change to 'new' project structure

.pre-commit-config.yaml

@@ -17,6 +17,7 @@ repos:
     rev: v3.10.1
     hooks:
       - id: pyupgrade
+        args: [--py311-plus]
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
     rev: v0.0.282

downloadimages.py

@@ -5,7 +5,6 @@
 import os
 import sys
 import time
-from typing import List, Optional
 
 import requests
 from parsel import Selector
@@ -22,7 +21,7 @@
 
 
 # this only works with traineras.es
-def main(rower_id: str, club_name: str, year: Optional[str] = None, output: str = "./out"):
+def main(rower_id: str, club_name: str, year: str | None = None, output: str = "./out"):
     client = Client(source=Datasource.TRAINERAS)  # type: ignore
     parser: TrainerasHtmlParser = client._html_parser  # type: ignore
 
@@ -32,7 +31,7 @@ def main(rower_id: str, club_name: str, year: Optional[str] = None, output: str
 
         t_date = find_date(selector.xpath(f"/html/body/div[1]/main/div/div/div/div[{1}]/h2/text()").get(""))
         t_date = t_date.strftime("%d%m%Y") if t_date else None
-        participants: List[Selector] = parser.get_participants(selector, day=1)
+        participants: list[Selector] = parser.get_participants(selector, day=1)
         for participant in participants:
             if (
                 club_name.upper() not in parser.get_club_name(participant)
@@ -44,7 +43,7 @@ def main(rower_id: str, club_name: str, year: Optional[str] = None, output: str
         time.sleep(20)
 
 
-def retrieve_images(url: str, t_date: Optional[str], output: str):
+def retrieve_images(url: str, t_date: str | None, output: str):
     content = requests.get(url=url, headers=HTTP_HEADERS).content.decode("utf-8")
     selector = Selector(content)
 

fillforms.py

@@ -5,7 +5,6 @@
 import os
 import sys
 from datetime import datetime
-from typing import List
 
 from rscraping.builder import (
     PdfItem,
@@ -22,7 +21,7 @@
 
 def main(
     signed_on: str,
-    types: List[str],
+    types: list[str],
     image_path: str,
     use_preset: bool,
     prompt_entity: bool,

findrace.py

@@ -4,7 +4,6 @@
 import logging
 import os
 import sys
-from typing import Optional
 
 from rscraping import find_race
 from rscraping.data.functions import save_csv
@@ -31,7 +30,7 @@ def _parse_arguments():
     return parser.parse_args()
 
 
-def main(race_id: str, datasource: str, is_female: bool, with_lineups: bool, save: bool, day: Optional[int]):
+def main(race_id: str, datasource: str, is_female: bool, with_lineups: bool, save: bool, day: int | None):
     if not Datasource.has_value(datasource):
         raise ValueError(f"invalid datasource={datasource}")
 

parseimage.py

@@ -4,7 +4,6 @@
 import logging
 import os
 import sys
-from typing import List
 
 from rscraping import parse_race_image
 from rscraping.data.functions import expand_path, save_csv
@@ -25,11 +24,11 @@ def _parse_arguments():
     return parser.parse_args()
 
 
-def main(paths: List[str], datasource: str, header_size: int = 3, allow_plot: bool = False, save: bool = False):
+def main(paths: list[str], datasource: str, header_size: int = 3, allow_plot: bool = False, save: bool = False):
     if not Datasource.is_OCR(datasource):
         raise ValueError(f"invalid datasource={datasource}")
 
-    parsed_items: List[Race] = []
+    parsed_items: list[Race] = []
     for path in paths:
         parsed_items.extend(
             parse_race_image(

pyproject.toml

@@ -0,0 +1,3 @@
+[build-system]
+requires = ["setuptools"]
+build-backend = "setuptools.build_meta"

requirements-dev.txt

@@ -0,0 +1,2 @@
+-r requirements.txt
+pytest

requirements.txt

@@ -1,14 +1,13 @@
 fillpdf==0.7.2
 inquirer==3.1.3
 matplotlib==3.8.0
-numpy==1.26.0
+numpy==1.26.1
 opencv-python==4.8.1.78
 openpyxl==3.1.2
 pandas==2.1.1
 parsel==1.8.1
 PyMuPDF==1.23.4
 pytesseract==0.3.10
-pytest==7.4.2
 pyutils @ git+https://github.com/iagocanalejas/pyutils.git@master
 reportlab~=4.0.5
 requests==2.31.0

rscraping/__init__.py

@@ -1,5 +1,6 @@
 import os
-from typing import Any, Generator, List, Optional
+from typing import Any, List, Optional
+from collections.abc import Generator
 
 from pyutils.strings import normalize_synonyms, remove_conjunctions, remove_symbols
 from rscraping.clients import Client
@@ -15,9 +16,9 @@ def find_race(
     race_id: str,
     datasource: Datasource,
     is_female: bool,
-    day: Optional[int] = None,
+    day: int | None = None,
     with_lineup: bool = False,
-) -> Optional[Race]:
+) -> Race | None:
     """
     Find a race based on the provided parameters.
 
@@ -100,7 +101,7 @@ def find_lineup(race_id: str, datasource: Datasource, is_female: bool) -> Genera
     return client.get_lineup_by_race_id(race_id)
 
 
-def lemmatize(phrase: str, lang: str = "es") -> List[str]:
+def lemmatize(phrase: str, lang: str = "es") -> list[str]:
     phrase = normalize_synonyms(phrase, SYNONYMS)
     phrase = remove_symbols(remove_conjunctions(phrase))
     return list(set(text_lemmatizer(phrase, lang=lang)))

rscraping/builder/_item.py

@@ -1,6 +1,5 @@
 from dataclasses import dataclass
 from datetime import datetime
-from typing import Optional
 
 import inquirer
 
@@ -9,40 +8,40 @@
 
 @dataclass
 class PdfItem:
-    name: Optional[str] = None
-    surname: Optional[str] = None
-    nif: Optional[str] = None
-    gender: Optional[str] = None
-    birth: Optional[str] = None
-    nationality: Optional[str] = None
-    category: Optional[str] = None
-
-    address: Optional[str] = None
-    address_number: Optional[str] = None
-    postal_code: Optional[str] = None
-    town: Optional[str] = None
-    state: Optional[str] = None
-    country: Optional[str] = None
-    phone: Optional[str] = None
-    email: Optional[str] = None
-
-    entity: Optional[str] = None
-    entity_town: Optional[str] = None
-    entity_state: Optional[str] = None
-
-    sign_in: Optional[str] = None
-    sign_on_day: Optional[str] = None
-    sign_on_month: Optional[str] = None
-    sign_on_year: Optional[str] = None
-
-    parent_name: Optional[str] = None
-    parent_surname: Optional[str] = None
-    parent_dni: Optional[str] = None
-    parent_category: Optional[str] = None
-    is_rower: Optional[bool] = False
-
-    is_coach: Optional[bool] = False
-    is_directive: Optional[bool] = False
+    name: str | None = None
+    surname: str | None = None
+    nif: str | None = None
+    gender: str | None = None
+    birth: str | None = None
+    nationality: str | None = None
+    category: str | None = None
+
+    address: str | None = None
+    address_number: str | None = None
+    postal_code: str | None = None
+    town: str | None = None
+    state: str | None = None
+    country: str | None = None
+    phone: str | None = None
+    email: str | None = None
+
+    entity: str | None = None
+    entity_town: str | None = None
+    entity_state: str | None = None
+
+    sign_in: str | None = None
+    sign_on_day: str | None = None
+    sign_on_month: str | None = None
+    sign_on_year: str | None = None
+
+    parent_name: str | None = None
+    parent_surname: str | None = None
+    parent_dni: str | None = None
+    parent_category: str | None = None
+    is_rower: bool | None = False
+
+    is_coach: bool | None = False
+    is_directive: bool | None = False
 
     @classmethod
     def preset(cls) -> "PdfItem":

rscraping/builder/fegar.py

@@ -1,6 +1,5 @@
 import logging
 import os
-from typing import Optional
 
 from fillpdf import fillpdfs
 
@@ -13,7 +12,7 @@
 
 
 def fill_fegar_form(
-    data: PdfItem, with_parent: bool, images_folder: Optional[str] = None, remove_temp_files: bool = True
+    data: PdfItem, with_parent: bool, images_folder: str | None = None, remove_temp_files: bool = True
 ):
     logging.info("fegar:: starting fegar form")
 

rscraping/clients/_client.py

@@ -1,6 +1,7 @@
 from abc import ABC, abstractmethod
+from collections.abc import Generator
 from datetime import date
-from typing import Any, Generator, Optional
+from typing import Any
 
 import requests
 from parsel import Selector
@@ -40,7 +41,7 @@ def validate_year_or_raise_exception(self, year: int):
         if year < since or year > today:
             raise ValueError(f"invalid 'year', available values are [{since}, {today}]")
 
-    def get_race_by_id(self, race_id: str, **kwargs) -> Optional[Race]:
+    def get_race_by_id(self, race_id: str, **kwargs) -> Race | None:
         url = self.get_race_details_url(race_id, is_female=self._is_female)
         race = self._html_parser.parse_race(
             selector=Selector(requests.get(url=url, headers=HTTP_HEADERS).content.decode("utf-8")),

rscraping/clients/act.py

@@ -1,4 +1,5 @@
-from typing import Any, Generator, override
+from collections.abc import Generator
+from typing import Any, override
 
 import fitz
 import requests

rscraping/clients/arc.py

@@ -1,4 +1,5 @@
-from typing import Any, Generator, override
+from collections.abc import Generator
+from typing import Any, override
 
 import requests
 from parsel import Selector

rscraping/clients/lgt.py

@@ -1,5 +1,6 @@
+from collections.abc import Generator
 from datetime import date
-from typing import Any, Dict, Generator, Optional, override
+from typing import Any, override
 
 import requests
 from fitz import fitz
@@ -109,7 +110,7 @@ def get_calendar_selector() -> Selector:
         return Selector(requests.post(url=url, headers=HTTP_HEADERS, data=data).content.decode("utf-8"))
 
     @override
-    def get_race_by_id(self, race_id: str, **kwargs) -> Optional[Race]:
+    def get_race_by_id(self, race_id: str, **kwargs) -> Race | None:
         if race_id in self._excluded_ids:
             return None
 
@@ -210,9 +211,9 @@ def get_race_ids_by_rower(self, **_):
     #                      UTILS                       #
     ####################################################
 
-    _RACE_YEARS: Dict[str, Optional[int]] = {}
+    _RACE_YEARS: dict[str, int | None] = {}
 
-    def _get_race_year(self, race_id: str) -> Optional[int]:
+    def _get_race_year(self, race_id: str) -> int | None:
         if race_id in self._RACE_YEARS:
             return self._RACE_YEARS[race_id]
 

rscraping/clients/traineras.py

@@ -1,4 +1,5 @@
-from typing import Any, Generator, Optional, override
+from collections.abc import Generator
+from typing import Any, override
 
 import requests
 from parsel import Selector
@@ -57,7 +58,7 @@ def get_race_ids_by_year(self, year: int, **_) -> Generator[str, Any, Any]:
         for page in self.get_pages(year):
             yield from self._html_parser.parse_race_ids(page, is_female=self._is_female)
 
-    def get_race_ids_by_rower(self, rower_id: str, year: Optional[str] = None, **_) -> Generator[str, Any, Any]:
+    def get_race_ids_by_rower(self, rower_id: str, year: str | None = None, **_) -> Generator[str, Any, Any]:
         content = requests.get(url=self.get_rower_url(rower_id), headers=HTTP_HEADERS).content.decode("utf-8")
         yield from self._html_parser.parse_rower_race_ids(Selector(content), year=year)
 

rscraping/data/functions.py

@@ -1,6 +1,5 @@
 import csv
 import os
-from typing import List
 
 from pyutils.strings import remove_symbols
 from rscraping.data.models import Lineup, Race
@@ -19,7 +18,7 @@ def is_branch_club(name: str, letter: str = "B") -> bool:
     return any(e == letter for e in clean_name.upper().split())
 
 
-def expand_path(path: str, valid_files: List[str]) -> List[str]:
+def expand_path(path: str, valid_files: list[str]) -> list[str]:
     def is_valid(file: str) -> bool:
         _, extension = os.path.splitext(file)
         return extension.upper() in valid_files
@@ -28,7 +27,7 @@ def is_valid(file: str) -> bool:
     return [f for f in files if is_valid(f)]
 
 
-def save_csv(lineups: List[Race] | List[Lineup], file_name: str):
+def save_csv(lineups: list[Race] | list[Lineup], file_name: str):
     if not len(lineups):
         return