feat(sources): PDF-Dokumente als neuer Quellentyp pdf_document

- SOURCE_TYPE_PATTERN um pdf_document erweitert
- src/services/pdf_ingest.py: pdfplumber + Tesseract-OCR-Fallback,
  Uebersetzung nach DE+EN, ein Pool-Artikel pro PDF
- Scheduler-Job pdf_ingest laeuft im Minuten-Takt und verarbeitet
  pdf_document-Quellen mit processed_at IS NULL
- scripts/migrate_pdf_source.py: idempotente DB-Migration
  (sources.pdf_path/pdf_sha256/processed_at, articles.headline_en/content_en)
- requirements.txt: pdfplumber, pytesseract, pdf2image, Pillow

scripts/migrate_pdf_source.py

@@ -0,0 +1,34 @@
+"""Idempotente Migration: Quellen-Typ pdf_document + EN-Spalten in articles.
+
+Beim Live-Promote anwenden:
+    python3 scripts/migrate_pdf_source.py /home/claude-dev/osint-data/osint.db
+"""
+import sqlite3
+import sys
+
+
+def add_col(db, table, col_def):
+    name = col_def.split()[0]
+    cols = {r[1] for r in db.execute(f"PRAGMA table_info({table})").fetchall()}
+    if name in cols:
+        return False
+    db.execute(f"ALTER TABLE {table} ADD COLUMN {col_def}")
+    return True
+
+
+def main(path):
+    with sqlite3.connect(path) as db:
+        for col in ("pdf_path TEXT", "pdf_sha256 TEXT", "processed_at TIMESTAMP"):
+            print(f"sources.{col.split()[0]}:", "added" if add_col(db, "sources", col) else "exists")
+        for col in ("headline_en TEXT", "content_en TEXT"):
+            print(f"articles.{col.split()[0]}:", "added" if add_col(db, "articles", col) else "exists")
+        db.execute("CREATE INDEX IF NOT EXISTS idx_sources_pdf_sha256 ON sources(pdf_sha256)")
+        db.commit()
+    print("DONE")
+
+
+if __name__ == "__main__":
+    if len(sys.argv) != 2:
+        print("Usage: migrate_pdf_source.py /path/to/osint.db")
+        sys.exit(1)
+    main(sys.argv[1])