Code formatting

parser/address/classifier.py

@@ -92,9 +92,12 @@ def find_room(token: pd.Series, pre_token: pd.Series) -> str:
 def find_litera(token: pd.Series, pre_token: pd.Series) -> str:
     if find_room(token, pre_token):
         return ""
-    if any_of_in(LETTER, token["obj"].lower()) or re.search(
+    # fmt: off
-        r"\d{1,3}([А-Я]|[а-я])( |$)", token["obj"]
+    if (
+        any_of_in(LETTER, token["obj"].lower()) or
+        re.search(r"\d{1,3}([А-Я]|[а-я])( |$)", token["obj"])
     ):
+    #fmt: on
         return "l"
     if (
         (
@@ -199,6 +202,7 @@ def address_classification(token: pd.Series, pre_token: pd.Series) -> pd.Series:
     brackets = re.search(r"\(.+\)", token["obj"])
     if brackets:
         token["obj"] = re.sub(r"\(.+\)", "()", token["obj"])
+
     token["class"] += find_district(token, pre_token)
     token["class"] += find_countryside(token, pre_token)
     token["class"] += find_territory(token, pre_token)
@@ -208,8 +212,11 @@ def address_classification(token: pd.Series, pre_token: pd.Series) -> pd.Series:
     token["class"] += find_edifice(token, pre_token)
     token["class"] += find_litera(token, pre_token)
     token["class"] += find_room(token, pre_token)
+
     if token["class"] == "":
         token["class"] = "w"
+
     if brackets:
         token["obj"] = re.sub(r"\(\)", brackets.group(), token["obj"])
+
     return token

parser/address/splitter.py

@@ -167,9 +167,12 @@ class AddressSplitter(Sequence):
         return list(tokens)
 
     def cut_address(self) -> pd.Series:
-        while len(self.accumulator["class"]) > 0 and CLASSES.index(
+        # fmt: off
-            self.prev_class()
+        while (
-        ) > CLASSES.index(self.next_class()):
+            len(self.accumulator["class"]) > 0
+            and CLASSES.index(self.prev_class()) > CLASSES.index(self.next_class())
+        ):
+        # fmt: on
             match self.accumulator["class"][-1]:
                 case "h":
                     self.accumulator["addresses"] = re.sub(

parser/address/utils.py

@@ -6,6 +6,7 @@ import pandas as pd
 
 T = TypeVar("T")
 
+
 def any_of_in(substrings: Iterable[str], string: str) -> bool:
     return any(map(lambda substring: substring in string, substrings))
 
@@ -13,6 +14,7 @@ def any_of_in(substrings: Iterable[str], string: str) -> bool:
 def flatten(arr: Iterable[list[T]]) -> list[T]:
     return sum(arr, [])
 
+
 def unfold_house_ranges(token: str) -> list[str]:
     addresses = []
     pairs_strings = re.findall(r"([\d]+-[\d]+)", token)
@@ -42,4 +44,4 @@ def create_token(obj: str = "", token_class: str = ""):
             "obj": obj,
             "class": token_class,
         }
-    )
+    )

parser/pipeline.py

@@ -1,9 +1,9 @@
 from typing import Optional
 
-from .lenenergo import LenenergoParser
-from .building_id import concurrent_fetch_builing_ids
-from .preprocess import preprocess_df
 from .address import split_addresses
+from .building_id import concurrent_fetch_builing_ids
+from .lenenergo import LenenergoParser
+from .preprocess import preprocess_df
 
 
 def pipeline(parser: Optional[LenenergoParser] = None) -> LenenergoParser:

runner/database.py

@@ -1,10 +1,10 @@
 from .config import (
+    DB_URL,
     POSTGRES_DB,
     POSTGRES_HOST,
     POSTGRES_PASSWORD,
     POSTGRES_PORT,
     POSTGRES_USER,
-    DB_URL,
 )
 
 db_credentials = {"conninfo": DB_URL}