csv-detective 0.9.3.dev2241__py3-none-any.whl → 0.9.3.dev2319__py3-none-any.whl

csv_detective/detect_fields/geo/iso_country_code_alpha3/__init__.py

@@ -1,14 +0,0 @@
-import re
-from os.path import dirname, join
-
-PROPORTION = 1
-
-with open(join(dirname(__file__), "iso_country_code_alpha3.txt"), "r") as iofile:
-    liste_pays = iofile.read().split("\n")
-
-
-def _is(val):
-    """Renvoie True si val peut etre un code iso pays alpha-3, False sinon"""
-    if not isinstance(val, str) or not bool(re.match(r"[A-Z]{3}$", val)):
-        return False
-    return val in set(liste_pays)

csv_detective/detect_fields/geo/iso_country_code_numeric/__init__.py

@@ -1,15 +0,0 @@
-import re
-from os.path import dirname, join
-
-PROPORTION = 1
-
-with open(join(dirname(__file__), "iso_country_code_numeric.txt"), "r") as iofile:
-    liste_pays = iofile.read().split("\n")
-liste_pays = set(liste_pays)
-
-
-def _is(val):
-    """Renvoie True si val peut etre un code iso pays numerique, False sinon"""
-    if not isinstance(val, str) or not bool(re.match(r"[0-9]{3}$", val)):
-        return False
-    return val in liste_pays

csv_detective/detect_fields/geo/json_geojson/__init__.py

@@ -1,18 +0,0 @@
-import json
-
-PROPORTION = 0.9
-
-
-def _is(val):
-    """Renvoie True si val peut etre un geojson"""
-
-    try:
-        j = json.loads(val)
-        if isinstance(j, dict):
-            if "type" in j and "coordinates" in j:
-                return True
-            if "geometry" in j and "coordinates" in j["geometry"]:
-                return True
-    except Exception:
-        pass
-    return False

csv_detective/detect_fields/geo/latitude_wgs/__init__.py

@@ -1,13 +0,0 @@
-from csv_detective.detect_fields.other.float import _is as is_float
-
-PROPORTION = 1
-
-
-def _is(val):
-    """Renvoie True si val peut etre une latitude"""
-    try:
-        return is_float(val) and float(val) >= -90 and float(val) <= 90
-    except ValueError:
-        return False
-    except OverflowError:
-        return False

csv_detective/detect_fields/geo/latlon_wgs/__init__.py

@@ -1,16 +0,0 @@
-from ..latitude_wgs import _is as is_lat
-from ..longitude_wgs import _is as is_lon
-
-PROPORTION = 1
-
-
-def _is(val):
-    """Renvoie True si val peut etre une latitude,longitude"""
-
-    if not isinstance(val, str) or val.count(",") != 1:
-        return False
-    lat, lon = val.split(",")
-    # handling [lat,lon]
-    if lat.startswith("[") and lon.endswith("]"):
-        lat, lon = lat[1:], lon[:-1]
-    return is_lat(lat) and is_lon(lon.replace(" ", ""))

csv_detective/detect_fields/geo/longitude_wgs/__init__.py

@@ -1,13 +0,0 @@
-from csv_detective.detect_fields.other.float import _is as is_float
-
-PROPORTION = 1
-
-
-def _is(val):
-    """Renvoie True si val peut etre une longitude"""
-    try:
-        return is_float(val) and float(val) >= -180 and float(val) <= 180
-    except ValueError:
-        return False
-    except OverflowError:
-        return False

csv_detective/detect_fields/geo/lonlat_wgs/__init__.py

@@ -1,16 +0,0 @@
-from ..latitude_wgs import _is as is_lat
-from ..longitude_wgs import _is as is_lon
-
-PROPORTION = 1
-
-
-def _is(val):
-    """Renvoie True si val peut etre une longitude,latitude"""
-
-    if not isinstance(val, str) or val.count(",") != 1:
-        return False
-    lon, lat = val.split(",")
-    # handling [lon,lat]
-    if lon.startswith("[") and lat.endswith("]"):
-        lon, lat = lon[1:], lat[:-1]
-    return is_lon(lon) and is_lat(lat.replace(" ", ""))

csv_detective/detect_fields/other/email/__init__.py

@@ -1,10 +0,0 @@
-import re
-
-PROPORTION = 0.9
-
-
-def _is(val):
-    """Detects e-mails"""
-    return isinstance(val, str) and bool(
-        re.match(r"^[a-z0-9._%+-]+@[a-z0-9.-]+\.[a-z]{2,}$", val, re.IGNORECASE)
-    )

csv_detective/detect_fields/other/money/__init__.py

@@ -1,11 +0,0 @@
-from ..float import _is as is_float
-
-currencies = set(["€", "$", "£", "¥"])
-
-PROPORTION = 0.8
-
-
-def _is(val: str):
-    if not isinstance(val, str) or val[-1] not in currencies:
-        return False
-    return is_float(val[:-1])

csv_detective/detect_fields/other/mongo_object_id/__init__.py

@@ -1,8 +0,0 @@
-import re
-
-PROPORTION = 0.8
-
-
-def _is(val):
-    """Detects Mongo ObjectIds"""
-    return isinstance(val, str) and bool(re.match(r"^[0-9a-fA-F]{24}$", val))

csv_detective/detect_fields/other/percent/__init__.py

@@ -1,9 +0,0 @@
-from ..float import _is as is_float
-
-PROPORTION = 0.8
-
-
-def _is(val: str):
-    if not isinstance(val, str) or val[-1] != "%":
-        return False
-    return is_float(val[:-1])

csv_detective/detect_fields/other/twitter/__init__.py

@@ -1,8 +0,0 @@
-import re
-
-PROPORTION = 1
-
-
-def _is(val):
-    """Detects twitter accounts"""
-    return isinstance(val, str) and bool(re.match(r"^@[A-Za-z0-9_]+$", val))

csv_detective/detect_fields/other/url/__init__.py

@@ -1,14 +0,0 @@
-import re
-
-PROPORTION = 1
-url_pattern = re.compile(
-    r"^((https?|ftp)://|www\.)(([A-Za-z0-9-]+\.)+[A-Za-z]{2,6})"
-    r"(/[A-Za-z0-9._~:/?#[@!$&'()*+,;=%-]*)?$"
-)
-
-
-def _is(val):
-    """Detects urls"""
-    if not isinstance(val, str):
-        return False
-    return bool(url_pattern.match(val))

csv_detective/detect_fields/other/uuid/__init__.py

@@ -1,10 +0,0 @@
-import re
-
-PROPORTION = 0.8
-
-
-def _is(val):
-    """Detects UUIDs"""
-    return isinstance(val, str) and bool(
-        re.match(r"^[{]?[0-9a-fA-F]{8}" + "-?([0-9a-fA-F]{4}-?)" + "{3}[0-9a-fA-F]{12}[}]?$", val)
-    )

csv_detective/detect_fields/temp/year/__init__.py

@@ -1,10 +0,0 @@
-PROPORTION = 1
-
-
-def _is(val):
-    """Returns True if val can be a year"""
-    try:
-        val = int(val)
-    except ValueError:
-        return False
-    return (1800 <= val) and (val <= 2100)

csv_detective/detect_labels/FR/geo/adresse/__init__.py

@@ -1,15 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    words_combinations_list = [
-        "adresse",
-        "adresse postale",
-        "adresse geographique",
-        "adr",
-        "adresse complete",
-        "adresse station",
-    ]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/FR/geo/code_commune_insee/__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 = [
-        "code commune insee",
-        "code insee",
-        "codes insee",
-        "code commune",
-        "code insee commune",
-        "insee",
-        "code com",
-        "com",
-    ]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/FR/geo/code_departement/__init__.py

@@ -1,15 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    # "dep": Possible confusion with dep name?
-    words_combinations_list = [
-        "code departement",
-        "code_departement",
-        "dep",
-        "departement",
-        "dept",
-    ]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/FR/geo/code_fantoir/__init__.py

@@ -1,12 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    words_combinations_list = [
-        "cadastre1",
-        "code fantoir",
-        "fantoir",
-    ]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/FR/geo/code_postal/__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 = [
-        "code postal",
-        "postal code",
-        "postcode",
-        "post code",
-        "cp",
-        "codes postaux",
-        "location postcode",
-    ]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/FR/geo/code_region/__init__.py

@@ -1,14 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    # "reg" : possible confusion with region name?
-    words_combinations_list = [
-        "code region",
-        "reg",
-        "code insee region",
-        "region",
-    ]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/FR/geo/commune/__init__.py

@@ -1,12 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    words_combinations_list = [
-        "commune",
-        "ville",
-        "libelle commune",
-    ]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/FR/geo/departement/__init__.py

@@ -1,22 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    words_combinations_list = [
-        "departement",
-        "libelle du departement",
-        "deplib",
-        "nom dept",
-        "dept",
-        "libdepartement",
-        "nom departement",
-        "libelle dep",
-        "libelle departement",
-        "lb departements",
-        "dep libusage",
-        "lb departement",
-        "nom dep",
-    ]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/FR/geo/insee_canton/__init__.py

@@ -1,13 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    words_combinations_list = [
-        "insee canton",
-        "canton",
-        "cant",
-        "nom canton",
-    ]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/FR/geo/latitude_l93/__init__.py

@@ -1,30 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    # Does not always detect CRS
-    words_combinations_list = [
-        "latitude",
-        "lat",
-        "y",
-        "yf",
-        "yd",
-        "y l93",
-        "coordonnee y",
-        "latitude lb93",
-        "coord y",
-        "ycoord",
-        "geocodage y gps",
-        "location latitude",
-        "ylatitude",
-        "ylat",
-        "latitude (y)",
-        "latitudeorg",
-        "coordinates.latitude",
-        "googlemap latitude",
-        "latitudelieu",
-        "latitude googlemap",
-    ]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/FR/geo/latitude_wgs_fr_metropole/__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/FR/geo/longitude_l93/__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/FR/geo/longitude_wgs_fr_metropole/__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/FR/geo/pays/__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 = [
-        "pays",
-        "payslieu",
-        "paysorg",
-        "country",
-        "pays lib",
-        "lieupays",
-        "pays beneficiaire",
-        "nom du pays",
-        "journey start country",
-        "libelle pays",
-        "journey end country",
-    ]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/FR/geo/region/__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 = [
-        "region",
-        "libelle region",
-        "nom region",
-        "libelle reg",
-        "nom reg",
-        "reg libusage",
-        "nom de la region",
-        "regionorg",
-        "regionlieu",
-        "reg",
-        "nom officiel region",
-    ]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/FR/other/code_csp_insee/__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 = ["code csp insee", "code csp"]
-    return header_score(header, words_combinations_list)

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

@@ -1,13 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    words_combinations_list = [
-        "code rna",
-        "rna",
-        "n° inscription association",
-        "identifiant association",
-    ]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/FR/other/code_waldec/__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 = ["code waldec", "waldec"]
-    return header_score(header, words_combinations_list)

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

@@ -1,13 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    # To improve? No specific header found in data
-    words_combinations_list = [
-        "csp insee",
-        "csp",
-        "categorie socioprofessionnelle",
-    ]
-    return header_score(header, words_combinations_list)

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

@@ -1,9 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    # To improve: no header specific to "fr" found in data
-    words_combinations_list = ["date"]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/FR/other/insee_ape700/__init__.py

@@ -1,15 +0,0 @@
-from csv_detective.parsing.text import header_score
-
-PROPORTION = 0.5
-
-
-def _is(header: str) -> float:
-    words_combinations_list = [
-        "code ape",
-        "code activite (ape)",
-        "code naf",
-        "code naf organisme designe",
-        "code naf organisme designant",
-        "base sirene : code ape de l'etablissement siege",
-    ]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/FR/other/sexe/__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 = ["sexe", "sex", "civilite", "genre", "id sexe"]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/FR/other/siren/__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 = [
-        "siren",
-        "siren organisme designe",
-        "siren organisme designant",
-        "n° siren",
-        "siren organisme",
-        "siren titulaire",
-        "numero siren",
-        "epci",
-    ]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/FR/other/siret/__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 = [
-        "siret",
-        "siret d",
-        "num siret",
-        "siretacheteur",
-        "n° siret",
-        "coll siret",
-        "epci",
-    ]
-    return header_score(header, words_combinations_list)

csv_detective/detect_labels/FR/other/tel_fr/__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 = [
-        "telephone",
-        "tel",
-        "tel1",
-        "tel2",
-        "phone",
-        "num tel",
-        "tel mob",
-        "telephone sav",
-        "telephone1",
-        "coordinates.phone",
-        "telephone du lieu",
-    ]
-    return header_score(header, words_combinations_list)