chore: remove black in favor of ruff

.vscode/extensions.json

@@ -5,7 +5,6 @@
     "recommendations": [
         "editorconfig.editorconfig",
         "njpwerner.autodocstring",
-        "ms-python.black-formatter",
         "ms-python.vscode-pylance",
         "ms-python.python",
         "donjayamanne.python-environment-manager",

.vscode/settings.json

@@ -1,6 +1,6 @@
 {
     "[python]": {
-        "editor.defaultFormatter": "ms-python.black-formatter",
+        "editor.defaultFormatter": "charliermarsh.ruff",
         "editor.formatOnSave": true
     },
     "cSpell.words": [

pyproject.toml

@@ -2,8 +2,6 @@
 line-length = 120
 [tool.ruff.lint]
 ignore = ["E501"]
-[tool.black]
-line-length = 120
 [tool.pytest.ini_options]
 minversion = "6.0"
 testpaths = ["tests", "src"]

readme.md

@@ -125,6 +125,7 @@ A normalized string representing the entire address that was passed into the con
 1. install required dependencies to work on sweeper
     - `pip install -e ".[tests]"`
 1. `test_metadata.py` uses a SQL database that needs to be restored via `src/sweeper/tests/data/Sweeper.bak` to your local SQL Server.
-1. run tests: `pytest`
-1. run linter: `ruff check .`
 1. run sweeper: `python -m sweeper`
+1. test: `pytest`
+1. lint: `ruff check .`
+1. format: `ruff format .`

setup.py

@@ -4,6 +4,7 @@
 setup.py
 A module that installs sweeper as a module
 """
+
 import glob
 from os.path import basename, splitext
 from pathlib import Path
@@ -59,7 +60,6 @@
             "pytest-mock==3.*",
             "pytest-watch==4.*",
             "pytest==8.*",
-            "black==24.*",
             "ruff==0.*",
         ],
     },

src/sweeper/__main__.py

@@ -22,6 +22,7 @@
   sweeper sweep           --workspace=c:\\data\\thing --try-fix --save-report=c:\\temp --backup-to=c:\\temp\\backup.gdb
   sweeper sweep addresses --workspace=c:\\data\\thing --try-fix --save-report=c:\\temp --backup-to=c:\\temp\\backup.gdb --field-name=ADDRESS
 """
+
 import datetime
 import logging
 import logging.handlers

src/sweeper/address_parser.py

@@ -1,9 +1,10 @@
 #!/usr/bin/env python
 # * coding: utf8 *
-'''
+"""
 address_parser.py
 A module that parses street addresses into their various parts.
-'''
+"""
+
 import json
 import pprint
 import re
@@ -12,44 +13,45 @@
 import usaddress
 
 TAG_MAPPING = {
-    'AddressNumber': 'address_number',
-    'AddressNumberPrefix': 'address_number',
-    'AddressNumberSuffix': 'address_number_suffix',
-    'StreetNamePreDirectional': 'prefix_direction',
-    'StreetName': 'street_name',
+    "AddressNumber": "address_number",
+    "AddressNumberPrefix": "address_number",
+    "AddressNumberSuffix": "address_number_suffix",
+    "StreetNamePreDirectional": "prefix_direction",
+    "StreetName": "street_name",
     # 'StreetNamePreModifier': 'street_name', #: handled in class below
     # 'StreetNamePreType': 'street_name', #: handled in class below
-    'StreetNamePostDirectional': 'street_direction',
-    'StreetNamePostModifier': 'street_type',
-    'StreetNamePostType': 'street_type',
+    "StreetNamePostDirectional": "street_direction",
+    "StreetNamePostModifier": "street_type",
+    "StreetNamePostType": "street_type",
     # 'CornerOf': 'address1',
     # 'IntersectionSeparator': 'address1',
     # 'LandmarkName': 'address1',
     # 'USPSBoxGroupID': 'address1',
     # 'USPSBoxGroupType': 'address1',
     # 'USPSBoxID': 'address1',
     # 'USPSBoxType': 'address1',
-    'BuildingName': 'unit_id',
-    'OccupancyType': 'unit_type',
-    'OccupancyIdentifier': 'unit_id',
-    'SubaddressIdentifier': 'unit_id',
-    'SubaddressType': 'unit_type',
-    'PlaceName': 'city',
-    'StateName': 'state',
-    'ZipCode': 'zip_code',
-    'USPSBoxID': 'po_box'
+    "BuildingName": "unit_id",
+    "OccupancyType": "unit_type",
+    "OccupancyIdentifier": "unit_id",
+    "SubaddressIdentifier": "unit_id",
+    "SubaddressType": "unit_type",
+    "PlaceName": "city",
+    "StateName": "state",
+    "ZipCode": "zip_code",
+    "USPSBoxID": "po_box",
 }
-TWO_CHAR_DIRECTIONS = ['NO', 'SO', 'EA', 'WE']
-with open(join(dirname(realpath(__file__)), 'street_types.json'), 'r') as file:
+TWO_CHAR_DIRECTIONS = ["NO", "SO", "EA", "WE"]
+with open(join(dirname(realpath(__file__)), "street_types.json"), "r") as file:
     STREET_TYPES = json.loads(file.read())
-HWY_REGEX = re.compile('(SR|STATE ROUTE|HIGHWAY)')
-UNIT_VALUES_NOT_APPROPRIATE_FOR_HASH_SIGN = ['rear']
+HWY_REGEX = re.compile("(SR|STATE ROUTE|HIGHWAY)")
+UNIT_VALUES_NOT_APPROPRIATE_FOR_HASH_SIGN = ["rear"]
 
 
-class Address():
-    '''
+class Address:
+    """
     Class for parsing address strings
-    '''
+    """
+
     address_number = None
     address_number_suffix = None
     prefix_direction = None
@@ -64,14 +66,14 @@ class Address():
     state = None
 
     def __init__(self, address_text):
-        parts, parsed_as = usaddress.tag(address_text.replace('.', ''), TAG_MAPPING)
-        if parsed_as not in ['Street Address', 'PO Box']:
+        parts, parsed_as = usaddress.tag(address_text.replace(".", ""), TAG_MAPPING)
+        if parsed_as not in ["Street Address", "PO Box"]:
             raise Exception(f'"{address_text}" is not recognized as a valid street address, or P.O. Box')
 
         for part in parts:
             try:
                 value = parts[part].upper()
-                if part.endswith('direction'):
+                if part.endswith("direction"):
                     value = normalize_direction(value)
 
                 setattr(self, part, value)
@@ -83,85 +85,95 @@ def __init__(self, address_text):
 
         try:
             #: e.g. US HWY
-            self.street_name = f'{normalize_street_name_pre_type(self.StreetNamePreType)} {self.street_name}'
+            self.street_name = f"{normalize_street_name_pre_type(self.StreetNamePreType)} {self.street_name}"
             del self.StreetNamePreType
         except AttributeError:
             pass
 
         try:
-            self.street_name = f'{self.StreetNamePreModifier} {self.street_name}'
+            self.street_name = f"{self.StreetNamePreModifier} {self.street_name}"
             del self.StreetNamePreModifier
         except AttributeError:
             pass
 
         #: look for two-character prefix directions which usaddress does not handle
         if self.street_name:
-            street_name_parts = self.street_name.split(' ')
+            street_name_parts = self.street_name.split(" ")
             if len(street_name_parts) > 1:
                 if street_name_parts[0].upper() in TWO_CHAR_DIRECTIONS and self.prefix_direction is None:
                     self.prefix_direction = normalize_direction(street_name_parts[0])
-                    self.street_name = ' '.join(street_name_parts[1:])
+                    self.street_name = " ".join(street_name_parts[1:])
                 elif street_name_parts[-1].upper() in TWO_CHAR_DIRECTIONS and self.street_direction is None:
                     self.street_direction = normalize_direction(street_name_parts[-1])
-                    self.street_name = ' '.join(street_name_parts[:-1])
+                    self.street_name = " ".join(street_name_parts[:-1])
 
         if self.street_type is not None:
             #: handle multiple street_types (assume only the last one is valid and move all others to the street name)
-            if len(self.street_type.split(' ')) > 1:
-                parsed_street_types = self.street_type.split(' ')
-                self.street_name += ' ' + ' '.join(parsed_street_types[:-1])
+            if len(self.street_type.split(" ")) > 1:
+                parsed_street_types = self.street_type.split(" ")
+                self.street_name += " " + " ".join(parsed_street_types[:-1])
                 self.street_type = parsed_street_types[-1]
 
             try:
                 self.street_type = normalize_street_type(self.street_type)
             except InvalidStreetTypeError:
                 #: must be part of the street name
-                self.street_name += f' {self.street_type}'
+                self.street_name += f" {self.street_type}"
                 self.street_type = None
 
         if self.unit_id is not None:
             #: add `#` if there is not unit type and the unit is numeric
-            if not self.unit_id.startswith('#') and self.unit_type is None and self.unit_id.lower() not in UNIT_VALUES_NOT_APPROPRIATE_FOR_HASH_SIGN:
-                self.unit_id = f'# {self.unit_id}'
+            if (
+                not self.unit_id.startswith("#")
+                and self.unit_type is None
+                and self.unit_id.lower() not in UNIT_VALUES_NOT_APPROPRIATE_FOR_HASH_SIGN
+            ):
+                self.unit_id = f"# {self.unit_id}"
 
             #: strip `#` if there is a unit type
-            elif self.unit_id.startswith('#') and self.unit_type is not None:
+            elif self.unit_id.startswith("#") and self.unit_type is not None:
                 self.unit_id = self.unit_id[1:].strip()
 
     def __repr__(self):
         properties = vars(self)
-        properties.update({'normalized': self.normalized})
+        properties.update({"normalized": self.normalized})
 
-        return f'Parsed Address:\n{pprint.pformat(properties)}'
+        return f"Parsed Address:\n{pprint.pformat(properties)}"
 
     @property
     def normalized(self):
-        '''
+        """
         getter for normalized address string
-        '''
+        """
         if self.po_box is not None:
-            return f'PO BOX {self.po_box}'
+            return f"PO BOX {self.po_box}"
 
         parts = [
-            self.address_number, self.address_number_suffix, self.prefix_direction, self.street_name, self.street_type, self.street_direction, self.unit_type,
-            self.unit_id
+            self.address_number,
+            self.address_number_suffix,
+            self.prefix_direction,
+            self.street_name,
+            self.street_type,
+            self.street_direction,
+            self.unit_type,
+            self.unit_id,
         ]
 
-        return ' '.join([part for part in parts if part is not None])
+        return " ".join([part for part in parts if part is not None])
 
 
 def normalize_direction(direction_text):
-    '''
+    """
     returns the single letter corresponding to the input direction
-    '''
+    """
 
     return direction_text[0].upper()
 
 
 def normalize_street_type(type_text):
-    '''
+    """
     returns the standard abbreviation for the input street type
-    '''
+    """
 
     type_text = type_text.upper()
     for abbreviation, values in STREET_TYPES.items():
@@ -172,18 +184,18 @@ def normalize_street_type(type_text):
 
 
 def normalize_street_name_pre_type(text):
-    '''normalizes highways by doing things like replaces SR with HWY and removes US
+    """normalizes highways by doing things like replaces SR with HWY and removes US
 
     No need to worried about casing or "."s because usaddress has already taken care of them by this point.
-    '''
-    return HWY_REGEX.sub('HWY', text).replace('US ', '')
+    """
+    return HWY_REGEX.sub("HWY", text).replace("US ", "")
 
 
 class InvalidStreetTypeError(Exception):
-    '''
+    """
     exception for when the street type does not have a corresponding value in street_types.json
-    '''
+    """
 
     def __init__(self, type_text):
         super().__init__()
-        self.message = f'No matching abbreviation found for {type_text}'
+        self.message = f"No matching abbreviation found for {type_text}"

src/sweeper/backup.py

@@ -4,6 +4,7 @@
 backup.py
 A module that creates a gdb if it doesn't exist and inserts a feature class
 """
+
 import logging
 import os
 from datetime import datetime