(pattern_guard_expr
value: {val}
pattern: (name_pattern identifier: (identifier #{name})))
pattern: {pat})
),
rule!(
(if_let_binding
@@ -693,8 +717,8 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
(for_each_stmt
pattern: {pat}
iterable: {iter}
guard: {guard}
body: (block stmt: {body}))
guard: {..guard}
body: (block stmt: {..body}))
),
// While loop
rule!(
@@ -702,7 +726,7 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
=>
(while_stmt
condition: {and_chain(&mut ctx, cond)}
body: (block stmt: {body}))
body: (block stmt: {..body}))
),
// Repeat-while loop
rule!(
@@ -710,28 +734,28 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
=>
(do_while_stmt
condition: {and_chain(&mut ctx, cond)}
body: (block stmt: {body}))
body: (block stmt: {..body}))
),
// Labeled statement (e.g. `outer: for ...`). Strip the trailing ':' from the label token.
rule!((labeled_statement label: (statement_label) @lbl statement: @stmt) => {
let text = ctx.ast.source_text(lbl);
let text = ctx.ast.source_text(lbl.into());
let name = &text[..text.len() - 1];
tree!((labeled_stmt label: (identifier #{name}) stmt: {stmt}))
}),
// ---- Collections ----
// Array literal
rule!((array_literal element: _* @elems) => (array_literal element: {elems})),
rule!((array_literal element: _* @elems) => (array_literal element: {..elems})),
// Empty array literal
rule!((array_literal) => (array_literal)),
// Dictionary literal — zip keys and values into key_value_pairs
rule!(
(dictionary_literal key: _* @keys value: _* @vals)
=>
(map_literal element: {keys.into_iter().zip(vals).map(|(k, v)|
(map_literal element: {..keys.into_iter().zip(vals).map(|(k, v)|
tree!((key_value_pair key: {k} value: {v}))
)})
),
rule!((dictionary_literal element: _* @elems) => (map_literal element: {elems})),
rule!((dictionary_literal element: _* @elems) => (map_literal element: {..elems})),
rule!((dictionary_literal_item key: @k value: @v) => (key_value_pair key: {k} value: {v})),
// ---- Optionals and errors ----
// Optional chaining — unwrap the marker
@@ -744,8 +768,8 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
(do_statement body: (block statement: _* @body) catch: (catch_block)* @catches)
=>
(try_expr
body: (block stmt: {body})
catch_clause: {catches})
body: (block stmt: {..body})
catch_clause: {..catches})
),
// Catch block with bound identifier; optional where-clause guard.
rule!(
@@ -757,14 +781,14 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
=>
(catch_clause
pattern: {pattern}
guard: {guard}
body: (block stmt: {body}))
guard: {..guard}
body: (block stmt: {..body}))
),
// Catch block without error binding
rule!(
(catch_block keyword: (catch_keyword) body: (block statement: _* @body))
=>
(catch_clause body: (block stmt: {body}))
(catch_clause body: (block stmt: {..body}))
),
// Empty catch block: catch {}
rule!(
@@ -778,7 +802,7 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
=>
(catch_clause
pattern: {pat}
body: (block stmt: {body}))
body: (block stmt: {..body}))
),
// As expression (type cast) — as?, as!
rule!((as_expression (as_operator) @op expr: @val type: @ty) => (type_cast_expr expr: {val} operator: (infix_operator #{op}) type: {ty})),
@@ -803,7 +827,7 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
pattern: (name_pattern identifier: (identifier #{parts.last().unwrap()}))
imported_expr: {name}
modifier: (modifier #{kind})
modifier: {mods})
modifier: {..mods})
),
// Non-scoped import declaration (for example `import Foundation`):
// flatten the identifier parts into a member_access_expr and use a
@@ -814,7 +838,7 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
(import_declaration
pattern: (bulk_importing_pattern)
imported_expr: {name}
modifier: {mods})
modifier: {..mods})
),
// ---- Types and classes ----
// Self expression → name_expr
@@ -822,7 +846,7 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
// Super expression → super_expr
rule!((super_expression) => (super_expr)),
// Modifiers — unwrap to individual modifier children
rule!((modifiers _* @mods) => {mods}),
rule!((modifiers _* @mods) => {..mods}),
rule!((attribute) @m => (modifier #{m})),
rule!((visibility_modifier) @m => (modifier #{m})),
rule!((function_modifier) @m => (modifier #{m})),
@@ -839,7 +863,7 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
// Keep a conservative textual fallback to avoid dropping type information.
rule!((user_type) @ty => (named_type_expr name: (identifier #{ty}))),
// Tuple type → tuple_type_expr
rule!((tuple_type element: _* @elems) => (tuple_type_expr element: {elems})),
rule!((tuple_type element: _* @elems) => (tuple_type_expr element: {..elems})),
rule!((tuple_type_item name: @name type: @ty) => (tuple_type_element name: (identifier #{name}) type: {ty})),
rule!((tuple_type_item type: @ty) => (tuple_type_element type: {ty})),
// Array type `[T]` → generic_type_expr with Array base
@@ -856,7 +880,7 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
base: (named_type_expr name: (identifier "Optional"))
type_argument: {w})),
// Function type `(Params) -> Ret` → function_type_expr.
rule!((function_type parameter: _* @ps return_type: @ret) => (function_type_expr parameter: {ps} return_type: {ret})),
rule!((function_type parameter: _* @ps return_type: @ret) => (function_type_expr parameter: {..ps} return_type: {ret})),
rule!((function_type_parameter name: @name type: @ty) => (parameter external_name: (identifier #{name}) type: {ty})),
rule!((function_type_parameter type: @ty) => (parameter type: {ty})),
// Selector expression: `#selector(inner)` -- not yet supported
@@ -880,10 +904,10 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
=>
(class_like_declaration
modifier: (modifier #{kind})
modifier: {mods}
modifier: {..mods}
name: (identifier #{name})
base_type: {bases}
member: {members})
base_type: {..bases}
member: {..members})
),
// Enum class declaration: same as a regular class but with an enum body.
rule!(
@@ -896,10 +920,10 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
=>
(class_like_declaration
modifier: (modifier #{kind})
modifier: {mods}
modifier: {..mods}
name: (identifier #{name})
base_type: {bases}
member: {members})
base_type: {..bases}
member: {..members})
),
// Class declaration with empty body
rule!(
@@ -912,9 +936,9 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
=>
(class_like_declaration
modifier: (modifier #{kind})
modifier: {mods}
modifier: {..mods}
name: (identifier #{name})
base_type: {bases})
base_type: {..bases})
),
// Protocol declaration
rule!(
@@ -926,10 +950,10 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
=>
(class_like_declaration
modifier: (modifier "protocol")
modifier: {mods}
modifier: {..mods}
name: (identifier #{name})
base_type: {bases}
member: {members})
base_type: {..bases}
member: {..members})
),
// Protocol function — return type and body statements both optional.
rule!(
@@ -941,11 +965,11 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
(modifiers)* @mods)
=>
(function_declaration
modifier: {mods}
modifier: {..mods}
name: (identifier #{name})
parameter: {params}
return_type: {ret}
body: (block stmt: {body_stmts}))
parameter: {..params}
return_type: {..ret}
body: (block stmt: {..body_stmts}))
),
// Init declaration → constructor_declaration. Body statements optional;
// body itself is also optional (protocol requirement).
@@ -956,9 +980,9 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
(modifiers)* @mods)
=>
(constructor_declaration
modifier: {mods}
parameter: {params}
body: (block stmt: {body_stmts}))
modifier: {..mods}
parameter: {..params}
body: (block stmt: {..body_stmts}))
),
// Deinit declaration → destructor_declaration. Body statements optional.
rule!(
@@ -967,15 +991,15 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
(modifiers)* @mods)
=>
(destructor_declaration
modifier: {mods}
body: (block stmt: {body_stmts}))
modifier: {..mods}
body: (block stmt: {..body_stmts}))
),
// Typealias declaration
rule!(
(typealias_declaration name: @name value: @val (modifiers)* @mods)
=>
(type_alias_declaration
modifier: {mods}
modifier: {..mods}
name: (identifier #{name})
r#type: {val})
),
@@ -990,9 +1014,9 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
(associatedtype_declaration name: @name inherits_from: _? @bound (modifiers)* @mods)
=>
(associated_type_declaration
modifier: {mods}
modifier: {..mods}
name: (identifier #{name})
bound: {bound})
bound: {..bound})
),
// Protocol property declaration: translate each accessor
// requirement to an `accessor_declaration` carrying the property
@@ -1002,25 +1026,28 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
// inner `getter_specifier`/`setter_specifier` rules emit
// complete nodes from the start (including the
// `chained_declaration` tag for non-first accessors).
rule!(
manual_rule!(
(protocol_property_declaration
name: (pattern bound_identifier: @name)
requirements: (protocol_property_requirements accessor: _+ @@accessors)
requirements: (protocol_property_requirements accessor: _+ @accessors)
type: _? @ty
(modifiers)* @mods)
=>
{{
{
ctx.property_name = Some(tree!((identifier #{name})));
ctx.property_type = ty;
ctx.outer_modifiers = mods;
ctx.property_type = ctx.translate_opt(ty)?;
let mut modifiers = Vec::new();
for m in mods {
modifiers.extend(ctx.translate(m)?);
}
ctx.outer_modifiers = modifiers;
let mut result = Vec::new();
for (i, acc) in accessors.into_iter().enumerate() {
ctx.is_chained = i > 0;
result.extend(ctx.translate(acc)?);
}
result
}}
Ok(result)
}
),
// getter_specifier / setter_specifier → bodyless accessor_declaration
// getter_specifier / setter_specifier → bodyless
@@ -1031,23 +1058,23 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
=>
(accessor_declaration
name: {ctx.property_name.ok_or("getter_specifier outside protocol_property_declaration context")?}
type: {ctx.property_type}
type: {..ctx.property_type}
accessor_kind: (accessor_kind "get")
modifier: {ctx.outer_modifiers.clone()}
modifier: {chained_modifier(&mut ctx)})
modifier: {..ctx.outer_modifiers.clone()}
modifier: {..chained_modifier(&mut ctx)})
),
rule!(
(setter_specifier)
=>
(accessor_declaration
name: {ctx.property_name.ok_or("setter_specifier outside protocol_property_declaration context")?}
type: {ctx.property_type}
type: {..ctx.property_type}
accessor_kind: (accessor_kind "set")
modifier: {ctx.outer_modifiers.clone()}
modifier: {chained_modifier(&mut ctx)})
modifier: {..ctx.outer_modifiers.clone()}
modifier: {..chained_modifier(&mut ctx)})
),
// protocol_property_requirements wrapper — should be consumed by above; fallback
rule!((protocol_property_requirements accessor: _* @accs) => {accs}),
rule!((protocol_property_requirements accessor: _* @accs) => {..accs}),
// Computed getter → accessor_declaration (body optional).
// Reads property name/type from the outer property_binding rule
// and binding/outer modifiers + chained tag from the outer
@@ -1056,58 +1083,58 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
(computed_getter body: (block statement: _* @body)?)
=>
(accessor_declaration
modifier: {ctx.binding_modifier}
modifier: {ctx.outer_modifiers.clone()}
modifier: {chained_modifier(&mut ctx)}
modifier: {..ctx.binding_modifier}
modifier: {..ctx.outer_modifiers.clone()}
modifier: {..chained_modifier(&mut ctx)}
name: {ctx.property_name.ok_or("computed_getter outside property_binding context")?}
type: {ctx.property_type}
type: {..ctx.property_type}
accessor_kind: (accessor_kind "get")
body: (block stmt: {body}))
body: (block stmt: {..body}))
),
// Computed setter with explicit parameter name.
rule!(
(computed_setter parameter: @param body: (block statement: _* @body))
=>
(accessor_declaration
modifier: {ctx.binding_modifier}
modifier: {ctx.outer_modifiers.clone()}
modifier: {chained_modifier(&mut ctx)}
modifier: {..ctx.binding_modifier}
modifier: {..ctx.outer_modifiers.clone()}
modifier: {..chained_modifier(&mut ctx)}
name: {ctx.property_name.ok_or("computed_setter outside property_binding context")?}
type: {ctx.property_type}
type: {..ctx.property_type}
accessor_kind: (accessor_kind "set")
parameter: (parameter pattern: (name_pattern identifier: (identifier #{param})))
body: (block stmt: {body}))
body: (block stmt: {..body}))
),
// Computed setter without explicit parameter name; body optional.
rule!(
(computed_setter body: (block statement: _* @body)?)
=>
(accessor_declaration
modifier: {ctx.binding_modifier}
modifier: {ctx.outer_modifiers.clone()}
modifier: {chained_modifier(&mut ctx)}
modifier: {..ctx.binding_modifier}
modifier: {..ctx.outer_modifiers.clone()}
modifier: {..chained_modifier(&mut ctx)}
name: {ctx.property_name.ok_or("computed_setter outside property_binding context")?}
type: {ctx.property_type}
type: {..ctx.property_type}
accessor_kind: (accessor_kind "set")
body: (block stmt: {body}))
body: (block stmt: {..body}))
),
// Computed modify → accessor_declaration
rule!(
(computed_modify body: (block statement: _* @body))
=>
(accessor_declaration
modifier: {ctx.binding_modifier}
modifier: {ctx.outer_modifiers.clone()}
modifier: {chained_modifier(&mut ctx)}
modifier: {..ctx.binding_modifier}
modifier: {..ctx.outer_modifiers.clone()}
modifier: {..chained_modifier(&mut ctx)}
name: {ctx.property_name.ok_or("computed_modify outside property_binding context")?}
type: {ctx.property_type}
type: {..ctx.property_type}
accessor_kind: (accessor_kind "modify")
body: (block stmt: {body}))
body: (block stmt: {..body}))
),
// willset/didset block — spread to children (only reachable as a
// fallback; the outer property_binding manual rule normally
// captures the willset/didset clauses directly).
rule!((willset_didset_block _* @clauses) => {clauses}),
rule!((willset_didset_block _* @clauses) => {..clauses}),
// willset clause → accessor_declaration (body optional). Reads
// `ctx.property_name` set by the outer property_binding rule and
// binding/outer modifiers + chained tag from the outer
@@ -1116,24 +1143,24 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
(willset_clause body: (block statement: _* @body)?)
=>
(accessor_declaration
modifier: {ctx.binding_modifier}
modifier: {ctx.outer_modifiers.clone()}
modifier: {chained_modifier(&mut ctx)}
modifier: {..ctx.binding_modifier}
modifier: {..ctx.outer_modifiers.clone()}
modifier: {..chained_modifier(&mut ctx)}
name: {ctx.property_name.ok_or("willset_clause outside property_binding context")?}
accessor_kind: (accessor_kind "willSet")
body: (block stmt: {body}))
body: (block stmt: {..body}))
),
// didset clause → accessor_declaration (body optional).
rule!(
(didset_clause body: (block statement: _* @body)?)
=>
(accessor_declaration
modifier: {ctx.binding_modifier}
modifier: {ctx.outer_modifiers.clone()}
modifier: {chained_modifier(&mut ctx)}
modifier: {..ctx.binding_modifier}
modifier: {..ctx.outer_modifiers.clone()}
modifier: {..chained_modifier(&mut ctx)}
name: {ctx.property_name.ok_or("didset_clause outside property_binding context")?}
accessor_kind: (accessor_kind "didSet")
body: (block stmt: {body}))
body: (block stmt: {..body}))
),
// Preprocessor conditionals — unsupported
rule!((diagnostic) => (unsupported_node)),

View File

@@ -573,10 +573,12 @@ top_level
name_expr
identifier: identifier "print"
pattern:
expr_equality_pattern
expr: int_literal "2"
expr_equality_pattern
expr: int_literal "3"
or_pattern
pattern:
expr_equality_pattern
expr: int_literal "2"
expr_equality_pattern
expr: int_literal "3"
switch_case
body:
block
@@ -592,6 +594,83 @@ top_level
name_expr
identifier: identifier "x"
===
If-case-let with shadowing in condition value
===
if case let x = x + 10 {
print(x)
}
---
source_file
statement:
if_statement
body:
block
statement:
call_expression
function: simple_identifier "print"
suffix:
call_suffix
arguments:
value_arguments
argument:
value_argument
value: simple_identifier "x"
condition:
if_condition
kind:
if_let_binding
pattern:
pattern
kind:
binding_pattern
binding:
value_binding_pattern
mutability: let
pattern:
pattern
bound_identifier: simple_identifier "x"
value:
additive_expression
lhs: simple_identifier "x"
op: +
rhs: integer_literal "10"
---
top_level
body:
block
stmt:
if_expr
condition:
pattern_guard_expr
pattern:
name_pattern
identifier: identifier "x"
value:
binary_expr
operator: infix_operator "+"
left:
name_expr
identifier: identifier "x"
right: int_literal "10"
then:
block
stmt:
call_expr
argument:
argument
value:
name_expr
identifier: identifier "x"
callee:
name_expr
identifier: identifier "print"
===
Switch with binding pattern
===

View File

@@ -978,6 +978,23 @@ module Unified {
}
}
/** A class representing `or_pattern` nodes. */
class OrPattern extends @unified_or_pattern, AstNode {
/** Gets the name of the primary QL class for this element. */
final override string getAPrimaryQlClass() { result = "OrPattern" }
/** Gets the node corresponding to the field `modifier`. */
final Modifier getModifier(int i) { unified_or_pattern_modifier(this, i, result) }
/** Gets the node corresponding to the field `pattern`. */
final Pattern getPattern(int i) { unified_or_pattern_pattern(this, i, result) }
/** Gets a field or child node of this node. */
final override AstNode getAFieldOrChild() {
unified_or_pattern_modifier(this, _, result) or unified_or_pattern_pattern(this, _, result)
}
}
/** A class representing `parameter` nodes. */
class Parameter extends @unified_parameter, AstNode {
/** Gets the name of the primary QL class for this element. */
@@ -1109,14 +1126,14 @@ module Unified {
final Modifier getModifier(int i) { unified_switch_case_modifier(this, i, result) }
/** Gets the node corresponding to the field `pattern`. */
final Pattern getPattern(int i) { unified_switch_case_pattern(this, i, result) }
final Pattern getPattern() { unified_switch_case_pattern(this, result) }
/** Gets a field or child node of this node. */
final override AstNode getAFieldOrChild() {
unified_switch_case_def(this, result) or
unified_switch_case_guard(this, result) or
unified_switch_case_modifier(this, _, result) or
unified_switch_case_pattern(this, _, result)
unified_switch_case_pattern(this, result)
}
}
@@ -1654,6 +1671,10 @@ module Unified {
i = -1 and
name = "getPrecedence"
or
result = node.(OrPattern).getModifier(i) and name = "getModifier"
or
result = node.(OrPattern).getPattern(i) and name = "getPattern"
or
result = node.(Parameter).getDefault() and i = -1 and name = "getDefault"
or
result = node.(Parameter).getExternalName() and i = -1 and name = "getExternalName"
@@ -1682,7 +1703,7 @@ module Unified {
or
result = node.(SwitchCase).getModifier(i) and name = "getModifier"
or
result = node.(SwitchCase).getPattern(i) and name = "getPattern"
result = node.(SwitchCase).getPattern() and i = -1 and name = "getPattern"
or
result = node.(SwitchExpr).getCase(i) and name = "getCase"
or

View File

@@ -716,6 +716,24 @@ unified_operator_syntax_declaration_def(
int name: @unified_token_identifier ref
);
#keyset[unified_or_pattern, index]
unified_or_pattern_modifier(
int unified_or_pattern: @unified_or_pattern ref,
int index: int ref,
unique int modifier: @unified_token_modifier ref
);
#keyset[unified_or_pattern, index]
unified_or_pattern_pattern(
int unified_or_pattern: @unified_or_pattern ref,
int index: int ref,
unique int pattern: @unified_pattern ref
);
unified_or_pattern_def(
unique int id: @unified_or_pattern
);
unified_parameter_default(
unique int unified_parameter: @unified_parameter ref,
unique int default: @unified_expr ref
@@ -747,7 +765,7 @@ unified_parameter_def(
unique int id: @unified_parameter
);
@unified_pattern = @unified_bulk_importing_pattern | @unified_constructor_pattern | @unified_expr_equality_pattern | @unified_name_pattern | @unified_token_ignore_pattern | @unified_token_unsupported_node | @unified_tuple_pattern
@unified_pattern = @unified_bulk_importing_pattern | @unified_constructor_pattern | @unified_expr_equality_pattern | @unified_name_pattern | @unified_or_pattern | @unified_token_ignore_pattern | @unified_token_unsupported_node | @unified_tuple_pattern
unified_pattern_element_key(
unique int unified_pattern_element: @unified_pattern_element ref,
@@ -795,10 +813,8 @@ unified_switch_case_modifier(
unique int modifier: @unified_token_modifier ref
);
#keyset[unified_switch_case, index]
unified_switch_case_pattern(
int unified_switch_case: @unified_switch_case ref,
int index: int ref,
unique int unified_switch_case: @unified_switch_case ref,
unique int pattern: @unified_pattern ref
);
@@ -1056,7 +1072,7 @@ unified_trivia_tokeninfo(
string value: string ref
);
@unified_ast_node = @unified_accessor_declaration | @unified_argument | @unified_array_literal | @unified_assign_expr | @unified_associated_type_declaration | @unified_base_type | @unified_binary_expr | @unified_block | @unified_bound_type_constraint | @unified_break_expr | @unified_bulk_importing_pattern | @unified_call_expr | @unified_catch_clause | @unified_class_like_declaration | @unified_compound_assign_expr | @unified_constructor_declaration | @unified_constructor_pattern | @unified_continue_expr | @unified_destructor_declaration | @unified_do_while_stmt | @unified_equality_type_constraint | @unified_expr_equality_pattern | @unified_for_each_stmt | @unified_function_declaration | @unified_function_expr | @unified_function_type_expr | @unified_generic_type_expr | @unified_guard_if_stmt | @unified_if_expr | @unified_import_declaration | @unified_initializer_declaration | @unified_key_value_pair | @unified_labeled_stmt | @unified_map_literal | @unified_member_access_expr | @unified_name_expr | @unified_name_pattern | @unified_named_type_expr | @unified_operator_syntax_declaration | @unified_parameter | @unified_pattern_element | @unified_pattern_guard_expr | @unified_return_expr | @unified_switch_case | @unified_switch_expr | @unified_throw_expr | @unified_token | @unified_top_level | @unified_trivia_token | @unified_try_expr | @unified_tuple_expr | @unified_tuple_pattern | @unified_tuple_type_element | @unified_tuple_type_expr | @unified_type_alias_declaration | @unified_type_cast_expr | @unified_type_parameter | @unified_type_test_expr | @unified_type_test_pattern | @unified_unary_expr | @unified_variable_declaration | @unified_while_stmt
@unified_ast_node = @unified_accessor_declaration | @unified_argument | @unified_array_literal | @unified_assign_expr | @unified_associated_type_declaration | @unified_base_type | @unified_binary_expr | @unified_block | @unified_bound_type_constraint | @unified_break_expr | @unified_bulk_importing_pattern | @unified_call_expr | @unified_catch_clause | @unified_class_like_declaration | @unified_compound_assign_expr | @unified_constructor_declaration | @unified_constructor_pattern | @unified_continue_expr | @unified_destructor_declaration | @unified_do_while_stmt | @unified_equality_type_constraint | @unified_expr_equality_pattern | @unified_for_each_stmt | @unified_function_declaration | @unified_function_expr | @unified_function_type_expr | @unified_generic_type_expr | @unified_guard_if_stmt | @unified_if_expr | @unified_import_declaration | @unified_initializer_declaration | @unified_key_value_pair | @unified_labeled_stmt | @unified_map_literal | @unified_member_access_expr | @unified_name_expr | @unified_name_pattern | @unified_named_type_expr | @unified_operator_syntax_declaration | @unified_or_pattern | @unified_parameter | @unified_pattern_element | @unified_pattern_guard_expr | @unified_return_expr | @unified_switch_case | @unified_switch_expr | @unified_throw_expr | @unified_token | @unified_top_level | @unified_trivia_token | @unified_try_expr | @unified_tuple_expr | @unified_tuple_pattern | @unified_tuple_type_element | @unified_tuple_type_expr | @unified_type_alias_declaration | @unified_type_cast_expr | @unified_type_parameter | @unified_type_test_expr | @unified_type_test_pattern | @unified_unary_expr | @unified_variable_declaration | @unified_while_stmt
unified_ast_node_location(
unique int node: @unified_ast_node ref,