-
+ {item.tags.map((tag) =>
- {tag} )} +
{item.snippet}
: null} +Vorschau wird geladen …
} +diff --git a/backend/app/api/sources.py b/backend/app/api/sources.py index aa0d4b0..1d5ef83 100644 --- a/backend/app/api/sources.py +++ b/backend/app/api/sources.py @@ -28,6 +28,7 @@ from app.sources import ( list_connectors, owned_connector, paperless_content, + paperless_thumbnail, parse_connector, probe, save_connector, @@ -264,40 +265,55 @@ def _mail_bytes(data: bytes, media_type: str, filename: str, inline: bool = Fals ) +class SearchFilters: + """The query parameters every search route shares. A source answers only those it declares.""" + + def __init__( + self, + mode: str = "", + title: str = "", + correspondent: str = "", + document_type: str = "", + storage_path: str = "", + tag: str = "", + tag_mode: str = "", + document_from: str = "", + document_to: str = "", + added_from: str = "", + added_to: str = "", + asn: str = "", + custom: str = "", + sort: str = "", + cursor: str = "", + ): + self.values = { + "mode": mode, + "title": title, + "correspondent": correspondent, + "document_type": document_type, + "storage_path": storage_path, + "tag": tag, + "tag_mode": tag_mode, + "document_from": document_from, + "document_to": document_to, + "added_from": added_from, + "added_to": added_to, + "asn": asn, + "custom": custom, + "sort": sort, + "cursor": cursor, + } + + @router.get("/api/v1/sources/paperless/documents") def search_paperless( q: str = "", connector_id: UUID | None = None, - title: str = "", - correspondent: str = "", - document_type: str = "", - tag: str = "", - document_from: str = "", - document_to: str = "", - sort: str = "", - cursor: str = "", + filters: SearchFilters = Depends(), principal: Principal = Depends(get_principal), conn: Connection = Depends(get_conn), ): - return _run_search( - "paperless", - conn, - principal.account_id, - q.strip(), - connector_id, - "", - None, - { - "title": title, - "correspondent": correspondent, - "document_type": document_type, - "tag": tag, - "document_from": document_from, - "document_to": document_to, - "sort": sort, - "cursor": cursor, - }, - ) + return _run_search("paperless", conn, principal.account_id, q.strip(), connector_id, "", None, filters.values) @router.get("/api/v1/sources/{kind}/facets") @@ -328,6 +344,17 @@ def preview_paperless_document( ) +@router.get("/api/v1/sources/paperless/documents/{document_id}/thumb") +def thumbnail_paperless_document( + document_id: str, + connector_id: UUID, + principal: Principal = Depends(get_principal), + conn: Connection = Depends(get_conn), +): + data, media = paperless_thumbnail(conn, principal.account_id, document_id, connector_id) + return Response(content=data, media_type=media, headers=_PRIVATE) + + @router.get("/api/v1/sources/imap/mailboxes") def list_mailboxes( connector_id: UUID, @@ -343,39 +370,15 @@ def search_mail( q: str = "", mailbox: str = "", before: int | None = None, - title: str = "", - correspondent: str = "", - document_type: str = "", - tag: str = "", - document_from: str = "", - document_to: str = "", - sort: str = "", - cursor: str = "", uidvalidity: int | None = None, + filters: SearchFilters = Depends(), principal: Principal = Depends(get_principal), conn: Connection = Depends(get_conn), ): if before is not None and before < 1: raise unprocessable("Die Seitenangabe ist ungültig.") return _run_search( - "imap", - conn, - principal.account_id, - q.strip(), - connector_id, - mailbox.strip(), - before, - { - "title": title, - "correspondent": correspondent, - "document_type": document_type, - "tag": tag, - "document_from": document_from, - "document_to": document_to, - "sort": sort, - "cursor": cursor, - }, - uidvalidity, + "imap", conn, principal.account_id, q.strip(), connector_id, mailbox.strip(), before, filters.values, uidvalidity ) @@ -432,12 +435,19 @@ def _connector_parts(body: ConnectorIn, current: dict | None) -> tuple[str, dict _SEARCH_FLAGS = { + "mode": "mode", "title": "title", "correspondent": "correspondent", "document_type": "document_type", + "storage_path": "storage_path", "tag": "tags", + "tag_mode": "tag_mode", "document_from": "document_range", "document_to": "document_range", + "added_from": "added_range", + "added_to": "added_range", + "asn": "asn", + "custom": "custom_fields", "sort": "sort", "cursor": "continuation", } @@ -474,38 +484,13 @@ def search_source( connector_id: UUID | None = None, mailbox: str = "", before: int | None = None, - title: str = "", - correspondent: str = "", - document_type: str = "", - tag: str = "", - document_from: str = "", - document_to: str = "", - sort: str = "", - cursor: str = "", + filters: SearchFilters = Depends(), principal: Principal = Depends(get_principal), conn: Connection = Depends(get_conn), ): if before is not None and before < 1: raise unprocessable("Die Seitenangabe ist ungültig.") - return _run_search( - kind, - conn, - principal.account_id, - q.strip(), - connector_id, - mailbox.strip(), - before, - { - "title": title, - "correspondent": correspondent, - "document_type": document_type, - "tag": tag, - "document_from": document_from, - "document_to": document_to, - "sort": sort, - "cursor": cursor, - }, - ) + return _run_search(kind, conn, principal.account_id, q.strip(), connector_id, mailbox.strip(), before, filters.values) @router.get("/api/v1/sources/{kind}/navigate") diff --git a/backend/app/sourceport.py b/backend/app/sourceport.py index 87d1428..35762ff 100644 --- a/backend/app/sourceport.py +++ b/backend/app/sourceport.py @@ -16,13 +16,20 @@ PAPERLESS_CAPABILITIES = { "edit_metadata": False, "search": { "query": True, + "mode": True, "title": True, "correspondent": True, "document_type": True, + "storage_path": True, "tags": True, + "tag_mode": True, "document_range": True, + "added_range": True, + "asn": True, + "custom_fields": True, "sort": True, "continuation": True, + "result_preview": True, }, } @@ -36,13 +43,20 @@ IMAP_CAPABILITIES = { "edit_metadata": False, "search": { "query": True, + "mode": False, "title": False, "correspondent": False, "document_type": False, + "storage_path": False, "tags": False, + "tag_mode": False, "document_range": False, + "added_range": False, + "asn": False, + "custom_fields": False, "sort": False, "continuation": True, + "result_preview": False, }, } @@ -57,12 +71,19 @@ EDITORS = { } UNSUPPORTED_SEARCH = ( + "mode", "title", "correspondent", "document_type", + "storage_path", "tag", + "tag_mode", "document_from", "document_to", + "added_from", + "added_to", + "asn", + "custom", "sort", "cursor", ) diff --git a/backend/app/sources.py b/backend/app/sources.py index b302840..fc292da 100644 --- a/backend/app/sources.py +++ b/backend/app/sources.py @@ -3,14 +3,18 @@ from __future__ import annotations import base64 +import hashlib import imaplib import json import re import ssl +import threading +import time from dataclasses import dataclass from email.header import decode_header from email.parser import BytesParser from email.utils import parsedate_to_datetime +from html import unescape from pathlib import Path from urllib.error import HTTPError, URLError from urllib.parse import urlencode, urlparse @@ -183,10 +187,24 @@ def _record_probe(conn, connector_id: UUID, ok: bool, detail: str) -> None: ) -def _paperless_choice(value, label: str) -> str | None: +PAPERLESS_PAGE_SIZE = 20 +_PAPERLESS_MODES = { + # Paperless-ngx offers these searches in its own filter bar. The first needs no search index. + "title_content": "title_content", + "title": "title__icontains", + "content": "content__icontains", + "index": "query", +} +_PAPERLESS_TAG_MODES = {"all": "tags__id__all", "any": "tags__id__in", "none": "tags__id__none"} +_PAPERLESS_SORTS = {"created", "-created", "added", "-added", "title", "-title", "score", "-score"} + + +def _paperless_choice(value, label: str, allow_none: bool = False) -> str | None: text = str(value or "").strip() if not text: return None + if allow_none and text == "none": + return text if not text.isdigit() or len(text) > 12: raise unprocessable(f"{label} ist keine Auswahl dieser Instanz.") return text @@ -201,45 +219,166 @@ def _paperless_day(value, label: str) -> str | None: return text -def _paperless_params(query: str, options: dict | None) -> dict: +def _paperless_range(options: dict, prefix: str, field: str, label: str, params: dict) -> None: + start = _paperless_day(options.get(f"{prefix}_from"), f"{label}, von") + end = _paperless_day(options.get(f"{prefix}_to"), f"{label}, bis") + if start and end and start > end: + raise unprocessable(f"{label}: Der Beginn liegt nach dem Ende.") + if start: + params[f"{field}__date__gte"] = start + if end: + params[f"{field}__date__lte"] = end + + +_CUSTOM_KINDS = { + "string": "text", + "url": "text", + "longtext": "text", + "integer": "number", + "float": "number", + "monetary": "number", + "date": "date", + "boolean": "boolean", + "select": "select", +} +_CUSTOM_OPERATORS = { + "text": {"exact", "icontains", "istartswith", "iendswith"}, + "number": {"exact", "gt", "gte", "lt", "lte", "range"}, + "date": {"exact", "gt", "gte", "lt", "lte", "range"}, + "boolean": {"exact"}, + "select": {"exact"}, +} +_CUSTOM_LIMIT = 5 + + +def _custom_number(value, label: str): + text = str(value).strip().replace(",", ".") + try: + number = float(text) + except ValueError as exc: + raise unprocessable(f"{label}: Der Wert ist keine Zahl.") from exc + if number != number or number in (float("inf"), float("-inf")): + raise unprocessable(f"{label}: Der Wert ist keine Zahl.") + return int(number) if "." not in text else number + + +def _custom_value(kind: str, op: str, value, field: dict): + label = field["name"] + if op == "exists": + if not isinstance(value, bool): + raise unprocessable(f"{label}: Gesetzt oder leer ist ungültig.") + return value + if op == "range": + if not isinstance(value, (list, tuple)) or len(value) != 2: + raise unprocessable(f"{label}: Der Bereich braucht Anfang und Ende.") + low, high = (_custom_value(kind, "exact", item, field) for item in value) + if low > high: + raise unprocessable(f"{label}: Der Beginn liegt nach dem Ende.") + return [low, high] + if kind == "text": + text = " ".join(str(value or "").split()) + if not text or len(text) > 200: + raise unprocessable(f"{label}: Der Text fehlt oder ist zu lang.") + return text + if kind == "number": + return _custom_number(value, label) + if kind == "date": + day = _paperless_day(value, label) + if not day: + raise unprocessable(f"{label}: Das Datum fehlt.") + return day + if kind == "boolean": + if not isinstance(value, bool): + raise unprocessable(f"{label}: Ja oder Nein ist ungültig.") + return value + allowed = {option["id"] for option in field.get("options") or []} + if str(value) not in allowed: + raise unprocessable(f"{label}: Das ist keine Auswahl dieses Feldes.") + return str(value) + + +def _paperless_custom_query(raw, fields: list[dict]) -> str | None: + """Paperless-ngx custom_field_query, built only from fields and operators this instance offers.""" + if raw in (None, "", []): + return None + if isinstance(raw, str): + try: + raw = json.loads(raw) + except json.JSONDecodeError as exc: + raise unprocessable("Die Filter der Zusatzfelder sind ungültig.") from exc + if not isinstance(raw, list) or len(raw) > _CUSTOM_LIMIT: + raise unprocessable(f"Es sind höchstens {_CUSTOM_LIMIT} Zusatzfeld-Filter möglich.") + known = {field["id"]: field for field in fields} + atoms = [] + for row in raw: + if not isinstance(row, dict): + raise unprocessable("Die Filter der Zusatzfelder sind ungültig.") + field = known.get(str(row.get("field") or "")) + if field is None: + raise unprocessable("Das Zusatzfeld gibt es an diesem Zugang nicht.") + kind = _CUSTOM_KINDS[field["type"]] + op = str(row.get("op") or "") + if op != "exists" and op not in _CUSTOM_OPERATORS[kind]: + raise unprocessable(f"{field['name']}: Diese Bedingung gibt es für den Feldtyp nicht.") + atoms.append([field["name"], op, _custom_value(kind, op, row.get("value"), field)]) + if not atoms: + return None + return json.dumps(atoms[0] if len(atoms) == 1 else ["AND", atoms], ensure_ascii=False) + + +def _paperless_params(query: str, options: dict | None, custom_fields: list[dict] | None = None) -> dict: """Paperless-ngx document date is the created field, not the upload or modified time.""" options = options or {} - params = {"page_size": "20"} + params = {"page_size": str(PAPERLESS_PAGE_SIZE)} text = " ".join(str(query or "").split()) + mode = str(options.get("mode") or "").strip() or "title_content" + if mode not in _PAPERLESS_MODES: + raise unprocessable("Diese Suchart gibt es nicht.") if text: - params["query"] = text + params[_PAPERLESS_MODES[mode]] = text title = " ".join(str(options.get("title") or "").split()) if title: + if "title__icontains" in params and params["title__icontains"] != title: + raise unprocessable("Die Suche nur im Titel und der Titelfilter sind beide gesetzt. Nutze eines davon.") params["title__icontains"] = title - correspondent = _paperless_choice(options.get("correspondent"), "Der Korrespondent") - if correspondent: - params["correspondent__id"] = correspondent - document_type = _paperless_choice(options.get("document_type"), "Der Dokumenttyp") - if document_type: - params["document_type__id"] = document_type + for name, field, label in ( + ("correspondent", "correspondent", "Der Korrespondent"), + ("document_type", "document_type", "Der Dokumenttyp"), + ("storage_path", "storage_path", "Der Speicherpfad"), + ): + chosen = _paperless_choice(options.get(name), label, allow_none=True) + if chosen == "none": + params[f"{field}__isnull"] = "true" + elif chosen: + params[f"{field}__id"] = chosen raw_tags = options.get("tag") or options.get("tags") or "" if isinstance(raw_tags, (list, tuple)): parts = [str(item) for item in raw_tags] else: parts = str(raw_tags).split(",") tag_ids = [chosen for chosen in (_paperless_choice(part, "Ein Tag") for part in parts) if chosen] + tag_mode = str(options.get("tag_mode") or "").strip() or "all" + if tag_mode not in _PAPERLESS_TAG_MODES: + raise unprocessable("Diese Tag-Verknüpfung gibt es nicht.") if tag_ids: - params["tags__id__all"] = ",".join(tag_ids) - start = _paperless_day(options.get("document_from"), "Das Dokumentdatum von") - end = _paperless_day(options.get("document_to"), "Das Dokumentdatum bis") - if start and end and start > end: - raise unprocessable("Das Dokumentdatum von liegt nach dem Dokumentdatum bis.") - if start: - params["created__date__gte"] = start - if end: - params["created__date__lte"] = end + params[_PAPERLESS_TAG_MODES[tag_mode]] = ",".join(tag_ids) + _paperless_range(options, "document", "created", "Dokumentdatum", params) + _paperless_range(options, "added", "added", "Hinzugefügt am", params) + custom = _paperless_custom_query(options.get("custom"), custom_fields or []) + if custom: + params["custom_field_query"] = custom + asn = str(options.get("asn") or "").strip() + if asn: + if not asn.isdigit() or len(asn) > 10: + raise unprocessable("Die Archivnummer ist keine Zahl.") + params["archive_serial_number"] = asn sort = str(options.get("sort") or "").strip() if sort: - if sort not in {"created", "-created", "title", "-title", "score", "-score"}: + if sort not in _PAPERLESS_SORTS: raise unprocessable("Diese Sortierung gibt es nicht.") if sort in {"score", "-score"}: - if not text: - raise unprocessable("Die Relevanz gilt zusammen mit einem Suchtext.") + if not text or mode != "index": + raise unprocessable("Die Relevanz gilt nur für die Suche im Volltextindex.") # Paperless-ngx 2.20.6 has no ordering field named score. A query without # ordering is the relevance order of the full-text index. else: @@ -276,45 +415,189 @@ def _paperless_row(conn, owner_id: UUID, connector_id: UUID | None): def paperless_documents(conn, owner_id: UUID, query: str, connector_id: UUID | None = None, options: dict | None = None) -> dict: row = _paperless_row(conn, owner_id, connector_id) base = row["settings"]["base_url"].rstrip("/") - params = _paperless_params(query, options) release_for_external(conn) + names = _paperless_lookup(row["id"], base, row["secret"]) + params = _paperless_params(query, options, names["custom_fields"]) payload = _paperless_get(base, row["secret"], "/api/documents/", params) assert_still_owned(conn, row["id"], owner_id) + terms = _search_terms(query, (options or {}).get("title")) items = [] for doc in payload.get("results") or []: created = str(doc.get("created") or "")[:10] + added = str(doc.get("added") or "")[:10] title = (doc.get("title") or doc.get("original_file_name") or f"Dokument {doc.get('id')}").strip() + pages = doc.get("page_count") + asn = doc.get("archive_serial_number") items.append( { "id": str(doc.get("id")), "title": title[:200], "document_on": created if len(created) == 10 else None, - "correspondent": _correspondent(doc), + "added_on": added if len(added) == 10 else None, + "correspondent": _correspondent(doc, names), + "document_type": _named(doc.get("document_type"), names["document_types"]), + "storage_path": _named(doc.get("storage_path"), names["storage_paths"]), + "tags": [name for name in (_named(tag, names["tags"]) for tag in doc.get("tags") or []) if name][:12], + "pages": pages if isinstance(pages, int) and pages > 0 else None, + "asn": asn if isinstance(asn, int) else None, + "snippet": _snippet(doc, terms), "open_url": f"{base}/documents/{doc.get('id')}/", } ) page = int(params.get("page") or 1) count = payload.get("count") if isinstance(count, int): - next_page = str(page + 1) if page * 20 < count else None + next_page = str(page + 1) if page * PAPERLESS_PAGE_SIZE < count else None else: - next_page = str(page + 1) if len(items) == 20 else None - return {"items": items, "connector_id": str(row["id"]), "next_page": next_page, "incomplete": False} + next_page = str(page + 1) if len(items) == PAPERLESS_PAGE_SIZE else None + return { + "items": items, + "connector_id": str(row["id"]), + "next_page": next_page, + "previous_page": str(page - 1) if page > 1 else None, + "total": count if isinstance(count, int) else None, + "incomplete": False, + } def paperless_facets(conn, owner_id: UUID, connector_id: UUID) -> dict: row = _paperless_row(conn, owner_id, connector_id) base = row["settings"]["base_url"].rstrip("/") - token = row["secret"] release_for_external(conn) - body = { + names = _paperless_lookup(row["id"], base, row["secret"]) + assert_still_owned(conn, row["id"], owner_id) + return { + "correspondents": names["correspondents"], + "document_types": names["document_types"], + "storage_paths": names["storage_paths"], + "tags": names["tags"], + "custom_fields": names["custom_fields"], + "tag_mode": "all", + "tag_modes": list(_PAPERLESS_TAG_MODES), + "modes": list(_PAPERLESS_MODES), + } + + +def paperless_thumbnail(conn, owner_id: UUID, document_id: str, connector_id: UUID) -> tuple[bytes, str]: + if not document_id.isdigit() or len(document_id) > 12: + raise unprocessable("Die Paperless-Nummer ist ungültig.") + row = _paperless_row(conn, owner_id, connector_id) + base = row["settings"]["base_url"].rstrip("/") + release_for_external(conn) + fetched = _paperless_file(base, row["secret"], f"/api/documents/{document_id}/thumb/", 2 * 1024 * 1024) + assert_still_owned(conn, row["id"], owner_id) + if fetched is None: + raise not_found() + data, media, _name = fetched + if not media.startswith("image/"): + raise unprocessable("Paperless hat kein Vorschaubild geliefert.") + return data, media + + +_LOOKUP_TTL = 60.0 +_LOOKUP_LIMIT = 32 +_lookup_cache: dict[tuple, tuple[float, dict]] = {} +_lookup_lock = threading.Lock() + + +def _paperless_lookup(connector_id, base: str, token: str) -> dict: + """Names behind the ids of a result list. Bound to the instance and key that asked, kept for a minute.""" + key = (str(connector_id), base, hashlib.sha256(token.encode("utf-8")).hexdigest()) + now = time.monotonic() + with _lookup_lock: + hit = _lookup_cache.get(key) + if hit and now - hit[0] < _LOOKUP_TTL: + return hit[1] + names = { "correspondents": _paperless_names(base, token, "/api/correspondents/"), "document_types": _paperless_names(base, token, "/api/document_types/"), "tags": _paperless_names(base, token, "/api/tags/"), - "tag_mode": "all", + # An instance without storage paths, or a key that may not read them, still searches. + "storage_paths": _paperless_names_or_none(base, token, "/api/storage_paths/"), + "custom_fields": _paperless_custom_fields(base, token), } - assert_still_owned(conn, row["id"], owner_id) - return body + with _lookup_lock: + if len(_lookup_cache) >= _LOOKUP_LIMIT: + _lookup_cache.clear() + _lookup_cache[key] = (now, names) + return names + + +def _paperless_custom_fields(base: str, token: str) -> list[dict]: + """Custom fields the picker can filter on. Types it cannot query, such as document links, are left out.""" + found = [] + try: + for page in range(1, 6): + payload = _paperless_get(base, token, "/api/custom_fields/", {"page": str(page), "page_size": "100"}) + rows = payload.get("results") or [] + for item in rows: + kind = item.get("data_type") + if item.get("id") is None or kind not in _CUSTOM_KINDS: + continue + extra = item.get("extra_data") if isinstance(item.get("extra_data"), dict) else {} + options = [ + {"id": str(option["id"]), "name": str(option.get("label") or option["id"])[:200]} + for option in extra.get("select_options") or [] + if isinstance(option, dict) and option.get("id") is not None + ] + found.append({"id": str(item["id"]), "name": str(item.get("name") or item["id"])[:200], "type": kind, "options": options}) + if len(rows) < 100: + break + except Problem: + return [] + return found + + +def _paperless_names_or_none(base: str, token: str, path: str) -> list[dict]: + try: + return _paperless_names(base, token, path) + except Problem: + return [] + + +def _named(value, entries: list[dict]) -> str | None: + if value is None or isinstance(value, bool): + return None + wanted = str(value) + for entry in entries: + if entry["id"] == wanted: + return entry["name"] + return None + + +_TAG_MARKUP = re.compile(r"<[^>]{0,200}>") +_SNIPPET_LENGTH = 260 + + +def _search_terms(query: str, title) -> list[str]: + words = re.findall(r"[\w-]{3,}", f"{query or ''} {title or ''}".casefold()) + return list(dict.fromkeys(words))[:8] + + +def _snippet(doc: dict, terms: list[str]) -> str | None: + """A short plain-text excerpt: the index hit when Paperless sends one, else the text around the first match.""" + hit = doc.get("__search_hit__") + if isinstance(hit, dict): + lines = hit.get("highlights") + if isinstance(lines, str) and lines.strip(): + text = " ".join(unescape(_TAG_MARKUP.sub("", lines)).split()) + if text: + return text[:_SNIPPET_LENGTH] + content = doc.get("content") + if not isinstance(content, str): + return None + text = " ".join(content.split()) + if not text: + return None + folded = text.casefold() + at = min((index for index in (folded.find(term) for term in terms) if index >= 0), default=-1) + if at < 0: + return text[:_SNIPPET_LENGTH] + ("…" if len(text) > _SNIPPET_LENGTH else "") + first = max(0, at - 60) + if first: + first = text.rfind(" ", 0, first) + 1 or first + last = first + _SNIPPET_LENGTH + return ("…" if first else "") + text[first:last] + ("…" if last < len(text) else "") def _paperless_names(base: str, token: str, path: str) -> list[dict]: @@ -679,10 +962,12 @@ def _paperless_get(base: str, token: str, path: str, params: dict) -> dict: raise unprocessable("Paperless ist nicht erreichbar.") from exc -def _correspondent(doc: dict) -> str | None: +def _correspondent(doc: dict, names: dict | None = None) -> str | None: value = doc.get("correspondent_name") or doc.get("correspondent") if isinstance(value, str) and value.strip(): return value.strip()[:200] + if names is not None: + return _named(value, names["correspondents"]) return None diff --git a/backend/tests/test_connector_basis.py b/backend/tests/test_connector_basis.py index be1b56f..40473cc 100644 --- a/backend/tests/test_connector_basis.py +++ b/backend/tests/test_connector_basis.py @@ -216,7 +216,7 @@ def test_two_paperless_instances_stay_bound_when_order_changes(client, db, monke ) assert filtered["items"][0]["title"] == "Treffer" assert calls[-1][3]["correspondent__id"] == "4" - assert calls[-1][3]["query"] == "Treffer" + assert calls[-1][3]["title_content"] == "Treffer" def test_ambiguous_legacy_stays_until_assignment(client, db, monkeypatch): diff --git a/backend/tests/test_connector_followup.py b/backend/tests/test_connector_followup.py index c536e15..82bbcbd 100644 --- a/backend/tests/test_connector_followup.py +++ b/backend/tests/test_connector_followup.py @@ -355,22 +355,34 @@ def test_paperless_filters_reach_the_api_and_cross_pages(client, db, monkeypatch params={ "connector_id": first["id"], "q": "nurinhalt", + "mode": "index", "title": "Vertrag", "correspondent": "4", "document_type": "8", + "storage_path": "6", "tag": "2,5", + "tag_mode": "any", "document_from": "2024-01-01", "document_to": "2024-12-31", + "added_from": "2024-02-01", + "added_to": "2024-02-28", + "asn": "1042", "sort": "-created", "cursor": "3", }, ) sent = calls[-1]["params"] assert sent["query"] == "nurinhalt" + assert "title_content" not in sent assert sent["title__icontains"] == "Vertrag" assert sent["correspondent__id"] == "4" assert sent["document_type__id"] == "8" - assert sent["tags__id__all"] == "2,5" + assert sent["storage_path__id"] == "6" + assert sent["tags__id__in"] == "2,5" + assert "tags__id__all" not in sent + assert sent["added__date__gte"] == "2024-02-01" + assert sent["added__date__lte"] == "2024-02-28" + assert sent["archive_serial_number"] == "1042" assert sent["created__date__gte"] == "2024-01-01" assert sent["created__date__lte"] == "2024-12-31" assert sent["ordering"] == "-created" @@ -378,9 +390,15 @@ def test_paperless_filters_reach_the_api_and_cross_pages(client, db, monkeypatch ada.request( "GET", "/api/v1/sources/paperless/documents", - params={"connector_id": first["id"], "q": "nurinhalt", "sort": "-score"}, + params={"connector_id": first["id"], "q": "nurinhalt", "mode": "index", "sort": "-score"}, ) assert "ordering" not in calls[-1]["params"] + ada.request( + "GET", + "/api/v1/sources/paperless/documents", + params={"connector_id": first["id"], "q": "nurinhalt", "sort": "-score"}, + status=422, + ) assert found["items"][0]["id"] == "41" assert found["connector_id"] == first["id"] preview = ada.client.get( @@ -431,6 +449,217 @@ def test_paperless_filters_reach_the_api_and_cross_pages(client, db, monkeypatch ) +def test_paperless_default_search_reads_title_and_content_and_shows_a_preview(client, db, monkeypatch): + import app.sources as sources + + calls = [] + body = "Vorspann " * 30 + "Die Kündigung des Mietvertrags erfolgt zum Jahresende. " + "Nachspann " * 30 + + def fake_get(base, token, path, params): + calls.append({"path": path, "params": dict(params)}) + if path == "/api/documents/": + return { + "count": 1, + "results": [ + { + "id": 7, + "title": "Schreiben", + "created": "2024-03-01T00:00:00+01:00", + "added": "2024-03-05T08:00:00Z", + "correspondent": 4, + "document_type": 8, + "storage_path": None, + "tags": [2, 5, 99], + "archive_serial_number": 1042, + "page_count": 3, + "content": body, + } + ], + } + if path == "/api/storage_paths/": + raise sources.unprocessable("Paperless hat die Anfrage nicht beantwortet.") + if path == "/api/tags/": + return {"results": [{"id": 2, "name": "Miete"}, {"id": 5, "name": "Wohnung"}]} + if path == "/api/correspondents/": + return {"results": [{"id": 4, "name": "Hausverwaltung"}]} + return {"results": [{"id": 8, "name": "Brief"}]} + + monkeypatch.setattr(sources, "_paperless_get", fake_get) + ada = Actor(client, "ada-preview@example.test", "Ada Preview") + register(db, ada.email, ada.name) + ada.login() + first = ada.request( + "POST", + "/api/v1/connectors", + json={"kind": "paperless", "name": "Archiv", "base_url": "https://paper.example.test", "token": "token-alpha"}, + status=201, + ) + found = ada.request( + "GET", + "/api/v1/sources/paperless/documents", + params={"connector_id": first["id"], "q": "kündigung", "correspondent": "none", "tag": "2", "tag_mode": "none"}, + ) + sent = [call for call in calls if call["path"] == "/api/documents/"][-1]["params"] + assert sent["title_content"] == "kündigung" + assert "query" not in sent + assert sent["correspondent__isnull"] == "true" + assert sent["tags__id__none"] == "2" + item = found["items"][0] + assert item["correspondent"] == "Hausverwaltung" + assert item["document_type"] == "Brief" + assert item["tags"] == ["Miete", "Wohnung"] + assert item["pages"] == 3 + assert item["asn"] == 1042 + assert item["document_on"] == "2024-03-01" + assert item["added_on"] == "2024-03-05" + assert "Kündigung des Mietvertrags" in item["snippet"] + assert len(item["snippet"]) <= 262 + assert item["snippet"].startswith("…") + assert found["total"] == 1 + assert found["previous_page"] is None + facets = ada.request("GET", "/api/v1/sources/paperless/facets", params={"connector_id": first["id"]}) + assert facets["storage_paths"] == [] + assert facets["tag_modes"] == ["all", "any", "none"] + for params in ( + {"mode": "regex"}, + {"tag_mode": "x"}, + {"asn": "x1"}, + {"storage_path": "a"}, + {"q": "miete", "mode": "title", "title": "vertrag"}, + ): + ada.request( + "GET", + "/api/v1/sources/paperless/documents", + params={"connector_id": first["id"], **params}, + status=422, + ) + + +def test_paperless_custom_field_filters_use_the_instance_fields(client, db, monkeypatch): + import json + + import app.sources as sources + + calls = [] + + def fake_get(base, token, path, params): + calls.append({"path": path, "params": dict(params)}) + if path == "/api/custom_fields/": + return { + "results": [ + {"id": 1, "name": "Rechnungsbetrag", "data_type": "monetary"}, + {"id": 2, "name": "bezahlt_am", "data_type": "date"}, + { + "id": 3, + "name": "Status", + "data_type": "select", + "extra_data": {"select_options": [{"id": "a", "label": "offen"}, {"id": "b", "label": "bezahlt"}]}, + }, + {"id": 4, "name": "Verweis", "data_type": "documentlink"}, + ] + } + if path == "/api/documents/": + return {"count": 0, "results": []} + return {"results": []} + + monkeypatch.setattr(sources, "_paperless_get", fake_get) + ada = Actor(client, "ada-custom@example.test", "Ada Custom") + register(db, ada.email, ada.name) + ada.login() + first = ada.request( + "POST", + "/api/v1/connectors", + json={"kind": "paperless", "name": "Archiv", "base_url": "https://paper.example.test", "token": "token-alpha"}, + status=201, + ) + facets = ada.request("GET", "/api/v1/sources/paperless/facets", params={"connector_id": first["id"]}) + assert [item["name"] for item in facets["custom_fields"]] == ["Rechnungsbetrag", "bezahlt_am", "Status"] + assert facets["custom_fields"][2]["options"] == [{"id": "a", "name": "offen"}, {"id": "b", "name": "bezahlt"}] + + def ask(rows, status=200): + return ada.request( + "GET", + "/api/v1/sources/paperless/documents", + params={"connector_id": first["id"], "custom": json.dumps(rows)}, + status=status, + ) + + ask([{"field": "2", "op": "range", "value": ["2024-01-01", "2024-06-30"]}]) + sent = [call for call in calls if call["path"] == "/api/documents/"][-1]["params"] + assert json.loads(sent["custom_field_query"]) == ["bezahlt_am", "range", ["2024-01-01", "2024-06-30"]] + ask( + [ + {"field": "1", "op": "gte", "value": "100,5"}, + {"field": "3", "op": "exact", "value": "a"}, + {"field": "2", "op": "exists", "value": False}, + ] + ) + sent = [call for call in calls if call["path"] == "/api/documents/"][-1]["params"] + assert json.loads(sent["custom_field_query"]) == [ + "AND", + [["Rechnungsbetrag", "gte", 100.5], ["Status", "exact", "a"], ["bezahlt_am", "exists", False]], + ] + ask([], 200) + assert "custom_field_query" not in [call for call in calls if call["path"] == "/api/documents/"][-1]["params"] + for rows in ( + [{"field": "9", "op": "exact", "value": "x"}], + [{"field": "4", "op": "contains", "value": "1"}], + [{"field": "2", "op": "icontains", "value": "2024"}], + [{"field": "3", "op": "exact", "value": "z"}], + [{"field": "1", "op": "gt", "value": "viel"}], + [{"field": "2", "op": "range", "value": ["2024-06-30", "2024-01-01"]}], + [{"field": "2", "op": "exists", "value": "ja"}], + [{"field": "1", "op": "exact", "value": "1"}] * 6, + ): + ask(rows, 422) + ada.request( + "GET", + "/api/v1/sources/paperless/documents", + params={"connector_id": first["id"], "custom": "kein json"}, + status=422, + ) + + +def test_paperless_thumbnail_is_bound_to_the_owners_instance(client, db, monkeypatch): + import app.sources as sources + + seen = [] + + def fake_file(base, token, path, max_bytes=0): + seen.append((token, path)) + if path.endswith("/9/thumb/"): + return b"RIFFxxxxWEBP", "image/webp", "" + if path.endswith("/8/thumb/"): + return b"
", "text/html", ""
+ return None
+
+ monkeypatch.setattr(sources, "_paperless_file", fake_file)
+ ada = Actor(client, "ada-thumb@example.test", "Ada Thumb")
+ register(db, ada.email, ada.name)
+ ada.login()
+ first = ada.request(
+ "POST",
+ "/api/v1/connectors",
+ json={"kind": "paperless", "name": "Archiv", "base_url": "https://paper.example.test", "token": "token-alpha"},
+ status=201,
+ )
+ url = "/api/v1/sources/paperless/documents/{}/thumb"
+ ok = ada.client.get(url.format(9), params={"connector_id": first["id"]}, headers=_headers(ada))
+ assert ok.status_code == 200
+ assert ok.headers["content-type"] == "image/webp"
+ assert ok.headers["cache-control"] == "private, no-store"
+ assert seen[-1] == ("token-alpha", "/api/documents/9/thumb/")
+ assert ada.client.get(url.format(8), params={"connector_id": first["id"]}, headers=_headers(ada)).status_code == 422
+ assert ada.client.get(url.format(5), params={"connector_id": first["id"]}, headers=_headers(ada)).status_code == 404
+ assert ada.client.get(url.format("x1"), params={"connector_id": first["id"]}, headers=_headers(ada)).status_code == 422
+ ben = Actor(client, "ben-thumb@example.test", "Ben Thumb")
+ register(db, ben.email, ben.name)
+ ben.login()
+ stranger = ben.client.get(url.format(9), params={"connector_id": first["id"]}, headers=_headers(ben))
+ assert stranger.status_code == 404
+ assert len(seen) == 3
+
+
def test_revoked_grant_hides_bytes_fetched_during_the_call(client, db, monkeypatch):
import app.sources as sources
diff --git a/backend/tests/test_correction_k1_k7.py b/backend/tests/test_correction_k1_k7.py
index 6601057..c5e9924 100644
--- a/backend/tests/test_correction_k1_k7.py
+++ b/backend/tests/test_correction_k1_k7.py
@@ -429,7 +429,7 @@ def test_paperless_filters_change_the_hits(client, db, monkeypatch):
return {"count": 1, "results": [{"id": 4, "name": "Haus"}]}
matched = []
for item in catalog:
- query = params.get("query") or ""
+ query = params.get("title_content") or params.get("query") or ""
title = params.get("title__icontains") or ""
if query and query.casefold() not in f"{item['title']} {item['content']}".casefold():
continue
diff --git a/docs/architecture/API_REFERENZ.md b/docs/architecture/API_REFERENZ.md
index 4d67450..9ed1d90 100644
--- a/docs/architecture/API_REFERENZ.md
+++ b/docs/architecture/API_REFERENZ.md
@@ -196,7 +196,10 @@ Legende Spalte „Auth“: **–** öffentlich, **S** gültige Session, **S+R**
| GET | `/api/v1/sources/{kind}/search` | Suche der registrierten Quelle im erklärten Umfang; unbekannte Art und nicht erklärte Filter antworten `422` |
| GET | `/api/v1/sources/{kind}/navigate?connector_id=` | Fachnavigation, wenn die Quelle sie erklärt |
| GET | `/api/v1/sources/{kind}/preview` | Vorschau vor dem Übernehmen, wenn die Quelle sie erklärt |
-| GET | `/api/v1/sources/paperless/documents?q=&connector_id=` | Kompatibilitätshülle der Paperless-Suche; delegiert an dieselbe Suche |
+| GET | `/api/v1/sources/paperless/documents?q=&connector_id=` | Paperless-Suche, 20 Treffer je Seite, `cursor` ist die Seitennummer. `mode`: `title_content` (Standard, Titel und Inhalt ohne Index), `title`, `content`, `index` (Volltextindex von Paperless). Filter: `title`, `correspondent`, `document_type`, `storage_path` (jeweils Nummer oder `none` für „ohne“), `tag` (Nummern, durch Komma) mit `tag_mode` `all` (Standard), `any` oder `none`, `document_from`/`document_to` (Dokumentdatum), `added_from`/`added_to` (Hinzugefügt), `asn`, `custom` (JSON-Liste `[{field, op, value}]`, höchstens 5, alle zugleich; `field` ist die Nummer aus `facets.custom_fields`, `op` je Feldtyp `exact`, `icontains`, `istartswith`, `iendswith`, `gt`, `gte`, `lt`, `lte`, `range` oder `exists`; Dokumentverweis-Felder sind nicht filterbar; wird als `custom_field_query` an Paperless gegeben), `sort` (`created`, `added`, `title`, jeweils mit `-`; `-score` nur bei `mode=index` mit Suchtext). Ein ungültiger Wert antwortet `422`. Je Treffer: `title`, `document_on`, `added_on`, `correspondent`, `document_type`, `storage_path`, `tags` (Namen), `pages`, `asn`, `snippet` (Textauszug, reiner Text) und `open_url`; dazu `total`, `next_page`, `previous_page` |
+| GET | `/api/v1/sources/{kind}/facets?connector_id=` | Auswahllisten der Instanz (Paperless: Korrespondenten, Dokumenttypen, Speicherpfade, Tags, Zusatzfelder mit Typ und Auswahlwerten). Namen und Listen werden je Instanz und Schlüssel eine Minute lang vorgehalten |
+| GET | `/api/v1/sources/paperless/documents/{id}/preview?connector_id=` | Datei zum Ansehen vor dem Übernehmen |
+| GET | `/api/v1/sources/paperless/documents/{id}/thumb?connector_id=` | Vorschaubild der Trefferliste. Läuft über den Server der eigenen Instanz, `private, no-store`; fremde Instanz `404`, Antwort ohne Bild `422` |
| GET | `/api/v1/sources/imap/mailboxes?connector_id=` | IMAP-Fächer |
| GET | `/api/v1/sources/imap/messages?connector_id=&mailbox=&q=&before=` | Nachrichtenliste, 30 je Seite, Fortsetzung über `before` |
| GET | `/api/v1/sources/imap/message?connector_id=&mailbox=&uid=` | Vorschau vor dem Übernehmen |
diff --git a/frontend/src/pages/Cases.jsx b/frontend/src/pages/Cases.jsx
index 3958560..377d477 100644
--- a/frontend/src/pages/Cases.jsx
+++ b/frontend/src/pages/Cases.jsx
@@ -389,7 +389,7 @@ export function CaseDetail() {
{SEARCH_LIMITS.paperless} Die Verbindung richtest du unter Quellen ein. Ausgewählte Belege bleiben erhalten, wenn du weiterblätterst oder neu suchst.
+ {items.length
+ ? `${total !== null ? `${total} Treffer` : "Treffer"}, Seite ${page}`
+ : "Dazu gibt es in Paperless keinen Treffer."}
+ {item.snippet} Vorschau wird geladen … Anlage: {shownFile.filename} Die Anlage wird geladen …
-
- {title}
diff --git a/frontend/src/pages/Sources.jsx b/frontend/src/pages/Sources.jsx
index 87f7aee..bc3e9b7 100644
--- a/frontend/src/pages/Sources.jsx
+++ b/frontend/src/pages/Sources.jsx
@@ -7,7 +7,7 @@ import { NewConnector, useSourceModules } from "../sources/connector-config.jsx"
import { SourceFrame, registerSourceModule } from "../sources/registry.jsx";
const SEARCH_LIMITS = {
- paperless: "Suchtext gilt für Titel und Dokumentinhalt. Zusätzlich gibt es Titel, Korrespondent, Dokumenttyp, Tags, Dokumentdatum und Sortierung.",
+ paperless: "Die Suche läuft in Paperless selbst, über Titel und Inhalt, den Titel allein, den Inhalt allein oder den Volltextindex. Filter nach Korrespondent, Dokumenttyp, Speicherpfad, Tags, Dokumentdatum, Hinzugefügt-Datum und Archivnummer grenzen sie ein.",
imap: "Die Suche gilt für das ganze gewählte Fach, auch über die erste Seite hinaus. Betreff, Absender und Nachrichtentext werden auf dem Server geprüft.",
};
import { formatDate } from "./content.jsx";
@@ -69,25 +69,228 @@ function paperlessLabel(item) {
return dated !== "Ohne Datum" ? `${dated} · ${item.title}` : item.title;
}
+function paperlessFacts(item) {
+ return [
+ formatDate(item.document_on) !== "Ohne Datum" ? formatDate(item.document_on) : "",
+ item.correspondent,
+ item.document_type,
+ item.pages ? `${item.pages} ${item.pages === 1 ? "Seite" : "Seiten"}` : "",
+ item.asn ? `ASN ${item.asn}` : "",
+ ].filter(Boolean);
+}
+
+const PAPERLESS_MODES = [
+ ["title_content", "Titel und Inhalt"],
+ ["title", "Nur Titel"],
+ ["content", "Nur Inhalt"],
+ ["index", "Volltextindex"],
+];
+
+const PAPERLESS_MODE_HINTS = {
+ title_content: "Sucht den Text im Titel und im erkannten Inhalt, wie „Titel & Inhalt“ in Paperless.",
+ title: "Sucht den Text nur im Titel.",
+ content: "Sucht den Text nur im erkannten Inhalt der Dokumente.",
+ index: "Der Volltextindex von Paperless findet ganze Wörter, auch mit AND, OR und Anführungszeichen, und ordnet nach Relevanz. Ein neues Dokument erscheint erst, wenn Paperless es indexiert hat.",
+};
+
+const NO_FACETS = { correspondents: [], document_types: [], storage_paths: [], tags: [], custom_fields: [] };
+
const EMPTY_FILTERS = {
query: "",
+ mode: "title_content",
title: "",
correspondent: "",
documentType: "",
+ storagePath: "",
tags: [],
+ tagMode: "all",
documentFrom: "",
documentTo: "",
+ addedFrom: "",
+ addedTo: "",
+ asn: "",
+ custom: [],
sort: "-created",
};
+function activeFilterCount(filters) {
+ return [
+ filters.title.trim(),
+ filters.correspondent,
+ filters.documentType,
+ filters.storagePath,
+ filters.tags.length ? "tags" : "",
+ filters.documentFrom,
+ filters.documentTo,
+ filters.addedFrom,
+ filters.addedTo,
+ filters.asn.trim(),
+ ].filter(Boolean).length + customPayload(filters.custom).length;
+}
+
+const CUSTOM_KINDS = {
+ string: "text",
+ url: "text",
+ longtext: "text",
+ integer: "number",
+ float: "number",
+ monetary: "number",
+ date: "date",
+ boolean: "boolean",
+ select: "select",
+};
+
+const CUSTOM_OPERATORS = {
+ text: [["icontains", "enthält"], ["exact", "ist gleich"], ["istartswith", "beginnt mit"], ["iendswith", "endet mit"]],
+ number: [["exact", "gleich"], ["gte", "mindestens"], ["lte", "höchstens"], ["gt", "größer als"], ["lt", "kleiner als"], ["range", "zwischen"]],
+ date: [["exact", "am"], ["gte", "ab"], ["lte", "bis"], ["gt", "nach"], ["lt", "vor"], ["range", "zwischen"]],
+ boolean: [["exact", "ist"]],
+ select: [["exact", "ist"]],
+};
+
+const CUSTOM_PRESENCE = [["set", "hat einen Wert"], ["unset", "ist leer"]];
+const CUSTOM_LIMIT = 5;
+
+function customKind(field) {
+ return CUSTOM_KINDS[field?.type] || "text";
+}
+
+// Only rows that are complete go to the server. An empty row is a row not filled in yet.
+function customPayload(rows) {
+ const payload = [];
+ for (const row of rows) {
+ if (!row.field) continue;
+ if (row.op === "set" || row.op === "unset") {
+ payload.push({ field: row.field, op: "exists", value: row.op === "set" });
+ } else if (row.op === "range") {
+ if (row.value && row.value2) payload.push({ field: row.field, op: "range", value: [row.value, row.value2] });
+ } else if (row.kind === "boolean") {
+ payload.push({ field: row.field, op: "exact", value: row.value !== "false" });
+ } else if (String(row.value).trim()) {
+ payload.push({ field: row.field, op: row.op, value: String(row.value).trim() });
+ }
+ }
+ return payload;
+}
+
+function CustomFieldFilters({ fields, rows, onChange }) {
+ if (!fields.length) return null;
+ const byId = new Map(fields.map((item) => [item.id, item]));
+
+ function update(key, patch) {
+ onChange(rows.map((row) => (row.key === key ? { ...row, ...patch } : row)));
+ }
+
+ function choose(key, id) {
+ const field = byId.get(id);
+ const kind = customKind(field);
+ const first = field ? CUSTOM_OPERATORS[kind][0][0] : "";
+ update(key, { field: id, kind, op: first, value: kind === "boolean" ? "true" : "", value2: "" });
+ }
+
+ function add() {
+ onChange([...rows, { key: `${Date.now()}-${rows.length}`, field: "", kind: "text", op: "", value: "", value2: "" }]);
+ }
+
+ return (
+
+ );
+}
+
+// The thumbnail comes through the server like every other Paperless call, so the key stays there.
+function PaperlessThumb({ connectorId, id }) {
+ const [url, setUrl] = useState("");
+ const [failed, setFailed] = useState(false);
+
+ useEffect(() => {
+ let alive = true;
+ let made = "";
+ setUrl("");
+ setFailed(false);
+ fetchBlob(`/api/v1/sources/paperless/documents/${id}/thumb?connector_id=${connectorId}`)
+ .then((blob) => {
+ if (!alive) return;
+ made = URL.createObjectURL(blob);
+ setUrl(made);
+ })
+ .catch(() => {
+ if (alive) setFailed(true);
+ });
+ return () => {
+ alive = false;
+ if (made) URL.revokeObjectURL(made);
+ };
+ }, [connectorId, id]);
+
+ if (url) return ;
+ return ;
+}
+
export function PaperlessPicker({ context, placement, chapterId = "", chapterTitle = "", targetLabel = "", onDone, onInserted }) {
const [filters, setFilters] = useState(EMPTY_FILTERS);
const [items, setItems] = useState([]);
const [connectors, setConnectors] = useState([]);
const [connectorId, setConnectorId] = useState("");
- const [facets, setFacets] = useState({ correspondents: [], document_types: [], tags: [] });
+ const [facets, setFacets] = useState(NO_FACETS);
+ const [page, setPage] = useState(1);
const [nextPage, setNextPage] = useState(null);
+ const [previousPage, setPreviousPage] = useState(null);
+ const [total, setTotal] = useState(null);
+ const [searched, setSearched] = useState(false);
const [picked, setPicked] = useState(() => new Map());
+ const [previewKey, setPreviewKey] = useState("");
const [previewUrl, setPreviewUrl] = useState("");
const [pending, setPending] = useState(false);
const [error, setError] = useState("");
@@ -107,7 +310,7 @@ export function PaperlessPicker({ context, placement, chapterId = "", chapterTit
useEffect(() => {
if (!connectorId) {
- setFacets({ correspondents: [], document_types: [], tags: [] });
+ setFacets(NO_FACETS);
return undefined;
}
const token = facetRef.current + 1;
@@ -115,7 +318,7 @@ export function PaperlessPicker({ context, placement, chapterId = "", chapterTit
let alive = true;
api(`/api/v1/sources/paperless/facets?connector_id=${connectorId}`)
.then((data) => {
- if (alive && token === facetRef.current) setFacets(data);
+ if (alive && token === facetRef.current) setFacets({ ...NO_FACETS, ...data });
})
.catch((err) => {
if (alive && token === facetRef.current) setError(err.message);
@@ -129,32 +332,51 @@ export function PaperlessPicker({ context, placement, chapterId = "", chapterTit
if (previewUrl) URL.revokeObjectURL(previewUrl);
}, [previewUrl]);
- function paramsFor(page) {
+ function paramsFor(pageNumber) {
const params = new URLSearchParams();
+ const text = filters.query.trim();
if (connectorId) params.set("connector_id", connectorId);
- if (filters.query.trim()) params.set("q", filters.query.trim());
- if (filters.title.trim()) params.set("title", filters.title.trim());
+ if (text) params.set("q", text);
+ if (text && filters.mode !== "title_content") params.set("mode", filters.mode);
+ // The search text already is the title in this mode.
+ if (filters.title.trim() && !(text && filters.mode === "title")) params.set("title", filters.title.trim());
if (filters.correspondent) params.set("correspondent", filters.correspondent);
if (filters.documentType) params.set("document_type", filters.documentType);
- if (filters.tags.length) params.set("tag", filters.tags.join(","));
+ if (filters.storagePath) params.set("storage_path", filters.storagePath);
+ if (filters.tags.length) {
+ params.set("tag", filters.tags.join(","));
+ if (filters.tagMode !== "all") params.set("tag_mode", filters.tagMode);
+ }
if (filters.documentFrom) params.set("document_from", filters.documentFrom);
if (filters.documentTo) params.set("document_to", filters.documentTo);
+ if (filters.addedFrom) params.set("added_from", filters.addedFrom);
+ if (filters.addedTo) params.set("added_to", filters.addedTo);
+ if (filters.asn.trim()) params.set("asn", filters.asn.trim());
+ const custom = customPayload(filters.custom);
+ if (custom.length) params.set("custom", JSON.stringify(custom));
if (filters.sort === "-score") {
- if (filters.query.trim()) params.set("sort", "-score");
+ if (text && filters.mode === "index") params.set("sort", "-score");
} else if (filters.sort) {
params.set("sort", filters.sort);
}
- if (page) params.set("cursor", String(page));
+ if (pageNumber) params.set("cursor", String(pageNumber));
return params;
}
+ function closePreview() {
+ previewRef.current += 1;
+ if (previewUrl) URL.revokeObjectURL(previewUrl);
+ setPreviewUrl("");
+ setPreviewKey("");
+ }
+
function invalidate() {
searchRef.current += 1;
previewRef.current += 1;
facetRef.current += 1;
}
- async function runSearch(event, page = "") {
+ async function runSearch(event, wanted = "") {
event?.preventDefault();
setError("");
if (connectors.length > 1 && !connectorId) {
@@ -165,10 +387,15 @@ export function PaperlessPicker({ context, placement, chapterId = "", chapterTit
searchRef.current = token;
const asked = connectorId;
try {
- const data = await api(`/api/v1/sources/paperless/documents?${paramsFor(page)}`);
+ const data = await api(`/api/v1/sources/paperless/documents?${paramsFor(wanted)}`);
if (token !== searchRef.current) return;
+ closePreview();
setItems(data.items || []);
+ setPage(Number(wanted) || 1);
setNextPage(data.next_page || data.continuation || null);
+ setPreviousPage(data.previous_page || null);
+ setTotal(typeof data.total === "number" ? data.total : null);
+ setSearched(true);
if (!asked && data.connector_id) setConnectorId(data.connector_id);
} catch (err) {
if (token !== searchRef.current) return;
@@ -177,9 +404,15 @@ export function PaperlessPicker({ context, placement, chapterId = "", chapterTit
}
function resetFilters() {
+ invalidate();
+ closePreview();
setFilters(EMPTY_FILTERS);
setItems([]);
setNextPage(null);
+ setPreviousPage(null);
+ setTotal(null);
+ setSearched(false);
+ setPage(1);
}
function toggle(item) {
@@ -195,17 +428,23 @@ export function PaperlessPicker({ context, placement, chapterId = "", chapterTit
async function preview(item) {
setError("");
- if (previewUrl) URL.revokeObjectURL(previewUrl);
- setPreviewUrl("");
+ const bound = item.connector_id || connectorId;
+ const key = `${bound}:${item.id}`;
+ if (key === previewKey) {
+ closePreview();
+ return;
+ }
+ closePreview();
const token = previewRef.current + 1;
previewRef.current = token;
- const bound = item.connector_id || connectorId;
+ setPreviewKey(key);
try {
const blob = await fetchBlob(`/api/v1/sources/paperless/documents/${item.id}/preview?connector_id=${bound}`);
if (token !== previewRef.current) return;
setPreviewUrl(URL.createObjectURL(blob));
} catch (err) {
if (token !== previewRef.current) return;
+ setPreviewKey("");
setError(err.message);
}
}
@@ -262,6 +501,10 @@ export function PaperlessPicker({ context, placement, chapterId = "", chapterTit
setFilters((current) => ({ ...current, [name]: value }));
}
+ function setMode(mode) {
+ setFilters((current) => ({ ...current, mode, sort: current.sort === "-score" && mode !== "index" ? "-created" : current.sort }));
+ }
+
function toggleTag(id) {
setFilters((current) => {
const tags = current.tags.includes(id) ? current.tags.filter((item) => item !== id) : [...current.tags, id];
@@ -270,21 +513,38 @@ export function PaperlessPicker({ context, placement, chapterId = "", chapterTit
}
const held = [...picked.values()].filter((item) => !items.some((entry) => `${connectorId}:${entry.id}` === `${item.connector_id}:${item.id}`));
+ const active = activeFilterCount(filters);
+ const relevance = filters.mode === "index" && filters.query.trim() !== "";
+
+ function choiceSelect(name, value, entries, empty) {
+ return (
+
+ );
+ }
return (
+ {item.tags.map((tag) =>
+ ) : null}
+ {item.snippet ? : null}
- {media === "pdf" && pdf ? : null}
- {shownFile && phase === "ready" && binding?.rights?.download && (media === "file" || (media === "pdf" && !pdf)) ? (
-