3fiddlZddlZddlmZmZmZmZmZmZddl m Z ddl m Z ejeZGdde Zy)N) AsyncIteratorDictIteratorListOptionalSequence)Document) BaseLoaderceZdZdZddddddedededeed eeed eeed ed dfd Z d e e fdZ d e e fdZd ee fdZd e e fdZded e fdZd eefdZ ddedeeded efdZy) MongodbLoaderzLoad MongoDB documents.NT)filter_criteria field_namesmetadata_names!include_db_collection_in_metadataconnection_stringdb_namecollection_namer rrrreturnc ddlm}|s td|s td|s td|||_||_||_|xsg|_|xsi|_|xsg|_ ||_ |jj||_ |jj||_y#t$r} td| d} ~ wwxYw)a Initializes the MongoDB loader with necessary database connection details and configurations. Args: connection_string (str): MongoDB connection URI. db_name (str):Name of the database to connect to. collection_name (str): Name of the collection to fetch documents from. filter_criteria (Optional[Dict]): MongoDB filter criteria for querying documents. field_names (Optional[Sequence[str]]): List of field names to retrieve from documents. metadata_names (Optional[Sequence[str]]): Additional metadata fields to extract from documents. include_db_collection_in_metadata (bool): Flag to include database and collection names in metadata. Raises: ImportError: If the motor library is not installed. ValueError: If any necessary argument is missing. r)AsyncIOMotorClientzBCannot import from motor, please install with `pip install motor`.Nz#connection_string must be provided.zdb_name must be provided.z!collection_name must be provided.)motor.motor_asyncior ImportError ValueErrorclientrrrr rr get_databasedbget_collection collection) selfrrrr rrrres j/var/www/auto_recruiter/arenv/lib/python3.12/site-packages/langchain_community/document_loaders/mongodb.py__init__zMongodbLoader.__init__s@  > !BC C89 9@A A():;  .&,".4",21R.++**73''00A/ T  sB33 C < CC cHtj|jS)aLoad data into Document objects. Attention: This implementation starts an asyncio event loop which will only work if running in a sync env. In an async env, it should fail since there is already an event loop running. This code should be updated to kick off the event loop from a separate thread if running within an async context. )asynciorunaload)rs r!loadzMongodbLoader.loadJs{{4::<((c#.K tj}|j } |j |j}|%#t$r,tj}tj|YjwxYw#t$rYywxYww)aA lazy loader for MongoDB documents. Attention: This implementation starts an asyncio event loop which will only work if running in a sync env. In an async env, it should fail since there is already an event loop running. This code should be updated to kick off the event loop from a separate thread if running within an async context. Yields: Document: A document from the MongoDB collection. N) r$get_running_loop RuntimeErrornew_event_loopset_event_loop alazy_loadrun_until_complete __anext__StopAsyncIteration)r event_loopasync_generatordocuments r! lazy_loadzMongodbLoader.lazy_loadXs / 113J //+ %889R9R9TU  / //1J  " ": . /&  sJBAB#B B2BBBB BBBBcK|j}|jj|j|23d{}|j |76yw)zAsynchronously yields Document objects one at a time. Yields: Document: A document from the MongoDB collection. N)_construct_projectionrfindr _process_document)r projectiondocs r!r.zMongodbLoader.alazy_loadvsV //1 --d.B.BJO . .#((- - .Os&7AAAAAAAcKg}|jj|jd{}|j}|jj |j|23d{}|j |j |*7d7'6t||k7r%tjdt|d|d|Sw)z0Asynchronously loads data into Document objects.Nz6Only partial collection of documents returned. Loaded z docs, expected .) rcount_documentsr r7r8appendr9lenloggerwarning)rresult total_docsr:r;s r!r&zMongodbLoader.aloads??::4;O;OPP //1 --d.B.BJO 7 7# MM$005 6 Q 7O v;* $ NNf+&6zl!E   s3+C B:C (B,B-B0#C B6C r;c|j||jd}|jr(|j|j|j d|j V|j||j d}|jDcgc] }t|}}dj|}n t|}t||Scc}w)zProcess a single MongoDB document into a Document object. Args: doc: The MongoDB document dictionary to process into a Document object. )default)databaser ) page_contentmetadata) _extract_fieldsrrupdaterrrvaluesstrjoinr )rr;rKfieldsvaluetextstexts r!r9zMongodbLoader._process_documents ''T-@-@"'M  1 1 OO $ "&"6"6     '))#t/?/?)LF-3]]_=ESZ=E=88E?Ds8DTH== >sC ct|jxsg}t|jxsg}||z}|r|Dcic]}|dc}SdScc}w)zuConstructs the projection dictionary for MongoDB query based on the specified field names and metadata names.N)listrr)rrr all_fieldsfields r!r7z#MongodbLoader._construct_projectionsW4++,2 d1128b >1 5?j1Uq1ITI1s A r4rQrGci}|xsgD]J}|}|jdD]}|j||}||k(sn|jdd}|||<L|S)zAExtracts and returns values for specified fields from a document.r=_)splitgetreplace) rr4rQrG extractedrYrRkeynew_field_names r!rLzMongodbLoader._extract_fieldssx \r .EE{{3'  #w/G# #]]34N(-In % .r()rF)__name__ __module__ __qualname____doc__rOrrrboolr"rr r'rr5rr.r&r9r7rLr(r!r r s!!+//326269B9B9B 9B "$ 9Bhsm,9B!#/9B,09B 9Bv )d8n )8H-< .-"9 .T(^$>T>h>6Jx~J     r(r )r$loggingtypingrrrrrrlangchain_core.documentsr )langchain_community.document_loaders.baser getLoggerrbrAr rgr(r!rms7JJ-@   8 $zJzr(