breakpilot-compliance/dsms-gateway/routers/documents.py

"""
Documents router — handles /api/v1/documents and /api/v1/legal-documents endpoints.
"""

import hashlib
import json
import io
from datetime import datetime
from typing import Optional

import httpx
from fastapi import APIRouter, Depends, File, HTTPException, UploadFile
from fastapi.responses import StreamingResponse

from models import DocumentList, DocumentMetadata, StoredDocument
from dependencies import verify_token, ipfs_add, ipfs_cat, ipfs_pin_ls
from config import IPFS_API_URL, IPFS_GATEWAY_URL

router = APIRouter()


@router.post("/api/v1/documents", response_model=StoredDocument)
async def store_document(
    file: UploadFile = File(...),
    document_type: str = "legal_document",
    document_id: Optional[str] = None,
    version: Optional[str] = None,
    language: str = "de",
    _auth: dict = Depends(verify_token)
):
    """
    Speichert ein Dokument im DSMS.

    - **file**: Das zu speichernde Dokument
    - **document_type**: Typ des Dokuments (legal_document, consent_record, audit_log)
    - **document_id**: Optionale ID des Dokuments
    - **version**: Optionale Versionsnummer
    - **language**: Sprache (default: de)
    """
    content = await file.read()

    # Checksum berechnen
    checksum = hashlib.sha256(content).hexdigest()

    # Metadaten erstellen
    metadata = DocumentMetadata(
        document_type=document_type,
        document_id=document_id,
        version=version,
        language=language,
        created_at=datetime.utcnow().isoformat(),
        checksum=checksum,
        encrypted=False
    )

    # Dokument mit Metadaten als JSON verpacken
    package = {
        "metadata": metadata.model_dump(),
        "content_base64": content.hex(),  # Hex-encodiert für JSON
        "filename": file.filename
    }

    package_bytes = json.dumps(package).encode()

    # Zu IPFS hinzufügen
    result = await ipfs_add(package_bytes)

    cid = result.get("Hash")
    size = int(result.get("Size", 0))

    return StoredDocument(
        cid=cid,
        size=size,
        metadata=metadata,
        gateway_url=f"{IPFS_GATEWAY_URL}/ipfs/{cid}",
        timestamp=datetime.utcnow().isoformat()
    )


@router.get("/api/v1/documents/{cid}")
async def get_document(
    cid: str,
    _auth: dict = Depends(verify_token)
):
    """
    Ruft ein Dokument aus dem DSMS ab.

    - **cid**: Content Identifier (IPFS Hash)
    """
    content = await ipfs_cat(cid)

    try:
        package = json.loads(content)
        metadata = package.get("metadata", {})
        original_content = bytes.fromhex(package.get("content_base64", ""))
        filename = package.get("filename", "document")

        return StreamingResponse(
            io.BytesIO(original_content),
            media_type="application/octet-stream",
            headers={
                "Content-Disposition": f'attachment; filename="{filename}"',
                "X-DSMS-Document-Type": metadata.get("document_type", "unknown"),
                "X-DSMS-Checksum": metadata.get("checksum", ""),
                "X-DSMS-Created-At": metadata.get("created_at", "")
            }
        )
    except json.JSONDecodeError:
        # Wenn es kein DSMS-Paket ist, gib rohen Inhalt zurück
        return StreamingResponse(
            io.BytesIO(content),
            media_type="application/octet-stream"
        )


@router.get("/api/v1/documents/{cid}/metadata")
async def get_document_metadata(
    cid: str,
    _auth: dict = Depends(verify_token)
):
    """
    Ruft nur die Metadaten eines Dokuments ab.

    - **cid**: Content Identifier (IPFS Hash)
    """
    content = await ipfs_cat(cid)

    try:
        package = json.loads(content)
        return {
            "cid": cid,
            "metadata": package.get("metadata", {}),
            "filename": package.get("filename"),
            "size": len(bytes.fromhex(package.get("content_base64", "")))
        }
    except json.JSONDecodeError:
        return {
            "cid": cid,
            "metadata": {},
            "raw_size": len(content)
        }


@router.get("/api/v1/documents", response_model=DocumentList)
async def list_documents(
    _auth: dict = Depends(verify_token)
):
    """
    Listet alle gespeicherten Dokumente auf.
    """
    cids = await ipfs_pin_ls()

    documents = []
    for cid in cids[:100]:  # Limit auf 100 für Performance
        try:
            content = await ipfs_cat(cid)
            package = json.loads(content)
            documents.append({
                "cid": cid,
                "metadata": package.get("metadata", {}),
                "filename": package.get("filename")
            })
        except Exception:
            # Überspringe nicht-DSMS Objekte
            continue

    return DocumentList(
        documents=documents,
        total=len(documents)
    )


@router.delete("/api/v1/documents/{cid}")
async def unpin_document(
    cid: str,
    _auth: dict = Depends(verify_token)
):
    """
    Entfernt ein Dokument aus dem lokalen Pin-Set.
    Das Dokument bleibt im Netzwerk, wird aber bei GC entfernt.

    - **cid**: Content Identifier (IPFS Hash)
    """
    async with httpx.AsyncClient(timeout=30.0) as client:
        response = await client.post(
            f"{IPFS_API_URL}/api/v0/pin/rm",
            params={"arg": cid}
        )

        if response.status_code != 200:
            raise HTTPException(
                status_code=404,
                detail=f"Konnte Pin nicht entfernen: {cid}"
            )

    return {
        "status": "unpinned",
        "cid": cid,
        "message": "Dokument wird bei nächster Garbage Collection entfernt"
    }


@router.post("/api/v1/legal-documents/archive")
async def archive_legal_document(
    document_id: str,
    version: str,
    content: str,
    language: str = "de",
    _auth: dict = Depends(verify_token)
):
    """
    Archiviert eine rechtliche Dokumentversion dauerhaft.
    Speziell für AGB, Datenschutzerklärung, etc.

    - **document_id**: ID des Legal Documents
    - **version**: Versionsnummer
    - **content**: HTML/Markdown Inhalt
    - **language**: Sprache
    """
    # Checksum berechnen
    content_bytes = content.encode('utf-8')
    checksum = hashlib.sha256(content_bytes).hexdigest()

    # Metadaten
    metadata = {
        "document_type": "legal_document",
        "document_id": document_id,
        "version": version,
        "language": language,
        "created_at": datetime.utcnow().isoformat(),
        "checksum": checksum,
        "content_type": "text/html"
    }

    # Paket erstellen
    package = {
        "metadata": metadata,
        "content": content,
        "archived_at": datetime.utcnow().isoformat()
    }

    package_bytes = json.dumps(package, ensure_ascii=False).encode('utf-8')

    # Zu IPFS hinzufügen
    result = await ipfs_add(package_bytes)

    cid = result.get("Hash")

    return {
        "cid": cid,
        "document_id": document_id,
        "version": version,
        "checksum": checksum,
        "archived_at": datetime.utcnow().isoformat(),
        "verification_url": f"{IPFS_GATEWAY_URL}/ipfs/{cid}"
    }


@router.get("/documents/{cid}/history")
async def get_document_history(cid: str):
    """Follow the parent_cid chain to reconstruct version history."""
    history = []
    current_cid = cid
    max_depth = 50  # prevent infinite loops

    for _ in range(max_depth):
        try:
            raw = await ipfs_cat(current_cid)
            package = json.loads(raw)
            metadata = package.get("metadata", {})
            history.append({
                "cid": current_cid,
                "version": metadata.get("version"),
                "document_type": metadata.get("document_type"),
                "document_id": metadata.get("document_id"),
                "parent_cid": metadata.get("parent_cid"),
                "created_at": metadata.get("created_at"),
                "checksum": metadata.get("checksum"),
            })
            parent = metadata.get("parent_cid")
            if not parent:
                break
            current_cid = parent
        except Exception:
            break

    return {"cid": cid, "history": history, "depth": len(history)}