mirror of
https://github.com/github/codeql.git
synced 2026-06-30 00:55:29 +02:00
Compare commits
4 Commits
andersfugm
...
yoff/pytho
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
e50e81390f | ||
|
|
66900c7d62 | ||
|
|
956d2dbec4 | ||
|
|
872c08148e |
@@ -28,6 +28,7 @@
|
||||
/swift/extractor/ @github/codeql-swift @github/code-scanning-language-coverage
|
||||
/misc/codegen/ @github/codeql-swift
|
||||
/java/kotlin-extractor/ @github/codeql-kotlin @github/code-scanning-language-coverage
|
||||
/java/ql/test-kotlin1/ @github/codeql-kotlin
|
||||
/java/ql/test-kotlin2/ @github/codeql-kotlin
|
||||
|
||||
# Experimental CodeQL cryptography
|
||||
|
||||
@@ -75,9 +75,6 @@ def get_version():
|
||||
|
||||
|
||||
def install(version: str, quiet: bool):
|
||||
if install_dir.exists():
|
||||
return
|
||||
|
||||
if quiet:
|
||||
info_out = subprocess.DEVNULL
|
||||
info = lambda *args: None
|
||||
@@ -86,6 +83,8 @@ def install(version: str, quiet: bool):
|
||||
info = lambda *args: print(*args, file=sys.stderr)
|
||||
file = file_template.format(version=version)
|
||||
url = url_template.format(version=version)
|
||||
if install_dir.exists():
|
||||
shutil.rmtree(install_dir)
|
||||
install_dir.mkdir()
|
||||
zips_dir.mkdir(exist_ok=True)
|
||||
zip = zips_dir / file
|
||||
@@ -157,11 +156,8 @@ def main(opts, forwarded_opts):
|
||||
selected_version = current_version or DEFAULT_VERSION
|
||||
if selected_version != current_version:
|
||||
# don't print information about install procedure unless explicitly using --select
|
||||
if install_dir.exists():
|
||||
shutil.rmtree(install_dir)
|
||||
install(selected_version, quiet=opts.select is None)
|
||||
version_file.write_text(selected_version)
|
||||
# don't print information about install procedure unless explicitly using --select
|
||||
install(selected_version, quiet=opts.select is None)
|
||||
if opts.select and not forwarded_opts and not opts.version:
|
||||
print(f"selected {selected_version}")
|
||||
return
|
||||
|
||||
@@ -6,8 +6,6 @@ import com.github.codeql.utils.*
|
||||
import com.github.codeql.utils.versions.*
|
||||
import com.semmle.extractor.java.OdasaOutput
|
||||
import java.io.Closeable
|
||||
import java.nio.file.Files
|
||||
import java.nio.file.Path
|
||||
import java.util.*
|
||||
import kotlin.collections.ArrayList
|
||||
import org.jetbrains.kotlin.backend.common.extensions.IrPluginContext
|
||||
@@ -52,7 +50,6 @@ import org.jetbrains.kotlin.load.java.structure.JavaMethod
|
||||
import org.jetbrains.kotlin.load.java.structure.JavaTypeParameter
|
||||
import org.jetbrains.kotlin.load.java.structure.JavaTypeParameterListOwner
|
||||
import org.jetbrains.kotlin.load.java.structure.impl.classFiles.BinaryJavaClass
|
||||
import org.jetbrains.kotlin.fir.java.VirtualFileBasedSourceElement
|
||||
import org.jetbrains.kotlin.name.FqName
|
||||
import org.jetbrains.kotlin.types.Variance
|
||||
import org.jetbrains.kotlin.util.OperatorNameConventions
|
||||
@@ -164,100 +161,23 @@ open class KotlinFileExtractor(
|
||||
}
|
||||
}
|
||||
|
||||
private fun javaBinaryDeclaresMethod(c: IrClass, name: String): Boolean? {
|
||||
// K1 path: source is JavaSourceElement wrapping a BinaryJavaClass - inspect class metadata
|
||||
val binaryJavaClass = (c.source as? JavaSourceElement)?.javaElement as? BinaryJavaClass
|
||||
if (binaryJavaClass != null) {
|
||||
return binaryJavaClass.methods.any { it.name.asString() == name }
|
||||
private fun javaBinaryDeclaresMethod(c: IrClass, name: String) =
|
||||
((c.source as? JavaSourceElement)?.javaElement as? BinaryJavaClass)?.methods?.any {
|
||||
it.name.asString() == name
|
||||
}
|
||||
|
||||
// K2 path: binary Java classes use VirtualFileBasedSourceElement instead of
|
||||
// JavaSourceElement. The BinaryJavaClass is not stored in the source element, so we parse
|
||||
// the class bytes directly using ASM to check if the method is explicitly declared.
|
||||
if (c.source is VirtualFileBasedSourceElement) {
|
||||
val virtualFile = (c.source as VirtualFileBasedSourceElement).virtualFile
|
||||
if (!virtualFile.name.endsWith(".class")) return null
|
||||
return try {
|
||||
val bytes = virtualFile.contentsToByteArray()
|
||||
var found = false
|
||||
var hasKotlinMetadata = false
|
||||
val reader = org.jetbrains.org.objectweb.asm.ClassReader(bytes)
|
||||
reader.accept(
|
||||
object : org.jetbrains.org.objectweb.asm.ClassVisitor(
|
||||
org.jetbrains.org.objectweb.asm.Opcodes.ASM9
|
||||
) {
|
||||
override fun visitAnnotation(
|
||||
descriptor: String,
|
||||
visible: Boolean
|
||||
): org.jetbrains.org.objectweb.asm.AnnotationVisitor? {
|
||||
if (descriptor == "Lkotlin/Metadata;") hasKotlinMetadata = true
|
||||
return null
|
||||
}
|
||||
|
||||
override fun visitMethod(
|
||||
access: Int,
|
||||
methodName: String,
|
||||
descriptor: String,
|
||||
signature: String?,
|
||||
exceptions: Array<String>?
|
||||
): org.jetbrains.org.objectweb.asm.MethodVisitor? {
|
||||
if (methodName == name) found = true
|
||||
return null
|
||||
}
|
||||
},
|
||||
org.jetbrains.org.objectweb.asm.ClassReader.SKIP_CODE or
|
||||
org.jetbrains.org.objectweb.asm.ClassReader.SKIP_DEBUG or
|
||||
org.jetbrains.org.objectweb.asm.ClassReader.SKIP_FRAMES
|
||||
)
|
||||
if (hasKotlinMetadata) false else found
|
||||
} catch (e: Exception) {
|
||||
logger.warn("Failed to check binary class methods for ${c.fqNameWhenAvailable}: $e")
|
||||
null
|
||||
}
|
||||
}
|
||||
return null
|
||||
}
|
||||
|
||||
private fun isJavaBinaryDeclaration(f: IrFunction) =
|
||||
f.parentClassOrNull?.let { javaBinaryDeclaresMethod(it, f.name.asString()) } ?: false
|
||||
|
||||
private fun hasConcreteSiblingObjectMethod(f: IrFunction): Boolean {
|
||||
val parentClass = f.parentClassOrNull ?: return false
|
||||
return parentClass.declarations
|
||||
.asSequence()
|
||||
.filterIsInstance<IrFunction>()
|
||||
.filter { sibling ->
|
||||
sibling !== f &&
|
||||
sibling.name == f.name &&
|
||||
sibling.codeQlValueParameters.size == f.codeQlValueParameters.size
|
||||
}
|
||||
.any { sibling ->
|
||||
val hasInvisibleFakeVisibility =
|
||||
sibling.visibility.let {
|
||||
it is DelegatedDescriptorVisibility && it.delegate == Visibilities.InvisibleFake
|
||||
}
|
||||
!sibling.isFakeOverride && !hasInvisibleFakeVisibility
|
||||
}
|
||||
}
|
||||
|
||||
private fun isJavaBinaryObjectMethodRedeclaration(d: IrDeclaration) =
|
||||
when (d) {
|
||||
is IrFunction ->
|
||||
d.parentClassOrNull?.typeParameters?.isEmpty() == true &&
|
||||
when (d.name.asString()) {
|
||||
"toString" -> d.codeQlValueParameters.isEmpty()
|
||||
"hashCode" -> d.codeQlValueParameters.isEmpty()
|
||||
// Under K2 (language version 2.0+), the Object.equals(Object) parameter is
|
||||
// typed as Any (non-nullable) rather than Any? (nullable). Accept both.
|
||||
"equals" ->
|
||||
d.codeQlValueParameters
|
||||
.singleOrNull()
|
||||
?.type
|
||||
?.let { it.isNullableAny() || it.isAny() } ?: false
|
||||
"equals" -> d.codeQlValueParameters.singleOrNull()?.type?.isNullableAny() ?: false
|
||||
else -> false
|
||||
} &&
|
||||
!hasConcreteSiblingObjectMethod(d) &&
|
||||
isJavaBinaryDeclaration(d)
|
||||
} && isJavaBinaryDeclaration(d)
|
||||
else -> false
|
||||
}
|
||||
|
||||
@@ -1392,28 +1312,27 @@ open class KotlinFileExtractor(
|
||||
): TypeResults {
|
||||
with("value parameter", vp) {
|
||||
val location = locOverride ?: getLocation(vp, classTypeArgsIncludingOuterClasses)
|
||||
val parentFunction = vp.parent as? IrFunction
|
||||
val javaCallable = parentFunction?.let { getJavaCallable(it) }
|
||||
val maybeAlteredType =
|
||||
parentFunction?.let {
|
||||
(vp.parent as? IrFunction)?.let {
|
||||
if (overridesCollectionsMethodWithAlteredParameterTypes(it))
|
||||
eraseCollectionsMethodParameterType(vp.type, it.name.asString(), idx)
|
||||
else if (
|
||||
(parentFunction as? IrConstructor)?.parentClassOrNull?.kind ==
|
||||
(vp.parent as? IrConstructor)?.parentClassOrNull?.kind ==
|
||||
ClassKind.ANNOTATION_CLASS
|
||||
)
|
||||
kClassToJavaClass(vp.type)
|
||||
else null
|
||||
} ?: vp.type
|
||||
val javaType = javaCallable?.let { jCallable -> getJavaValueParameterType(jCallable, idx) }
|
||||
val addParameterWildcardsByDefault =
|
||||
!getInnermostWildcardSupppressionAnnotation(vp) &&
|
||||
!(javaCallable == null &&
|
||||
parentFunction?.origin == IrDeclarationOrigin.IR_EXTERNAL_JAVA_DECLARATION_STUB)
|
||||
val javaType =
|
||||
(vp.parent as? IrFunction)?.let {
|
||||
getJavaCallable(it)?.let { jCallable ->
|
||||
getJavaValueParameterType(jCallable, idx)
|
||||
}
|
||||
}
|
||||
val typeWithWildcards =
|
||||
addJavaLoweringWildcards(
|
||||
maybeAlteredType,
|
||||
addParameterWildcardsByDefault,
|
||||
!getInnermostWildcardSupppressionAnnotation(vp),
|
||||
javaType
|
||||
)
|
||||
val substitutedType =
|
||||
@@ -1427,9 +1346,9 @@ open class KotlinFileExtractor(
|
||||
vp.origin == IrDeclarationOrigin.UNDERSCORE_PARAMETER ||
|
||||
((vp.parent as? IrFunction)?.let { hasSynthesizedParameterNames(it) } ?: true)
|
||||
val javaParameter =
|
||||
when (javaCallable) {
|
||||
is JavaConstructor -> javaCallable.valueParameters.getOrNull(idx)
|
||||
is JavaMethod -> javaCallable.valueParameters.getOrNull(idx)
|
||||
when (val callable = (vp.parent as? IrFunction)?.let { getJavaCallable(it) }) {
|
||||
is JavaConstructor -> callable.valueParameters.getOrNull(idx)
|
||||
is JavaMethod -> callable.valueParameters.getOrNull(idx)
|
||||
else -> null
|
||||
}
|
||||
val extraAnnotations =
|
||||
@@ -2955,45 +2874,6 @@ open class KotlinFileExtractor(
|
||||
return v
|
||||
}
|
||||
|
||||
private val sourceTextCache = mutableMapOf<String, String?>()
|
||||
|
||||
private fun getCurrentFileSourceText() =
|
||||
sourceTextCache.getOrPut(filePath) {
|
||||
runCatching { Files.readString(Path.of(filePath)) }.getOrNull()
|
||||
}
|
||||
|
||||
private fun getVariableNameLocation(v: IrVariable): Label<DbLocation>? {
|
||||
if (v.startOffset < 0 || v.endOffset < v.startOffset) return null
|
||||
|
||||
val source = getCurrentFileSourceText() ?: return null
|
||||
if (v.startOffset >= source.length) return null
|
||||
|
||||
val name = v.name.asString()
|
||||
if (name.isEmpty()) return null
|
||||
|
||||
val endExclusive = minOf(v.endOffset + 1, source.length)
|
||||
val declarationText = source.substring(v.startOffset, endExclusive)
|
||||
val nameOffsetInDeclaration = declarationText.indexOf(name)
|
||||
if (nameOffsetInDeclaration < 0) return null
|
||||
|
||||
val nameStartOffset = v.startOffset + nameOffsetInDeclaration
|
||||
val nameEndOffset = nameStartOffset + name.length - 1
|
||||
return tw.getLocation(nameStartOffset, nameEndOffset)
|
||||
}
|
||||
|
||||
private fun shouldUseVariableNameLocation(v: IrVariable): Boolean {
|
||||
val initializer = v.initializer
|
||||
return initializer is IrTypeOperatorCall && initializer.operator == IrTypeOperator.IMPLICIT_NOTNULL
|
||||
}
|
||||
|
||||
private fun getVariableLocation(v: IrVariable): Label<DbLocation> {
|
||||
if (shouldUseVariableNameLocation(v)) {
|
||||
val nameLocation = getVariableNameLocation(v)
|
||||
if (nameLocation != null) return nameLocation
|
||||
}
|
||||
return tw.getLocation(getVariableLocationProvider(v))
|
||||
}
|
||||
|
||||
private fun extractVariable(
|
||||
v: IrVariable,
|
||||
callable: Label<out DbCallable>,
|
||||
@@ -3002,7 +2882,7 @@ open class KotlinFileExtractor(
|
||||
) {
|
||||
with("variable", v) {
|
||||
val stmtId = tw.getFreshIdLabel<DbLocalvariabledeclstmt>()
|
||||
val locId = getVariableLocation(v)
|
||||
val locId = tw.getLocation(getVariableLocationProvider(v))
|
||||
tw.writeStmts_localvariabledeclstmt(stmtId, parent, idx, callable)
|
||||
tw.writeHasLocation(stmtId, locId)
|
||||
extractVariableExpr(v, callable, stmtId, 1, stmtId)
|
||||
@@ -3020,7 +2900,7 @@ open class KotlinFileExtractor(
|
||||
with("variable expr", v) {
|
||||
val varId = useVariable(v)
|
||||
val exprId = tw.getFreshIdLabel<DbLocalvariabledeclexpr>()
|
||||
val locId = getVariableLocation(v)
|
||||
val locId = tw.getLocation(getVariableLocationProvider(v))
|
||||
val type = useType(v.type)
|
||||
tw.writeLocalvars(varId, v.name.asString(), type.javaResult.id, exprId)
|
||||
tw.writeLocalvarsKotlinType(varId, type.kotlinResult.id)
|
||||
@@ -4186,28 +4066,6 @@ open class KotlinFileExtractor(
|
||||
else -> false
|
||||
}
|
||||
|
||||
private fun getCallResultType(c: IrCall, syntacticCallTarget: IrFunction): IrType {
|
||||
if (syntacticCallTarget.origin != IrDeclarationOrigin.IR_EXTERNAL_JAVA_DECLARATION_STUB) {
|
||||
return c.type
|
||||
}
|
||||
|
||||
val primitiveInfo =
|
||||
(c.type as? IrSimpleType)?.let { primitiveTypeMapping.getPrimitiveInfo(it) } ?: return c.type
|
||||
val parentClass = syntacticCallTarget.parentClassOrNull ?: return c.type
|
||||
val returnIsClassifier =
|
||||
javaBinaryMethodReturnIsClassifierType(
|
||||
parentClass,
|
||||
getFunctionShortName(syntacticCallTarget).nameInDB,
|
||||
syntacticCallTarget.codeQlValueParameters.size,
|
||||
syntacticCallTarget is IrConstructor
|
||||
)
|
||||
return if (returnIsClassifier == true) {
|
||||
primitiveInfo.javaClass.symbol.typeWith()
|
||||
} else {
|
||||
c.type
|
||||
}
|
||||
}
|
||||
|
||||
private fun isGenericArrayType(typeName: String) =
|
||||
when (typeName) {
|
||||
"Array" -> true
|
||||
@@ -4253,7 +4111,7 @@ open class KotlinFileExtractor(
|
||||
extractRawMethodAccess(
|
||||
syntacticCallTarget,
|
||||
c,
|
||||
getCallResultType(c, syntacticCallTarget),
|
||||
c.type,
|
||||
callable,
|
||||
parent,
|
||||
idx,
|
||||
|
||||
@@ -36,7 +36,6 @@ import org.jetbrains.kotlin.load.java.BuiltinMethodsWithSpecialGenericSignature
|
||||
import org.jetbrains.kotlin.load.java.JvmAbi
|
||||
import org.jetbrains.kotlin.load.java.sources.JavaSourceElement
|
||||
import org.jetbrains.kotlin.load.java.structure.*
|
||||
import org.jetbrains.kotlin.load.java.structure.impl.classFiles.BinaryJavaClass
|
||||
import org.jetbrains.kotlin.load.java.typeEnhancement.hasEnhancedNullability
|
||||
import org.jetbrains.kotlin.name.FqName
|
||||
import org.jetbrains.kotlin.name.NameUtils
|
||||
@@ -997,20 +996,7 @@ open class KotlinUsesExtractor(
|
||||
)
|
||||
return null
|
||||
}
|
||||
val fileClassId = extractFileClass(fqName)
|
||||
// Under K2, external file class members sit directly under IrExternalPackageFragment
|
||||
// rather than under their IrClass parent. In that case the file class entity won't
|
||||
// get a location set through the normal extractClassSource path.
|
||||
if (d is IrMemberWithContainerSource && tw.lm.externalFileClassLocationsExtracted.add(fqName)) {
|
||||
val binaryPath =
|
||||
getContainerSourceBinaryPath(d.containerSource)
|
||||
?.let { normalizeExternalFileClassBinaryPath(it, fqName) }
|
||||
if (binaryPath != null && shouldUseConcreteExternalFileClassLocation(binaryPath)) {
|
||||
val fileId = tw.mkFileId(binaryPath, true)
|
||||
tw.writeHasLocation(fileClassId, tw.getWholeFileLocation(fileId))
|
||||
}
|
||||
}
|
||||
return fileClassId
|
||||
return extractFileClass(fqName)
|
||||
}
|
||||
return useDeclarationParent(parent, canBeTopLevel, classTypeArguments, inReceiverContext)
|
||||
}
|
||||
@@ -1385,13 +1371,8 @@ open class KotlinUsesExtractor(
|
||||
parentId: Label<out DbElement>,
|
||||
classTypeArgsIncludingOuterClasses: List<IrTypeArgument>?,
|
||||
maybeParameterList: List<IrValueParameter>? = null
|
||||
): String {
|
||||
val javaCallable = getJavaCallable(f)
|
||||
val addParameterWildcardsByDefault =
|
||||
!getInnermostWildcardSupppressionAnnotation(f) &&
|
||||
!(javaCallable == null && f.origin == IrDeclarationOrigin.IR_EXTERNAL_JAVA_DECLARATION_STUB)
|
||||
|
||||
return getFunctionLabel(
|
||||
): String =
|
||||
getFunctionLabel(
|
||||
f.parent,
|
||||
parentId,
|
||||
getFunctionShortName(f).nameInDB,
|
||||
@@ -1401,10 +1382,9 @@ open class KotlinUsesExtractor(
|
||||
getFunctionTypeParameters(f),
|
||||
classTypeArgsIncludingOuterClasses,
|
||||
overridesCollectionsMethodWithAlteredParameterTypes(f),
|
||||
javaCallable,
|
||||
addParameterWildcardsByDefault
|
||||
getJavaCallable(f),
|
||||
!getInnermostWildcardSupppressionAnnotation(f)
|
||||
)
|
||||
}
|
||||
|
||||
/*
|
||||
* This function actually generates the label for a function.
|
||||
@@ -1491,41 +1471,15 @@ open class KotlinUsesExtractor(
|
||||
// Finally, mimic the Java extractor's behaviour by naming functions with type
|
||||
// parameters for their erased types;
|
||||
// those without type parameters are named for the generic type.
|
||||
var maybeErased =
|
||||
val maybeErased =
|
||||
if (functionTypeParameters.isEmpty()) maybeSubbed else erase(maybeSubbed)
|
||||
// K2 compatibility: under K2, Java @NotNull reference types such as @NotNull Integer
|
||||
// are enhanced to Kotlin primitives (e.g. kotlin.Int). But the Java extractor uses
|
||||
// the original reference type (java.lang.Integer) in callable labels. When we detect
|
||||
// that the original Java parameter type is a reference (classifier) type but the
|
||||
// Kotlin IR type is a primitive, revert to the boxed Java class so both extractors
|
||||
// produce matching callable IDs.
|
||||
if (functionTypeParameters.isEmpty()) {
|
||||
val primitiveInfo = (maybeErased as? IrSimpleType)?.let {
|
||||
primitiveTypeMapping.getPrimitiveInfo(it)
|
||||
}
|
||||
if (primitiveInfo != null) {
|
||||
val parentClass = parent as? IrClass
|
||||
if (parentClass != null) {
|
||||
val isClassifierType = javaBinaryMethodParamIsClassifierType(
|
||||
parentClass,
|
||||
name,
|
||||
allParamTypes.size,
|
||||
name == "<init>",
|
||||
it.index
|
||||
)
|
||||
if (isClassifierType == true) {
|
||||
maybeErased = primitiveInfo.javaClass.symbol.typeWith()
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
"{${useType(maybeErased).javaResult.id}}"
|
||||
}
|
||||
val paramTypeIds =
|
||||
allParamTypes
|
||||
.withIndex()
|
||||
.joinToString(separator = ",", transform = getIdForFunctionLabel)
|
||||
var labelReturnType =
|
||||
val labelReturnType =
|
||||
if (name == "<init>") pluginContext.irBuiltIns.unitType
|
||||
else
|
||||
erase(
|
||||
@@ -1535,28 +1489,6 @@ open class KotlinUsesExtractor(
|
||||
pluginContext
|
||||
)
|
||||
)
|
||||
// K2 compatibility: same as for parameters, if the Java binary method return type is a
|
||||
// reference type but K2 enhanced it to a Kotlin primitive, use the boxed Java class.
|
||||
if (functionTypeParameters.isEmpty() && name != "<init>") {
|
||||
val primitiveInfo = (labelReturnType as? IrSimpleType)?.let {
|
||||
primitiveTypeMapping.getPrimitiveInfo(it)
|
||||
}
|
||||
if (primitiveInfo != null) {
|
||||
val parentClass = parent as? IrClass
|
||||
if (parentClass != null) {
|
||||
val returnIsClassifier =
|
||||
javaBinaryMethodReturnIsClassifierType(
|
||||
parentClass,
|
||||
name,
|
||||
allParamTypes.size,
|
||||
false
|
||||
)
|
||||
if (returnIsClassifier == true) {
|
||||
labelReturnType = primitiveInfo.javaClass.symbol.typeWith()
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
// Note that `addJavaLoweringWildcards` is not required here because the return type used to
|
||||
// form the function
|
||||
// label is always erased.
|
||||
@@ -1662,23 +1594,9 @@ open class KotlinUsesExtractor(
|
||||
}
|
||||
|
||||
@OptIn(ObsoleteDescriptorBasedAPI::class)
|
||||
fun getJavaCallable(f: IrFunction): JavaMember? {
|
||||
val fromDescriptor = (f.descriptor.source as? JavaSourceElement)?.javaElement as? JavaMember
|
||||
if (fromDescriptor != null) return fromDescriptor
|
||||
fun getJavaCallable(f: IrFunction) =
|
||||
(f.descriptor.source as? JavaSourceElement)?.javaElement as? JavaMember
|
||||
|
||||
// K2 fallback: under K2, descriptor.source may not carry JavaSourceElement for binary Java
|
||||
// methods. Try to get the JavaMember from the parent class's binary class directly.
|
||||
val parentClass = f.parentClassOrNull ?: return null
|
||||
val binaryJavaClass = (parentClass.source as? JavaSourceElement)?.javaElement as? BinaryJavaClass
|
||||
?: return null
|
||||
val name = getFunctionShortName(f).nameInDB
|
||||
val nParams = f.codeQlValueParameters.size
|
||||
return if (f is IrConstructor) {
|
||||
binaryJavaClass.constructors.find { it.valueParameters.size == nParams }
|
||||
} else {
|
||||
binaryJavaClass.methods.find { it.name.asString() == name && it.valueParameters.size == nParams }
|
||||
}
|
||||
}
|
||||
fun getJavaValueParameterType(m: JavaMember, idx: Int) =
|
||||
when (m) {
|
||||
is JavaMethod -> m.valueParameters[idx].type
|
||||
|
||||
@@ -51,13 +51,6 @@ class TrapLabelManager {
|
||||
* to avoid duplication.
|
||||
*/
|
||||
val fileClassLocationsExtracted = HashSet<IrFile>()
|
||||
|
||||
/**
|
||||
* Tracks external file classes (by FqName) whose location has been set from a binary path.
|
||||
* Used to avoid writing duplicate hasLocation facts for external file class entities extracted
|
||||
* through the K2 code path where declarations sit directly under IrExternalPackageFragment.
|
||||
*/
|
||||
val externalFileClassLocationsExtracted = HashSet<org.jetbrains.kotlin.name.FqName>()
|
||||
}
|
||||
|
||||
/**
|
||||
|
||||
@@ -17,7 +17,6 @@ import org.jetbrains.kotlin.load.kotlin.JvmPackagePartSource
|
||||
import org.jetbrains.kotlin.load.kotlin.KotlinJvmBinarySourceElement
|
||||
import org.jetbrains.kotlin.load.kotlin.VirtualFileKotlinClass
|
||||
import org.jetbrains.kotlin.name.FqName
|
||||
import org.jetbrains.kotlin.serialization.deserialization.descriptors.DeserializedContainerSource
|
||||
|
||||
// Adapted from Kotlin's interpreter/Utils.kt function 'internalName'
|
||||
// Translates class names into their JLS section 13.1 binary name,
|
||||
@@ -177,238 +176,15 @@ fun getIrDeclarationBinaryPath(d: IrDeclaration): String? {
|
||||
// This is in a file class.
|
||||
val fqName = getFileClassFqName(d)
|
||||
if (fqName != null) {
|
||||
if (d is IrMemberWithContainerSource) {
|
||||
val containerBinaryPath = getContainerSourceBinaryPath(d.containerSource)
|
||||
if (containerBinaryPath != null) {
|
||||
return normalizeExternalFileClassBinaryPath(containerBinaryPath, fqName)
|
||||
}
|
||||
}
|
||||
return getUnknownBinaryLocation(fqName.asString())
|
||||
}
|
||||
}
|
||||
return null
|
||||
}
|
||||
|
||||
/**
|
||||
* Attempts to get the binary file path from a container source (typically a
|
||||
* [JvmPackagePartSource]). Returns null if the path is unavailable.
|
||||
*/
|
||||
fun getContainerSourceBinaryPath(containerSource: org.jetbrains.kotlin.serialization.deserialization.descriptors.DeserializedContainerSource?): String? {
|
||||
if (containerSource !is JvmPackagePartSource) return null
|
||||
val binaryClass = containerSource.knownJvmBinaryClass ?: return null
|
||||
return when (binaryClass) {
|
||||
is VirtualFileKotlinClass -> {
|
||||
val vf = binaryClass.file
|
||||
val path = vf.path
|
||||
if (vf.fileSystem.protocol == StandardFileSystems.JRT_PROTOCOL)
|
||||
"/${path.split("!/", limit = 2)[1]}"
|
||||
else path
|
||||
}
|
||||
else -> binaryClass.location.takeIf { it.isNotEmpty() }
|
||||
}
|
||||
}
|
||||
|
||||
private fun getUnknownBinaryLocation(s: String): String {
|
||||
return "/!unknown-binary-location/${s.replace(".", "/")}.class"
|
||||
}
|
||||
|
||||
fun normalizeExternalFileClassBinaryPath(path: String, fqName: FqName): String {
|
||||
if (path.contains(".kotlinc_installed")) {
|
||||
return getUnknownBinaryLocation(fqName.asString())
|
||||
}
|
||||
val normalizedPath = path.replace('\\', '/')
|
||||
val classInternalPath = "${fqName.asString().replace(".", "/")}.class"
|
||||
val classSuffix = "/$classInternalPath"
|
||||
if (normalizedPath.endsWith(classSuffix)) {
|
||||
val classpathRoot = normalizedPath.removeSuffix(classSuffix).substringAfterLast('/')
|
||||
if (classpathRoot.isNotEmpty()) {
|
||||
return "$classpathRoot/$classInternalPath"
|
||||
}
|
||||
}
|
||||
return path
|
||||
}
|
||||
|
||||
fun shouldUseConcreteExternalFileClassLocation(path: String): Boolean {
|
||||
val normalizedPath = path.replace('\\', '/')
|
||||
return normalizedPath.contains("/") &&
|
||||
!normalizedPath.startsWith("/!unknown-binary-location/")
|
||||
}
|
||||
|
||||
fun getJavaEquivalentClassId(c: IrClass) =
|
||||
c.fqNameWhenAvailable?.toUnsafe()?.let { JavaToKotlinClassMap.mapKotlinToJava(it) }
|
||||
|
||||
/**
|
||||
* Checks whether a specific parameter of a Java binary method (identified by [methodName] and
|
||||
* [paramIndex]) is a reference type (as opposed to a Java primitive). This is used to detect
|
||||
* cases where K2 FIR has enhanced a reference type parameter (e.g. `@NotNull Integer`) to a
|
||||
* Kotlin primitive (e.g. `kotlin.Int`), so that callable labels can use the original reference
|
||||
* type and remain compatible with the Java extractor's callable IDs.
|
||||
*
|
||||
* Under K1, binary Java classes use [JavaSourceElement] and we can check [BinaryJavaClass.methods]
|
||||
* directly. Under K2, they use [VirtualFileBasedSourceElement] and we fall back to reading the
|
||||
* class bytes with ASM.
|
||||
*
|
||||
* Returns `null` if the information cannot be determined.
|
||||
*/
|
||||
fun javaBinaryMethodParamIsClassifierType(
|
||||
parentClass: IrClass,
|
||||
methodName: String,
|
||||
nParams: Int,
|
||||
isConstructor: Boolean,
|
||||
paramIndex: Int
|
||||
): Boolean? {
|
||||
// K1 path: binary Java class has JavaSourceElement with a BinaryJavaClass.
|
||||
val k1ParamKinds =
|
||||
((parentClass.source as? JavaSourceElement)?.javaElement as? BinaryJavaClass)?.let {
|
||||
binaryJavaClass ->
|
||||
if (isConstructor)
|
||||
binaryJavaClass.constructors
|
||||
.asSequence()
|
||||
.filter { it.valueParameters.size == nParams }
|
||||
.mapNotNull { it.valueParameters.getOrNull(paramIndex)?.type }
|
||||
.map { it is org.jetbrains.kotlin.load.java.structure.JavaClassifierType }
|
||||
.toSet()
|
||||
else
|
||||
binaryJavaClass.methods
|
||||
.asSequence()
|
||||
.filter { it.name.asString() == methodName && it.valueParameters.size == nParams }
|
||||
.mapNotNull { it.valueParameters.getOrNull(paramIndex)?.type }
|
||||
.map { it is org.jetbrains.kotlin.load.java.structure.JavaClassifierType }
|
||||
.toSet()
|
||||
}
|
||||
if (k1ParamKinds != null && k1ParamKinds.isNotEmpty()) {
|
||||
return k1ParamKinds.singleOrNull()
|
||||
}
|
||||
|
||||
// K2 path: binary Java class has VirtualFileBasedSourceElement
|
||||
if (parentClass.source !is VirtualFileBasedSourceElement) return null
|
||||
val vf = (parentClass.source as VirtualFileBasedSourceElement).virtualFile
|
||||
if (!vf.name.endsWith(".class")) return null
|
||||
|
||||
return try {
|
||||
val bytes = vf.contentsToByteArray()
|
||||
val expectedMethodName = if (isConstructor) "<init>" else methodName
|
||||
val descriptorKinds = mutableSetOf<Boolean>()
|
||||
val reader = org.jetbrains.org.objectweb.asm.ClassReader(bytes)
|
||||
reader.accept(
|
||||
object : org.jetbrains.org.objectweb.asm.ClassVisitor(
|
||||
org.jetbrains.org.objectweb.asm.Opcodes.ASM9
|
||||
) {
|
||||
override fun visitMethod(
|
||||
access: Int,
|
||||
name: String,
|
||||
descriptor: String,
|
||||
signature: String?,
|
||||
exceptions: Array<String>?
|
||||
): org.jetbrains.org.objectweb.asm.MethodVisitor? {
|
||||
if (name != expectedMethodName) return null
|
||||
val paramDescriptors = parseAsmMethodDescriptorParams(descriptor)
|
||||
if (paramDescriptors.size != nParams) return null
|
||||
val paramDesc = paramDescriptors.getOrNull(paramIndex) ?: return null
|
||||
// Reference types start with 'L' or '['; Java primitives are single chars
|
||||
descriptorKinds.add(paramDesc.startsWith("L") || paramDesc.startsWith("["))
|
||||
return null
|
||||
}
|
||||
},
|
||||
org.jetbrains.org.objectweb.asm.ClassReader.SKIP_CODE or
|
||||
org.jetbrains.org.objectweb.asm.ClassReader.SKIP_DEBUG or
|
||||
org.jetbrains.org.objectweb.asm.ClassReader.SKIP_FRAMES
|
||||
)
|
||||
descriptorKinds.singleOrNull()
|
||||
} catch (e: Exception) {
|
||||
null
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Checks whether the return type of a Java binary method (identified by [methodName] and
|
||||
* [nParams]) is a reference type (as opposed to a Java primitive).
|
||||
*
|
||||
* Returns `null` if the information cannot be determined.
|
||||
*/
|
||||
fun javaBinaryMethodReturnIsClassifierType(
|
||||
parentClass: IrClass,
|
||||
methodName: String,
|
||||
nParams: Int,
|
||||
isConstructor: Boolean
|
||||
): Boolean? {
|
||||
if (isConstructor) return false
|
||||
|
||||
// K1 path: binary Java class has JavaSourceElement with a BinaryJavaClass.
|
||||
val k1ReturnKinds =
|
||||
((parentClass.source as? JavaSourceElement)?.javaElement as? BinaryJavaClass)?.methods
|
||||
?.asSequence()
|
||||
?.filter { it.name.asString() == methodName && it.valueParameters.size == nParams }
|
||||
?.map { it.returnType is org.jetbrains.kotlin.load.java.structure.JavaClassifierType }
|
||||
?.toSet()
|
||||
if (k1ReturnKinds != null && k1ReturnKinds.isNotEmpty()) {
|
||||
return k1ReturnKinds.singleOrNull()
|
||||
}
|
||||
|
||||
// K2 path: binary Java class has VirtualFileBasedSourceElement
|
||||
if (parentClass.source !is VirtualFileBasedSourceElement) return null
|
||||
val vf = (parentClass.source as VirtualFileBasedSourceElement).virtualFile
|
||||
if (!vf.name.endsWith(".class")) return null
|
||||
|
||||
return try {
|
||||
val bytes = vf.contentsToByteArray()
|
||||
val returnKinds = mutableSetOf<Boolean>()
|
||||
val reader = org.jetbrains.org.objectweb.asm.ClassReader(bytes)
|
||||
reader.accept(
|
||||
object : org.jetbrains.org.objectweb.asm.ClassVisitor(
|
||||
org.jetbrains.org.objectweb.asm.Opcodes.ASM9
|
||||
) {
|
||||
override fun visitMethod(
|
||||
access: Int,
|
||||
name: String,
|
||||
descriptor: String,
|
||||
signature: String?,
|
||||
exceptions: Array<String>?
|
||||
): org.jetbrains.org.objectweb.asm.MethodVisitor? {
|
||||
if (name != methodName) return null
|
||||
if (parseAsmMethodDescriptorParams(descriptor).size != nParams) return null
|
||||
val returnDescriptor = descriptor.substring(descriptor.lastIndexOf(')') + 1)
|
||||
returnKinds.add(
|
||||
returnDescriptor.startsWith("L") || returnDescriptor.startsWith("[")
|
||||
)
|
||||
return null
|
||||
}
|
||||
},
|
||||
org.jetbrains.org.objectweb.asm.ClassReader.SKIP_CODE or
|
||||
org.jetbrains.org.objectweb.asm.ClassReader.SKIP_DEBUG or
|
||||
org.jetbrains.org.objectweb.asm.ClassReader.SKIP_FRAMES
|
||||
)
|
||||
returnKinds.singleOrNull()
|
||||
} catch (e: Exception) {
|
||||
null
|
||||
}
|
||||
}
|
||||
|
||||
fun parseAsmMethodDescriptorParams(descriptor: String): List<String> {
|
||||
val params = mutableListOf<String>()
|
||||
var i = descriptor.indexOf('(') + 1
|
||||
val end = descriptor.lastIndexOf(')')
|
||||
while (i < end) {
|
||||
when (val c = descriptor[i]) {
|
||||
'L' -> {
|
||||
val semi = descriptor.indexOf(';', i)
|
||||
params.add(descriptor.substring(i, semi + 1))
|
||||
i = semi + 1
|
||||
}
|
||||
'[' -> {
|
||||
var j = i + 1
|
||||
while (j < end && descriptor[j] == '[') j++
|
||||
if (descriptor[j] == 'L') {
|
||||
val semi = descriptor.indexOf(';', j)
|
||||
params.add(descriptor.substring(i, semi + 1))
|
||||
i = semi + 1
|
||||
} else {
|
||||
params.add(descriptor.substring(i, j + 1))
|
||||
i = j + 1
|
||||
}
|
||||
}
|
||||
else -> { params.add(c.toString()); i++ }
|
||||
}
|
||||
}
|
||||
return params
|
||||
}
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
import pathlib
|
||||
|
||||
|
||||
def test(codeql, java_full):
|
||||
def test(codeql, java_full, kotlinc_2_3_20):
|
||||
java_srcs = " ".join([str(s) for s in pathlib.Path().glob("*.java")])
|
||||
codeql.database.create(
|
||||
command=[
|
||||
f"javac {java_srcs} -d build",
|
||||
"kotlinc -language-version 2.0 user.kt -cp build",
|
||||
"kotlinc -language-version 1.9 user.kt -cp build",
|
||||
]
|
||||
)
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import commands
|
||||
|
||||
|
||||
def test(codeql, java_full):
|
||||
commands.run("kotlinc -language-version 2.0 test.kt -d lib")
|
||||
codeql.database.create(command="kotlinc -language-version 2.0 user.kt -cp lib")
|
||||
def test(codeql, java_full, kotlinc_2_3_20):
|
||||
commands.run("kotlinc -language-version 1.9 test.kt -d lib")
|
||||
codeql.database.create(command="kotlinc -language-version 1.9 user.kt -cp lib")
|
||||
|
||||
@@ -9,4 +9,4 @@
|
||||
| Percentage of calls with call target | 100 |
|
||||
| Total number of lines | 3 |
|
||||
| Total number of lines with extension kt | 3 |
|
||||
| Uses Kotlin 2: true | 1 |
|
||||
| Uses Kotlin 2: false | 1 |
|
||||
|
||||
@@ -1,2 +1,2 @@
|
||||
def test(codeql, java_full):
|
||||
codeql.database.create(command="kotlinc -J-Xmx2G -language-version 2.0 SomeClass.kt")
|
||||
def test(codeql, java_full, kotlinc_2_3_20):
|
||||
codeql.database.create(command=f"kotlinc -J-Xmx2G -language-version 1.9 SomeClass.kt")
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import commands
|
||||
|
||||
|
||||
def test(codeql, java_full):
|
||||
commands.run("kotlinc -language-version 2.0 A.kt")
|
||||
codeql.database.create(command="kotlinc -cp . -language-version 2.0 B.kt C.kt")
|
||||
def test(codeql, java_full, kotlinc_2_3_20):
|
||||
commands.run("kotlinc -language-version 1.9 A.kt")
|
||||
codeql.database.create(command="kotlinc -cp . -language-version 1.9 B.kt C.kt")
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import commands
|
||||
|
||||
|
||||
def test(codeql, java_full):
|
||||
def test(codeql, java_full, kotlinc_2_3_20):
|
||||
commands.run(["javac", "Test.java", "-d", "bin"])
|
||||
codeql.database.create(command="kotlinc -language-version 2.0 user.kt -cp bin")
|
||||
codeql.database.create(command="kotlinc -language-version 1.9 user.kt -cp bin")
|
||||
|
||||
@@ -1,13 +1,13 @@
|
||||
import commands
|
||||
|
||||
|
||||
def test(codeql, java_full):
|
||||
def test(codeql, java_full, kotlinc_2_3_20):
|
||||
# Compile the JavaDefns2 copy outside tracing, to make sure the Kotlin view of it matches the Java view seen by the traced javac compilation of JavaDefns.java below.
|
||||
commands.run(["javac", "JavaDefns2.java"])
|
||||
codeql.database.create(
|
||||
command=[
|
||||
"kotlinc kotlindefns.kt",
|
||||
"javac JavaUser.java JavaDefns.java -cp .",
|
||||
"kotlinc -language-version 2.0 -cp . kotlinuser.kt",
|
||||
"kotlinc -language-version 1.9 -cp . kotlinuser.kt",
|
||||
]
|
||||
)
|
||||
|
||||
2
python/ql/consistency-queries/CfgConsistency.ql
Normal file
2
python/ql/consistency-queries/CfgConsistency.ql
Normal file
@@ -0,0 +1,2 @@
|
||||
import semmle.python.controlflow.internal.AstNodeImpl
|
||||
import ControlFlow::Consistency
|
||||
4
python/ql/lib/change-notes/2026-05-19-add-shared-cfg.md
Normal file
4
python/ql/lib/change-notes/2026-05-19-add-shared-cfg.md
Normal file
@@ -0,0 +1,4 @@
|
||||
---
|
||||
category: minorAnalysis
|
||||
---
|
||||
* A new Python control flow graph implementation has been added under `semmle.python.controlflow.internal.Cfg` (backed by `AstNodeImpl.qll`), built on the shared `codeql.controlflow.ControlFlowGraph` library. It is not yet used by the dataflow library or any production query; the legacy CFG in `semmle/python/Flow.qll` remains the default. The new library is exposed for tests and for upcoming migrations.
|
||||
@@ -0,0 +1,4 @@
|
||||
---
|
||||
category: minorAnalysis
|
||||
---
|
||||
* The new (shared-CFG-based) Python control flow graph now visits parameter and return type annotations as CFG nodes for function definitions, matching the legacy CFG. This restores annotation-based type tracking through framework models such as FastAPI's `Depends()`, Pydantic request models, Starlette `WebSocket` handlers, and any other models that flow a class reference through `Parameter.getAnnotation()` to identify instances of the annotated class.
|
||||
42
python/ql/lib/ide-contextual-queries/printCfg.ql
Normal file
42
python/ql/lib/ide-contextual-queries/printCfg.ql
Normal file
@@ -0,0 +1,42 @@
|
||||
/**
|
||||
* @name Print CFG
|
||||
* @description Produces a representation of a file's Control Flow Graph.
|
||||
* This query is used by the VS Code extension.
|
||||
* @id py/print-cfg
|
||||
* @kind graph
|
||||
* @tags ide-contextual-queries/print-cfg
|
||||
*/
|
||||
|
||||
import semmle.python.Files as Files
|
||||
// import semmle.python.Scope
|
||||
import semmle.python.controlflow.internal.AstNodeImpl
|
||||
|
||||
external string selectedSourceFile();
|
||||
|
||||
private predicate selectedSourceFileAlias = selectedSourceFile/0;
|
||||
|
||||
external int selectedSourceLine();
|
||||
|
||||
private predicate selectedSourceLineAlias = selectedSourceLine/0;
|
||||
|
||||
external int selectedSourceColumn();
|
||||
|
||||
private predicate selectedSourceColumnAlias = selectedSourceColumn/0;
|
||||
|
||||
module ViewCfgQueryInput implements ControlFlow::ViewCfgQueryInputSig<Files::File> {
|
||||
predicate selectedSourceFile = selectedSourceFileAlias/0;
|
||||
|
||||
predicate selectedSourceLine = selectedSourceLineAlias/0;
|
||||
|
||||
predicate selectedSourceColumn = selectedSourceColumnAlias/0;
|
||||
|
||||
predicate cfgScopeSpan(
|
||||
Ast::Callable scope, Files::File file, int startLine, int startColumn, int endLine,
|
||||
int endColumn
|
||||
) {
|
||||
file = scope.getLocation().getFile() and
|
||||
scope.getLocation().hasLocationInfo(_, startLine, startColumn, endLine, endColumn)
|
||||
}
|
||||
}
|
||||
|
||||
import ControlFlow::ViewCfgQuery<Files::File, ViewCfgQueryInput>
|
||||
1771
python/ql/lib/semmle/python/controlflow/internal/AstNodeImpl.qll
Normal file
1771
python/ql/lib/semmle/python/controlflow/internal/AstNodeImpl.qll
Normal file
File diff suppressed because it is too large
Load Diff
1022
python/ql/lib/semmle/python/controlflow/internal/Cfg.qll
Normal file
1022
python/ql/lib/semmle/python/controlflow/internal/Cfg.qll
Normal file
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,4 @@
|
||||
consistencyOverview
|
||||
| deadEnd | 1 |
|
||||
deadEnd
|
||||
| without_loop.py:7:5:7:9 | Break |
|
||||
@@ -0,0 +1,32 @@
|
||||
/**
|
||||
* Phase -1 of the dataflow CFG migration: verifies that every variable
|
||||
* binding visible to the AST (`Name.defines(v)`) corresponds to a CFG node
|
||||
* in the new CFG (`semmle.python.controlflow.internal.AstNodeImpl`).
|
||||
*
|
||||
* The expected tag is `cfgdefines=<name>`. Each binding annotation in the
|
||||
* test sources looks like `# $ cfgdefines=x` for a binding currently
|
||||
* covered by the new CFG, or `# $ MISSING: cfgdefines=x` for a binding
|
||||
* that is known to be uncovered (a "red" test case that should be
|
||||
* green-flipped once the corresponding `cfg-ext-*` extension lands).
|
||||
*/
|
||||
|
||||
import python
|
||||
import semmle.python.controlflow.internal.AstNodeImpl as CfgImpl
|
||||
import utils.test.InlineExpectationsTest
|
||||
|
||||
module CfgBindingsTest implements TestSig {
|
||||
string getARelevantTag() { result = "cfgdefines" }
|
||||
|
||||
predicate hasActualResult(Location location, string element, string tag, string value) {
|
||||
exists(Name n, Variable v, CfgImpl::ControlFlowNode cfg |
|
||||
n.defines(v) and
|
||||
cfg.getAstNode().asExpr() = n and
|
||||
location = n.getLocation() and
|
||||
element = n.toString() and
|
||||
tag = "cfgdefines" and
|
||||
value = v.getId()
|
||||
)
|
||||
}
|
||||
}
|
||||
|
||||
import MakeTest<CfgBindingsTest>
|
||||
@@ -0,0 +1,13 @@
|
||||
# Annotated assignment (PEP 526). Both with and without an initializer.
|
||||
|
||||
a: int = 1 # $ cfgdefines=a
|
||||
b: str = "hi" # $ cfgdefines=b
|
||||
|
||||
# Annotation without value: the AST records `c` as defined,
|
||||
# and the new CFG now visits it via the AnnAssignStmt wrapper.
|
||||
c: int # $ cfgdefines=c
|
||||
|
||||
class K: # $ cfgdefines=K
|
||||
field: int = 0 # $ cfgdefines=field
|
||||
|
||||
|
||||
@@ -0,0 +1,14 @@
|
||||
# Compound (tuple/list) assignment targets — actually wired in the new CFG.
|
||||
|
||||
a, b = (1, 2) # $ cfgdefines=a cfgdefines=b
|
||||
[c, d] = [3, 4] # $ cfgdefines=c cfgdefines=d
|
||||
|
||||
# Nested unpacking.
|
||||
(e, (f, g)) = (1, (2, 3)) # $ cfgdefines=e cfgdefines=f cfgdefines=g
|
||||
|
||||
# Star unpacking.
|
||||
h, *i = [1, 2, 3] # $ cfgdefines=h cfgdefines=i
|
||||
|
||||
# Chained assignment with compound target.
|
||||
j = k, l = (5, 6) # $ cfgdefines=j cfgdefines=k cfgdefines=l
|
||||
|
||||
@@ -0,0 +1,21 @@
|
||||
# Comprehension and `for` loop targets — wired in the new CFG.
|
||||
# Comprehensions are nested function scopes with a synthetic `.0` parameter
|
||||
# bound to the iterable.
|
||||
|
||||
# Bare-name `for` target.
|
||||
for i in range(3): # $ cfgdefines=i
|
||||
pass
|
||||
|
||||
# Compound `for` target.
|
||||
for k, v in [(1, 2)]: # $ cfgdefines=k cfgdefines=v
|
||||
pass
|
||||
|
||||
# Comprehension targets.
|
||||
_ = [x for x in range(3)] # $ cfgdefines=_ cfgdefines=x cfgdefines=.0
|
||||
_ = {y: z for y, z in []} # $ cfgdefines=_ cfgdefines=y cfgdefines=z cfgdefines=.0
|
||||
_ = (a for a in []) # $ cfgdefines=_ cfgdefines=a cfgdefines=.0
|
||||
|
||||
# Nested comprehensions.
|
||||
_ = [b for c in [] for b in c] # $ cfgdefines=_ cfgdefines=c cfgdefines=b cfgdefines=.0
|
||||
|
||||
|
||||
@@ -0,0 +1,53 @@
|
||||
# Reachability of code following a try whose body always returns.
|
||||
#
|
||||
# The new CFG models exception edges for raise-prone expressions when
|
||||
# they appear inside a `try` (or `with`) statement, mirroring Java's
|
||||
# `mayThrow`. This means the body of a `try` has both a normal
|
||||
# completion edge and an exception edge to its handlers, so code
|
||||
# following the try-statement is reachable via the except-handler path
|
||||
# even when the try-body would otherwise always return.
|
||||
#
|
||||
# Code that is not reachable under either normal or exception flow
|
||||
# (for example, the `else` clause of a try whose body unconditionally
|
||||
# raises) remains correctly classified as dead.
|
||||
|
||||
|
||||
def f(obj): # $ cfgdefines=f cfgdefines=obj
|
||||
try:
|
||||
return len(obj)
|
||||
except TypeError:
|
||||
pass
|
||||
|
||||
# The try-body always returns, but `len(obj)` can raise (it is
|
||||
# inside the try, so we model its exception edge). The
|
||||
# `except TypeError: pass` handler falls through to here, making
|
||||
# the code below reachable.
|
||||
try:
|
||||
hint = type(obj).__length_hint__ # $ cfgdefines=hint
|
||||
except AttributeError:
|
||||
return None
|
||||
return hint
|
||||
|
||||
|
||||
def g(): # $ cfgdefines=g
|
||||
try:
|
||||
raise Exception("inner")
|
||||
except:
|
||||
raise Exception("outer")
|
||||
else:
|
||||
# Unreachable: the inner try body always raises (via an explicit
|
||||
# `raise`, which is modelled unconditionally), so the `else:`
|
||||
# clause never runs.
|
||||
hit_inner_else = True
|
||||
|
||||
|
||||
def h(cache, key): # $ cfgdefines=h cfgdefines=cache cfgdefines=key
|
||||
try:
|
||||
return cache[key]
|
||||
except KeyError:
|
||||
pass
|
||||
|
||||
# Same pattern as `f`: reachable via the except-handler fall-through.
|
||||
value = compute(key) # $ cfgdefines=value
|
||||
cache[key] = value
|
||||
return value
|
||||
@@ -0,0 +1,30 @@
|
||||
# Decorated `def`/`class` — wired in the new CFG.
|
||||
|
||||
|
||||
def deco(f): # $ cfgdefines=deco cfgdefines=f
|
||||
return f
|
||||
|
||||
|
||||
@deco
|
||||
def decorated_func(): # $ cfgdefines=decorated_func
|
||||
pass
|
||||
|
||||
|
||||
@deco
|
||||
class DecoratedClass: # $ cfgdefines=DecoratedClass
|
||||
pass
|
||||
|
||||
|
||||
# Stacked decorators.
|
||||
@deco
|
||||
@deco
|
||||
def doubly(): # $ cfgdefines=doubly
|
||||
pass
|
||||
|
||||
|
||||
# Inside a class body.
|
||||
class Outer: # $ cfgdefines=Outer
|
||||
@staticmethod
|
||||
def inner(): # $ cfgdefines=inner
|
||||
pass
|
||||
|
||||
@@ -0,0 +1,19 @@
|
||||
# Exception-handler name bindings. These are already wired in the new
|
||||
# CFG provided the try body can raise; `raise` statements are reliably
|
||||
# treated as exception sources.
|
||||
|
||||
try:
|
||||
raise ValueError("oops")
|
||||
except ValueError as e: # $ cfgdefines=e
|
||||
pass
|
||||
|
||||
try:
|
||||
raise TypeError("oops")
|
||||
except (TypeError, KeyError) as err: # $ cfgdefines=err
|
||||
pass
|
||||
|
||||
# Exception groups (Python 3.11+).
|
||||
try:
|
||||
raise ValueError("oops")
|
||||
except* ValueError as eg: # $ cfgdefines=eg
|
||||
pass
|
||||
14
python/ql/test/library-tests/ControlFlow/bindings/imports.py
Normal file
14
python/ql/test/library-tests/ControlFlow/bindings/imports.py
Normal file
@@ -0,0 +1,14 @@
|
||||
# Import aliases — all bound names below are now reachable via the new
|
||||
# CFG's `ImportStmt` wrapper.
|
||||
|
||||
import os # $ cfgdefines=os
|
||||
import os.path # $ cfgdefines=os
|
||||
import os as o # $ cfgdefines=o
|
||||
from os import path # $ cfgdefines=path
|
||||
from os import path as p # $ cfgdefines=p
|
||||
from os import sep, linesep # $ cfgdefines=sep cfgdefines=linesep
|
||||
from os import (
|
||||
getcwd, # $ cfgdefines=getcwd
|
||||
getcwdb, # $ cfgdefines=getcwdb
|
||||
)
|
||||
|
||||
@@ -0,0 +1,24 @@
|
||||
# Match-statement pattern bindings — wired in the new CFG.
|
||||
|
||||
def f(subject): # $ cfgdefines=f cfgdefines=subject
|
||||
match subject:
|
||||
case x: # $ cfgdefines=x
|
||||
pass
|
||||
case [a, b]: # $ cfgdefines=a cfgdefines=b
|
||||
pass
|
||||
case {"k": v}: # $ cfgdefines=v
|
||||
pass
|
||||
case Point(p, q): # $ cfgdefines=p cfgdefines=q
|
||||
pass
|
||||
case [_, *rest]: # $ cfgdefines=rest
|
||||
pass
|
||||
case (1 | 2) as n: # $ cfgdefines=n
|
||||
pass
|
||||
|
||||
|
||||
class Point: # $ cfgdefines=Point
|
||||
__match_args__ = ("x", "y") # $ cfgdefines=__match_args__
|
||||
x: int # $ cfgdefines=x
|
||||
y: int # $ cfgdefines=y
|
||||
|
||||
|
||||
@@ -0,0 +1,42 @@
|
||||
# Function parameters.
|
||||
|
||||
def positional(a, b): # $ cfgdefines=positional cfgdefines=a cfgdefines=b
|
||||
pass
|
||||
|
||||
|
||||
def with_default(x=1, y=2): # $ cfgdefines=with_default cfgdefines=x cfgdefines=y
|
||||
pass
|
||||
|
||||
|
||||
def with_vararg(*args): # $ cfgdefines=with_vararg cfgdefines=args
|
||||
pass
|
||||
|
||||
|
||||
def with_kwarg(**kwargs): # $ cfgdefines=with_kwarg cfgdefines=kwargs
|
||||
pass
|
||||
|
||||
|
||||
def with_kwonly(*, k1, k2=5): # $ cfgdefines=with_kwonly cfgdefines=k1 cfgdefines=k2
|
||||
pass
|
||||
|
||||
|
||||
def kitchen_sink(a, b=2, *args, k1, k2=5, **kw): # $ cfgdefines=kitchen_sink cfgdefines=a cfgdefines=b cfgdefines=args cfgdefines=k1 cfgdefines=k2 cfgdefines=kw
|
||||
pass
|
||||
|
||||
|
||||
# Methods get `self` / `cls`.
|
||||
class C: # $ cfgdefines=C
|
||||
def method(self, x): # $ cfgdefines=method cfgdefines=self cfgdefines=x
|
||||
pass
|
||||
|
||||
@classmethod
|
||||
def cmethod(cls, x): # $ cfgdefines=cmethod cfgdefines=cls cfgdefines=x
|
||||
pass
|
||||
|
||||
|
||||
# Lambda parameter.
|
||||
_ = lambda p: p + 1 # $ cfgdefines=_ cfgdefines=p
|
||||
|
||||
# PEP 570 positional-only.
|
||||
def pos_only(a, b, /, c): # $ cfgdefines=pos_only cfgdefines=a cfgdefines=b cfgdefines=c
|
||||
pass
|
||||
14
python/ql/test/library-tests/ControlFlow/bindings/simple.py
Normal file
14
python/ql/test/library-tests/ControlFlow/bindings/simple.py
Normal file
@@ -0,0 +1,14 @@
|
||||
# Simple bindings that should already work in the new CFG.
|
||||
# No MISSING annotations expected.
|
||||
|
||||
x = 1 # $ cfgdefines=x
|
||||
y = x + 1 # $ cfgdefines=y
|
||||
|
||||
def f(): # $ cfgdefines=f
|
||||
pass
|
||||
|
||||
class C: # $ cfgdefines=C
|
||||
pass
|
||||
|
||||
# Re-assignment.
|
||||
x = 2 # $ cfgdefines=x
|
||||
@@ -0,0 +1,21 @@
|
||||
# PEP 695 type parameters (Python 3.12+).
|
||||
|
||||
# PEP 695 type-param names on `def`/`class` bind in an annotation scope
|
||||
# that nests the function/class body — they have no CFG node in the
|
||||
# enclosing scope (matching the legacy CFG).
|
||||
def func[T](x: T) -> T: # $ cfgdefines=func cfgdefines=x
|
||||
return x
|
||||
|
||||
|
||||
class Box[T]: # $ cfgdefines=Box
|
||||
item: T # $ cfgdefines=item
|
||||
|
||||
|
||||
# Multi-parameter, with bound and variadics.
|
||||
def multi[T: int, *Ts, **P](x: T, *args: *Ts, **kwargs: P.kwargs) -> T: # $ cfgdefines=multi cfgdefines=x cfgdefines=args cfgdefines=kwargs
|
||||
return x
|
||||
|
||||
|
||||
# `type` statement (PEP 695).
|
||||
type Alias[T] = list[T] # $ cfgdefines=Alias cfgdefines=T
|
||||
|
||||
@@ -0,0 +1,14 @@
|
||||
# Walrus and starred-target edge cases — wired in the new CFG.
|
||||
|
||||
# Walrus in expression context.
|
||||
if (y := 5) > 0: # $ cfgdefines=y
|
||||
pass
|
||||
|
||||
# Walrus in a comprehension. The comprehension introduces a synthetic
|
||||
# `.0` parameter bound to the iterable.
|
||||
_ = [w for _ in range(3) if (w := 1)] # $ cfgdefines=_ cfgdefines=w cfgdefines=.0
|
||||
|
||||
# Starred target in a Tuple LHS.
|
||||
*head, tail = [1, 2, 3] # $ cfgdefines=head cfgdefines=tail
|
||||
|
||||
|
||||
@@ -0,0 +1,21 @@
|
||||
# `with cm() as x:` bindings — wired in the new CFG.
|
||||
|
||||
class CM: # $ cfgdefines=CM
|
||||
def __enter__(self): return self # $ cfgdefines=__enter__ cfgdefines=self
|
||||
def __exit__(self, *a): pass # $ cfgdefines=__exit__ cfgdefines=self cfgdefines=a
|
||||
|
||||
with CM() as x: # $ cfgdefines=x
|
||||
pass
|
||||
|
||||
# Multiple items.
|
||||
with CM() as a, CM() as b: # $ cfgdefines=a cfgdefines=b
|
||||
pass
|
||||
|
||||
# Parenthesised form (Python 3.10+).
|
||||
with (CM() as p, CM() as q): # $ cfgdefines=p cfgdefines=q
|
||||
pass
|
||||
|
||||
# Compound target in `with`.
|
||||
with CM() as (m, n): # $ cfgdefines=m cfgdefines=n
|
||||
pass
|
||||
|
||||
@@ -0,0 +1,14 @@
|
||||
/** New-CFG version of AllLiveReachable. */
|
||||
|
||||
import python
|
||||
import TimerUtils
|
||||
import NewCfgImpl
|
||||
|
||||
private module Utils = EvalOrderCfgUtils<NewCfg>;
|
||||
|
||||
private import Utils
|
||||
private import Utils::CfgTests
|
||||
|
||||
from TimerCfgNode a, TestFunction f
|
||||
where allLiveReachable(a, f)
|
||||
select a, "Unreachable live annotation; entry of $@ does not reach this node", f, f.getName()
|
||||
@@ -0,0 +1 @@
|
||||
|
||||
@@ -0,0 +1,18 @@
|
||||
/**
|
||||
* New-CFG version of AnnotationHasCfgNode.
|
||||
*
|
||||
* Checks that every timer annotation has a corresponding CFG node.
|
||||
*/
|
||||
|
||||
import python
|
||||
import TimerUtils
|
||||
import NewCfgImpl
|
||||
|
||||
private module Utils = EvalOrderCfgUtils<NewCfg>;
|
||||
|
||||
private import Utils::CfgTests
|
||||
|
||||
from TimerAnnotation ann
|
||||
where annotationWithoutCfgNode(ann)
|
||||
select ann, "Annotation in $@ has no CFG node", ann.getTestFunction(),
|
||||
ann.getTestFunction().getName()
|
||||
@@ -0,0 +1,26 @@
|
||||
/**
|
||||
* New-CFG version of BasicBlockAnnotationGap.
|
||||
*
|
||||
* Original:
|
||||
* Checks that within a basic block, if a node is annotated then its
|
||||
* successor is also annotated (or excluded). A gap in annotations
|
||||
* within a basic block indicates a missing annotation, since there
|
||||
* are no branches to justify the gap.
|
||||
*
|
||||
* Nodes with exceptional successors are excluded, as the exception
|
||||
* edge leaves the basic block and the normal successor may be dead.
|
||||
*/
|
||||
|
||||
import python
|
||||
import TimerUtils
|
||||
import NewCfgImpl
|
||||
|
||||
private module Utils = EvalOrderCfgUtils<NewCfg>;
|
||||
|
||||
private import Utils
|
||||
private import Utils::CfgTests
|
||||
|
||||
from TimerCfgNode a, CfgNode succ
|
||||
where basicBlockAnnotationGap(a, succ)
|
||||
select a, "Annotated node followed by unannotated $@ in the same basic block", succ,
|
||||
succ.getNode().toString()
|
||||
@@ -0,0 +1,21 @@
|
||||
/**
|
||||
* New-CFG version of BasicBlockOrdering.
|
||||
*
|
||||
* Original:
|
||||
* Checks that within a single basic block, annotations appear in
|
||||
* increasing minimum-timestamp order.
|
||||
*/
|
||||
|
||||
import python
|
||||
import TimerUtils
|
||||
import NewCfgImpl
|
||||
|
||||
private module Utils = EvalOrderCfgUtils<NewCfg>;
|
||||
|
||||
private import Utils
|
||||
private import Utils::CfgTests
|
||||
|
||||
from TimerCfgNode a, TimerCfgNode b, int minA, int minB
|
||||
where basicBlockOrdering(a, b, minA, minB)
|
||||
select a, "Basic block ordering: $@ appears before $@", a.getTimestampExpr(minA),
|
||||
"timestamp " + minA, b.getTimestampExpr(minB), "timestamp " + minB
|
||||
@@ -0,0 +1,80 @@
|
||||
/**
|
||||
* New-CFG version of BranchTimestamps.
|
||||
*
|
||||
* Checks that when a node has both a true and false successor, the
|
||||
* live timestamps on one branch are marked as dead on the other.
|
||||
* This ensures that boolean branches are fully annotated with dead()
|
||||
* markers for the paths not taken.
|
||||
*
|
||||
* Limitation: the `@ t[ts, ...]` / `dead(ts)` annotation scheme can only
|
||||
* model branch-dead-ness for plain boolean control flow that reconverges
|
||||
* linearly after the split — i.e. `if`-with-else and `if`-expression.
|
||||
* It cannot model:
|
||||
*
|
||||
* * loops (`while` / `for`): body timestamps repeat across iterations,
|
||||
* so the loop-exit annotation can't list them as dead;
|
||||
* * `match` statements: each `case` body is a syntactically distinct
|
||||
* sub-tree, and the branches don't reconverge through a common
|
||||
* annotation point in the timeline;
|
||||
* * `try` / `with` and `raise` / `assert`: exception edges are modelled
|
||||
* as true/false but flow to syntactically distinct handlers, with no
|
||||
* reconvergence in the linear annotation order;
|
||||
* * short-circuit `and` / `or` (`BoolExpr`): the branches reconverge at
|
||||
* the BoolExpr's after-node, so timestamps on one branch are live
|
||||
* downstream of the other rather than dead;
|
||||
* * `if` without an `else` clause, and `if`/`elif` chains: the false
|
||||
* branch reconverges with the true branch at the post-if statement
|
||||
* (no-else) or fans out across multiple elif-test annotations,
|
||||
* neither of which fit the binary annotation scheme.
|
||||
*
|
||||
* Branch nodes inside those constructs are therefore whitelisted out
|
||||
* below. The check still fires (and is useful) for plain `if`/`else`
|
||||
* and conditional-expression branching.
|
||||
*/
|
||||
|
||||
import python
|
||||
import TimerUtils
|
||||
import NewCfgImpl
|
||||
|
||||
private module Utils = EvalOrderCfgUtils<NewCfg>;
|
||||
|
||||
private import Utils
|
||||
private import Utils::CfgTests
|
||||
|
||||
/**
|
||||
* Holds if `f` contains a construct whose branches the linear-timestamp
|
||||
* annotation scheme cannot describe (see file-level comment).
|
||||
*/
|
||||
private predicate hasUnmodellableBranching(Function f) {
|
||||
exists(AstNode bad |
|
||||
bad.getScope() = f and
|
||||
(
|
||||
bad instanceof While
|
||||
or
|
||||
bad instanceof For
|
||||
or
|
||||
bad instanceof MatchStmt
|
||||
or
|
||||
bad instanceof Try
|
||||
or
|
||||
bad instanceof With
|
||||
or
|
||||
bad instanceof Raise
|
||||
or
|
||||
bad instanceof Assert
|
||||
or
|
||||
bad instanceof BoolExpr
|
||||
or
|
||||
bad instanceof If and
|
||||
(not exists(bad.(If).getAnOrelse()) or bad.(If).isElif())
|
||||
)
|
||||
)
|
||||
}
|
||||
|
||||
from TimerCfgNode node, int ts, string branch
|
||||
where
|
||||
missingBranchTimestamp(node, ts, branch) and
|
||||
not hasUnmodellableBranching(node.getTestFunction())
|
||||
select node,
|
||||
"Timestamp " + ts + " on true/false branch is missing a dead() annotation on the " + branch +
|
||||
" successor in $@", node.getTestFunction(), node.getTestFunction().getName()
|
||||
@@ -0,0 +1 @@
|
||||
|
||||
@@ -0,0 +1,22 @@
|
||||
/**
|
||||
* New-CFG version of ConsecutivePredecessorTimestamps.
|
||||
*
|
||||
* Checks that each annotated node (except the minimum timestamp) has
|
||||
* a predecessor annotation with timestamp `a - 1`. This is the reverse
|
||||
* of ConsecutiveTimestamps: it catches nodes that are reachable but
|
||||
* arrived at from the wrong place (skipping an intermediate node).
|
||||
*/
|
||||
|
||||
import python
|
||||
import TimerUtils
|
||||
import NewCfgImpl
|
||||
|
||||
private module Utils = EvalOrderCfgUtils<NewCfg>;
|
||||
|
||||
private import Utils
|
||||
private import Utils::CfgTests
|
||||
|
||||
from TimerAnnotation ann, int a
|
||||
where consecutivePredecessorTimestamps(ann, a)
|
||||
select ann, "$@ in $@ has no consecutive predecessor (expected " + (a - 1) + ")",
|
||||
ann.getTimestampExpr(a), "Timestamp " + a, ann.getTestFunction(), ann.getTestFunction().getName()
|
||||
@@ -0,0 +1,29 @@
|
||||
/**
|
||||
* New-CFG version of ConsecutiveTimestamps.
|
||||
*
|
||||
* Original:
|
||||
* Checks that consecutive annotated nodes have consecutive timestamps:
|
||||
* for each annotation with timestamp `a`, some CFG node for that annotation
|
||||
* must have a next annotation containing `a + 1`.
|
||||
*
|
||||
* Handles CFG splitting (e.g., finally blocks duplicated for normal/exceptional
|
||||
* flow) by checking that at least one split has the required successor.
|
||||
*
|
||||
* Only applies to functions where all annotations are in the function's
|
||||
* own scope (excludes tests with generators, async, comprehensions, or
|
||||
* lambdas that have annotations in nested scopes).
|
||||
*/
|
||||
|
||||
import python
|
||||
import TimerUtils
|
||||
import NewCfgImpl
|
||||
|
||||
private module Utils = EvalOrderCfgUtils<NewCfg>;
|
||||
|
||||
private import Utils
|
||||
private import Utils::CfgTests
|
||||
|
||||
from TimerAnnotation ann, int a
|
||||
where consecutiveTimestamps(ann, a)
|
||||
select ann, "$@ in $@ has no consecutive successor (expected " + (a + 1) + ")",
|
||||
ann.getTimestampExpr(a), "Timestamp " + a, ann.getTestFunction(), ann.getTestFunction().getName()
|
||||
@@ -0,0 +1,120 @@
|
||||
/**
|
||||
* Implementation of the evaluation-order CFG signature using the new
|
||||
* shared control flow graph from AstNodeImpl.
|
||||
*/
|
||||
|
||||
private import python as Py
|
||||
import TimerUtils
|
||||
private import semmle.python.controlflow.internal.AstNodeImpl as CfgImpl
|
||||
private import codeql.controlflow.SuccessorType
|
||||
|
||||
private class NewControlFlowNode = CfgImpl::ControlFlowNode;
|
||||
|
||||
private class NewBasicBlock = CfgImpl::BasicBlock;
|
||||
|
||||
/** New (shared) CFG implementation of the evaluation-order signature. */
|
||||
module NewCfg implements EvalOrderCfgSig {
|
||||
class CfgNode instanceof NewControlFlowNode {
|
||||
// We must pick a *unique* representative CFG node for each AST node. The
|
||||
// shared CFG has several nodes per AST node (before / in-post-order / after
|
||||
// / after-value splits), but the timer test framework keys annotations on
|
||||
// `getNode()` and assumes one CFG node per annotated AST node. Without a
|
||||
// filter, an annotated `f()` would map to both `f()` and `After f()`, which
|
||||
// breaks two framework invariants: (1) the "no shared reachable" check
|
||||
// requires that two distinct nodes sharing a timestamp be mutually
|
||||
// unreachable (true/false branches of a condition), but `Before f()`,
|
||||
// `f()` and `After f()` share the annotation's timestamp *and* lie on one
|
||||
// linear path; and (2) the annotation walk (`nextTimerAnnotation`) halts at
|
||||
// the first reachable representative, so a second node for the same AST
|
||||
// node would stall the walk on the same timestamp instead of advancing to
|
||||
// the next evaluation event.
|
||||
//
|
||||
// We use the "after" node (`isAfter`) rather than the canonical `injects`
|
||||
// node, because `injects` represents short-circuit / conditional
|
||||
// expressions (`and`/`or`/`not`/ternary) by their *before* node, placing
|
||||
// them ahead of their operands — wrong for evaluation order. `isAfter`
|
||||
// instead picks the post-evaluation node: the merged before/after node for
|
||||
// simple leaves, the `TAfterNode` for post-order expressions, and the
|
||||
// `AfterValueNode`(s) for pre-order conditionals, all positioned after the
|
||||
// operands. The two value-split nodes of a conditional are genuinely
|
||||
// distinct evaluation outcomes (handled by `getATrueSuccessor` /
|
||||
// `getAFalseSuccessor`), so they do not violate the uniqueness assumption.
|
||||
CfgNode() { NewControlFlowNode.super.isAfter(_) }
|
||||
|
||||
string toString() { result = NewControlFlowNode.super.toString() }
|
||||
|
||||
Py::Location getLocation() { result = NewControlFlowNode.super.getLocation() }
|
||||
|
||||
Py::AstNode getNode() {
|
||||
result = CfgImpl::astNodeToPyNode(NewControlFlowNode.super.getAstNode())
|
||||
}
|
||||
|
||||
CfgNode getASuccessor() { nextCfgNode(this, result) }
|
||||
|
||||
CfgNode getATrueSuccessor() {
|
||||
NewControlFlowNode.super.isAfterTrue(_) and
|
||||
// Only where there's also a false branch (true boolean split)
|
||||
exists(NewControlFlowNode other | other.isAfterFalse(NewControlFlowNode.super.getAstNode())) and
|
||||
nextCfgNodeFrom(this, result)
|
||||
}
|
||||
|
||||
CfgNode getAFalseSuccessor() {
|
||||
NewControlFlowNode.super.isAfterFalse(_) and
|
||||
// Only where there's also a true branch (true boolean split)
|
||||
exists(NewControlFlowNode other | other.isAfterTrue(NewControlFlowNode.super.getAstNode())) and
|
||||
nextCfgNodeFrom(this, result)
|
||||
}
|
||||
|
||||
CfgNode getAnExceptionalSuccessor() {
|
||||
exists(NewControlFlowNode mid |
|
||||
mid = NewControlFlowNode.super.getAnExceptionSuccessor() and
|
||||
nextCfgNodeFrom(mid, result)
|
||||
)
|
||||
}
|
||||
|
||||
Py::Scope getScope() { result = NewControlFlowNode.super.getEnclosingCallable().asScope() }
|
||||
|
||||
BasicBlock getBasicBlock() {
|
||||
exists(NewBasicBlock bb, int i | bb.getNode(i) = this and result = bb)
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Holds if `next` is the nearest CfgNode reachable from `n` via
|
||||
* one or more raw CFG successor edges, skipping non-CfgNode intermediaries.
|
||||
*/
|
||||
private predicate nextCfgNodeFrom(NewControlFlowNode n, CfgNode next) {
|
||||
next = n.getASuccessor()
|
||||
or
|
||||
exists(NewControlFlowNode mid |
|
||||
mid = n.getASuccessor() and
|
||||
not mid instanceof CfgNode and
|
||||
nextCfgNodeFrom(mid, next)
|
||||
)
|
||||
}
|
||||
|
||||
/**
|
||||
* Holds if `next` is the nearest CfgNode successor of `n`,
|
||||
* skipping synthetic intermediate nodes.
|
||||
*/
|
||||
private predicate nextCfgNode(CfgNode n, CfgNode next) { nextCfgNodeFrom(n, next) }
|
||||
|
||||
class BasicBlock instanceof NewBasicBlock {
|
||||
string toString() { result = NewBasicBlock.super.toString() }
|
||||
|
||||
CfgNode getNode(int n) { result = NewBasicBlock.super.getNode(n) }
|
||||
|
||||
predicate reaches(BasicBlock bb) { this = bb or this.strictlyReaches(bb) }
|
||||
|
||||
predicate strictlyReaches(BasicBlock bb) { NewBasicBlock.super.getASuccessor+() = bb }
|
||||
|
||||
predicate strictlyDominates(BasicBlock bb) { NewBasicBlock.super.strictlyDominates(bb) }
|
||||
}
|
||||
|
||||
CfgNode scopeGetEntryNode(Py::Scope s) {
|
||||
exists(CfgImpl::ControlFlow::EntryNode entry |
|
||||
entry.getEnclosingCallable().asScope() = s and
|
||||
nextCfgNodeFrom(entry, result)
|
||||
)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,21 @@
|
||||
/**
|
||||
* New-CFG version of NeverReachable.
|
||||
*
|
||||
* Original:
|
||||
* Checks that expressions annotated with `t.never` either have no CFG
|
||||
* node, or if they do, that the node is not reachable from its scope's
|
||||
* entry (including within the same basic block).
|
||||
*/
|
||||
|
||||
import python
|
||||
import TimerUtils
|
||||
import NewCfgImpl
|
||||
|
||||
private module Utils = EvalOrderCfgUtils<NewCfg>;
|
||||
|
||||
private import Utils::CfgTests
|
||||
|
||||
from TimerAnnotation ann
|
||||
where neverReachable(ann)
|
||||
select ann, "Node annotated with t.never is reachable in $@", ann.getTestFunction(),
|
||||
ann.getTestFunction().getName()
|
||||
@@ -0,0 +1,22 @@
|
||||
/**
|
||||
* New-CFG version of NoBackwardFlow.
|
||||
*
|
||||
* Original:
|
||||
* Checks that time never flows backward between consecutive timer annotations
|
||||
* in the CFG. For each pair of consecutive annotated nodes (A -> B), there must
|
||||
* exist timestamps a in A and b in B with a < b.
|
||||
*/
|
||||
|
||||
import python
|
||||
import TimerUtils
|
||||
import NewCfgImpl
|
||||
|
||||
private module Utils = EvalOrderCfgUtils<NewCfg>;
|
||||
|
||||
private import Utils
|
||||
private import Utils::CfgTests
|
||||
|
||||
from TimerCfgNode a, TimerCfgNode b, int minA, int maxB
|
||||
where noBackwardFlow(a, b, minA, maxB)
|
||||
select a, "Backward flow: $@ flows to $@ (max timestamp $@)", a.getTimestampExpr(minA),
|
||||
minA.toString(), b, b.getNode().toString(), b.getTimestampExpr(maxB), maxB.toString()
|
||||
@@ -0,0 +1 @@
|
||||
|
||||
@@ -0,0 +1,18 @@
|
||||
/**
|
||||
* New-CFG version of NoBasicBlock.
|
||||
*
|
||||
* Checks that every annotated CFG node belongs to a basic block.
|
||||
*/
|
||||
|
||||
import python
|
||||
import TimerUtils
|
||||
import NewCfgImpl
|
||||
|
||||
private module Utils = EvalOrderCfgUtils<NewCfg>;
|
||||
|
||||
private import Utils
|
||||
private import Utils::CfgTests
|
||||
|
||||
from CfgNode n, TestFunction f
|
||||
where noBasicBlock(n, f)
|
||||
select n, "CFG node in $@ does not belong to any basic block", f, f.getName()
|
||||
@@ -0,0 +1,21 @@
|
||||
/**
|
||||
* New-CFG version of NoSharedReachable.
|
||||
*
|
||||
* Original:
|
||||
* Checks that two annotations sharing a timestamp value are on
|
||||
* mutually exclusive CFG paths (neither can reach the other).
|
||||
*/
|
||||
|
||||
import python
|
||||
import TimerUtils
|
||||
import NewCfgImpl
|
||||
|
||||
private module Utils = EvalOrderCfgUtils<NewCfg>;
|
||||
|
||||
private import Utils
|
||||
private import Utils::CfgTests
|
||||
|
||||
from TimerCfgNode a, TimerCfgNode b, int ts
|
||||
where noSharedReachable(a, b, ts)
|
||||
select a, "Shared timestamp $@ but this node reaches $@", a.getTimestampExpr(ts), ts.toString(), b,
|
||||
b.getNode().toString()
|
||||
@@ -0,0 +1,22 @@
|
||||
/**
|
||||
* New-CFG version of StrictForward.
|
||||
*
|
||||
* Original:
|
||||
* Stronger version of NoBackwardFlow: for consecutive annotated nodes
|
||||
* A -> B that both have a single timestamp (non-loop code) and B does
|
||||
* NOT dominate A (forward edge), requires max(A) < min(B).
|
||||
*/
|
||||
|
||||
import python
|
||||
import TimerUtils
|
||||
import NewCfgImpl
|
||||
|
||||
private module Utils = EvalOrderCfgUtils<NewCfg>;
|
||||
|
||||
private import Utils
|
||||
private import Utils::CfgTests
|
||||
|
||||
from TimerCfgNode a, TimerCfgNode b, int maxA, int minB
|
||||
where strictForward(a, b, maxA, minB)
|
||||
select a, "Strict forward violation: $@ flows to $@", a.getTimestampExpr(maxA), "timestamp " + maxA,
|
||||
b.getTimestampExpr(minB), "timestamp " + minB
|
||||
@@ -3,14 +3,14 @@
|
||||
* Python control flow graph.
|
||||
*/
|
||||
|
||||
private import python as PY
|
||||
private import python as Py
|
||||
import TimerUtils
|
||||
|
||||
/** Existing Python CFG implementation of the evaluation-order signature. */
|
||||
module OldCfg implements EvalOrderCfgSig {
|
||||
class CfgNode = PY::ControlFlowNode;
|
||||
class CfgNode = Py::ControlFlowNode;
|
||||
|
||||
class BasicBlock = PY::BasicBlock;
|
||||
class BasicBlock = Py::BasicBlock;
|
||||
|
||||
CfgNode scopeGetEntryNode(PY::Scope s) { result = s.getEntryNode() }
|
||||
CfgNode scopeGetEntryNode(Py::Scope s) { result = s.getEntryNode() }
|
||||
}
|
||||
|
||||
@@ -85,7 +85,7 @@ def test_nested_if_else(t):
|
||||
else:
|
||||
z = 2 @ t[dead(4)]
|
||||
else:
|
||||
z = 3 @ t[dead(4)]
|
||||
z = 3 @ t[dead(3), dead(4)]
|
||||
w = 0 @ t[5]
|
||||
|
||||
|
||||
|
||||
@@ -0,0 +1,41 @@
|
||||
/**
|
||||
* Inline-expectations test for the store/load/delete/parameter
|
||||
* classification predicates on the new-CFG facade.
|
||||
*
|
||||
* Each tag fires when the corresponding predicate (`isLoad`,
|
||||
* `isStore`, `isDelete`, `isParameter`, `isAugLoad`, `isAugStore`)
|
||||
* holds on the canonical CFG node wrapping a `Py::Name` with the
|
||||
* given identifier. Subscript and attribute stores are not covered
|
||||
* by these tags — only the `Name`-typed targets/loads they involve.
|
||||
*/
|
||||
|
||||
import python
|
||||
import semmle.python.controlflow.internal.Cfg as Cfg
|
||||
import utils.test.InlineExpectationsTest
|
||||
|
||||
module StoreLoadTest implements TestSig {
|
||||
string getARelevantTag() { result = ["load", "store", "delete", "param", "augload", "augstore"] }
|
||||
|
||||
predicate hasActualResult(Location location, string element, string tag, string value) {
|
||||
exists(Cfg::NameNode n |
|
||||
location = n.getLocation() and
|
||||
element = n.toString() and
|
||||
value = n.getId() and
|
||||
(
|
||||
n.isLoad() and not n.isAugLoad() and tag = "load"
|
||||
or
|
||||
n.isStore() and not n.isAugStore() and tag = "store"
|
||||
or
|
||||
n.isDelete() and tag = "delete"
|
||||
or
|
||||
n.isParameter() and tag = "param"
|
||||
or
|
||||
n.isAugLoad() and tag = "augload"
|
||||
or
|
||||
n.isAugStore() and tag = "augstore"
|
||||
)
|
||||
)
|
||||
}
|
||||
}
|
||||
|
||||
import MakeTest<StoreLoadTest>
|
||||
56
python/ql/test/library-tests/ControlFlow/store-load/test.py
Normal file
56
python/ql/test/library-tests/ControlFlow/store-load/test.py
Normal file
@@ -0,0 +1,56 @@
|
||||
# Store/load/delete/parameter classification on the new-CFG facade.
|
||||
#
|
||||
# Each annotated location carries the (sorted, deduplicated) set of
|
||||
# kinds the CFG facade reports there. Comparing against the legacy
|
||||
# 'semmle.python.Flow' classification is done by the comparison query
|
||||
# 'StoreLoadParity.ql' — annotations here are only the positive
|
||||
# assertions for the new facade.
|
||||
#
|
||||
# Tags:
|
||||
# load=<id> -- isLoad() fires on the Name
|
||||
# store=<id> -- isStore() fires
|
||||
# delete=<id> -- isDelete() fires
|
||||
# param=<id> -- isParameter() fires
|
||||
# augload=<id> -- isAugLoad() fires (the LHS of x += ... when read)
|
||||
# augstore=<id> -- isAugStore() fires (the LHS of x += ... when written)
|
||||
|
||||
|
||||
# --- plain load / store / delete ---
|
||||
|
||||
x = 1 # $ store=x
|
||||
y = x + 1 # $ store=y load=x
|
||||
print(y) # $ load=print load=y
|
||||
del x # $ delete=x
|
||||
|
||||
|
||||
# --- function definitions (parameters) ---
|
||||
|
||||
def f(a, b=2, *args, c, **kwargs): # $ store=f param=a param=b param=args param=c param=kwargs
|
||||
return a + b + c # $ load=a load=b load=c
|
||||
|
||||
|
||||
# --- augmented assignment splits one Name into load + store halves ---
|
||||
|
||||
def aug(): # $ store=aug
|
||||
n = 0 # $ store=n
|
||||
n += 1 # $ augload=n augstore=n
|
||||
return n # $ load=n
|
||||
|
||||
|
||||
# --- subscript / attribute stores ---
|
||||
|
||||
class C: # $ store=C
|
||||
pass
|
||||
|
||||
|
||||
def stores(obj, container, idx): # $ store=stores param=obj param=container param=idx
|
||||
obj.attr = 1 # $ load=obj
|
||||
container[idx] = 2 # $ load=container load=idx
|
||||
return obj # $ load=obj
|
||||
|
||||
|
||||
# --- tuple unpacking ---
|
||||
|
||||
def unpack(pair): # $ store=unpack param=pair
|
||||
a, b = pair # $ store=a store=b load=pair
|
||||
return a + b # $ load=a load=b
|
||||
@@ -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;
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -304,8 +304,7 @@ 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 +342,7 @@ 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 +356,7 @@ 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 +429,49 @@ 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 +488,101 @@ 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 +603,35 @@ 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;
|
||||
}
|
||||
|
||||
@@ -516,7 +649,7 @@ 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.
|
||||
/// so the bound `NodeRef` refers to the raw (input-schema) node.
|
||||
raw: bool,
|
||||
}
|
||||
|
||||
@@ -671,17 +804,22 @@ 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 +850,7 @@ 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 +859,14 @@ 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 +898,7 @@ 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
|
||||
}
|
||||
@@ -781,7 +919,7 @@ pub fn parse_rule_top(input: TokenStream) -> Result<TokenStream> {
|
||||
__translator.auto_translate_captures(&mut __captures, __ast, __user_ctx, __skip)?;
|
||||
#(#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)
|
||||
}))
|
||||
}
|
||||
@@ -818,6 +956,13 @@ 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 == "_")
|
||||
}
|
||||
|
||||
@@ -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!)
|
||||
)
|
||||
```
|
||||
|
||||
@@ -291,17 +277,21 @@ 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>
|
||||
)
|
||||
```
|
||||
|
||||
Inside `rule!`, captures are Rust variables, so `{name}` inserts a
|
||||
single capture (`Id`) and `{..name}` splices a repeated capture
|
||||
(`Vec<Id>`).
|
||||
|
||||
### Raw captures (`@@name`)
|
||||
|
||||
The default `@name` capture marker is *auto-translated*: in OneShot
|
||||
@@ -312,7 +302,7 @@ 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`:
|
||||
input-schema `NodeRef`:
|
||||
|
||||
```rust
|
||||
yeast::rule!(
|
||||
@@ -320,7 +310,7 @@ yeast::rule!(
|
||||
=>
|
||||
{
|
||||
// raw_lhs is untranslated: read its original source text.
|
||||
let text = ctx.ast.source_text(raw_lhs);
|
||||
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()})
|
||||
|
||||
@@ -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> {
|
||||
|
||||
@@ -54,15 +54,37 @@ 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 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,
|
||||
mut f: impl FnMut(Id) -> Result<Vec<Id>, E>,
|
||||
) -> Result<(), E> {
|
||||
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)?);
|
||||
}
|
||||
*ids = new_ids;
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Like [`try_map_all_captures`] but leaves captures whose name appears
|
||||
/// in `skip` untouched. Used by the `rule!` macro to support `@@name`
|
||||
/// (raw) captures alongside the default auto-translated `@name`
|
||||
/// captures.
|
||||
pub fn try_map_captures_except<E>(
|
||||
&mut self,
|
||||
skip: &[&str],
|
||||
@@ -80,6 +102,12 @@ 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 {
|
||||
|
||||
8
shared/yeast/src/cursor.rs
Normal file
8
shared/yeast/src/cursor.rs
Normal 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;
|
||||
}
|
||||
@@ -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<(
|
||||
|
||||
@@ -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;
|
||||
@@ -18,61 +19,38 @@ mod visitor;
|
||||
pub use yeast_macros::{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
|
||||
}
|
||||
}
|
||||
|
||||
impl From<Id> for NodeRef {
|
||||
fn from(value: Id) -> Self {
|
||||
NodeRef(value)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -89,21 +67,21 @@ 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 +150,6 @@ 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 +170,37 @@ 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 +347,16 @@ 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 +380,11 @@ 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 +427,7 @@ impl Ast {
|
||||
is_named,
|
||||
source_range,
|
||||
});
|
||||
Id(id)
|
||||
id
|
||||
}
|
||||
|
||||
fn union_source_range_of_children(
|
||||
@@ -515,6 +494,15 @@ 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 +524,7 @@ 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 +608,10 @@ pub struct Node {
|
||||
}
|
||||
|
||||
impl Node {
|
||||
pub fn kind(&self) -> &'static str {
|
||||
self.kind_name
|
||||
}
|
||||
|
||||
pub fn kind_name(&self) -> &'static str {
|
||||
self.kind_name
|
||||
}
|
||||
@@ -964,7 +956,7 @@ 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 +1008,7 @@ 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 +1041,7 @@ 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 +1075,7 @@ 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)? {
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -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
|
||||
@@ -1063,7 +1059,7 @@ 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
|
||||
/// the body sees the *raw* (input-schema) NodeRef 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.
|
||||
@@ -1076,7 +1072,7 @@ fn test_raw_capture_marker() {
|
||||
yeast::rule!(
|
||||
(program (_)* @stmts)
|
||||
=>
|
||||
(program stmt: {stmts})
|
||||
(program stmt: {..stmts})
|
||||
),
|
||||
// `@@raw_lhs` is untranslated: the body reads its source text
|
||||
// ("x") and embeds it directly as the identifier content. `@rhs`
|
||||
@@ -1085,7 +1081,7 @@ fn test_raw_capture_marker() {
|
||||
(assignment left: (_) @@raw_lhs right: (_) @rhs)
|
||||
=>
|
||||
{
|
||||
let text = ctx.ast.source_text(raw_lhs);
|
||||
let text = ctx.ast.source_text(raw_lhs.into());
|
||||
tree!((call
|
||||
method: (identifier #{text.as_str()})
|
||||
receiver: {rhs}))
|
||||
@@ -1120,7 +1116,7 @@ fn test_raw_capture_marker() {
|
||||
}
|
||||
|
||||
/// Companion to `test_raw_capture_marker`: confirms that calling
|
||||
/// `ctx.translate(raw)` on a `@@`-captured `Id` from the rule body
|
||||
/// `ctx.translate(raw)` on a `@@`-captured NodeRef 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
|
||||
@@ -1134,7 +1130,7 @@ fn test_raw_capture_marker_explicit_translate() {
|
||||
yeast::rule!(
|
||||
(program (_)* @stmts)
|
||||
=>
|
||||
(program stmt: {stmts})
|
||||
(program stmt: {..stmts})
|
||||
),
|
||||
yeast::rule!(
|
||||
(assignment left: (_) @@raw_lhs right: (_) @rhs)
|
||||
@@ -1142,7 +1138,7 @@ fn test_raw_capture_marker_explicit_translate() {
|
||||
{
|
||||
let translated_lhs = ctx.translate(raw_lhs)?;
|
||||
tree!((call
|
||||
method: {translated_lhs}
|
||||
method: {..translated_lhs}
|
||||
receiver: {rhs}))
|
||||
}
|
||||
),
|
||||
@@ -1176,11 +1172,11 @@ 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 +1187,10 @@ 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 +1235,10 @@ 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 +1266,7 @@ 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 +1304,12 @@ 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);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -15,26 +15,26 @@ struct SwiftContext {
|
||||
/// (`computed_getter`/`computed_setter`/`computed_modify`/
|
||||
/// `willset_clause`/`didset_clause`/`getter_specifier`/
|
||||
/// `setter_specifier`).
|
||||
property_name: Option<yeast::Id>,
|
||||
property_name: Option<yeast::NodeRef>,
|
||||
/// Translated type node for the property type. Set by the outer
|
||||
/// `property_binding` rule (computed accessors variant) and
|
||||
/// `protocol_property_declaration` when present; read by the
|
||||
/// accessor inner rules.
|
||||
property_type: Option<yeast::Id>,
|
||||
property_type: Option<yeast::NodeRef>,
|
||||
/// Default-value expression for the next translated `parameter`. Set
|
||||
/// by the outer `function_parameter` rule; read by the `parameter`
|
||||
/// rules.
|
||||
default_value: Option<yeast::Id>,
|
||||
default_value: Option<yeast::NodeRef>,
|
||||
/// Translated outer modifiers (e.g. visibility, attributes) to
|
||||
/// attach to each child of a flattening outer rule. Set by
|
||||
/// `property_declaration`, `enum_entry`, and
|
||||
/// `protocol_property_declaration`.
|
||||
outer_modifiers: Vec<yeast::Id>,
|
||||
outer_modifiers: Vec<yeast::NodeRef>,
|
||||
/// The `let`/`var` binding modifier for a `property_declaration`.
|
||||
/// Set by `property_declaration`; read by the inner declaration
|
||||
/// rules (`property_binding` variants, accessor rules) so they
|
||||
/// emit it as part of the output node's `modifier:` field.
|
||||
binding_modifier: Option<yeast::Id>,
|
||||
binding_modifier: Option<yeast::NodeRef>,
|
||||
/// True when the current child of a flattening outer rule is not
|
||||
/// the first one — its inner rule should emit a
|
||||
/// `chained_declaration` modifier so the original grouping can be
|
||||
@@ -45,10 +45,10 @@ 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.
|
||||
fn chained_modifier(ctx: &mut yeast::build::BuildCtx<'_, SwiftContext>) -> Option<yeast::Id> {
|
||||
/// rule. Returns `Option<NodeRef>` so it splices via `{..…}` to 0 or 1 ids.
|
||||
fn chained_modifier(ctx: &mut yeast::build::BuildCtx<'_, SwiftContext>) -> Option<yeast::NodeRef> {
|
||||
if ctx.is_chained {
|
||||
Some(ctx.literal("modifier", "chained_declaration"))
|
||||
Some(ctx.literal("modifier", "chained_declaration").into())
|
||||
} else {
|
||||
None
|
||||
}
|
||||
@@ -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
|
||||
@@ -198,8 +198,8 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
|
||||
type: _? @ty
|
||||
computed_value: (computed_property accessor: _+ @@accessors))
|
||||
=>
|
||||
{{
|
||||
ctx.property_name = Some(tree!((identifier #{pattern})));
|
||||
{..{
|
||||
ctx.property_name = Some(tree!((identifier #{pattern})).into());
|
||||
ctx.property_type = ty;
|
||||
|
||||
let mut result = Vec::new();
|
||||
@@ -223,13 +223,13 @@ 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
|
||||
@@ -249,19 +249,19 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
|
||||
value: _? @val
|
||||
observers: (willset_didset_block willset: _? @@ws didset: _? @@ds))
|
||||
=>
|
||||
{{
|
||||
{..{
|
||||
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: {..ty}
|
||||
value: {..val})
|
||||
);
|
||||
|
||||
// Publish the property name for the observer rules.
|
||||
ctx.property_name = Some(tree!((identifier #{name})));
|
||||
ctx.property_name = Some(tree!((identifier #{name})).into());
|
||||
// Observers are subsequent outputs of this flattening
|
||||
// rule, so they always get `chained_declaration`.
|
||||
ctx.is_chained = true;
|
||||
@@ -282,12 +282,12 @@ 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
|
||||
@@ -305,9 +305,9 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
|
||||
declarator: _* @@decls
|
||||
(modifiers)* @mods)
|
||||
=>
|
||||
{{
|
||||
let binding_text = ctx.ast.source_text(binding_kind);
|
||||
ctx.binding_modifier = Some(ctx.literal("modifier", &binding_text));
|
||||
{..{
|
||||
let binding_text = ctx.ast.source_text(binding_kind.into());
|
||||
ctx.binding_modifier = Some(ctx.literal("modifier", &binding_text).into());
|
||||
ctx.outer_modifiers = mods;
|
||||
|
||||
let mut result = Vec::new();
|
||||
@@ -342,19 +342,19 @@ 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 +364,8 @@ 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})))
|
||||
),
|
||||
@@ -376,7 +376,7 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
|
||||
rule!(
|
||||
(enum_entry case: _+ @@cases (modifiers)* @mods)
|
||||
=>
|
||||
{{
|
||||
{..{
|
||||
ctx.outer_modifiers = mods;
|
||||
|
||||
let mut result = Vec::new();
|
||||
@@ -418,7 +418,7 @@ 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 +426,10 @@ 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)
|
||||
@@ -452,9 +452,9 @@ 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`
|
||||
@@ -463,7 +463,7 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
|
||||
rule!(
|
||||
(function_parameter parameter: @@p default_value: _? @def)
|
||||
=>
|
||||
{{
|
||||
{..{
|
||||
ctx.default_value = def;
|
||||
ctx.translate(p)?
|
||||
}}
|
||||
@@ -475,7 +475,7 @@ 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 +484,7 @@ 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 +492,7 @@ 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 +500,7 @@ 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 +514,7 @@ 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 +537,7 @@ 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 +556,20 @@ 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 +615,7 @@ 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 +623,7 @@ 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!(
|
||||
@@ -635,7 +635,7 @@ 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 multiple patterns and body
|
||||
rule!(
|
||||
@@ -644,19 +644,19 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
|
||||
pattern: (switch_pattern pattern: @rest)+
|
||||
statement: _* @body)
|
||||
=>
|
||||
(switch_case pattern: (or_pattern pattern: {first} pattern: {rest}) 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_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 PATTERN = expr — preserve the pattern directly (no Optional wrapping)
|
||||
rule!(
|
||||
@@ -702,8 +702,8 @@ 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!(
|
||||
@@ -711,7 +711,7 @@ 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!(
|
||||
@@ -719,28 +719,28 @@ 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
|
||||
@@ -753,8 +753,8 @@ 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!(
|
||||
@@ -766,14 +766,14 @@ 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!(
|
||||
@@ -787,7 +787,7 @@ 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})),
|
||||
@@ -812,7 +812,7 @@ 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
|
||||
@@ -823,7 +823,7 @@ 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
|
||||
@@ -831,7 +831,7 @@ 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})),
|
||||
@@ -848,7 +848,7 @@ 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
|
||||
@@ -865,7 +865,7 @@ 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
|
||||
@@ -889,10 +889,10 @@ 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!(
|
||||
@@ -905,10 +905,10 @@ 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!(
|
||||
@@ -921,9 +921,9 @@ 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!(
|
||||
@@ -935,10 +935,10 @@ 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!(
|
||||
@@ -950,11 +950,11 @@ 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).
|
||||
@@ -965,9 +965,9 @@ 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!(
|
||||
@@ -976,15 +976,15 @@ 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})
|
||||
),
|
||||
@@ -999,9 +999,9 @@ 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
|
||||
@@ -1018,8 +1018,8 @@ fn translation_rules() -> Vec<Rule<SwiftContext>> {
|
||||
type: _? @ty
|
||||
(modifiers)* @mods)
|
||||
=>
|
||||
{{
|
||||
ctx.property_name = Some(tree!((identifier #{name})));
|
||||
{..{
|
||||
ctx.property_name = Some(tree!((identifier #{name})).into());
|
||||
ctx.property_type = ty;
|
||||
ctx.outer_modifiers = mods;
|
||||
|
||||
@@ -1040,23 +1040,23 @@ 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
|
||||
@@ -1065,58 +1065,58 @@ 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
|
||||
@@ -1125,24 +1125,24 @@ 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)),
|
||||
|
||||
Reference in New Issue
Block a user