Feat/protoocls

src/ficamp/__main__.py

@@ -23,7 +23,7 @@ def cli() -> argparse.Namespace:
     subparsers = parser.add_subparsers(dest="command", required=True)
 
     # Subparser for the import command
-    import_parser = subparsers.add_parser("import", help="Import a Transactions")
+    import_parser = subparsers.add_parser("import", help="Import transactions")
     import_parser.add_argument(
         "--bank",
         choices=[e.value for e in BankParser],

src/ficamp/classifier/google_apis.py

@@ -94,7 +94,7 @@ def query_gmaps_category(concept):
         cached_category = cached.get(concept)
         if not cached_category:
             try:
-                #ams = "52.3676,4.9041"
+                # ams = "52.3676,4.9041"
                 gmaps_category = find_business_category_in_google(concept)
             except GoogleException as error:
                 print(f"error: {error}")

src/ficamp/classifier/keywords.py

@@ -1,11 +1,13 @@
 """
 Logic to sort transactions based on keywords.
 """
-import json
-import pathlib
 
+from typing import Any
 
-def sort_by_keyword_matches(categories: dict, description: str) -> list[str]:
+
+def sort_by_keyword_matches(
+    categories: dict, description: str
+) -> list[tuple[int, Any]]:
     description = description.lower()
     matches = []
     for category, keywords in categories.items():

src/ficamp/datastructures.py

@@ -30,12 +30,14 @@ class Concept:
 class Tx(SQLModel, table=True):
     """Represents a transaction extracted from a bank"""
 
-    id: Optional[int] = Field(default=None, primary_key=True)
     date: datetime
     amount: Decimal
     currency: Currency
     concept: str
     concept_clean: Optional[str]
     category: None | str
+
+    # fields with defaults
+    id: Optional[int] = Field(default=None, primary_key=True)
     tx_metadata: dict[str, str] = Field(sa_column=Column(JSON))
     tags: list[str] = Field(sa_column=Column(JSON))

src/ficamp/parsers/abn.py

@@ -11,7 +11,7 @@
 import xlrd  # type: ignore
 
 from ficamp.datastructures import Currency, Tx
-from ficamp.parsers.protocols import Parser
+from ficamp.parsers.protocols import ParserProtocol
 
 TRANSACTIONDATE_REGEX = r"(\d{4})(\d{2})(\d{2})"
 transactiondate_re = re.compile(TRANSACTIONDATE_REGEX)
@@ -105,7 +105,7 @@ def parse_abn(self, concept: str) -> str:
         return "ABN AMRO|" + concept
 
 
-class AbnParser(Parser):
+class AbnParser(ParserProtocol):
     """Parser for ABN AMRO bank statements.
 
     ABN uses the old `.xls` excel version, and we require xlrd
@@ -162,10 +162,12 @@ def build_transaction(
         _concept = self.concept_parser.parse(concept)
 
         return Tx(
+            id=None,
             date=_date,
             amount=_amount,
             currency=_currency,
             concept=_concept,
+            concept_clean=None,
             category=None,
             tx_metadata={},
             tags=[],

src/ficamp/parsers/bbva.py

@@ -5,10 +5,10 @@
 from openpyxl import load_workbook
 
 from ficamp.datastructures import Currency, Tx
-from ficamp.parsers.protocols import Parser
+from ficamp.parsers.protocols import ParserProtocol
 
 
-class AccountBBVAParser(Parser):
+class AccountBBVAParser(ParserProtocol):
     """Parser for BBVA bank account extract"""
 
     def load(self, filename: Path):
@@ -49,7 +49,7 @@ def row_processor(self, row):
         )
 
 
-class CreditCardBBVAParser(Parser):
+class CreditCardBBVAParser(ParserProtocol):
     """Parser for BBVA Credit Card Extract"""
 
     def load(self, filename: Path):

src/ficamp/parsers/bsabadell.py

@@ -5,10 +5,10 @@
 from openpyxl import load_workbook
 
 from ficamp.datastructures import Currency, Tx
-from ficamp.parsers.protocols import Parser
+from ficamp.parsers.protocols import ParserProtocol
 
 
-class AccountBSabadellParser(Parser):
+class AccountBSabadellParser(ParserProtocol):
     """Parser for BSabadell bank account extract"""
 
     def load(self, filename: Path):
@@ -62,7 +62,7 @@ def concept_builder(self, row):
         return concept
 
 
-class CreditCardBSabadellParser(Parser):
+class CreditCardBSabadellParser(ParserProtocol):
     """Parser for BSabadell Credit Card Extract"""
 
     def load(self, filename: Path):

src/ficamp/parsers/caixabank.py

@@ -5,10 +5,10 @@
 from openpyxl import load_workbook
 
 from ficamp.datastructures import Currency, Tx
-from ficamp.parsers.protocols import Parser
+from ficamp.parsers.protocols import ParserProtocol
 
 
-class CaixaBankParser(Parser):
+class CaixaBankParser(ParserProtocol):
     """Parser for CaixaBank bank account extract"""
 
     def load(self, filename: Path):

src/ficamp/parsers/enums.py

@@ -4,6 +4,7 @@
 from ficamp.parsers.bbva import AccountBBVAParser, CreditCardBBVAParser
 from ficamp.parsers.bsabadell import AccountBSabadellParser, CreditCardBSabadellParser
 from ficamp.parsers.caixabank import CaixaBankParser
+from ficamp.parsers.protocols import ParserProtocol
 
 
 class BankParser(StrEnum):
@@ -14,7 +15,7 @@ class BankParser(StrEnum):
     BSABADELL_CREDIT = "bsabadell-credit"
     CAIXABANK = "caixabank"
 
-    def get_parser(self):
+    def get_parser(self) -> ParserProtocol:
         if self == BankParser.ABN:
             return AbnParser()
         if self == BankParser.BBVA_ACCOUNT:

src/ficamp/parsers/protocols.py

@@ -4,7 +4,7 @@
 from ficamp.datastructures import Tx
 
 
-class Parser(Protocol):
+class ParserProtocol(Protocol):
     """Main protocol to define parsers for different banks."""
 
     def load(self, filename: Path): ...

src/ficamp/sinks/protocols.py

@@ -0,0 +1,17 @@
+from enum import Enum
+from typing import Protocol
+
+from ficamp.datastructures import Tx
+
+
+class BaseSinkException(Exception):
+    """Base exception for all sink exceptions.
+
+    If your sink function is going to raise an exception, it should inherit from this class.
+    """
+
+    pass
+
+
+class SinkProtocol(Protocol):
+    def write(self, transations: list[Tx]): ...

tests/test_preprocessing.py

@@ -5,9 +5,9 @@
     remove_colon,
     remove_comma,
     remove_digits,
+    remove_isolated_digits,
     remove_pipes,
     remove_punctuation,
-    remove_isolated_digits,
     remove_short_words,
 )