perf(model): Filter down to relevant files before getting the main license

As an alternative to adding caching, which also included lookups for
irrelevant files, use another approach to only look for relevant files
in the first place. As only configured license file patterns can
contribute to the main license, add a preceding step to only keep
findings from those files before determining the main license.

Signed-off-by: Sebastian Schuberth <[email protected]>

Author: sschuberth

model/src/main/kotlin/licenses/ResolvedLicenseInfo.kt

@@ -28,6 +28,7 @@ import org.ossreviewtoolkit.model.config.CopyrightGarbage
 import org.ossreviewtoolkit.model.config.LicenseFilePatterns
 import org.ossreviewtoolkit.model.config.PathExclude
 import org.ossreviewtoolkit.model.utils.PathLicenseMatcher
+import org.ossreviewtoolkit.utils.common.FileMatcher
 import org.ossreviewtoolkit.utils.ort.CopyrightStatementsProcessor
 import org.ossreviewtoolkit.utils.spdx.SpdxExpression
 import org.ossreviewtoolkit.utils.spdx.SpdxLicenseChoice
@@ -83,12 +84,23 @@ data class ResolvedLicenseInfo(
      * in any of the configured [LicenseFilePatterns] matched against the root path of the package (or project).
      */
     fun mainLicense(): SpdxExpression? {
-        val licenseMatcher = PathLicenseMatcher(LicenseFilePatterns.getInstance())
-        val licensePaths = flatMap { resolvedLicense ->
+        val licenseFilePatterns = LicenseFilePatterns.getInstance()
+        val fileMatcher = FileMatcher(licenseFilePatterns.allLicenseFilenames, ignoreCase = true)
+        val licenseMatcher = PathLicenseMatcher(licenseFilePatterns)
+
+        // Only keep those resolved licenses that can contribute to the main license as they match the configured
+        // license file patterns. This vastly reduces the search for applicable license files for scan results with a
+        // lot of detected license findings, like from file headers in a large code base.
+        val relevantResolvedLicenses = mapNotNull { resolvedLicense ->
+            val locations = resolvedLicense.locations.filterTo(mutableSetOf()) { fileMatcher.matches(it.location.path) }
+            if (locations.isNotEmpty()) resolvedLicense.copy(locations = locations) else null
+        }
+
+        val licensePaths = relevantResolvedLicenses.flatMap { resolvedLicense ->
             resolvedLicense.locations.map { it.location.path }
         }
 
-        val detectedLicenses = filterTo(mutableSetOf()) { resolvedLicense ->
+        val detectedLicenses = relevantResolvedLicenses.filterTo(mutableSetOf()) { resolvedLicense ->
             resolvedLicense.locations.any {
                 val rootPath = (it.provenance as? RepositoryProvenance)?.vcsInfo?.path.orEmpty()