Bi Ci gaban Fassarar Bayanin Banki. Biyan kuɗi ta [RSS] (/changelog/rss.xml) ko kalli majigin GitHub don sanarwar sanarwa.

v0.0.8 — 2026-04-11 (Latest) — "Full Platform"

Multi-currency balance verification — verify_balance_multi_currency() groups by currency, runs Golden Rule per group.
hledger + beancount export — to_hledger() and to_beancount() in bankstatementparser.export.
Bulk directory scanner — scan_and_ingest() scans folder trees, deduplicates across batch.
Account mapping rules — AccountMapper with ordered regex rules from JSON config.
REST API — FastAPI wrapper with /ingest and /health endpoints ([api] extra).

v0.0.7 — 2026-04-08 — "Universal Vision"

Direct Ollama bridge (ollama_direct_completion) — bypasses LiteLLM long-prompt hang.
Strip mode (VisionExtractor.strip_rows=True) — splits dense pages into overlapping bands for small local models.
Recommended vision model changed from llava to minicpm-v.

Dropped Python 3.9 support (now 3.10-3.14).
Enrichment module (Categorizer, EnrichedTransaction, DEFAULT_CATEGORY_SCHEMA).
Interactive review mode with --type review CLI command.
Per-row bounding box extraction (Transaction.source_bbox).

Hybrid PDF pipeline (smart_ingest()) with deterministic/text-LLM/vision-LLM routing.
LLMExtractor for digital PDFs via LiteLLM.
VisionExtractor for scanned PDFs via multimodal vision models.
Golden Rule balance verification (opening + credits - debits == closing).
Idempotent deduplication via transaction_hash (MD5 fingerprint).

Ƙara daidaitaccen fayil ɗin bincike tare daparse_files_parallel()ta amfani da ProcessPoolExecutor.
Ƙara ingantaccen yawo don manyan fayilolin PAIN.001 (50 MB+) tare da ƙayyadaddun ƙwaƙwalwar ajiya.
Haɓaka aiki: Abubuwan da aka samar na CAMT yanzu sun wuce 27,000 tx/s, PAIN.001 ya wuce 52,000 tx/s.
KaraDeduplicatoraji don gano ainihin kwafi da matches da ake zargi tare da makin amincewa.
Karafrom_string()kumafrom_bytes()hanyoyin don tantancewa cikin ƙwaƙwalwar ajiya ba tare da faifai I/O ba.
Karaiter_secure_xml_entries()don amintaccen sarrafa kayan tarihin ZIP.
Ƙarfafa CI tare da aiwatar da matakin aiki.

Ƙara CSV, OFX, QFX, da tallafin parser MT940.
Ƙara tsarin ganowa ta atomatik tare dadetect_statement_format()kumacreate_parser().
Ƙara sabuntawar PII (a kunne ta tsohuwa a cikin CLI da yanayin yawo).
Ƙara mataimakan fitarwa zuwa CSV, JSON, da Excel.
Ƙara goyon bayan Polars DataFrame na zaɓi.
Fadada ɗakin gwaji zuwa gwaje-gwaje 718 tare da ɗaukar hoto 100%.

An ƙara PAIN.001 parser (Pain001Parser) don fayilolin ƙaddamar da canja wurin kuɗi na ISO 20022.
Ƙara CLI interface (python -m bankstatementparser.cli).
Ƙara yanayin yawo tare daparse_streaming().
Ƙara ingantaccen shigarwar da iyakokin girman fayil.

Sakin farko. Bayani: CAMT.053CamtParser) don bayanan banki-da-abokin ciniki na ISO 20022.
Pandas DataFrame fitarwa.
Ƙarfafa tsaro na XML na asali (kariyar XXE, no_network).

Duba cikakken tarihin sadaukarwa akan GitHub.