fix: ENISA URLs + increase curl timeout for large PDFs

- Update ENISA download URLs to new site structure (publications → sites/default/files)
- Increase curl max-time from 300s to 600s for IFRS PDFs (7.5-8.2MB)
- Update ENISA Secure by Design metadata (title changed)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Benjamin Admin
2026-02-28 09:07:01 +01:00
parent 9496e758fc
commit 9026e392dc

View File

@@ -28,7 +28,7 @@ set -euo pipefail
WORK_DIR="${WORK_DIR:-$HOME/rag-ingestion}"
RAG_URL="https://localhost:8097/api/v1/documents/upload"
QDRANT_URL="http://localhost:6333"
CURL_OPTS="-sk --connect-timeout 10 --max-time 300"
CURL_OPTS="-sk --connect-timeout 10 --max-time 600"
# Counters
UPLOADED=0
@@ -161,11 +161,11 @@ phase_download() {
# --- A3: ENISA Publications ---
log "--- ENISA Publications ---"
download_pdf \
"https://www.enisa.europa.eu/publications/secure-development-best-practices/@@download/fullReport" \
"https://www.enisa.europa.eu/sites/default/files/publications/ENISA%20Report%20-%20Advancing%20Software%20Security%20in%20the%20EU.pdf" \
"$WORK_DIR/pdfs/enisa_secure_by_design.pdf"
download_pdf \
"https://www.enisa.europa.eu/publications/threat-landscape-for-supply-chain-attacks/@@download/fullReport" \
"https://www.enisa.europa.eu/sites/default/files/publications/ENISA%20Threat%20Landscape%20for%20Supply%20Chain%20Attacks.pdf" \
"$WORK_DIR/pdfs/enisa_supply_chain_security.pdf"
# --- A4: NIST Publications ---
@@ -256,8 +256,8 @@ phase_datenschutz() {
# 3. ENISA Secure by Design
upload_file "$WORK_DIR/pdfs/enisa_secure_by_design.pdf" "$col" "compliance_datenschutz" "guidance" "2023" \
'{"source_id":"enisa","doc_type":"guidance","guideline_name":"Secure Software Development — Best Practices","license":"reuse_notice","attribution":"European Union Agency for Cybersecurity (ENISA)","source":"enisa.europa.eu"}' \
"ENISA: Secure by Design Best Practices"
'{"source_id":"enisa","doc_type":"guidance","guideline_name":"Advancing Software Security in the EU","license":"reuse_notice","attribution":"European Union Agency for Cybersecurity (ENISA)","source":"enisa.europa.eu"}' \
"ENISA: Advancing Software Security in the EU"
# 4. ENISA Supply Chain Security
upload_file "$WORK_DIR/pdfs/enisa_supply_chain_security.pdf" "$col" "compliance_datenschutz" "guidance" "2021" \