fix(reporter): Add ScanCode license texts to reporter docker image

Dump the ScanCode license texts to directory /opt/scancode-license-data when creating the reporter docker container. This directory is used by ORT as fallback option if the ScanCode license texts cannot be located by the existing heuristic look-up algorithm. See oss-review-toolkit/ort#9622. Signed-off-by: Wolfgang Klenk <[email protected]>
boschglobal · Dec 20, 2024 · 4da28f7 · 4da28f7
1 parent 2b997df
commit 4da28f7
Showing 1 changed file with 20 additions and 0 deletions.
diff --git a/workers/reporter/docker/Reporter.Dockerfile b/workers/reporter/docker/Reporter.Dockerfile
@@ -51,4 +51,24 @@ RUN chgrp -R 0 /home/ort && chmod -R g+rwX /home/ort
 USER $USERNAME
 WORKDIR $HOMEDIR
 
+COPY --from=scancode-license-data-build --chown=$USER:$USER /opt/scancode-license-data /opt/scancode-license-data
+
 ENTRYPOINT ["/bin/bash"]
+
+# Build-Stage for Python executing scancode-license-data to get the license texts in a directory
+FROM python:3.11-slim AS scancode-license-data-build
+
+# Keep in sync with Scanner.Dockerfile
+ARG SCANCODE_VERSION=32.2.1
+
+RUN apt-get update && apt-get install -y curl libgomp1 && rm -rf /var/lib/apt/lists/*
+
+# Use pip to install ScanCode
+RUN curl -Os https://raw.githubusercontent.com/nexB/scancode-toolkit/v$SCANCODE_VERSION/requirements.txt && \
+    pip install -U --constraint requirements.txt scancode-toolkit==$SCANCODE_VERSION && \
+    rm requirements.txt
+
+# Extract ScanCode license data to 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