From 49df8e71594b26673f9a546a4cd0f8b40fc2c977 Mon Sep 17 00:00:00 2001
From: root <root@docker03.hackbase.int>
Date: Tue, 10 Nov 2026 21:39:03 +0100
Subject: [PATCH] Initial Oracle security mirror

---
 .gitea/workflows/update.yml |  59 +++++++++++++++++
 .gitignore                  |   3 +
 README.md                   |  50 ++++++++++++++
 scripts/sync.py             | 129 ++++++++++++++++++++++++++++++++++++
 scripts/validate.py         |  23 +++++++
 5 files changed, 264 insertions(+)
 create mode 100644 .gitea/workflows/update.yml
 create mode 100644 .gitignore
 create mode 100644 README.md
 create mode 100644 scripts/sync.py
 create mode 100644 scripts/validate.py

diff --git a/.gitea/workflows/update.yml b/.gitea/workflows/update.yml
new file mode 100644
index 0000000..b87c80b
--- /dev/null
+++ b/.gitea/workflows/update.yml
@@ -0,0 +1,59 @@
+name: Oracle Security Mirror
+
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: "11 */6 * * *"
+
+permissions:
+  contents: write
+
+jobs:
+  mirror:
+    runs-on: vuln-runner
+    timeout-minutes: 180
+    steps:
+      - name: Synchronisieren im persistenten Git-Checkout
+        env:
+          GITEA_JOB_TOKEN: ${{ secrets.GITEA_TOKEN }}
+          CACHE_ROOT: /var/lib/act_runner/cache/vuln-oracle
+          REPO_URL: https://git.apex-project.de/VULN/vuln-oracle.git
+        shell: bash
+        run: |
+          set -Eeuo pipefail
+          umask 077
+          : "${GITEA_JOB_TOKEN:?GITEA_TOKEN fehlt oder ist leer}"
+          mkdir -p "$CACHE_ROOT"
+          exec 9>"$CACHE_ROOT/.sync.lock"
+          flock -w 300 9 || { echo 'Ein anderer Lauf ist noch aktiv' >&2; exit 1; }
+          ASKPASS_FILE=$(mktemp "$CACHE_ROOT/.askpass.XXXXXX")
+          trap 'rm -f "$ASKPASS_FILE"' EXIT
+          cat > "$ASKPASS_FILE" <<'SH'
+          #!/bin/sh
+          case "$1" in
+            *Username*) printf '%s\n' 'oauth2' ;;
+            *Password*) printf '%s\n' "$GITEA_JOB_TOKEN" ;;
+            *) exit 1 ;;
+          esac
+          SH
+          chmod 700 "$ASKPASS_FILE"
+          export GIT_ASKPASS="$ASKPASS_FILE" GIT_TERMINAL_PROMPT=0
+          if [ ! -d "$CACHE_ROOT/repo/.git" ]; then
+            git clone --depth 1 --branch main "$REPO_URL" "$CACHE_ROOT/repo"
+          fi
+          cd "$CACHE_ROOT/repo"
+          git remote set-url origin "$REPO_URL"
+          git fetch --depth 1 origin main
+          git reset --hard FETCH_HEAD
+          git clean -fd -- data state
+          python3 scripts/sync.py --since-year 2017
+          python3 scripts/validate.py
+          git config user.name 'Vulnerability Bot'
+          git config user.email 'vulnerability-bot@users.noreply.local'
+          git add -A data state
+          if git diff --cached --quiet; then
+            echo 'Keine Datenänderungen'
+            exit 0
+          fi
+          git commit -m "Update Oracle advisories $(date -u +%Y-%m-%dT%H:%M:%SZ)"
+          git push origin HEAD:main
diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..c6a221a
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,3 @@
+__pycache__/
+*.pyc
+*.tmp
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..28d7882
--- /dev/null
+++ b/README.md
@@ -0,0 +1,50 @@
+# vuln-oracle – Oracle Security Advisory Mirror
+
+Öffentliche Oracle Security Advisories ab 2017 als **unveränderte HTML-Rohdokumente** plus **von Oracle verlinkte CSAF-JSON-Risikomatrizen**, wo vorhanden.
+
+## Datenquellen
+- https://www.oracle.com/security-alerts/
+- https://www.oracle.com/security-alerts/cpuarchive.html
+
+Erfasst CPUs, CSPUs, Security Alerts und Solaris Third Party Bulletins, sofern in den beiden Übersichtsseiten mit Jahresangabe gelistet. Ältere Advisories haben nicht zwingend CSAF-JSON. My Oracle Support (Login/Patches) wird nicht abgerufen.
+
+## Einrichtung
+
+1. In Gitea unter `VULN` das leere Repository `vuln-oracle` anlegen.
+2. Dateien hochladen (`git init`, `git branch -M main`, `git add .`, `git commit ...`, `git remote add origin ...`, `git push -u origin main`).
+3. Auf der Gitea-VM als root:
+
+```bash
+apt-get install -y python3 git util-linux
+install -d -o act_runner -g act_runner -m 700 /var/lib/act_runner/cache/vuln-oracle
+```
+
+4. Gitea Actions für dieses Repository aktivieren und mit dem vorhandenen Host-Runner `vuln-runner` starten. Zeitplan: alle 6 Stunden um Minute 11 (UTC, soweit Gitea entsprechend konfiguriert).
+
+Der Workflow nutzt das automatisch bereitgestellte `secrets.GITEA_TOKEN`. Das Secret muss im Job vorhanden sein und `contents: write` erhalten; andernfalls die Variable in der YAML auf den eigenen Token-Namen ändern.
+
+## Layout
+
+```text
+data/index/               # Originale Übersichtsseiten
+ data/advisories/YYYY/     # Originale Oracle HTML-Advisories
+ data/csaf/YYYY/           # Originale CSAF JSON (nur wo verlinkt)
+ state/catalog.json        # Indizierte Advisory-Liste
+```
+
+## Verhalten
+
+- Alle 6 Stunden werden **alle gelisteten** Dokumente erneut per HTTP abgerufen und nur bei veränderten Bytes in Git geschrieben.
+- Das ist ein inkrementeller **Git-Commit**, aber **kein HTTP-Delta-Download**. Der Oracle-Datenumfang ist deutlich kleiner als OSV/NVD.
+- Link- oder Download-Fehler führen zum Abbruch ohne Commit. Fehlende historische Dokumente werden nicht automatisch gelöscht.
+- Die Discovery prüft einen Mindestumfang; bei geändertem HTML-Layout wird kein vermeintlich erfolgreicher leerer Sync veröffentlicht.
+- Enthält *keine* kommerziellen Patches oder interne MOS-Dokumente. Oracle-Lizenz-/Nutzungsbedingungen vor einer öffentlichen Weiterverteilung der Rohdaten prüfen.
+
+## Lokal testen
+
+```bash
+python3 scripts/sync.py --since-year 2017
+python3 scripts/validate.py
+```
+
+Hinweis: Die URL-Strukturen und die HTML/CSAF-Verknüpfung sind geprüft. Vollständige Live-Läufe und Git-Pushes müssen auf der eigenen Gitea-VM getestet werden.
diff --git a/scripts/sync.py b/scripts/sync.py
new file mode 100644
index 0000000..0a71501
--- /dev/null
+++ b/scripts/sync.py
@@ -0,0 +1,129 @@
+#!/usr/bin/env python3
+"""Mirror public Oracle security advisories (HTML and linked CSAF JSON)."""
+import argparse
+import hashlib
+from html.parser import HTMLParser
+import json
+import os
+from pathlib import Path
+import re
+import time
+from urllib.parse import urljoin, urlparse
+from urllib.request import Request, urlopen
+from urllib.error import HTTPError, URLError
+
+BASE = 'https://www.oracle.com'
+INDEX = BASE + '/security-alerts/'
+ARCHIVE = BASE + '/security-alerts/cpuarchive.html'
+UA = 'vuln-oracle-mirror/1.0 (+security data mirror; contact site administrator)'
+YEAR = re.compile(r'\b(20\d{2})\b')
+
+class Links(HTMLParser):
+    def __init__(self):
+        super().__init__()
+        self.links=[]; self.href=None; self.parts=[]
+    def handle_starttag(self, tag, attrs):
+        if tag=='a':
+            self.href=dict(attrs).get('href'); self.parts=[]
+    def handle_data(self, data):
+        if self.href is not None: self.parts.append(data)
+    def handle_endtag(self,tag):
+        if tag=='a' and self.href is not None:
+            self.links.append((self.href,' '.join(''.join(self.parts).split())))
+            self.href=None; self.parts=[]
+
+def get(url, tries=4):
+    last=None
+    for i in range(tries):
+        try:
+            with urlopen(Request(url, headers={'User-Agent':UA,'Accept':'text/html,application/json,*/*'}), timeout=90) as response:
+                body=response.read(30_000_001)
+                if len(body)>30_000_000: raise ValueError('Document too large')
+                return body
+        except (HTTPError, URLError, TimeoutError) as exc:
+            last=exc
+            if isinstance(exc,HTTPError) and exc.code in (400,401,403,404): break
+            time.sleep(min(2**i,12))
+    raise RuntimeError(f'Failed to fetch {url}: {last}')
+
+def parse_links(data,url):
+    p=Links(); p.feed(data.decode('utf-8','replace'))
+    return [(urljoin(url,href),label) for href,label in p.links]
+
+def allowed(url):
+    return urlparse(url).hostname in ('www.oracle.com','oracle.com') and url.startswith('https://')
+
+def discover(index_html, archive_html, since):
+    found={}
+    for page,src in ((index_html,INDEX),(archive_html,ARCHIVE)):
+        for url,label in parse_links(page,src):
+            if not allowed(url): continue
+            path=urlparse(url).path.lower()
+            if not path.startswith('/security-alerts/') or not path.endswith('.html'): continue
+            if path.endswith(('cpuarchive.html','index.html')): continue
+            title=label.lower()
+            if not any(x in title for x in ('critical patch update','critical security patch update','security alert','solaris third party bulletin')): continue
+            # Years are from the advisory title, not CVE numbers or page modification date.
+            years=[int(y) for y in YEAR.findall(label)]
+            if not years or max(years)<since: continue
+            found[url]={'url':url,'title':label,'year':max(years)}
+    return sorted(found.values(),key=lambda v:v['url'])
+
+def csaf_links(html,url):
+    result=[]
+    for link,label in parse_links(html,url):
+        if not allowed(link): continue
+        path=urlparse(link).path.lower()
+        if path.endswith('.json') and ('csaf' in label.lower() or 'csaf' in path):
+            result.append(link)
+    return sorted(set(result))
+
+def write_changed(path,contents):
+    path.parent.mkdir(parents=True,exist_ok=True)
+    if path.exists() and path.read_bytes()==contents: return False
+    temp=path.with_name(path.name+'.tmp')
+    temp.write_bytes(contents)
+    os.replace(temp,path)
+    return True
+
+def run(root,since,delay):
+    root=Path(root)
+    index=get(INDEX); archive=get(ARCHIVE)
+    items=discover(index,archive,since)
+    if len(items)<25:
+        raise RuntimeError(f'Only {len(items)} advisories discovered: page structure may have changed; refusing incomplete sync')
+    changed=0; errors=[]; csaf_count=0
+    changed+=write_changed(root/'data/index/security-alerts.html',index)
+    changed+=write_changed(root/'data/index/cpuarchive.html',archive)
+    for i,item in enumerate(items,1):
+        url=item['url']; filename=urlparse(url).path.rsplit('/',1)[-1]
+        target=root/'data/advisories'/str(item['year'])/filename
+        try:
+            html=get(url)
+            if b'<html' not in html.lower() and b'<!doctype html' not in html.lower():
+                raise ValueError('Unexpected non-HTML response')
+            links=csaf_links(html,url)
+            # Fetch JSON before committing HTML, fail full run if a linked CSAF is unreachable.
+            for csaf in links:
+                raw=get(csaf); doc=json.loads(raw)
+                if not isinstance(doc,dict): raise ValueError('CSAF must be object')
+                filename_json=urlparse(csaf).path.rsplit('/',1)[-1]
+                csaf_path=root/'data/csaf'/str(item['year'])/filename_json
+                changed+=write_changed(csaf_path,raw)
+                csaf_count+=1
+            changed+=write_changed(target,html)
+            print(f'[{i}/{len(items)}] {filename}: {len(links)} CSAF',flush=True)
+        except Exception as e:
+            errors.append(f'{url}: {e}')
+            print(f'ERROR {url}: {e}',flush=True)
+        if delay: time.sleep(delay)
+    if errors:
+        raise RuntimeError(f'{len(errors)} advisory errors; sync state not updated. First: {errors[0]}')
+    state={'source':INDEX,'since_year':since,'advisory_count':len(items),'csaf_links_found':csaf_count,
+           'advisories':items}
+    changed+=write_changed(root/'state/catalog.json',(json.dumps(state,ensure_ascii=False,indent=2)+'\n').encode())
+    print(f'Complete: {len(items)} advisories, {csaf_count} CSAF links, {changed} changed files')
+
+if __name__=='__main__':
+    p=argparse.ArgumentParser(); p.add_argument('--root',default='.'); p.add_argument('--since-year',type=int,default=2017); p.add_argument('--delay',type=float,default=0.2)
+    a=p.parse_args(); run(a.root,a.since_year,a.delay)
diff --git a/scripts/validate.py b/scripts/validate.py
new file mode 100644
index 0000000..88169a8
--- /dev/null
+++ b/scripts/validate.py
@@ -0,0 +1,23 @@
+#!/usr/bin/env python3
+import json
+from pathlib import Path
+import sys
+
+def validate(root):
+    root=Path(root)
+    catalog=json.loads((root/'state/catalog.json').read_text())
+    assert catalog['advisory_count'] >= 25, 'Incomplete discovery'
+    assert len(catalog['advisories'])==catalog['advisory_count']
+    for item in catalog['advisories']:
+        name=item['url'].split('/')[-1]
+        p=root/'data/advisories'/str(item['year'])/name
+        raw=p.read_bytes().lower()
+        assert b'<html' in raw or b'<!doctype html' in raw, str(p)
+    for p in (root/'data/csaf').rglob('*.json') if (root/'data/csaf').exists() else []:
+        doc=json.loads(p.read_bytes())
+        assert isinstance(doc,dict),str(p)
+    print(f"Validated {catalog['advisory_count']} Oracle advisories")
+
+if __name__=='__main__':
+    try: validate(sys.argv[1] if len(sys.argv)>1 else '.')
+    except Exception as exc: print(f'INVALID: {exc}',file=sys.stderr); sys.exit(1)