diff --git a/backend/app/api/sources.py b/backend/app/api/sources.py index 6ca79ae..aa0d4b0 100644 --- a/backend/app/api/sources.py +++ b/backend/app/api/sources.py @@ -242,13 +242,18 @@ def download_mail_attachment( if index < 0 or index >= len(parsed.attachments): raise not_found() item = parsed.attachments[index] - return _mail_bytes(item.data, item.media_type or "application/octet-stream", item.filename, inline=True) + name = item.display_name or item.filename or "anlage" + media = (item.media_type or "application/octet-stream").split(";", 1)[0].strip() + if item.data[:1024].lstrip(b"\xef\xbb\xbf\r\n\t ").startswith(b"%PDF"): + media = "application/pdf" + if not name.lower().endswith(".pdf"): + leaf = name.replace("\\", "/").split("/")[-1] + name = name if "." in leaf else f"{name}.pdf" + return _mail_bytes(item.data, media or "application/octet-stream", name, inline=True) def _mail_bytes(data: bytes, media_type: str, filename: str, inline: bool = False) -> Response: - disposition = content_disposition(filename) - if inline: - disposition = disposition.replace("attachment;", "inline;", 1) + disposition = content_disposition(filename, inline=inline) return Response( content=data, media_type=media_type, diff --git a/backend/app/mailpack.py b/backend/app/mailpack.py index 0dda38f..a487510 100644 --- a/backend/app/mailpack.py +++ b/backend/app/mailpack.py @@ -6,6 +6,7 @@ The same tree feeds preview, reading, attachment download and export. from __future__ import annotations +import base64 import hashlib import html import re @@ -164,9 +165,13 @@ def parse_mail(raw: bytes) -> ParsedMail: missing.append(label or f"Anlage {index}") notices.append(f"Die Anlage {label or index} ließ sich nicht vollständig lesen.") continue + data = _unwrap_pdf_payload(data, media, label) + if _is_pdf(data): + media = "application/pdf" + label = _pdf_filename(label) name = _unique_filename(label or f"anlage-{index}.bin", used) inline = disposition == "inline" or bool(content_id) - attachments.append(_attachment(part, name, label or name, data, inline=inline)) + attachments.append(_attachment(part, name, label or name, data, inline=inline, media=media)) simplified = "\n".join(chunk for chunk in plain if chunk).strip() rendered = "" if html_parts: @@ -410,10 +415,49 @@ def _content_id(part: EmailMessage) -> str: return token -def _attachment(part: EmailMessage, filename: str, label: str, data: bytes, inline: bool) -> AttachmentBytes: +def _is_pdf(data: bytes) -> bool: + return data[:1024].lstrip(b"\xef\xbb\xbf\r\n\t ").startswith(b"%PDF") + + +def _unwrap_pdf_payload(data: bytes, media: str, name: str) -> bytes: + """A PDF that arrived as undecoded Base64 is still the PDF, not the transfer text.""" + if _is_pdf(data): + return data + declared = (media or "").split(";", 1)[0].strip().lower() + hinted = "pdf" in declared or (name or "").lower().endswith(".pdf") or declared in { + "application/octet-stream", + "application/x-octet-stream", + "binary/octet-stream", + } + if not hinted: + return data + stripped = b"".join(data.split()) + if len(stripped) < 16 or re.fullmatch(rb"[A-Za-z0-9+/=]+", stripped) is None: + return data + try: + decoded = base64.b64decode(stripped, validate=True) + except Exception: + return data + return decoded if _is_pdf(decoded) else data + + +def _pdf_filename(name: str) -> str: + text = (name or "").strip() or "anlage" + if text.lower().endswith(".pdf"): + return text + if text.lower().endswith(".bin"): + text = text[:-4].rstrip(" .") or "anlage" + leaf = text.replace("\\", "/").split("/")[-1] + if "." in leaf: + return text + return f"{text}.pdf" + + +def _attachment(part: EmailMessage, filename: str, label: str, data: bytes, inline: bool, media: str | None = None) -> AttachmentBytes: + resolved = (media or part.get_content_type() or "application/octet-stream").split(";", 1)[0].strip() return AttachmentBytes( filename=filename, - media_type=(part.get_content_type() or "application/octet-stream")[:120], + media_type=(resolved or "application/octet-stream")[:120], data=data, sha256=hashlib.sha256(data).hexdigest(), display_name=label or filename, diff --git a/backend/app/media/storage.py b/backend/app/media/storage.py index ed45d9a..1cc618e 100644 --- a/backend/app/media/storage.py +++ b/backend/app/media/storage.py @@ -4,6 +4,7 @@ from __future__ import annotations import hashlib from pathlib import Path +from urllib.parse import quote from uuid import UUID from app.core.errors import storage_unavailable, unprocessable @@ -66,10 +67,17 @@ def display_filename(name: str) -> str: return text[:240] -def content_disposition(filename: str) -> str: +def content_disposition(filename: str, *, inline: bool = False) -> str: """The real name goes along in UTF-8 (RFC 5987), with a plain ASCII fallback for old clients.""" - from urllib.parse import quote - - safe = display_filename(filename).replace('"', "") - fallback = safe.encode("ascii", "replace").decode("ascii").replace("?", "_") - return f"attachment; filename=\"{fallback}\"; filename*=UTF-8''{quote(safe, safe='')}" + name = display_filename(filename) + kind = "inline" if inline else "attachment" + suffix = "" + leaf = name.rsplit(".", 1) + if len(leaf) == 2 and leaf[1].isascii() and leaf[1].isalnum(): + suffix = f".{leaf[1]}" + fallback = name.encode("ascii", "replace").decode("ascii").replace("?", "_").replace('"', "").replace("\\", "_").replace(";", "_") + fallback = " ".join(fallback.split()) + if suffix and not fallback.lower().endswith(suffix.lower()): + fallback = f"{fallback}{suffix}".strip() + fallback = fallback or f"datei{suffix}" + return f"{kind}; filename=\"{fallback}\"; filename*=UTF-8''{quote(name, safe='')}" diff --git a/backend/tests/test_correction_k1_k7.py b/backend/tests/test_correction_k1_k7.py index 317b672..6601057 100644 --- a/backend/tests/test_correction_k1_k7.py +++ b/backend/tests/test_correction_k1_k7.py @@ -104,6 +104,40 @@ def test_parse_mail_keeps_names_html_and_attached_messages(): assert named.attachments[0].data == b"pdf" +def test_an_undecoded_pdf_stays_a_named_pdf(): + import base64 + from app.media.storage import content_disposition + + pdf = b"%PDF-1.4\n1 0 obj\n<<>>\nendobj\ntrailer\n<<>>\n%%EOF\n" + raw = ( + b"Subject: Scan\r\n" + b"MIME-Version: 1.0\r\n" + b"Content-Type: multipart/mixed; boundary=bound\r\n" + b"\r\n" + b"--bound\r\n" + b"Content-Type: text/plain; charset=utf-8\r\n" + b"\r\n" + b"text\r\n" + b"--bound\r\n" + b"Content-Type: application/octet-stream\r\n" + b"Content-Transfer-Encoding: 8bit\r\n" + b"Content-Disposition: attachment; filename=\"scan-7f3a9c\"\r\n" + b"\r\n" + + base64.b64encode(pdf) + b"\r\n" + b"--bound--\r\n" + ) + item = parse_mail(raw).attachments[0] + assert item.data.startswith(b"%PDF") + assert item.media_type == "application/pdf" + assert item.display_name == "scan-7f3a9c.pdf" + header = content_disposition("\u00dcbergabe.pdf", inline=True) + assert header.startswith("inline;") + header.encode("ascii") + assert ".pdf" in header + assert "filename*=UTF-8''" in header + assert "%C3%9Cbergabe.pdf" in header + + class QuotedIMAP: def __init__(self, *args, **kwargs): self.untagged_responses = {} diff --git a/frontend/src/sources/builtin-views.jsx b/frontend/src/sources/builtin-views.jsx index 7551a93..9714762 100644 --- a/frontend/src/sources/builtin-views.jsx +++ b/frontend/src/sources/builtin-views.jsx @@ -1,4 +1,3 @@ -import { DocumentView } from "../pages/DocumentView.jsx"; import { useEffect, useRef, useState } from "react"; import { api, documentToText, downloadMailPart, fetchExternal, fetchMailPart, markDirty, textToDocument } from "../api.js"; import { MailAttachments, MailBody } from "../mail-view.jsx"; @@ -17,6 +16,18 @@ function previewKind(type, filename) { return "other"; } +function isPdfBytes(buffer) { + const sample = new TextDecoder("iso-8859-1").decode(buffer.slice(0, 1024)).trim(); + return sample.startsWith("%PDF"); +} + +function downloadName(file, pdf) { + const name = file?.filename || "anlage"; + if (!pdf || name.toLowerCase().endsWith(".pdf")) return name; + const stem = name.toLowerCase().endsWith(".bin") ? name.slice(0, -4).trim() : name; + return `${stem || "anlage"}.pdf`; +} + export function NoteStage({ element, context, binding, onReload }) { const editor = editors.note; const [text, setText] = useState(() => documentToText(element.document)); @@ -162,19 +173,41 @@ export function MailStage({ element, context, binding, shownDirection }) { }, [element.id, element.external?.source, context?.kind, context?.id]); useEffect(() => { - if (shownIndex === null) return undefined; + if (shownIndex === null) { + setMedia(""); + setPdf(null); + setPages(0); + setPhase("idle"); + if (objectUrl.current) { + URL.revokeObjectURL(objectUrl.current); + objectUrl.current = ""; + } + setBlobUrl(""); + return undefined; + } const file = (letter?.attachments || []).find((item) => item.index === shownIndex); if (!file) return undefined; let alive = true; setPhase("loading"); + setPdf(null); + setPages(0); + setPage(1); + setMedia(""); fetchMailPart(element.id, context, `attachments/${file.index}`).then(async (blob) => { if (!alive) return; - if (objectUrl.current) URL.revokeObjectURL(objectUrl.current); - const url = URL.createObjectURL(blob); - objectUrl.current = url; - setBlobUrl(url); - const kind = previewKind(blob.type || file.content_type, file.filename); + const buffer = await blob.arrayBuffer(); + if (!alive) return; + const declared = previewKind(blob.type || file.content_type, file.filename); + const kind = isPdfBytes(buffer) ? "pdf" : declared; + if (objectUrl.current) { + URL.revokeObjectURL(objectUrl.current); + objectUrl.current = ""; + } + setBlobUrl(""); if (kind === "image") { + const url = URL.createObjectURL(new Blob([buffer], { type: blob.type || file.content_type || "application/octet-stream" })); + objectUrl.current = url; + setBlobUrl(url); setMedia("image"); setPhase("ready"); return; @@ -182,10 +215,9 @@ export function MailStage({ element, context, binding, shownDirection }) { if (kind === "pdf") { setMedia("pdf"); try { - const bytes = await blob.arrayBuffer(); const pdfjs = await import("pdfjs-dist/legacy/build/pdf.mjs"); pdfjs.GlobalWorkerOptions.workerSrc = workerSrc; - const doc = await pdfjs.getDocument({ data: bytes }).promise; + const doc = await pdfjs.getDocument({ data: new Uint8Array(buffer) }).promise; if (!alive) { doc.destroy(); return; @@ -195,16 +227,17 @@ export function MailStage({ element, context, binding, shownDirection }) { setPhase("ready"); } catch (err) { if (!alive) return; - setMedia("pdf-frame"); + setPdf(null); setPhase("ready"); } return; } - setMedia("other"); + setMedia("file"); setPhase("ready"); }).catch((err) => { if (!alive) return; setPhase("ready"); + setMedia(""); setError(err.message || "Die Anlage ist nicht verfügbar."); }); return () => { @@ -243,6 +276,17 @@ export function MailStage({ element, context, binding, shownDirection }) { } } + async function saveAttachment() { + if (!shownFile) return; + setError(""); + const namedPdf = media === "pdf" || (shownFile.content_type || "").toLowerCase().includes("pdf") || (shownFile.filename || "").toLowerCase().endsWith(".pdf"); + try { + await downloadMailPart(element.id, context, `attachments/${shownFile.index}`, downloadName(shownFile, namedPdf)); + } catch (err) { + setError(err.message); + } + } + return (

{directionWord(shownDirection) ? {directionWord(shownDirection)} : null}

@@ -262,8 +306,11 @@ export function MailStage({ element, context, binding, shownDirection }) { {shownFile && phase === "loading" ?

Die Anlage wird geladen …

: null} {media === "image" && blobUrl ? {shownFile?.filename : null} {media === "pdf" && pdf ? : null} - {media === "pdf-frame" && blobUrl ? : null} - {media === "other" && blobUrl && binding?.rights?.download ? Anlage öffnen : null} + {shownFile && phase === "ready" && binding?.rights?.download && (media === "file" || (media === "pdf" && !pdf)) ? ( +

+ +

+ ) : null} {pages > 1 ? (