fix: minor improvements

README.md

@@ -17,4 +17,6 @@ This repository presents some practical examples on using HuSpaCy for various te
 
 ## Development
 
-To start the demo: `poetry run python app.py`
+To start the demo: `poetry run python app.py`
+
+If you upgrade dependencies via poetry don't forget to update `requirements.txt` with ` poetry export --without-hashes > requirements.txt`

examples/anon.py

@@ -1,3 +1,5 @@
+from typing import Tuple, List
+
 import gradio as gr
 
 from presidio_analyzer import AnalyzerEngine
@@ -8,7 +10,7 @@ from faker import Faker
 from presidio_anonymizer.entities.engine import OperatorConfig
 
 
-def process(text: str, fake_data: bool) -> str:
+def process(text: str, fake_data: bool) -> Tuple[str, List]:
     configuration = {
         "nlp_engine_name": "spacy",
         "models": [{"lang_code": "hu", "model_name": "hu_core_news_lg", }],
@@ -44,7 +46,7 @@ EXAMPLES = [
 demo = gr.Interface(
     fn=process,
     inputs=[gr.Textbox(value=EXAMPLES[0][0], lines=10, label="Input text", show_label=True),
-            gr.Checkbox(value=EXAMPLES[0][1], label="Use fake data", show_label=True)],
+            gr.Checkbox(value=EXAMPLES[0][1], label="Use fake data", show_label=True),],
     outputs=[gr.Textbox(label="Anonymized text", show_label=True),
              gr.Textbox(label="Tags", show_label=True)],
     examples=EXAMPLES,

examples/common.py

@@ -26,6 +26,7 @@ def _compute_idf(freq_file: Path) -> Dict[str, float]:
 
 
 IDF: Dict[str, float] = _compute_idf(Path(__file__).parent.parent / "resources" / "freq.list")
+
 NEWS_EXAMPLES = [
     """A magyar futballválogatott negyedik Nemzetek Ligája mérkőzésén másodszor nyert, a hazai 1-0-s siker után idegenben 4-0-val megsemmisítette Angliát. Nagy győzelem volt, az enervált angolokat a saját közönségük fütyülte ki, miután a második félidőben el sem találták a kaput. 96 éve nem kaptak ekkora verést az angolok hazai pályán.
 Az angol kapitány, Gareth Southgate kilenc helyen változtatott azon a csapaton, amelyik az olaszok ellen gól nélküli döntetlent játszott szombaton. Marco Rossi a kapuban cserélt, Dibusz Dénes állt a gólvonalon, Schäfer András visszatért a középpályára, miután a németek ellen letöltötte eltiltását. A 3-4-2-1-es felállás ezúttal sem változott. Ha végig akarja nézni helyszíni közvetítésünket, mit műveltek az angolok a Himnusz alatt, itt megteheti.

poetry.lock

@@ -60,8 +60,8 @@ idna = ">=2.8"
 sniffio = ">=1.1"
 
 [package.extras]
-doc = ["packaging", "sphinx-rtd-theme", "sphinx-autodoc-typehints (>=1.2.0)"]
 test = ["coverage[toml] (>=4.5)", "hypothesis (>=4.0)", "pytest (>=7.0)", "pytest-mock (>=3.6.1)", "trustme", "contextlib2", "uvloop (<0.15)", "mock (>=4)", "uvloop (>=0.15)"]
+doc = ["packaging", "sphinx-rtd-theme", "sphinx-autodoc-typehints (>=1.2.0)"]
 trio = ["trio (>=0.16)"]
 
 [[package]]
@@ -92,10 +92,10 @@ optional = false
 python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
 
 [package.extras]
-dev = ["coverage[toml] (>=5.0.2)", "hypothesis", "pympler", "pytest (>=4.3.0)", "six", "mypy", "pytest-mypy-plugins", "zope.interface", "furo", "sphinx", "sphinx-notfound-page", "pre-commit", "cloudpickle"]
 docs = ["furo", "sphinx", "zope.interface", "sphinx-notfound-page"]
 tests = ["coverage[toml] (>=5.0.2)", "hypothesis", "pympler", "pytest (>=4.3.0)", "six", "mypy", "pytest-mypy-plugins", "zope.interface", "cloudpickle"]
 tests_no_zope = ["coverage[toml] (>=5.0.2)", "hypothesis", "pympler", "pytest (>=4.3.0)", "six", "mypy", "pytest-mypy-plugins", "cloudpickle"]
+dev = ["coverage[toml] (>=5.0.2)", "hypothesis", "pympler", "pytest (>=4.3.0)", "six", "mypy", "pytest-mypy-plugins", "zope.interface", "furo", "sphinx", "sphinx-notfound-page", "pre-commit", "cloudpickle"]
 
 [[package]]
 name = "backoff"
@@ -117,8 +117,8 @@ python-versions = ">=3.6"
 cffi = ">=1.1"
 
 [package.extras]
-tests = ["pytest (>=3.2.1,!=3.3.0)"]
 typecheck = ["mypy"]
+tests = ["pytest (>=3.2.1,!=3.3.0)"]
 
 [[package]]
 name = "beautifulsoup4"
@@ -132,8 +132,8 @@ python-versions = ">=3.6.0"
 soupsieve = ">1.2"
 
 [package.extras]
-html5lib = ["html5lib"]
 lxml = ["lxml"]
+html5lib = ["html5lib"]
 
 [[package]]
 name = "blis"
@@ -223,11 +223,11 @@ python-versions = ">=3.6"
 cffi = ">=1.12"
 
 [package.extras]
-docs = ["sphinx (>=1.6.5,!=1.8.0,!=3.1.0,!=3.1.1)", "sphinx-rtd-theme"]
-docstest = ["pyenchant (>=1.6.11)", "twine (>=1.12.0)", "sphinxcontrib-spelling (>=4.0.1)"]
 pep8test = ["black", "flake8", "flake8-import-order", "pep8-naming"]
+docstest = ["pyenchant (>=1.6.11)", "twine (>=1.12.0)", "sphinxcontrib-spelling (>=4.0.1)"]
 sdist = ["setuptools_rust (>=0.11.4)"]
 ssh = ["bcrypt (>=3.1.5)"]
+docs = ["sphinx (>=1.6.5,!=1.8.0,!=3.1.0,!=3.1.1)", "sphinx-rtd-theme"]
 test = ["pytest (>=6.2.0)", "pytest-benchmark", "pytest-cov", "pytest-subtests", "pytest-xdist", "pretend", "iso8601", "pytz", "hypothesis (>=1.11.4,!=3.79.2)"]
 
 [[package]]
@@ -292,10 +292,10 @@ pydantic = ">=1.6.2,<1.7 || >1.7,<1.7.1 || >1.7.1,<1.7.2 || >1.7.2,<1.7.3 || >1.
 starlette = "0.19.1"
 
 [package.extras]
+test = ["pytest (>=6.2.4,<7.0.0)", "pytest-cov (>=2.12.0,<4.0.0)", "mypy (==0.910)", "flake8 (>=3.8.3,<4.0.0)", "black (==22.3.0)", "isort (>=5.0.6,<6.0.0)", "requests (>=2.24.0,<3.0.0)", "httpx (>=0.14.0,<0.19.0)", "email_validator (>=1.1.1,<2.0.0)", "sqlalchemy (>=1.3.18,<1.5.0)", "peewee (>=3.13.3,<4.0.0)", "databases[sqlite] (>=0.3.2,<0.6.0)", "orjson (>=3.2.1,<4.0.0)", "ujson (>=4.0.1,!=4.0.2,!=4.1.0,!=4.2.0,!=4.3.0,!=5.0.0,!=5.1.0,<6.0.0)", "python-multipart (>=0.0.5,<0.0.6)", "flask (>=1.1.2,<3.0.0)", "anyio[trio] (>=3.2.1,<4.0.0)", "types-ujson (==4.2.1)", "types-orjson (==3.6.2)", "types-dataclasses (==0.6.5)"]
+doc = ["mkdocs (>=1.1.2,<2.0.0)", "mkdocs-material (>=8.1.4,<9.0.0)", "mdx-include (>=1.4.1,<2.0.0)", "mkdocs-markdownextradata-plugin (>=0.1.7,<0.3.0)", "typer (>=0.4.1,<0.5.0)", "pyyaml (>=5.3.1,<7.0.0)"]
 all = ["requests (>=2.24.0,<3.0.0)", "jinja2 (>=2.11.2,<4.0.0)", "python-multipart (>=0.0.5,<0.0.6)", "itsdangerous (>=1.1.0,<3.0.0)", "pyyaml (>=5.3.1,<7.0.0)", "ujson (>=4.0.1,!=4.0.2,!=4.1.0,!=4.2.0,!=4.3.0,!=5.0.0,!=5.1.0,<6.0.0)", "orjson (>=3.2.1,<4.0.0)", "email_validator (>=1.1.1,<2.0.0)", "uvicorn[standard] (>=0.12.0,<0.18.0)"]
 dev = ["python-jose[cryptography] (>=3.3.0,<4.0.0)", "passlib[bcrypt] (>=1.7.2,<2.0.0)", "autoflake (>=1.4.0,<2.0.0)", "flake8 (>=3.8.3,<4.0.0)", "uvicorn[standard] (>=0.12.0,<0.18.0)", "pre-commit (>=2.17.0,<3.0.0)"]
-doc = ["mkdocs (>=1.1.2,<2.0.0)", "mkdocs-material (>=8.1.4,<9.0.0)", "mdx-include (>=1.4.1,<2.0.0)", "mkdocs-markdownextradata-plugin (>=0.1.7,<0.3.0)", "typer (>=0.4.1,<0.5.0)", "pyyaml (>=5.3.1,<7.0.0)"]
-test = ["pytest (>=6.2.4,<7.0.0)", "pytest-cov (>=2.12.0,<4.0.0)", "mypy (==0.910)", "flake8 (>=3.8.3,<4.0.0)", "black (==22.3.0)", "isort (>=5.0.6,<6.0.0)", "requests (>=2.24.0,<3.0.0)", "httpx (>=0.14.0,<0.19.0)", "email_validator (>=1.1.1,<2.0.0)", "sqlalchemy (>=1.3.18,<1.5.0)", "peewee (>=3.13.3,<4.0.0)", "databases[sqlite] (>=0.3.2,<0.6.0)", "orjson (>=3.2.1,<4.0.0)", "ujson (>=4.0.1,!=4.0.2,!=4.1.0,!=4.2.0,!=4.3.0,!=5.0.0,!=5.1.0,<6.0.0)", "python-multipart (>=0.0.5,<0.0.6)", "flask (>=1.1.2,<3.0.0)", "anyio[trio] (>=3.2.1,<4.0.0)", "types-ujson (==4.2.1)", "types-orjson (==3.6.2)", "types-dataclasses (==0.6.5)"]
 
 [[package]]
 name = "feedfinder2"
@@ -350,18 +350,18 @@ optional = false
 python-versions = ">=3.7"
 
 [package.extras]
+plot = ["matplotlib"]
 all = ["fs (>=2.2.0,<3)", "lxml (>=4.0,<5)", "zopfli (>=0.1.4)", "lz4 (>=1.7.4.2)", "matplotlib", "sympy", "skia-pathops (>=0.5.0)", "uharfbuzz (>=0.23.0)", "brotlicffi (>=0.8.0)", "scipy", "brotli (>=1.0.1)", "munkres", "unicodedata2 (>=14.0.0)", "xattr"]
-graphite = ["lz4 (>=1.7.4.2)"]
-interpolatable = ["scipy", "munkres"]
 lxml = ["lxml (>=4.0,<5)"]
+interpolatable = ["scipy", "munkres"]
+ufo = ["fs (>=2.2.0,<3)"]
 pathops = ["skia-pathops (>=0.5.0)"]
-plot = ["matplotlib"]
-repacker = ["uharfbuzz (>=0.23.0)"]
+woff = ["zopfli (>=0.1.4)", "brotlicffi (>=0.8.0)", "brotli (>=1.0.1)"]
 symfont = ["sympy"]
-type1 = ["xattr"]
-ufo = ["fs (>=2.2.0,<3)"]
+graphite = ["lz4 (>=1.7.4.2)"]
 unicode = ["unicodedata2 (>=14.0.0)"]
-woff = ["zopfli (>=0.1.4)", "brotlicffi (>=0.8.0)", "brotli (>=1.0.1)"]
+repacker = ["uharfbuzz (>=0.23.0)"]
+type1 = ["xattr"]
 
 [[package]]
 name = "frozenlist"
@@ -371,9 +371,40 @@ category = "main"
 optional = false
 python-versions = ">=3.7"
 
+[[package]]
+name = "fsspec"
+version = "2022.5.0"
+description = "File-system specification"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.extras]
+oci = ["ocifs"]
+hdfs = ["pyarrow (>=1)"]
+entrypoints = ["importlib-metadata"]
+git = ["pygit2"]
+gs = ["gcsfs"]
+s3 = ["s3fs"]
+gui = ["panel"]
+sftp = ["paramiko"]
+github = ["requests"]
+gcs = ["gcsfs"]
+fuse = ["fusepy"]
+tqdm = ["tqdm"]
+ssh = ["paramiko"]
+arrow = ["pyarrow (>=1)"]
+dropbox = ["dropboxdrivefs", "requests", "dropbox"]
+abfs = ["adlfs"]
+http = ["requests", "aiohttp"]
+adl = ["adlfs"]
+libarchive = ["libarchive-c"]
+dask = ["dask", "distributed"]
+smb = ["smbprotocol"]
+
 [[package]]
 name = "gradio"
-version = "3.0.17"
+version = "3.0.18"
 description = "Python library for easily interacting with trained machine learning models"
 category = "main"
 optional = false
@@ -384,6 +415,7 @@ aiohttp = "*"
 analytics-python = "*"
 fastapi = "*"
 ffmpy = "*"
+fsspec = "*"
 Jinja2 = "*"
 markdown-it-py = {version = "*", extras = ["linkify", "plugins"]}
 matplotlib = "*"
@@ -497,10 +529,10 @@ python-versions = ">=3.6"
 uc-micro-py = "*"
 
 [package.extras]
+test = ["coverage", "pytest", "pytest-cov"]
+doc = ["sphinx", "sphinx-book-theme", "myst-parser"]
 benchmark = ["pytest", "pytest-benchmark"]
 dev = ["pre-commit", "isort", "flake8", "black"]
-doc = ["sphinx", "sphinx-book-theme", "myst-parser"]
-test = ["coverage", "pytest", "pytest-cov"]
 
 [[package]]
 name = "lxml"
@@ -511,10 +543,10 @@ optional = false
 python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, != 3.4.*"
 
 [package.extras]
+source = ["Cython (>=0.29.7)"]
 cssselect = ["cssselect (>=0.7)"]
 html5 = ["html5lib"]
 htmlsoup = ["beautifulsoup4"]
-source = ["Cython (>=0.29.7)"]
 
 [[package]]
 name = "markdown-it-py"
@@ -530,14 +562,14 @@ mdit-py-plugins = {version = "*", optional = true, markers = "extra == \"plugins
 mdurl = ">=0.1,<1.0"
 
 [package.extras]
-benchmarking = ["psutil", "pytest", "pytest-benchmark (>=3.2,<4.0)"]
-code_style = ["pre-commit (==2.6)"]
+rtd = ["attrs", "myst-parser", "pyyaml", "sphinx", "sphinx-copybutton", "sphinx-design", "sphinx-book-theme"]
 compare = ["commonmark (>=0.9.1,<0.10.0)", "markdown (>=3.3.6,<3.4.0)", "mistletoe (>=0.8.1,<0.9.0)", "mistune (>=2.0.2,<2.1.0)", "panflute (>=2.1.3,<2.2.0)"]
-linkify = ["linkify-it-py (>=1.0,<2.0)"]
-plugins = ["mdit-py-plugins"]
 profiling = ["gprof2dot"]
-rtd = ["attrs", "myst-parser", "pyyaml", "sphinx", "sphinx-copybutton", "sphinx-design", "sphinx-book-theme"]
+code_style = ["pre-commit (==2.6)"]
 testing = ["coverage", "pytest", "pytest-cov", "pytest-regressions"]
+plugins = ["mdit-py-plugins"]
+linkify = ["linkify-it-py (>=1.0,<2.0)"]
+benchmarking = ["psutil", "pytest", "pytest-benchmark (>=3.2,<4.0)"]
 
 [[package]]
 name = "markupsafe"
@@ -578,8 +610,8 @@ python-versions = "~=3.6"
 markdown-it-py = ">=1.0.0,<3.0.0"
 
 [package.extras]
-code_style = ["pre-commit (==2.6)"]
 rtd = ["myst-parser (>=0.14.0,<0.15.0)", "sphinx-book-theme (>=0.1.0,<0.2.0)"]
+code_style = ["pre-commit (==2.6)"]
 testing = ["coverage", "pytest (>=3.6,<4)", "pytest-cov", "pytest-regressions"]
 
 [[package]]
@@ -624,10 +656,10 @@ python-versions = ">=3.8"
 
 [package.extras]
 default = ["numpy (>=1.19)", "scipy (>=1.8)", "matplotlib (>=3.4)", "pandas (>=1.3)"]
-developer = ["pre-commit (>=2.19)", "mypy (>=0.960)"]
 doc = ["sphinx (>=5)", "pydata-sphinx-theme (>=0.9)", "sphinx-gallery (>=0.10)", "numpydoc (>=1.4)", "pillow (>=9.1)", "nb2plots (>=0.6)", "texext (>=0.6.6)"]
-extra = ["lxml (>=4.6)", "pygraphviz (>=1.9)", "pydot (>=1.4.2)", "sympy (>=1.10)"]
 test = ["pytest (>=7.1)", "pytest-cov (>=3.0)", "codecov (>=2.1)"]
+developer = ["pre-commit (>=2.19)", "mypy (>=0.960)"]
+extra = ["lxml (>=4.6)", "pygraphviz (>=1.9)", "pydot (>=1.4.2)", "sympy (>=1.10)"]
 
 [[package]]
 name = "newspaper3k"
@@ -667,12 +699,12 @@ regex = ">=2021.8.3"
 tqdm = "*"
 
 [package.extras]
-all = ["numpy", "pyparsing", "scipy", "matplotlib", "twython", "requests", "scikit-learn", "python-crfsuite"]
-corenlp = ["requests"]
-machine_learning = ["numpy", "python-crfsuite", "scikit-learn", "scipy"]
 plot = ["matplotlib"]
-tgrep = ["pyparsing"]
+all = ["numpy", "pyparsing", "scipy", "matplotlib", "twython", "requests", "scikit-learn", "python-crfsuite"]
 twitter = ["twython"]
+tgrep = ["pyparsing"]
+machine_learning = ["numpy", "python-crfsuite", "scikit-learn", "scipy"]
+corenlp = ["requests"]
 
 [[package]]
 name = "numpy"
@@ -736,8 +768,8 @@ pynacl = ">=1.0.1"
 six = "*"
 
 [package.extras]
-all = ["pyasn1 (>=0.1.7)", "pynacl (>=1.0.1)", "bcrypt (>=3.1.3)", "invoke (>=1.3)", "gssapi (>=1.4.1)", "pywin32 (>=2.1.8)"]
 ed25519 = ["pynacl (>=1.0.1)", "bcrypt (>=3.1.3)"]
+all = ["pyasn1 (>=0.1.7)", "pynacl (>=1.0.1)", "bcrypt (>=3.1.3)", "invoke (>=1.3)", "gssapi (>=1.4.1)", "pywin32 (>=2.1.8)"]
 gssapi = ["pyasn1 (>=0.1.7)", "gssapi (>=1.4.1)", "pywin32 (>=2.1.8)"]
 invoke = ["invoke (>=1.3)"]
 
@@ -754,10 +786,10 @@ smart-open = ">=5.0.0,<6.0.0"
 typer = ">=0.3.0,<1.0.0"
 
 [package.extras]
-all = ["google-cloud-storage (>=1.26.0,<2.0.0)", "boto3", "pytest", "pytest-coverage", "mock", "typer-cli"]
-gcs = ["google-cloud-storage (>=1.26.0,<2.0.0)"]
 s3 = ["boto3"]
 test = ["pytest", "pytest-coverage", "mock", "typer-cli"]
+all = ["google-cloud-storage (>=1.26.0,<2.0.0)", "boto3", "pytest", "pytest-coverage", "mock", "typer-cli"]
+gcs = ["google-cloud-storage (>=1.26.0,<2.0.0)"]
 
 [[package]]
 name = "phonenumbers"
@@ -891,8 +923,8 @@ optional = false
 python-versions = ">=3.7"
 
 [package.extras]
-doc = ["sphinx", "sphinx-rtd-theme"]
 test = ["pytest", "pytest-cov", "pytest-flake8", "pytest-isort", "coverage"]
+doc = ["sphinx", "sphinx-rtd-theme"]
 
 [[package]]
 name = "python-dateutil"
@@ -955,8 +987,8 @@ idna = ">=2.5,<4"
 urllib3 = ">=1.21.1,<1.27"
 
 [package.extras]
-socks = ["PySocks (>=1.5.6,!=1.5.7)"]
 use_chardet_on_py3 = ["chardet (>=3.0.2,<5)"]
+socks = ["PySocks (>=1.5.6,!=1.5.7)"]
 
 [[package]]
 name = "requests-file"
@@ -985,10 +1017,10 @@ scipy = ">=1.3.2"
 threadpoolctl = ">=2.0.0"
 
 [package.extras]
-benchmark = ["matplotlib (>=3.1.2)", "pandas (>=1.0.5)", "memory-profiler (>=0.57.0)"]
 docs = ["matplotlib (>=3.1.2)", "scikit-image (>=0.14.5)", "pandas (>=1.0.5)", "seaborn (>=0.9.0)", "memory-profiler (>=0.57.0)", "sphinx (>=4.0.1)", "sphinx-gallery (>=0.7.0)", "numpydoc (>=1.2.0)", "Pillow (>=7.1.2)", "sphinx-prompt (>=1.3.0)", "sphinxext-opengraph (>=0.4.2)"]
-examples = ["matplotlib (>=3.1.2)", "scikit-image (>=0.14.5)", "pandas (>=1.0.5)", "seaborn (>=0.9.0)"]
 tests = ["matplotlib (>=3.1.2)", "scikit-image (>=0.14.5)", "pandas (>=1.0.5)", "pytest (>=5.0.1)", "pytest-cov (>=2.9.0)", "flake8 (>=3.8.2)", "black (>=22.3.0)", "mypy (>=0.770)", "pyamg (>=4.0.0)", "numpydoc (>=1.2.0)"]
+benchmark = ["matplotlib (>=3.1.2)", "pandas (>=1.0.5)", "memory-profiler (>=0.57.0)"]
+examples = ["matplotlib (>=3.1.2)", "scikit-image (>=0.14.5)", "pandas (>=1.0.5)", "seaborn (>=0.9.0)"]
 
 [[package]]
 name = "scipy"
@@ -1043,12 +1075,12 @@ python-versions = ">=3.6,<4.0"
 
 [package.extras]
 all = ["boto3", "google-cloud-storage", "azure-storage-blob", "azure-common", "azure-core", "requests"]
-azure = ["azure-storage-blob", "azure-common", "azure-core"]
-gcs = ["google-cloud-storage"]
 http = ["requests"]
 s3 = ["boto3"]
-test = ["boto3", "google-cloud-storage", "azure-storage-blob", "azure-common", "azure-core", "requests", "moto[server] (==1.3.14)", "pathlib2", "responses", "paramiko", "parameterizedtestcase", "pytest", "pytest-rerunfailures"]
 webhdfs = ["requests"]
+azure = ["azure-storage-blob", "azure-common", "azure-core"]
+gcs = ["google-cloud-storage"]
+test = ["boto3", "google-cloud-storage", "azure-storage-blob", "azure-common", "azure-core", "requests", "moto[server] (==1.3.14)", "pathlib2", "responses", "paramiko", "parameterizedtestcase", "pytest", "pytest-rerunfailures"]
 
 [[package]]
 name = "sniffio"
@@ -1096,27 +1128,27 @@ typer = ">=0.3.0,<0.5.0"
 wasabi = ">=0.9.1,<1.1.0"
 
 [package.extras]
+lookups = ["spacy-lookups-data (>=1.0.3,<1.1.0)"]
+transformers = ["spacy-transformers (>=1.1.2,<1.2.0)"]
 apple = ["thinc-apple-ops (>=0.0.4,<1.0.0)"]
-cuda = ["cupy (>=5.0.0b4,<11.0.0)"]
-cuda100 = ["cupy-cuda100 (>=5.0.0b4,<11.0.0)"]
-cuda101 = ["cupy-cuda101 (>=5.0.0b4,<11.0.0)"]
-cuda102 = ["cupy-cuda102 (>=5.0.0b4,<11.0.0)"]
-cuda110 = ["cupy-cuda110 (>=5.0.0b4,<11.0.0)"]
-cuda111 = ["cupy-cuda111 (>=5.0.0b4,<11.0.0)"]
-cuda112 = ["cupy-cuda112 (>=5.0.0b4,<11.0.0)"]
-cuda113 = ["cupy-cuda113 (>=5.0.0b4,<11.0.0)"]
-cuda114 = ["cupy-cuda114 (>=5.0.0b4,<11.0.0)"]
-cuda115 = ["cupy-cuda115 (>=5.0.0b4,<11.0.0)"]
-cuda80 = ["cupy-cuda80 (>=5.0.0b4,<11.0.0)"]
 cuda90 = ["cupy-cuda90 (>=5.0.0b4,<11.0.0)"]
 cuda91 = ["cupy-cuda91 (>=5.0.0b4,<11.0.0)"]
 cuda92 = ["cupy-cuda92 (>=5.0.0b4,<11.0.0)"]
-ja = ["sudachipy (>=0.5.2,!=0.6.1)", "sudachidict-core (>=20211220)"]
+cuda115 = ["cupy-cuda115 (>=5.0.0b4,<11.0.0)"]
 ko = ["natto-py (==0.9.0)"]
-lookups = ["spacy-lookups-data (>=1.0.3,<1.1.0)"]
-ray = ["spacy-ray (>=0.1.0,<1.0.0)"]
+cuda102 = ["cupy-cuda102 (>=5.0.0b4,<11.0.0)"]
+ja = ["sudachipy (>=0.5.2,!=0.6.1)", "sudachidict-core (>=20211220)"]
+cuda112 = ["cupy-cuda112 (>=5.0.0b4,<11.0.0)"]
+cuda113 = ["cupy-cuda113 (>=5.0.0b4,<11.0.0)"]
+cuda110 = ["cupy-cuda110 (>=5.0.0b4,<11.0.0)"]
+cuda111 = ["cupy-cuda111 (>=5.0.0b4,<11.0.0)"]
+cuda101 = ["cupy-cuda101 (>=5.0.0b4,<11.0.0)"]
+cuda100 = ["cupy-cuda100 (>=5.0.0b4,<11.0.0)"]
 th = ["pythainlp (>=2.0)"]
-transformers = ["spacy-transformers (>=1.1.2,<1.2.0)"]
+cuda80 = ["cupy-cuda80 (>=5.0.0b4,<11.0.0)"]
+cuda = ["cupy (>=5.0.0b4,<11.0.0)"]
+cuda114 = ["cupy-cuda114 (>=5.0.0b4,<11.0.0)"]
+ray = ["spacy-ray (>=0.1.0,<1.0.0)"]
 
 [[package]]
 name = "spacy-legacy"
@@ -1187,11 +1219,11 @@ spacy = ">=3.0.0"
 tqdm = ">=4.19.6"
 
 [package.extras]
+viz = ["matplotlib (>=3.0.0)"]
+docs = ["recommonmark (>=0.6.0,<0.7.0)", "sphinx (>=3.0.0,<4.0.0)"]
 build_and_test = ["build", "pytest (>=6.0,<7.0)", "pytest-cov", "twine (>=3.0.0)", "wheel"]
 dev = ["black", "build", "flake8 (>=3.8.0)", "mypy (>=0.900)", "recommonmark (>=0.6.0,<0.7.0)", "sphinx (>=3.0.0,<4.0.0)", "pytest (>=6.0,<7.0)", "pytest-cov", "twine (>=3.0.0)", "wheel"]
-docs = ["recommonmark (>=0.6.0,<0.7.0)", "sphinx (>=3.0.0,<4.0.0)"]
 lint_and_format = ["black", "flake8 (>=3.8.0)", "mypy (>=0.900)"]
-viz = ["matplotlib (>=3.0.0)"]
 
 [[package]]
 name = "thinc"
@@ -1213,24 +1245,24 @@ srsly = ">=2.4.0,<3.0.0"
 wasabi = ">=0.8.1,<1.1.0"
 
 [package.extras]
-cuda = ["cupy (>=5.0.0b4)"]
-cuda100 = ["cupy-cuda100 (>=5.0.0b4)"]
-cuda101 = ["cupy-cuda101 (>=5.0.0b4)"]
-cuda102 = ["cupy-cuda102 (>=5.0.0b4)"]
-cuda110 = ["cupy-cuda110 (>=5.0.0b4)"]
-cuda111 = ["cupy-cuda111 (>=5.0.0b4)"]
+datasets = ["ml-datasets (>=0.2.0,<0.3.0)"]
+mxnet = ["mxnet (>=1.5.1,<1.6.0)"]
+cuda90 = ["cupy-cuda90 (>=5.0.0b4)"]
+cuda91 = ["cupy-cuda91 (>=5.0.0b4)"]
+cuda92 = ["cupy-cuda92 (>=5.0.0b4)"]
+torch = ["torch (>=1.6.0)"]
 cuda112 = ["cupy-cuda112 (>=5.0.0b4)"]
 cuda113 = ["cupy-cuda113 (>=5.0.0b4)"]
-cuda114 = ["cupy-cuda114 (>=5.0.0b4)"]
+cuda110 = ["cupy-cuda110 (>=5.0.0b4)"]
 cuda115 = ["cupy-cuda115 (>=5.0.0b4)"]
+cuda101 = ["cupy-cuda101 (>=5.0.0b4)"]
+cuda = ["cupy (>=5.0.0b4)"]
+cuda114 = ["cupy-cuda114 (>=5.0.0b4)"]
 cuda80 = ["cupy-cuda80 (>=5.0.0b4)"]
-cuda90 = ["cupy-cuda90 (>=5.0.0b4)"]
-cuda91 = ["cupy-cuda91 (>=5.0.0b4)"]
-cuda92 = ["cupy-cuda92 (>=5.0.0b4)"]
-datasets = ["ml-datasets (>=0.2.0,<0.3.0)"]
-mxnet = ["mxnet (>=1.5.1,<1.6.0)"]
 tensorflow = ["tensorflow (>=2.0.0,<2.6.0)"]
-torch = ["torch (>=1.6.0)"]
+cuda111 = ["cupy-cuda111 (>=5.0.0b4)"]
+cuda102 = ["cupy-cuda102 (>=5.0.0b4)"]
+cuda100 = ["cupy-cuda100 (>=5.0.0b4)"]
 
 [[package]]
 name = "threadpoolctl"
@@ -1290,10 +1322,10 @@ python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,>=2.7"
 colorama = {version = "*", markers = "platform_system == \"Windows\""}
 
 [package.extras]
-dev = ["py-make (>=0.1.0)", "twine", "wheel"]
+telegram = ["requests"]
 notebook = ["ipywidgets (>=6)"]
 slack = ["slack-sdk"]
-telegram = ["requests"]
+dev = ["py-make (>=0.1.0)", "twine", "wheel"]
 
 [[package]]
 name = "typer"
@@ -1307,10 +1339,10 @@ python-versions = ">=3.6"
 click = ">=7.1.1,<9.0.0"
 
 [package.extras]
+test = ["shellingham (>=1.3.0,<2.0.0)", "pytest (>=4.4.0,<5.4.0)", "pytest-cov (>=2.10.0,<3.0.0)", "coverage (>=5.2,<6.0)", "pytest-xdist (>=1.32.0,<2.0.0)", "pytest-sugar (>=0.9.4,<0.10.0)", "mypy (==0.910)", "black (>=22.3.0,<23.0.0)", "isort (>=5.0.6,<6.0.0)"]
+doc = ["mkdocs (>=1.1.2,<2.0.0)", "mkdocs-material (>=8.1.4,<9.0.0)", "mdx-include (>=1.4.1,<2.0.0)"]
 all = ["colorama (>=0.4.3,<0.5.0)", "shellingham (>=1.3.0,<2.0.0)"]
 dev = ["autoflake (>=1.3.1,<2.0.0)", "flake8 (>=3.8.3,<4.0.0)"]
-doc = ["mkdocs (>=1.1.2,<2.0.0)", "mkdocs-material (>=8.1.4,<9.0.0)", "mdx-include (>=1.4.1,<2.0.0)"]
-test = ["shellingham (>=1.3.0,<2.0.0)", "pytest (>=4.4.0,<5.4.0)", "pytest-cov (>=2.10.0,<3.0.0)", "coverage (>=5.2,<6.0)", "pytest-xdist (>=1.32.0,<2.0.0)", "pytest-sugar (>=0.9.4,<0.10.0)", "mypy (==0.910)", "black (>=22.3.0,<23.0.0)", "isort (>=5.0.6,<6.0.0)"]
 
 [[package]]
 name = "typing-extensions"
@@ -1383,7 +1415,7 @@ multidict = ">=4.0"
 [metadata]
 lock-version = "1.1"
 python-versions = "~3.8"
-content-hash = "5cd74ccc6f7bed486bb65b9e0c4245a6bf1eb74c0252b1b1f71fe740b6ce6fdd"
+content-hash = "f2bf888b325ef9d3f418a6cdcbd951892aeebf16eff5cbad5fc73088a0b3b36f"
 
 [metadata.files]
 aiohttp = [
@@ -1745,9 +1777,13 @@ frozenlist = [
     {file = "frozenlist-1.3.0-cp39-cp39-win_amd64.whl", hash = "sha256:772965f773757a6026dea111a15e6e2678fbd6216180f82a48a40b27de1ee2ab"},
     {file = "frozenlist-1.3.0.tar.gz", hash = "sha256:ce6f2ba0edb7b0c1d8976565298ad2deba6f8064d2bebb6ffce2ca896eb35b0b"},
 ]
+fsspec = [
+    {file = "fsspec-2022.5.0-py3-none-any.whl", hash = "sha256:2c198c50eb541a80bbd03540b07602c4a957366f3fb416a1f270d34bd4ff0926"},
+    {file = "fsspec-2022.5.0.tar.gz", hash = "sha256:7a5459c75c44e760fbe6a3ccb1f37e81e023cde7da8ba20401258d877ec483b4"},
+]
 gradio = [
-    {file = "gradio-3.0.17-py3-none-any.whl", hash = "sha256:1d3056a9143af291e0a42307c6e7f1d3b3dc88a68d31bfbad6c4888e460e4f0d"},
-    {file = "gradio-3.0.17.tar.gz", hash = "sha256:f3a926f2309d76aefb56cb869dbfee44be68dc5f6f76391a3eeb34c2847bb956"},
+    {file = "gradio-3.0.18-py3-none-any.whl", hash = "sha256:396c92d432defeec2a04b557dc9816989a021617315ad35b8458cab0ea8d0286"},
+    {file = "gradio-3.0.18.tar.gz", hash = "sha256:3e8edaca3dc7ee888a4583d029b5278da0068d341b8c85e1bbebfabdf152ac5d"},
 ]
 h11 = [
     {file = "h11-0.13.0-py3-none-any.whl", hash = "sha256:8ddd78563b633ca55346c8cd41ec0af27d3c79931828beffb46ce70a379e7442"},

pyproject.toml

@@ -11,7 +11,7 @@ textacy = "^0.12.0"
 hu-core-news-lg = {url = "https://huggingface.co/huspacy/hu_core_news_lg/resolve/v3.3.0/hu_core_news_lg-any-py3-none-any.whl"}
 scipy = "~1.8.0"
 newspaper3k = "^0.2.8"
-gradio = "^3.0.11"
+gradio = "^3.0.18"
 Faker = "^13.13.0"
 presidio-analyzer = "^2.2.28"
 presidio-anonymizer = "^2.2.28"
@@ -19,5 +19,5 @@ presidio-anonymizer = "^2.2.28"
 [tool.poetry.dev-dependencies]
 
 [build-system]
-requires = ["poetry-core>=1.0.0"]
+requires = ["poetry-core>=1.0.0", "pip>=22.1.2"]
 build-backend = "poetry.core.masonry.api"

requirements.txt

@@ -1,109 +1,108 @@
-aiohttp==3.8.1
-aiosignal==1.2.0
-analytics-python==1.4.0
-anyio==3.6.1
-asgiref==3.5.2
-async-timeout==4.0.2
-attrs==21.4.0
-backoff==1.10.0
-bcrypt==3.2.2
-beautifulsoup4==4.11.1
-blis==0.7.7
-cachetools==5.2.0
-catalogue==2.0.7
-certifi==2022.5.18.1
-cffi==1.15.0
-charset-normalizer==2.0.12
-charset-normalizer==2.0.12; python_version >= "3"
-click==8.1.3
-colorama==0.4.4; platform_system == "Windows"
-cryptography==37.0.2
-cssselect==1.1.0
-cycler==0.11.0
-cymem==2.0.6
-cytoolz==0.11.2
-fastapi==0.78.0
+aiohttp==3.8.1; python_version >= "3.7"
+aiosignal==1.2.0; python_version >= "3.7"
+analytics-python==1.4.0; python_version >= "3.7"
+anyio==3.6.1; python_full_version >= "3.6.2" and python_version >= "3.7"
+asgiref==3.5.2; python_version >= "3.7"
+async-timeout==4.0.2; python_version >= "3.7"
+attrs==21.4.0; python_version >= "3.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0" and python_version >= "3.7"
+backoff==1.10.0; python_version >= "3.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0" and python_version >= "3.7"
+bcrypt==3.2.2; python_version >= "3.7"
+beautifulsoup4==4.11.1; python_full_version >= "3.6.0"
+blis==0.7.7; python_version >= "3.8"
+cachetools==5.2.0; python_version >= "3.8" and python_version < "4.0"
+catalogue==2.0.7; python_version >= "3.8"
+certifi==2022.6.15; python_version >= "3.8" and python_version < "4"
+cffi==1.15.0; python_version >= "3.7"
+charset-normalizer==2.0.12; python_version >= "3.8" and python_version < "4" and python_full_version >= "3.5.0"
+click==8.1.3; python_version >= "3.8"
+colorama==0.4.5; python_version >= "3.8" and python_full_version < "3.0.0" and platform_system == "Windows" or python_full_version >= "3.5.0" and python_version >= "3.8" and platform_system == "Windows"
+cryptography==37.0.2; python_version >= "3.7"
+cssselect==1.1.0; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.4.0"
+cycler==0.11.0; python_version >= "3.7"
+cymem==2.0.6; python_version >= "3.8"
+cytoolz==0.11.2; python_version >= "3.8"
+faker==13.13.0; python_version >= "3.6"
+fastapi==0.78.0; python_full_version >= "3.6.1" and python_version >= "3.7"
 feedfinder2==0.0.4
-feedparser==6.0.10
-ffmpy==0.3.0
-filelock==3.7.1
-fonttools==4.33.3
-frozenlist==1.3.0
-gradio==3.0.11
-h11==0.13.0
+feedparser==6.0.10; python_version >= "3.6"
+ffmpy==0.3.0; python_version >= "3.7"
+filelock==3.7.1; python_version >= "3.7"
+fonttools==4.33.3; python_version >= "3.7"
+frozenlist==1.3.0; python_version >= "3.7"
+fsspec==2022.5.0; python_version >= "3.7"
+gradio==3.0.18; python_version >= "3.7"
+h11==0.13.0; python_version >= "3.7"
 hu-core-news-lg @ https://huggingface.co/huspacy/hu_core_news_lg/resolve/v3.3.0/hu_core_news_lg-any-py3-none-any.whl
-idna==3.3
-idna==3.3; python_version >= "3"
-jellyfish==0.9.0
+idna==3.3; python_version >= "3.8" and python_version < "4" and python_full_version >= "3.6.2"
+jellyfish==0.9.0; python_version >= "3.8"
 jieba3k==0.35.1
-jinja2==3.1.2
-joblib==1.1.0
-kiwisolver==1.4.2
-langcodes==3.3.0
-linkify-it-py==1.0.3
-lxml==4.9.0
-markdown-it-py==2.1.0
-markupsafe==2.1.1
-matplotlib==3.5.2
-mdit-py-plugins==0.3.0
-mdurl==0.1.1
-monotonic==1.6
-multidict==6.0.2
-murmurhash==1.0.7
-networkx==2.8.2
+jinja2==3.1.2; python_version >= "3.8"
+joblib==1.1.0; python_version >= "3.8"
+kiwisolver==1.4.3; python_version >= "3.7"
+langcodes==3.3.0; python_version >= "3.8"
+linkify-it-py==1.0.3; python_version >= "3.7"
+lxml==4.9.0; python_version >= "2.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0"
+markdown-it-py==2.1.0; python_version >= "3.7" and python_version < "4.0"
+markupsafe==2.1.1; python_version >= "3.8"
+matplotlib==3.5.2; python_version >= "3.7"
+mdit-py-plugins==0.3.0; python_version >= "3.7" and python_version < "4.0"
+mdurl==0.1.1; python_version >= "3.7"
+monotonic==1.6; python_version >= "3.7"
+multidict==6.0.2; python_version >= "3.7"
+murmurhash==1.0.7; python_version >= "3.8"
+networkx==2.8.4; python_version >= "3.8"
 newspaper3k==0.2.8
-nltk==3.7
+nltk==3.7; python_version >= "3.7"
 numpy==1.22.4
-numpy==1.22.4; platform_machine != "aarch64" and platform_machine != "arm64" and python_version < "3.10"
-numpy==1.22.4; platform_machine == "aarch64" and python_version < "3.10"
-numpy==1.22.4; platform_machine == "arm64" and python_version < "3.10"
-orjson==3.7.0
-packaging==21.3
-pandas==1.4.2
-paramiko==2.11.0
-pathy==0.6.1
-pillow==9.1.1
-preshed==3.0.6
-pycparser==2.21
-pycryptodome==3.14.1
-pydantic==1.8.2
-pydub==0.25.1
-pynacl==1.5.0
-pyparsing==3.0.9
-pyphen==0.12.0
-python-dateutil==2.8.2
-python-multipart==0.0.5
-pytz==2022.1
-pyyaml==6.0
-regex==2022.6.2
-requests-file==1.5.1
-requests==2.27.1
-scikit-learn==1.1.1
-scipy==1.8.1
-setuptools-scm==6.4.2
-sgmllib3k==1.0.0
-six==1.16.0
-smart-open==5.2.1
-sniffio==1.2.0
-soupsieve==2.3.2.post1
-spacy-legacy==3.0.9
-spacy-loggers==1.0.2
-spacy==3.3.0
-srsly==2.4.3
-starlette==0.19.1
-textacy==0.12.0
-thinc==8.0.17
-threadpoolctl==3.1.0
+orjson==3.7.2; python_version >= "3.7"
+packaging==21.3; python_version >= "3.8"
+pandas==1.4.2; python_version >= "3.8"
+paramiko==2.11.0; python_version >= "3.7"
+pathy==0.6.1; python_version >= "3.8"
+phonenumbers==8.12.50
+pillow==9.1.1; python_version >= "3.7"
+preshed==3.0.6; python_version >= "3.8"
+presidio-analyzer==2.2.28
+presidio-anonymizer==2.2.28; python_version >= "3.5"
+pycparser==2.21; python_version >= "3.7" and python_full_version < "3.0.0" or python_full_version >= "3.4.0" and python_version >= "3.7"
+pycryptodome==3.14.1; python_version >= "3.7" and python_full_version < "3.0.0" or python_full_version >= "3.5.0" and python_version >= "3.7"
+pydantic==1.8.2; python_full_version >= "3.6.1" and python_version >= "3.8"
+pydub==0.25.1; python_version >= "3.7"
+pynacl==1.5.0; python_version >= "3.7"
+pyparsing==3.0.9; python_full_version >= "3.6.8" and python_version >= "3.8"
+pyphen==0.12.0; python_version >= "3.8"
+python-dateutil==2.8.2; python_version >= "3.8" and python_full_version < "3.0.0" or python_full_version >= "3.3.0" and python_version >= "3.8"
+python-multipart==0.0.5; python_version >= "3.7"
+pytz==2022.1; python_version >= "3.8"
+pyyaml==6.0; python_version >= "3.6"
+regex==2022.6.2; python_version >= "3.7"
+requests-file==1.5.1; python_version >= "3.7"
+requests==2.28.0; python_version >= "3.8" and python_version < "4"
+scikit-learn==1.1.1; python_version >= "3.8"
+scipy==1.8.1; python_version >= "3.8" and python_version < "3.11"
+setuptools-scm==6.4.2; python_version >= "3.7"
+sgmllib3k==1.0.0; python_version >= "3.6"
+six==1.16.0; python_version >= "3.7" and python_full_version < "3.0.0" or python_full_version >= "3.3.0" and python_version >= "3.7"
+smart-open==5.2.1; python_version >= "3.8" and python_version < "4.0"
+sniffio==1.2.0; python_full_version >= "3.6.2" and python_version >= "3.7"
+soupsieve==2.3.2.post1; python_version >= "3.6" and python_full_version >= "3.6.0"
+spacy-legacy==3.0.9; python_version >= "3.8"
+spacy-loggers==1.0.2; python_version >= "3.8"
+spacy==3.3.1; python_version >= "3.8"
+srsly==2.4.3; python_version >= "3.8"
+starlette==0.19.1; python_full_version >= "3.6.1" and python_version >= "3.7"
+textacy==0.12.0; python_version >= "3.8"
+thinc==8.0.17; python_version >= "3.8"
+threadpoolctl==3.1.0; python_version >= "3.8"
 tinysegmenter==0.3
-tldextract==3.3.0
-tomli==2.0.1
-toolz==0.11.2
-tqdm==4.64.0
-typer==0.4.1
-typing-extensions==4.2.0
-typing-extensions==4.2.0; python_version < "3.10"
-uc-micro-py==1.0.1
-urllib3==1.26.9
-uvicorn==0.17.6
-wasabi==0.9.1
-yarl==1.7.2
+tldextract==3.3.0; python_version >= "3.7"
+tomli==2.0.1; python_version >= "3.7"
+toolz==0.11.2; python_version >= "3.8"
+tqdm==4.64.0; python_version >= "3.8" and python_full_version < "3.0.0" or python_full_version >= "3.4.0" and python_version >= "3.8"
+typer==0.4.1; python_version >= "3.8"
+typing-extensions==4.2.0; python_full_version >= "3.6.1" and python_version >= "3.8" and python_version < "3.10"
+uc-micro-py==1.0.1; python_version >= "3.7"
+urllib3==1.26.9; python_version >= "3.8" and python_full_version < "3.0.0" and python_version < "4" or python_full_version >= "3.5.0" and python_version < "4" and python_version >= "3.8"
+uvicorn==0.17.6; python_version >= "3.7"
+wasabi==0.9.1; python_version >= "3.8"
+yarl==1.7.2; python_version >= "3.7"