From a9fd947cc8e3e28d154bb00423334ee7f5b23f43 Mon Sep 17 00:00:00 2001
From: Kiko Fernandez-Reyes <kiko@erlang.org>
Date: Wed, 4 Dec 2024 15:35:14 +0100
Subject: [PATCH] feat(scanner): Add flag to scanner to detect unlicensed files

Add flag `includeUnlicensed` to the scanner configuration. Its default
is `false`. When set to `true`, the scanner add to a `ScanResult` files
without license as LicenseFindings with license set to `NONE`.

This contribution makes possible to the scanner to display all files as
license findings. The ultimate goal is that any file without license is
catched by the scanner, so that curation mechanism can override files
without licenses in cases where a license applies to a whole folder.

Signed-off-by: Kiko Fernandez-Reyes <kiko@erlang.org>
---
 .../kotlin/config/ScannerConfiguration.kt     |  5 +++
 scanner/src/main/kotlin/Scanner.kt            | 38 ++++++++++++++++++-
 2 files changed, 41 insertions(+), 2 deletions(-)

diff --git a/model/src/main/kotlin/config/ScannerConfiguration.kt b/model/src/main/kotlin/config/ScannerConfiguration.kt
index dedc38a1cbe64..b924cac5984e2 100644
--- a/model/src/main/kotlin/config/ScannerConfiguration.kt
+++ b/model/src/main/kotlin/config/ScannerConfiguration.kt
@@ -39,6 +39,11 @@ data class ScannerConfiguration(
      */
     val skipConcluded: Boolean = false,
 
+    /**
+     * A flag to indicate whether the scanner should add files without license to the scanner results.
+     */
+    val includeUnlicensed: Boolean = false,
+
     /**
      * A flag to control whether excluded scopes and paths should be skipped during the scan.
      */
diff --git a/scanner/src/main/kotlin/Scanner.kt b/scanner/src/main/kotlin/Scanner.kt
index 8747a2c411358..4d4f3b371ea5c 100644
--- a/scanner/src/main/kotlin/Scanner.kt
+++ b/scanner/src/main/kotlin/Scanner.kt
@@ -36,6 +36,7 @@ import org.ossreviewtoolkit.model.FileList
 import org.ossreviewtoolkit.model.Identifier
 import org.ossreviewtoolkit.model.Issue
 import org.ossreviewtoolkit.model.KnownProvenance
+import org.ossreviewtoolkit.model.LicenseFinding
 import org.ossreviewtoolkit.model.OrtResult
 import org.ossreviewtoolkit.model.Package
 import org.ossreviewtoolkit.model.PackageType
@@ -43,6 +44,7 @@ import org.ossreviewtoolkit.model.ProvenanceResolutionResult
 import org.ossreviewtoolkit.model.ScanResult
 import org.ossreviewtoolkit.model.ScanSummary
 import org.ossreviewtoolkit.model.ScannerRun
+import org.ossreviewtoolkit.model.TextLocation
 import org.ossreviewtoolkit.model.VcsInfo
 import org.ossreviewtoolkit.model.config.DownloaderConfiguration
 import org.ossreviewtoolkit.model.config.ScannerConfiguration
@@ -192,8 +194,6 @@ class Scanner(
 
         val vcsPathsForProvenances = getVcsPathsForProvenances(provenances)
 
-        val filteredScanResults = filterScanResultsByVcsPaths(controller.getAllScanResults(), vcsPathsForProvenances)
-
         val files = controller.getAllFileLists().mapTo(mutableSetOf()) { (provenance, fileList) ->
             FileList(
                 provenance = provenance.alignRevisions() as KnownProvenance,
@@ -207,6 +207,40 @@ class Scanner(
             }
         }
 
+        val filteredScanResults = filterScanResultsByVcsPaths(controller.getAllScanResults(), vcsPathsForProvenances)
+            .mapTo(mutableSetOf()) { scanResult ->
+                val licenseFiles = scanResult.summary.licenseFindings.mapTo(mutableSetOf()) { licenseFinding ->
+                    licenseFinding.location.path
+                }
+
+                if (!scannerConfig.includeUnlicensed) {
+                    scanResult.copy(provenance = scanResult.provenance.alignRevisions())
+                } else {
+                    // Adds files without license to the scanned results
+                    val scanSummary =
+                        controller.getAllFileLists()[scanResult.provenance]?.files
+                            .orEmpty().asSequence().mapNotNull { fileEntry ->
+                                if (fileEntry.path in licenseFiles) {
+                                    null
+                                } else {
+                                    fileEntry.path
+                                }
+                            }.toSet().let { fileEntryFindings ->
+                                (fileEntryFindings subtract licenseFiles).mapTo(mutableSetOf()) {
+                                    LicenseFinding(license = "NONE", location = TextLocation(fileEntryFindings, 1))
+                                }.let {
+                                    val allFindings = scanResult.summary.licenseFindings union fileEntryFindings
+                                    scanResult.summary.copy(licenseFindings = allFindings)
+                                }
+                            }
+
+                    scanResult.copy(
+                        provenance = scanResult.provenance.alignRevisions(),
+                        summary = scanSummary
+                    )
+                }
+            }
+
         val scannerNames = scannerWrappers.mapTo(mutableSetOf()) { it.name }
         val scanners = packages.associateBy({ it.id }) { scannerNames }