Feature: Get valid values data from an external source instead of a local file

docs/formats.md

@@ -18,5 +18,6 @@
 | Region | Nom de région | Vérifie les régions françaises valides pour un Code Officiel Géographique donné. Depuis 2017, la liste des régions françaises n'a pas changé. |
 | Siren | SIREN | Check french SIREN number validity, but does not check if SIREN number exists. |
 | Siret | SIRET | Check french SIRET number validity, but does not check if SIRET number exists. |
+| Validator | Nom de validateur | Vérification si la valeur donnée est bien valide selon des valeurs valides récupérées |
 
 [If you want to add a new French Format, click here!](../CONTRIBUTING.md#implementing-a-new-french-format)

src/frformat/__init__.py

@@ -21,10 +21,12 @@
 from .formats.region import Region as Region
 from .formats.siren import Siren as Siren
 from .formats.siret import Siret as Siret
+from .formats.validator import Validator as Validator
 from .options import Options as Options
 from .versions import Millesime as Millesime
 
 all_formats = [
+    Validator,
     Canton,
     CodeCommuneInsee,
     CodeFantoir,

src/frformat/formats/canton.py

@@ -1,5 +1,5 @@
 from frformat import set_format
-from frformat.formats.canton_frozenset import CANTON_COG_2023, CANTON_COG_2024
+from frformat.get_values_script import get_valid_values
 from frformat.set_format import INSEE_SOURCE
 from frformat.versioned_set import VersionedSet
 from frformat.versions import Millesime
@@ -9,7 +9,14 @@
 source = INSEE_SOURCE
 
 canton_versioned_data = VersionedSet[Millesime]()
-canton_versioned_data.add_version(Millesime.M2023, CANTON_COG_2023)
-canton_versioned_data.add_version(Millesime.M2024, CANTON_COG_2024)
+canton_values_2023 = get_valid_values(
+    "https://www.insee.fr/fr/statistiques/fichier/6800675/v_canton_2023.csv", "LIBELLE"
+)
+canton_versioned_data.add_version(Millesime.M2023, canton_values_2023)
+
+canton_values_2024 = get_valid_values(
+    "https://www.insee.fr/fr/statistiques/fichier/7766585/v_canton_2024.csv", "LIBELLE"
+)
+canton_versioned_data.add_version(Millesime.M2024, canton_values_2024)
 
 Canton = set_format.new("Canton", name, description, source, canton_versioned_data)

src/frformat/formats/validator.py

@@ -0,0 +1,20 @@
+from frformat import set_format
+from frformat.get_values_script import get_valid_values
+from frformat.versioned_set import VersionedSet
+from frformat.versions import Millesime
+
+name = "Nom de validateur"
+description = "Vérification si la valeur donnée est bien valide selon des valeurs valides récupérées"
+source = "source1"
+
+validator_versioned_data = VersionedSet[Millesime]()
+
+valid_values_2023 = get_valid_values(
+    "https://www.insee.fr/fr/statistiques/fichier/8377162/v_commune_2025.csv", "COM"
+)
+validator_versioned_data.add_version(Millesime.M2023, valid_values_2023)
+
+
+Validator = set_format.new(
+    "Validator", name, description, source, validator_versioned_data
+)

src/frformat/get_values_script.py

@@ -0,0 +1,43 @@
+import csv
+import io
+import os
+import urllib.parse
+import urllib.request
+
+
+def get_valid_values(path: str, column: str) -> frozenset[str]:
+
+    parsed_url = urllib.parse.urlparse(path)
+    is_url = parsed_url.scheme in ("http", "https")
+
+    valid_values = []
+
+    if is_url:
+        try:
+            response = urllib.request.urlopen(path)
+            csvfile = io.StringIO(response.read().decode("utf-8"))
+        except Exception as e:
+            raise ValueError(f"Failed to fetch CSV from URL: {e} .")
+
+    elif os.path.isfile(path):
+        splitted_path = path.split(".")
+        if splitted_path[len(splitted_path) - 1] == "csv":
+            try:
+                csvfile = open(path, newline="", encoding="utf-8")
+
+            except Exception as e:
+                raise ValueError(f"Failed to open local CSV file: {e} .")
+        else:
+            raise ValueError("The given path must be referenced to a csv file.")
+    else:
+        raise ValueError(f"Invalid path: {path}.It must be a URL or existing csv file.")
+
+    with csvfile:
+        reader = csv.DictReader(csvfile)
+        for row in reader:
+            if column in row:
+                valid_values.append(row[column])
+            else:
+                raise ValueError(f"CSV file is missing the {column} column.")
+
+    return frozenset(valid_values)

src/tests/test_files_data/values.csv

@@ -0,0 +1,3 @@
+"Username","Identifier","First name","Last name"
+"booker12","9012","Rachel","Booker"
+"grey07","2070","Laura","Grey"

src/tests/test_validator.py

@@ -0,0 +1,57 @@
+import pytest
+
+from frformat import Millesime, Validator
+from frformat.get_values_script import get_valid_values
+
+
+def test_validator():
+    isvalid = Validator(Millesime.M2023).is_valid("01001")
+    assert isvalid is True
+
+
+def test_get_valid_values_with_local_file():
+    valid_values = get_valid_values(
+        "src/tests/test_files_data/values.csv", "First name"
+    )
+    assert valid_values == frozenset({"Rachel", "Laura"})
+
+    with pytest.raises(
+        ValueError, match="The given path must be referenced to a csv file."
+    ):
+        valid_values = get_valid_values(
+            "src/tests/test_files_data/text_file.odt", "coucou"
+        )
+
+    with pytest.raises(ValueError, match="CSV file is missing the Link column."):
+        valid_values = get_valid_values("src/tests/test_files_data/values.csv", "Link")
+
+
+# mocking ?
+""" def test_get_valid_values_with_url():
+    valid_values = get_valid_values(
+        "https://cdn.wsform.com/wp-content/uploads/2021/04/month.csv",
+        "Name",
+    )
+    assert valid_values == frozenset(
+        {
+            "January",
+            "Feburary",
+            "March",
+            "April",
+            "May",
+            "June",
+            "July",
+            "August",
+            "September",
+            "October",
+            "November",
+            "December",
+        }
+    )
+
+    with pytest.raises(ValueError):
+        valid_values = get_valid_values(
+            "https://coucou.csv/",
+            "Name",
+        )
+ """