fix(scancode): Ensure to find license texts in the Docker image

Dump the ScanCode license texts to directory /opt/scancode-license-data
when creating the ORT docker container. Use this directory as
fallback option if the ScanCode license texts cannot be located by
the existing heuristic algorithm.

Fixes #8147.

Signed-off-by: Wolfgang Klenk <[email protected]>

Author: wkl3nk

Dockerfile

@@ -157,6 +157,11 @@ RUN ARCH=$(arch | sed s/aarch64/arm64/) \
     rm requirements.txt; \
     fi
 
+# Extract ScanCode license texts to a directory.
+RUN scancode-license-data --path /opt/scancode-license-data \
+    && find /opt/scancode-license-data -type f -not -name "*.LICENSE" -exec rm -f {} + \
+    && rm -rf /opt/scancode-license-data/static
+
 RUN pip install --no-cache-dir -U \
     pip=="$PIPTOOL_VERSION" \
     wheel \
@@ -171,6 +176,9 @@ RUN pip install --no-cache-dir -U \
 FROM scratch AS python
 COPY --from=pythonbuild /opt/python /opt/python
 
+FROM scratch as scancode-license-data
+COPY --from=pythonbuild /opt/scancode-license-data /opt/scancode-license-data
+
 #------------------------------------------------------------------------
 # NODEJS - Build NodeJS as a separate component with nvm
 FROM base AS nodejsbuild
@@ -493,6 +501,8 @@ ENV GEM_HOME=/var/tmp/gem
 ENV PATH=$PATH:$RBENV_ROOT/bin:$RBENV_ROOT/shims:$RBENV_ROOT/plugins/ruby-install/bin
 COPY --from=ruby --chown=$USER:$USER $RBENV_ROOT $RBENV_ROOT
 
+COPY --from=scancode-license-data --chown=$USER:$USER /opt/scancode-license-data /opt/scancode-license-data
+
 #------------------------------------------------------------------------
 # Container with all supported package managers.
 FROM minimal-tools as all-tools

utils/spdx/src/main/kotlin/Utils.kt

@@ -49,7 +49,8 @@ val scanCodeLicenseTextDir by lazy {
     val pythonBinDir = listOf("bin", "Scripts")
     val scanCodeBaseDir = scanCodeExeDir?.takeUnless { it.name in pythonBinDir } ?: scanCodeExeDir?.parentFile
 
-    scanCodeBaseDir?.walkTopDown()?.find { it.isDirectory && it.endsWith("licensedcode/data/licenses") }
+    scanCodeBaseDir?.walkTopDown()?.find { it.isDirectory && it.endsWith("licensedcode/data/licenses") } ?:
+        File("/opt/scancode-license-data").takeIf { it.isDirectory }
 }
 
 /**