def records(document_id=None, collection_id=None):
require(request.authz.can_export())
if collection_id is not None:
get_db_collection(collection_id, request.authz.READ)
record_audit(Audit.ACT_COLLECTION, id=collection_id)
elif document_id is not None:
get_db_document(document_id)
record_audit(Audit.ACT_ENTITY, id=document_id)
else:
# no authz on records, this means *full* export.
require(request.authz.is_admin)
records = iter_records(document_id=document_id,
collection_id=collection_id)
return stream_ijson(records)
def file(document_id):
document = get_db_document(document_id)
record_audit(Audit.ACT_ENTITY, id=document_id)
resp = _serve_archive(document.content_hash,
document.safe_file_name,
document.mime_type)
return _resp_canonical(resp, document_id)
def update(document_id):
document = get_db_document(document_id, request.authz.WRITE)
data = parse_request(DocumentUpdateSchema)
document.update(data)
db.session.commit()
update_document(document, shallow=True, sync=get_flag('sync', True))
return view(document_id)
def pdf(document_id):
document = get_db_document(document_id)
if not document.supports_pages:
raise BadRequest("PDF is only available for text documents")
file_name = document.safe_file_name
if document.pdf_version != document.content_hash:
file_name = '%s.pdf' % file_name
return _serve_archive(document.pdf_version, file_name, PDF_MIME)
def update(document_id):
document = get_db_document(document_id, request.authz.WRITE)
data = parse_request(DocumentUpdateSchema)
document.update(data)
db.session.commit()
update_document(document)
update_collection(document.collection)
return view(document_id)
def record(document_id, index):
enable_cache()
document = get_db_document(document_id)
if not document.supports_records:
raise BadRequest("This document does not have records.")
record = DocumentRecord.by_index(document.id, index)
if record is None:
raise NotFound("No such record: %s" % index)
return jsonify(record, schema=RecordSchema)
def records(document_id):
enable_cache()
document = get_db_document(document_id)
if not document.supports_records:
raise BadRequest("This document does not have records.")
result = RecordsQuery.handle(request,
document=document,
schema=RecordSchema)
return jsonify(result)
def record(document_id, index):
enable_cache()
document = get_db_document(document_id)
record_audit(Audit.ACT_ENTITY, id=document_id)
if not document.supports_records:
raise BadRequest("This document does not have records.")
record = DocumentRecord.by_index(document.id, index)
if record is None:
raise NotFound("No such record: %s" % index)
return serialize_data(record, RecordSchema)
def pdf(document_id):
document = get_db_document(document_id)
record_audit(Audit.ACT_ENTITY, id=document_id)
if not document.supports_pages:
raise BadRequest("PDF is only available for text documents")
file_name = document.safe_file_name
if document.pdf_version != document.content_hash:
file_name = '%s.pdf' % file_name
resp = _serve_archive(document.pdf_version, file_name, PDF)
return _resp_canonical(resp, document_id)
def content(document_id):
enable_cache()
document = get_db_document(document_id)
record_audit(Audit.ACT_ENTITY, id=document_id)
return jsonify({
'headers':
document.headers,
'text':
document.body_text,
'html':
sanitize_html(document.body_raw, document.source_url)
})
def view(document_id):
enable_cache()
data = get_index_document(document_id)
document = get_db_document(document_id)
data['headers'] = document.headers
# TODO: should this be it's own API? Probably so, but for that it would
# be unclear if we should JSON wrap it, or serve plain with the correct
# MIME type?
if Document.SCHEMA_HTML in document.model.names:
data['html'] = sanitize_html(document.body_raw, document.source_url)
if Document.SCHEMA_TEXT in document.model.names:
data['text'] = document.body_text
return jsonify(data, schema=CombinedSchema)
def delete(document_id):
document = get_db_document(document_id, request.authz.WRITE)
delete_document(document, sync=True)
return ('', 204)
def delete(document_id):
document = get_db_document(document_id, request.authz.WRITE)
delete_document(document, sync=True)
return ('', 204)
def file(document_id):
document = get_db_document(document_id)
return _serve_archive(document.content_hash, document.safe_file_name,
document.mime_type)
def delete(document_id):
document = get_db_document(document_id, request.authz.WRITE)
delete_document(document)
update_collection(document.collection)
return jsonify({'status': 'ok'}, status=410)
def delete(document_id):
document = get_db_document(document_id, request.authz.WRITE)
delete_document(document)
update_collection(document.collection)
refresh_index(entities_index())
return ('', 204)
def file(document_id):
document = get_db_document(document_id)
resp = _serve_archive(document.content_hash, document.safe_file_name,
document.mime_type)
return _resp_canonical(resp, document_id)