Kotlin extractor: anchor local variable locations to the identifier

Why this is needed:
- With Kotlin 2.0 analysis, some local-variable locations resolve to a wider
  declaration span than before.
- The previous extractor logic used provider-based ranges that can cover type,
  annotations, and modifiers, which shifts expected variable location facts.
- This caused parity drift in tests that expect the location to point at the
  variable name token itself.

What this changes:
- Cache current source text per file during extraction.
- Derive variable-name offsets by scanning the declaration slice and locating
  the declared identifier token.
- Emit local-variable declaration/expr locations from that identifier span,
  with fallback to the previous provider when source offsets are unavailable.

This restores stable name-anchored variable locations under Kotlin 2.0.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
Anders Fugmann
2026-06-26 12:54:21 +02:00
parent c5e1f38583
commit 572e096ed3

View File

@@ -6,6 +6,8 @@ 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
@@ -2874,6 +2876,45 @@ 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>,
@@ -2882,7 +2923,7 @@ open class KotlinFileExtractor(
) {
with("variable", v) {
val stmtId = tw.getFreshIdLabel<DbLocalvariabledeclstmt>()
val locId = tw.getLocation(getVariableLocationProvider(v))
val locId = getVariableLocation(v)
tw.writeStmts_localvariabledeclstmt(stmtId, parent, idx, callable)
tw.writeHasLocation(stmtId, locId)
extractVariableExpr(v, callable, stmtId, 1, stmtId)
@@ -2900,7 +2941,7 @@ open class KotlinFileExtractor(
with("variable expr", v) {
val varId = useVariable(v)
val exprId = tw.getFreshIdLabel<DbLocalvariabledeclexpr>()
val locId = tw.getLocation(getVariableLocationProvider(v))
val locId = getVariableLocation(v)
val type = useType(v.type)
tw.writeLocalvars(varId, v.name.asString(), type.javaResult.id, exprId)
tw.writeLocalvarsKotlinType(varId, type.kotlinResult.id)