├── .deepsource.toml ├── .github └── workflows │ ├── python-package.yml │ └── python-publish.yml ├── .gitignore ├── LICENSE ├── README.md ├── receipt_parser ├── __init__.py ├── benchmarks │ ├── README.md │ ├── evaluate.ipynb │ ├── prepare_benchmark.ipynb │ ├── standard.csv │ └── tinkoff_test.csv ├── cat_model.py ├── data │ ├── blacklist.csv │ └── cleaned │ │ ├── all_clean.csv │ │ ├── brands_en.csv │ │ ├── brands_ru.csv │ │ └── products.csv ├── dicts.py ├── finder.py ├── models │ ├── cat_bpe_model.yttm │ └── cat_model.pth ├── normalizer.py ├── notebooks │ └── cat_model.ipynb ├── parsers │ ├── README.md │ ├── magnit.py │ ├── perecrestok.py │ ├── peterochka.py │ └── tinkoff.py └── receipt_parser.py ├── requirements.txt └── setup.py /.deepsource.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/.deepsource.toml -------------------------------------------------------------------------------- /.github/workflows/python-package.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/.github/workflows/python-package.yml -------------------------------------------------------------------------------- /.github/workflows/python-publish.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/.github/workflows/python-publish.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/README.md -------------------------------------------------------------------------------- /receipt_parser/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/receipt_parser/__init__.py -------------------------------------------------------------------------------- /receipt_parser/benchmarks/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/receipt_parser/benchmarks/README.md -------------------------------------------------------------------------------- /receipt_parser/benchmarks/evaluate.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/receipt_parser/benchmarks/evaluate.ipynb -------------------------------------------------------------------------------- /receipt_parser/benchmarks/prepare_benchmark.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/receipt_parser/benchmarks/prepare_benchmark.ipynb -------------------------------------------------------------------------------- /receipt_parser/benchmarks/standard.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/receipt_parser/benchmarks/standard.csv -------------------------------------------------------------------------------- /receipt_parser/benchmarks/tinkoff_test.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/receipt_parser/benchmarks/tinkoff_test.csv -------------------------------------------------------------------------------- /receipt_parser/cat_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/receipt_parser/cat_model.py -------------------------------------------------------------------------------- /receipt_parser/data/blacklist.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/receipt_parser/data/blacklist.csv -------------------------------------------------------------------------------- /receipt_parser/data/cleaned/all_clean.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/receipt_parser/data/cleaned/all_clean.csv -------------------------------------------------------------------------------- /receipt_parser/data/cleaned/brands_en.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/receipt_parser/data/cleaned/brands_en.csv -------------------------------------------------------------------------------- /receipt_parser/data/cleaned/brands_ru.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/receipt_parser/data/cleaned/brands_ru.csv -------------------------------------------------------------------------------- /receipt_parser/data/cleaned/products.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/receipt_parser/data/cleaned/products.csv -------------------------------------------------------------------------------- /receipt_parser/dicts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/receipt_parser/dicts.py -------------------------------------------------------------------------------- /receipt_parser/finder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/receipt_parser/finder.py -------------------------------------------------------------------------------- /receipt_parser/models/cat_bpe_model.yttm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/receipt_parser/models/cat_bpe_model.yttm -------------------------------------------------------------------------------- /receipt_parser/models/cat_model.pth: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/receipt_parser/models/cat_model.pth -------------------------------------------------------------------------------- /receipt_parser/normalizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/receipt_parser/normalizer.py -------------------------------------------------------------------------------- /receipt_parser/notebooks/cat_model.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/receipt_parser/notebooks/cat_model.ipynb -------------------------------------------------------------------------------- /receipt_parser/parsers/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/receipt_parser/parsers/README.md -------------------------------------------------------------------------------- /receipt_parser/parsers/magnit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/receipt_parser/parsers/magnit.py -------------------------------------------------------------------------------- /receipt_parser/parsers/perecrestok.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/receipt_parser/parsers/perecrestok.py -------------------------------------------------------------------------------- /receipt_parser/parsers/peterochka.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/receipt_parser/parsers/peterochka.py -------------------------------------------------------------------------------- /receipt_parser/parsers/tinkoff.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/receipt_parser/parsers/tinkoff.py -------------------------------------------------------------------------------- /receipt_parser/receipt_parser.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/receipt_parser/receipt_parser.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/requirements.txt -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/slgero/receipt_parser/HEAD/setup.py --------------------------------------------------------------------------------