csv-detective 0.9.3.dev2258__py3-none-any.whl → 0.9.3.dev2348__py3-none-any.whl

csv_detective/detect_labels/FR/other/uai/__init__.py

@@ -1,25 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    words_combinations_list = [
-        "uai",
-        "code etablissement",
-        "code uai",
-        "uai - identifiant",
-        "numero uai",
-        "rne",
-        "numero de l'etablissement",
-        "code rne",
-        "codeetab",
-        "code uai de l'etablissement",
-        "ref uai",
-        "cd rne",
-        "numerouai",
-        "numero d etablissement",
-        "code etablissement",
-        "numero etablissement",
-    ]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/FR/temp/jour_de_la_semaine/__init__.py

@@ -1,16 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    words_combinations_list = [
-        "jour semaine",
-        "type jour",
-        "jour de la semaine",
-        "saufjour",
-        "nomjour",
-        "jour",
-        "jour de fermeture",
-    ]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/FR/temp/mois_de_annee/__init__.py

@@ -1,8 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    words_combinations_list = ["mois de annee", "mois", "month"]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/__init__.py

@@ -1,94 +0,0 @@
-from .FR.geo import (
-    adresse,
-    code_commune_insee,
-    code_departement,
-    code_fantoir,
-    code_postal,
-    code_region,
-    commune,
-    departement,
-    insee_canton,
-    latitude_l93,
-    latitude_wgs_fr_metropole,
-    longitude_l93,
-    longitude_wgs_fr_metropole,
-    pays,
-    region,
-)
-from .FR.other import (
-    code_csp_insee,
-    code_rna,
-    code_waldec,
-    csp_insee,
-    date_fr,
-    insee_ape700,
-    sexe,
-    siren,
-    siret,
-    tel_fr,
-    uai,
-)
-from .FR.temp import jour_de_la_semaine, mois_de_annee
-from .geo import (
-    iso_country_code_alpha2,
-    iso_country_code_alpha3,
-    iso_country_code_numeric,
-    json_geojson,
-    latitude_wgs,
-    latlon_wgs,
-    longitude_wgs,
-    lonlat_wgs,
-)
-from .other import booleen, email, float, int, money, mongo_object_id, twitter, url, uuid
-from .temp import date, datetime_rfc822, year
-
-__all__ = [
-    "adresse",
-    "code_commune_insee",
-    "code_departement",
-    "code_fantoir",
-    "code_postal",
-    "code_region",
-    "commune",
-    "departement",
-    "insee_canton",
-    "latitude_l93",
-    "latitude_wgs_fr_metropole",
-    "longitude_l93",
-    "longitude_wgs_fr_metropole",
-    "pays",
-    "region",
-    "code_csp_insee",
-    "code_rna",
-    "code_waldec",
-    "csp_insee",
-    "date_fr",
-    "insee_ape700",
-    "sexe",
-    "siren",
-    "siret",
-    "tel_fr",
-    "uai",
-    "iso_country_code_alpha2",
-    "iso_country_code_alpha3",
-    "iso_country_code_numeric",
-    "json_geojson",
-    "latitude_wgs",
-    "latlon_wgs",
-    "longitude_wgs",
-    "lonlat_wgs",
-    "jour_de_la_semaine",
-    "mois_de_annee",
-    "booleen",
-    "email",
-    "float",
-    "int",
-    "money",
-    "mongo_object_id",
-    "twitter",
-    "url",
-    "uuid",
-    "date",
-    "datetime_rfc822",
-    "year",
-]

csv_detective/detect_labels/geo/iso_country_code_alpha2/__init__.py

@@ -1,16 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    words_combinations_list = [
-        "iso country code",
-        "code pays",
-        "pays",
-        "country",
-        "nation",
-        "pays code",
-        "code pays (iso)",
-    ]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/geo/iso_country_code_alpha3/__init__.py

@@ -1,16 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    words_combinations_list = [
-        "iso country code",
-        "code pays",
-        "pays",
-        "country",
-        "nation",
-        "pays code",
-        "code pays (iso)",
-    ]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/geo/iso_country_code_numeric/__init__.py

@@ -1,16 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    words_combinations_list = [
-        "iso country code",
-        "code pays",
-        "pays",
-        "country",
-        "nation",
-        "pays code",
-        "code pays (iso)",
-    ]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/geo/json_geojson/__init__.py

@@ -1,17 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    words_combinations_list = [
-        "json geojson",
-        "json",
-        "geojson",
-        "geo shape",
-        "geom",
-        "geometry",
-        "geo shape",
-        "geoshape",
-    ]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/geo/latitude_wgs/__init__.py

@@ -1,30 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    words_combinations_list = [
-        "latitude",
-        "lat",
-        "y",
-        "yf",
-        "yd",
-        "coordonnee y",
-        "coord y",
-        "ycoord",
-        "geocodage y gps",
-        "location latitude",
-        "ylatitude",
-        "ylat",
-        "latitude (y)",
-        "latitudeorg",
-        "coordinates.latitude",
-        "googlemap latitude",
-        "latitudelieu",
-        "latitude googlemap",
-        "latitude wgs84",
-        "y wgs84",
-        "latitude (wgs84)",
-    ]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/geo/latlon_wgs/__init__.py

@@ -1,39 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-COMMON_COORDS_LABELS = [
-    "ban",
-    "coordinates",
-    "coordonnees",
-    "coordonnees insee",
-    "geo",
-    "geopoint",
-    "geoloc",
-    "geolocalisation",
-    "geom",
-    "geometry",
-    "gps",
-    "localisation",
-    "point",
-    "position",
-    "wgs84",
-]
-
-specific = [
-    "latlon",
-    "lat lon",
-    "x y",
-    "xy",
-]
-
-# we aim wide to catch exact matches if possible for the highest possible score
-words = (
-    COMMON_COORDS_LABELS
-    + specific
-    + [w + sep + suf for suf in specific for w in COMMON_COORDS_LABELS for sep in ["", " "]]
-)
-
-
-def _is(header: str) -> float:
-    return header_score(header, words)

csv_detective/detect_labels/geo/longitude_wgs/__init__.py

@@ -1,21 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    #  Does not detect CRS
-    words_combinations_list = [
-        "longitude",
-        "lon",
-        "long",
-        "geocodage x gps",
-        "location longitude",
-        "xlongitude",
-        "lng",
-        "xlong",
-        "x",
-        "xf",
-        "xd",
-    ]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/geo/lonlat_wgs/__init__.py

@@ -1,23 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-from ..latlon_wgs import COMMON_COORDS_LABELS
-
-PROPORTION = 0.5
-
-specific = [
-    "lonlat",
-    "lon lat",
-    "y x",
-    "yx",
-]
-
-# we aim wide to catch exact matches if possible for the highest possible score
-words = (
-    COMMON_COORDS_LABELS
-    + specific
-    + [w + sep + suf for suf in specific for w in COMMON_COORDS_LABELS for sep in ["", " "]]
-)
-
-
-def _is(header: str) -> float:
-    return header_score(header, words)

csv_detective/detect_labels/other/booleen/__init__.py

@@ -1,8 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    words_combinations_list = ["is ", "has ", "est "]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/other/email/__init__.py

@@ -1,20 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    words_combinations_list = [
-        "email",
-        "mail",
-        "courriel",
-        "contact",
-        "mel",
-        "lieucourriel",
-        "coordinates.emailcontact",
-        "e mail",
-        "mo mail",
-        "adresse mail",
-        "adresse email",
-    ]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/other/float/__init__.py

@@ -1,8 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    words_combinations_list = ["part", "ratio", "taux"]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/other/int/__init__.py

@@ -1,8 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    words_combinations_list = ["nb", "nombre", "nbre"]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/other/money/__init__.py

@@ -1,8 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    words_combinations_list = ["budget", "salaire", "euro", "euros", "prêt", "montant"]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/other/mongo_object_id/__init__.py

@@ -1,8 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    words_combinations_list = ["id", "objectid"]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/other/twitter/__init__.py

@@ -1,8 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    words_combinations_list = ["twitter", "twitter account", "twitter username"]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/other/url/__init__.py

@@ -1,23 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    words_combinations_list = [
-        "url",
-        "url source",
-        "site web",
-        "source url",
-        "site internet",
-        "remote url",
-        "web",
-        "site",
-        "lien",
-        "site data",
-        "lien url",
-        "lien vers le fichier",
-        "sitweb",
-        "interneturl",
-    ]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/other/uuid/__init__.py

@@ -1,8 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    words_combinations_list = ["id", "uuid", "guid"]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/temp/date/__init__.py

@@ -1,28 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    words_combinations_list = [
-        "date",
-        "jour",
-        "date de mise a jour",
-        "sns date",
-        "date maj",
-        "rem date",
-        "periode",
-        "date de publication",
-        "dpc",
-        "extract date",
-        "date immatriculation",
-        "date jeu donnees",
-        "datemaj",
-        "dateouv",
-        "date der maj",
-        "dmaj",
-        "jour",
-        "yyyymmdd",
-        "aaaammjj",
-    ]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/temp/datetime_rfc822/__init__.py

@@ -1,19 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    words_combinations_list = [
-        "datetime",
-        "timestamp",
-        "osm_timestamp",
-        "date",
-        "created at",
-        "last update",
-        "date maj",
-        "createdat",
-        "date naissance",
-        "date donnees",
-    ]  # Almost same as IS0, no example in data
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/temp/year/__init__.py

@@ -1,19 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    words_combinations_list = [
-        "year",
-        "annee",
-        "annee depot",
-        "an nais",
-        "exercice",
-        "data year",
-        "annee de publication",
-        "exercice comptable",
-        "annee de naissance",
-        "annee ouverture",
-    ]
-    return header_score(header, words_combinations_list)

csv_detective/load_tests.py

@@ -1,59 +0,0 @@
-import os
-
-from csv_detective import detect_fields, detect_labels  # noqa
-
-
-def get_all_packages(detect_type) -> list:
-    root_dir = os.path.dirname(os.path.abspath(__file__)) + "/" + detect_type
-    modules = []
-    for dirpath, _, filenames in os.walk(root_dir):
-        for filename in filenames:
-            file = os.path.join(dirpath, filename).replace(root_dir, "")
-            if file.endswith("__init__.py"):
-                module = file.replace("__init__.py", "").replace("/", ".").replace("\\", ".")[:-1]
-                if module:
-                    modules.append(detect_type + module)
-    return modules
-
-
-def return_all_tests(
-    user_input_tests: str | list,
-    detect_type: str,
-) -> dict[str, dict]:
-    """
-    returns all tests that have a method _is and are listed in the user_input_tests
-    the function can select a sub_package from csv_detective
-    user_input_tests may look like this:
-        - "ALL": all possible tests are made
-        - "FR.other.siren" (or any other path-like string to one of the tests, or a group of tests, like "FR.geo"):
-        this specifc (group of) test(s) only
-        - ["FR.temp.mois_de_annee", "geo", ...]: only the specified tests will be made ; you may also skip
-        specific (groups of) tests by add "-" at the start (e.g "-temp.date")
-    """
-    assert detect_type in ["detect_fields", "detect_labels"]
-    all_packages = get_all_packages(detect_type=detect_type)
-
-    if isinstance(user_input_tests, str):
-        user_input_tests = [user_input_tests]
-    if "ALL" in user_input_tests or all(x[0] == "-" for x in user_input_tests):
-        tests_to_do = [detect_type]
-    else:
-        tests_to_do = [f"{detect_type}.{x}" for x in user_input_tests if x[0] != "-"]
-    tests_skipped = [f"{detect_type}.{x[1:]}" for x in user_input_tests if x[0] == "-"]
-    # removing specified (groups of) tests
-    all_tests = [
-        # this is why we need to import detect_fields/labels
-        eval(x)
-        for x in all_packages
-        if any([y == x[: len(y)] for y in tests_to_do])
-        and all([y != x[: len(y)] for y in tests_skipped])
-    ]
-    return {
-        test.__name__.split(".")[-1]: {
-            "func": test._is,
-            "prop": test.PROPORTION,
-            "module": test,
-        }
-        for test in all_tests
-        if "_is" in dir(test)
-    }