rehlert/bea-edit
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

name generation improvement

Browse Source
This commit is contained in:
rehlert
2026-06-12 14:40:46 +02:00
parent 0629ca88c9
commit e3518eaed0
1 changed files with 78 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/lib/zip-processing.ts
+78 -45
View File
@@ -1,6 +1,6 @@
import { unzip } from "fflate";
import { unzip } from 'fflate';
export type ZipAttachmentKind = "pdf" | "image";
export type ZipAttachmentKind = 'pdf' | 'image';
export type ZipAttachment = {
name: string;
@@ -10,25 +10,31 @@ export type ZipAttachment = {
};
export type ProcessedZipArchive = {
name: string
attachments: ZipAttachment[]
name: string;
attachments: ZipAttachment[];
};
type XJustizMetadata = {
sender: string;
receiver: string;
documentNames: string[];
};
const IMAGE_EXTENSIONS = new Set([
".avif",
".bmp",
".gif",
".heic",
".jpeg",
".jpg",
".jp2",
".png",
".tif",
".tiff",
".webp",
'.avif',
'.bmp',
'.gif',
'.heic',
'.jpeg',
'.jpg',
'.jp2',
'.png',
'.tif',
'.tiff',
'.webp'
]);
const ZIP_META_FILE_NAME = "xjustiz_nachricht.xml";
const ZIP_META_FILE_NAME = 'xjustiz_nachricht.xml';
const XML_TEXT_DECODER = new TextDecoder();
const unzipArchive = (data: Uint8Array) =>
@@ -43,37 +49,37 @@ const unzipArchive = (data: Uint8Array) =>
});
});
const getBaseName = (path: string) => path.split("/").pop() ?? path;
const getBaseName = (path: string) => path.split('/').pop() ?? path;
const getExtension = (path: string) => {
const baseName = getBaseName(path).toLowerCase();
const lastDotIndex = baseName.lastIndexOf(".");
const lastDotIndex = baseName.lastIndexOf('.');
return lastDotIndex === -1 ? "" : baseName.slice(lastDotIndex);
return lastDotIndex === -1 ? '' : baseName.slice(lastDotIndex);
};
const isPdf = (path: string) => getExtension(path) === ".pdf";
const isPdf = (path: string) => getExtension(path) === '.pdf';
const isImage = (path: string) => IMAGE_EXTENSIONS.has(getExtension(path));
const isZipArchive = (path: string) => getExtension(path) === ".zip";
const isZipArchive = (path: string) => getExtension(path) === '.zip';
const normalizeKey = (value: string) => value.replaceAll("\\", "/").toLowerCase().trim();
const normalizeKey = (value: string) => value.replaceAll('\\', '/').toLowerCase().trim();
const isMacMetadataEntry = (path: string) => {
const normalizedPath = normalizeKey(path);
const baseName = getBaseName(normalizedPath);
return (
normalizedPath.startsWith("__macosx/") ||
normalizedPath.includes("/__macosx/") ||
baseName === ".ds_store" ||
baseName.startsWith("._")
normalizedPath.startsWith('__macosx/') ||
normalizedPath.includes('/__macosx/') ||
baseName === '.ds_store' ||
baseName.startsWith('._')
);
};
const matchesElementName = (element: Element, requestedName: string) => {
const requestedLocalName = requestedName.split(".").pop() ?? requestedName;
const requestedLocalName = requestedName.split('.').pop() ?? requestedName;
return (
element.localName === requestedName ||
@@ -88,7 +94,9 @@ const getDirectChildByLocalName = (element: Element, localName: string) =>
Array.from(element.children).find((child) => matchesElementName(child, localName)) ?? null;
const getFirstDescendantByLocalName = (root: Document | Element, localName: string) =>
Array.from(root.querySelectorAll("*")).find((element) => matchesElementName(element, localName)) ?? null;
Array.from(root.querySelectorAll('*')).find((element) =>
matchesElementName(element, localName)
) ?? null;
const getTextContentByPath = (root: Element, path: string[]) => {
let current: Element | null = root;
@@ -106,37 +114,54 @@ const getTextContentByPath = (root: Element, path: string[]) => {
return textContent ? textContent : null;
};
const getTextContentByLocalName = (root: Document | Element, localName: string) =>
getFirstDescendantByLocalName(root, localName)?.textContent?.trim() ?? null;
const parseXmlDocument = (xmlBytes: Uint8Array) => {
const parser = new DOMParser();
const document = parser.parseFromString(XML_TEXT_DECODER.decode(xmlBytes), "application/xml");
const document = parser.parseFromString(XML_TEXT_DECODER.decode(xmlBytes), 'application/xml');
if (document.querySelector("parsererror")) {
if (document.querySelector('parsererror')) {
return null;
}
return document;
};
const getXJustizDocumentNames = (xmlBytes: Uint8Array) => {
const parseXJustizMetadata = (xmlBytes: Uint8Array): XJustizMetadata | null => {
const document = parseXmlDocument(xmlBytes);
if (!document) {
return [];
return null;
}
const schriftgutobjekte = getFirstDescendantByLocalName(document, "schriftgutobjekte");
const sender = getTextContentByLocalName(document, 'aktenzeichen.absender') ?? '';
const receiver = getTextContentByLocalName(document, 'aktenzeichen.empfaenger') ?? '';
const schriftgutobjekte = getFirstDescendantByLocalName(document, 'schriftgutobjekte');
if (!schriftgutobjekte) {
return [];
return {
sender,
receiver,
documentNames: []
};
}
const dokumentNodes = Array.from(schriftgutobjekte.children).filter((child) =>
matchesElementName(child, "dokument"),
matchesElementName(child, 'dokument')
);
return dokumentNodes
.map((dokument) => getTextContentByPath(dokument, ["xjustiz.fachspezifischeDaten", "datei", "dateiname"]))
const documentNames = dokumentNodes
.map((dokument) =>
getTextContentByPath(dokument, ['xjustiz.fachspezifischeDaten', 'datei', 'dateiname'])
)
.filter((name): name is string => Boolean(name));
return {
sender,
receiver,
documentNames
};
};
const orderAttachmentsByDocumentNames = (attachments: ZipAttachment[], documentNames: string[]) => {
@@ -190,7 +215,10 @@ const orderAttachmentsByDocumentNames = (attachments: ZipAttachment[], documentN
return orderedAttachments;
};
const extractZipEntries = async (archiveBytes: Uint8Array, fallbackName: string): Promise<ProcessedZipArchive[]> => {
const extractZipEntries = async (
archiveBytes: Uint8Array,
_fallbackName: string
): Promise<ProcessedZipArchive[]> => {
const files = await unzipArchive(archiveBytes);
const attachments: ZipAttachment[] = [];
const nestedArchives: ProcessedZipArchive[] = [];
@@ -218,8 +246,8 @@ const extractZipEntries = async (archiveBytes: Uint8Array, fallbackName: string)
attachments.push({
name: baseName,
path,
kind: "pdf",
data,
kind: 'pdf',
data
});
continue;
}
@@ -228,21 +256,26 @@ const extractZipEntries = async (archiveBytes: Uint8Array, fallbackName: string)
attachments.push({
name: baseName,
path,
kind: "image",
data,
kind: 'image',
data
});
}
}
const documentNames = xjustizNachrichtXml ? getXJustizDocumentNames(xjustizNachrichtXml) : [];
const metadata = xjustizNachrichtXml ? parseXJustizMetadata(xjustizNachrichtXml) : null;
const documentNames = metadata?.documentNames ?? [];
const orderedAttachments = orderAttachmentsByDocumentNames(attachments, documentNames);
const archiveName = documentNames[0] ? getBaseName(documentNames[0]) : fallbackName;
const now = new Date();
const date = `${now.getFullYear()}-${String(now.getMonth() + 1).padStart(2, '0')}-${String(now.getDate()).padStart(2, '0')}`;
const archiveName = metadata
? `${date}_${metadata.sender}_${metadata.receiver}.pdf`
: `${date}_unbekannt_unbekannt.pdf`;
const archives: ProcessedZipArchive[] = [];
if (orderedAttachments.length > 0) {
archives.push({
name: archiveName,
attachments: orderedAttachments,
attachments: orderedAttachments
});
}