Initial pull

.github/workflows/ci.yml

@@ -1,9 +1,21 @@
 name: CI
 
 on:
+  workflow_dispatch:
+    inputs:
+      logLevel:
+        description: 'Log level'
+        required: true
+        default: 'warning'
+        type: choice
+        options:
+        - info
+        - warning
+        - debug
   push:
     branches:
       - develop
+      - dev
       - release
   pull_request:
     branches:
@@ -15,26 +27,39 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python: ["3.8", "3.9"]
+        python: ["3.8", "3.9", "3.10", "3.11", "3.12"]
         os: [ubuntu-latest, macos-latest, windows-latest]
-        include:
-          - os: ubuntu-latest
-            install_graphviz:
-              sudo apt install graphviz graphviz-dev
-          - os: macos-latest
-            install_graphviz: brew install graphviz
-          - os: windows-latest
-            install_graphviz:
-              choco install graphviz --version=2.48.0;
-              poetry run pip install --global-option=build_ext --global-option="-IC:\Program Files\Graphviz\include" --global-option="-LC:\Program Files\Graphviz\lib" pygraphviz;
     runs-on: ${{ matrix.os }}
     steps:
-      - uses: actions/checkout@v2
+      - name: Checkout
+        uses: actions/checkout@v2
 
       - uses: actions/setup-python@v2
         with:
           python-version: ${{ matrix.python }}
 
+      - name: "Windows Graphviz install"
+        if: runner.os == 'Windows'
+        uses: crazy-max/ghaction-chocolatey@v3
+        with:
+          args: -h
+
+      - name: Install Graphviz for Windows
+        if: runner.os == 'Windows'
+        run: |
+          choco install graphviz --version=2.49.3
+
+      - name: Install pygraphviz for Windows
+        if: runner.os == 'Windows'
+        run: |
+          python -m pip install --use-pep517 --config-settings="--global-option=build_ext" --config-settings="--global-option=-IC:\\Program Files\\Graphviz\\include" --config-settings="--global-option=-LC:\\Program Files\\Graphviz\\lib" pygraphviz
+
+      - name: Install Graphviz for other platforms
+        if: runner.os != 'Windows'
+        uses: ts-graphviz/setup-graphviz@v2
+        with:
+          macos-skip-brew-update: 'true'
+
       - name: Cache venv
         uses: actions/cache@v2
         with:
@@ -47,7 +72,7 @@ jobs:
           ${{ matrix.install_graphviz }}
           echo "Cache Version ${{ secrets.CACHE_VERSION }}"
           poetry install
-          poetry run pip install ERAlchemy
+          poetry run pip install ERAlchemy2
           poetry config --list
 
       - name: Print tool versions
@@ -95,6 +120,9 @@ jobs:
     steps:
       - uses: actions/checkout@v2
 
+      - name: Setup Graphviz
+        uses: ts-graphviz/setup-graphviz@v1.2.0
+
       - name: Install dependencies
         run: |
           pip install poetry
@@ -110,6 +138,8 @@ jobs:
         run: |
           pip install poetry
           poetry install
+          poetry run pip install ERAlchemy2
+
 
       - name: Build docs
         run: poetry run sphinx-build -M html docs/source docs/build

dataprep/__init__.py

@@ -4,6 +4,7 @@
 
 Dataprep let you prepare your data using a single library with a few lines of code.
 """
+
 import logging
 
 DEFAULT_PARTITIONS = 1

dataprep/clean/address_utils.py

@@ -1,6 +1,7 @@
 """
 Constants used by the clean_address() and validate_address() functions
 """
+
 # pylint: disable=C0301, C0302, E1101
 
 from builtins import zip

dataprep/clean/clean_ad_nrt.py

@@ -2,6 +2,7 @@
 Clean and validate a DataFrame column containing
 Andorra NRT (Número de Registre Tributari, Andorra tax number).
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches, unused-argument, E1101, E1133
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_al_nipt.py

@@ -2,6 +2,7 @@
 Clean and validate a DataFrame column containing
 NIPT (Numri i Identifikimit për Personin e Tatueshëm, Albanian VAT number).
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches, unused-argument, E1101, E1133
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_ar_cbu.py

@@ -2,6 +2,7 @@
 Clean and validate a DataFrame column containing
 CBU (Clave Bancaria Uniforme, Argentine bank account number).
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches, unused-argument, E1101, E1133
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_ar_cuit.py

@@ -2,6 +2,7 @@
 Clean and validate a DataFrame column containing
 CUIT (Código Único de Identificación Tributaria, Argentinian tax number).
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches, unused-argument, E1101, E1133
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_ar_dni.py

@@ -2,6 +2,7 @@
 Clean and validate a DataFrame column containing
 DNI (Documento Nacional de Identidad, Argentinian national identity nr.).
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches, unused-argument, E1101, E1133
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_at_uid.py

@@ -2,6 +2,7 @@
 Clean and validate a DataFrame column containing
 UID (Umsatzsteuer-Identifikationsnummer, Austrian VAT number).
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches, unused-argument, E1101, E1133
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_at_vnr.py

@@ -2,6 +2,7 @@
 Clean and validate a DataFrame column containing
 VNR, SVNR, VSNR (Versicherungsnummer, Austrian social security number).
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches, unused-argument, E1101, E1133
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_au_abn.py

@@ -1,6 +1,7 @@
 """
 Clean and validate a DataFrame column containing Australian Business Numbers (ABNs).
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_au_acn.py

@@ -1,6 +1,7 @@
 """
 Clean and validate a DataFrame column containing Australian Company Numbers (ACNs).
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_au_tfn.py

@@ -1,6 +1,7 @@
 """
 Clean and validate a DataFrame column containing Australian Tax File Numbers (TFNs).
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_be_iban.py

@@ -1,6 +1,7 @@
 """
 Clean and validate a DataFrame column containing Belgian IBANs.
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_be_vat.py

@@ -1,6 +1,7 @@
 """
 Clean and validate a DataFrame column containing Belgian VAT numbers (VATs).
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_bg_egn.py

@@ -1,6 +1,7 @@
 """
 Clean and validate a DataFrame column containing Bulgarian national identification numbers (EGNs).
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_bg_pnf.py

@@ -1,6 +1,7 @@
 """
 Clean and validate a DataFrame column containing Bulgarian personal number of a foreigner.
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_bg_vat.py

@@ -1,6 +1,7 @@
 """
 Clean and validate a DataFrame column containing Bulgarian VAT numbers (VATs).
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_bic.py

@@ -1,6 +1,7 @@
 """
 Clean and validate a DataFrame column containing ISO 9362 Business identifier codes.
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_bitcoin.py

@@ -1,6 +1,7 @@
 """
 Clean and validate a DataFrame column containing Bitcoin Addresses.
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches, unused-argument
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_br_cnpj.py

@@ -1,6 +1,7 @@
 """
 Clean and validate a DataFrame column containing CNPJ numbers, Brazilian company identifier.
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_br_cpf.py

@@ -1,6 +1,7 @@
 """
 Clean and validate a DataFrame column containing CPF numbers, Brazilian national identifier.
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_by_unp.py

@@ -1,6 +1,7 @@
 """
 Clean and validate a DataFrame column containing Belarusian UNP numbers (UNPs).
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_ca_bn.py

@@ -1,6 +1,7 @@
 """
 Clean and validate a DataFrame column containing Canadian Business Numbers (BNs).
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_ca_sin.py

@@ -1,6 +1,7 @@
 """
 Clean and validate a DataFrame column containing Canadian Social Insurance Numbers(SINs).
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_casrn.py

@@ -1,6 +1,7 @@
 """
 Clean and validate a DataFrame column containing CAS Registry Numbers.
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches, unused-argument
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_ch_esr.py

@@ -1,6 +1,7 @@
 """
 Clean and validate a DataFrame column containing Swiss EinzahlungsSchein mit Referenznummer (ESRs).
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_ch_ssn.py

@@ -1,6 +1,7 @@
 """
 Clean and validate a DataFrame column containing Swiss social security numbers (SSNs).
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_ch_uid.py

@@ -1,6 +1,7 @@
 """
 Clean and validate a DataFrame column containing Swiss business identifiers (UIDs).
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_ch_vat.py

@@ -1,6 +1,7 @@
 """
 Clean and validate a DataFrame column containing Swiss VAT numbers (VATs).
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_cl_rut.py

@@ -1,6 +1,7 @@
 """
 Clean and validate a DataFrame column containing Chile RUT/RUN numbers (RUTs).
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_cn_ric.py

@@ -1,6 +1,7 @@
 """
 Clean and validate a DataFrame column containing Chinese Resident Identity Card Number (RICs).
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_cn_uscc.py

@@ -2,6 +2,7 @@
 Clean and validate a DataFrame column containing Chinese Unified Social Credit Code
 (China tax number) (USCCs).
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_co_nit.py

@@ -1,6 +1,7 @@
 """
 Clean and validate a DataFrame column containing Colombian identity codes (NITs).
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches
 from typing import Any, Union
 from operator import itemgetter

dataprep/clean/clean_country.py

@@ -1,6 +1,7 @@
 """
 Clean and validate a DataFrame column containing country names.
 """
+
 from functools import lru_cache
 from operator import itemgetter
 from os import path
@@ -371,9 +372,7 @@ def _get_format_if_allowed(input_format: str, allowed_formats: Tuple[str, ...])
         return (
             "name"
             if "name" in allowed_formats
-            else "official"
-            if "official" in allowed_formats
-            else None
+            else "official" if "official" in allowed_formats else None
         )
 
     return input_format if input_format in allowed_formats else None

dataprep/clean/clean_cr_cpf.py

@@ -1,6 +1,7 @@
 """
 Clean and validate a DataFrame column containing Costa Rica physical person ID number (CPFs).
 """
+
 # pylint: disable=too-many-lines, too-many-arguments, too-many-branches
 from typing import Any, Union
 from operator import itemgetter