csv-detective 0.10.1.dev2590__py3-none-any.whl → 0.10.1.dev2616__py3-none-any.whl

csv_detective/formats/latitude_l93.py

@@ -2,33 +2,17 @@ from frformat import LatitudeL93
 
 from csv_detective.formats.float import _is as is_float
 from csv_detective.formats.float import float_casting
+from csv_detective.formats.latitude_wgs import SHARED_LATITUDE_LABELS
 
 proportion = 1
 tags = ["fr", "geo"]
 mandatory_label = True
 python_type = "float"
-labels = [
-    "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",
-]
+labels = SHARED_LATITUDE_LABELS | {
+    "y l93": 1,
+    "latitude lb93": 1,
+    "lamby": 1,
+}
 
 _latitudel93 = LatitudeL93()
 

csv_detective/formats/latitude_wgs.py

@@ -1,44 +1,44 @@
 from csv_detective.formats.float import _is as is_float
+from csv_detective.formats.int import _is as is_int
 
 proportion = 1
 tags = ["geo"]
 mandatory_label = True
 python_type = "float"
-labels = [
-    "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)",
-]
+SHARED_LATITUDE_LABELS = {
+    "latitude": 1,
+    "lat": 0.75,
+    "y": 0.5,
+    "yf": 0.5,
+    "yd": 0.5,
+    "coordonnee y": 1,
+    "coord y": 1,
+    "ycoord": 1,
+    "ylat": 1,
+}
+labels = SHARED_LATITUDE_LABELS | {
+    "y gps": 1,
+    "latitude wgs84": 1,
+    "y wgs84": 1,
+    "wsg": 0.75,
+    "gps": 0.5,
+}
 
 
 def _is(val):
     try:
-        return is_float(val) and float(val) >= -90 and float(val) <= 90
-    except ValueError:
-        return False
-    except OverflowError:
+        return (
+            is_float(val)
+            and -90 <= float(val) <= 90
+            # we ideally would like a certain level of decimal precision
+            # but 1.200 is saved as 1.2 in csv so we just discriminate ints
+            and not is_int(val)
+        )
+    except Exception:
         return False
 
 
 _test_values = {
-    True: ["43.2", "-22"],
-    False: ["100"],
+    True: ["43.2872", "-22.61", "-3.0"],
+    False: ["100.1973", "40"],
 }

csv_detective/formats/latitude_wgs_fr_metropole.py

@@ -1,44 +1,19 @@
-from csv_detective.formats.float import _is as is_float
+from csv_detective.formats.latitude_wgs import _is as is_latitude, labels  # noqa
 
 proportion = 1
 tags = ["fr", "geo"]
 mandatory_label = True
 python_type = "float"
-labels = [
-    "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)",
-]
 
 
 def _is(val):
     try:
-        return is_float(val) and float(val) >= 41.3 and float(val) <= 51.3
-    except ValueError:
-        return False
-    except OverflowError:
+        return is_latitude(val) and 41.3 <= float(val) <= 51.3
+    except Exception:
         return False
 
 
 _test_values = {
-    True: ["42.5"],
-    False: ["22.5", "62.5"],
+    True: ["42.576", "42.5"],
+    False: ["22.5"],
 }

csv_detective/formats/latlon_wgs.py

@@ -5,36 +5,36 @@ proportion = 1
 tags = ["geo"]
 mandatory_label = True
 
-SHARED_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",
-]
+SHARED_COORDS_LABELS = {
+    "ban": 1,
+    "coordinates": 1,
+    "coordonnees": 1,
+    "coordonnees insee": 1,
+    "geo": 0.5,
+    "geopoint": 1,
+    "geoloc": 1,
+    "geolocalisation": 1,
+    "geom": 0.75,
+    "geometry": 1,
+    "gps": 1,
+    "localisation": 1,
+    "point": 1,
+    "position": 1,
+    "wgs84": 1,
+}
+
+specific = {
+    "latlon": 1,
+    "lat lon": 1,
+    "x y": 0.75,
+    "xy": 0.75,
+}
 
 # we aim wide to catch exact matches if possible for the highest possible score
 labels = (
     SHARED_COORDS_LABELS
-    + specific
-    + [w + sep + suf for suf in specific for w in SHARED_COORDS_LABELS for sep in ["", " "]]
+    | specific
+    | {w + sep + suf: 1 for suf in specific for w in SHARED_COORDS_LABELS for sep in ["", " "]}
 )
 
 
@@ -49,6 +49,6 @@ def _is(val):
 
 
 _test_values = {
-    True: ["43.2,-22.6", "-10.7,140", "-40.7, 10.8", "[12,-0.28]"],
-    False: ["0.1,192", "-102, 92", "[23.02,4.1", "23.02,4.1]", "160.1,-27"],
+    True: ["43.2,-22.6", "-10.71,140.0", "-40.791, 10.81", "[12.01,-0.28]"],
+    False: ["0.1,192", "-102, 92", "[23.02,4.1", "23.02,4.1]", "160.1,-27", "1,2", "43, -23"],
 }

csv_detective/formats/longitude_l93.py

@@ -2,24 +2,17 @@ from frformat import LongitudeL93
 
 from csv_detective.formats.float import _is as is_float
 from csv_detective.formats.float import float_casting
+from csv_detective.formats.longitude_wgs import SHARED_LONGITUDE_LABELS
 
 proportion = 1
 tags = ["fr", "geo"]
 mandatory_label = True
 python_type = "float"
-labels = [
-    "longitude",
-    "lon",
-    "long",
-    "geocodage x gps",
-    "location longitude",
-    "xlongitude",
-    "lng",
-    "xlong",
-    "x",
-    "xf",
-    "xd",
-]
+labels = SHARED_LONGITUDE_LABELS | {
+    "x l93": 1,
+    "longitude lb93": 1,
+    "lambx": 1,
+}
 
 _longitudel93 = LongitudeL93()
 

csv_detective/formats/longitude_wgs.py

@@ -1,34 +1,47 @@
 from csv_detective.formats.float import _is as is_float
+from csv_detective.formats.int import _is as is_int
 
 proportion = 1
 tags = ["geo"]
 mandatory_label = True
 python_type = "float"
-labels = [
-    "longitude",
-    "lon",
-    "long",
-    "geocodage x gps",
-    "location longitude",
-    "xlongitude",
-    "lng",
-    "xlong",
-    "x",
-    "xf",
-    "xd",
-]
+SHARED_LONGITUDE_LABELS = {
+    "longitude": 1,
+    "long": 0.75,
+    "lon": 0.75,
+    "lng": 0.5,
+    "x": 0.5,
+    "xf": 0.5,
+    "xd": 0.5,
+    "coordonnee x": 1,
+    "coord x": 1,
+    "xcoord": 1,
+    "xlon": 1,
+    "xlong": 1,
+}
+labels = SHARED_LONGITUDE_LABELS | {
+    "x gps": 1,
+    "longitude wgs84": 1,
+    "x wgs84": 1,
+    "wsg": 0.75,
+    "gps": 0.5,
+}
 
 
 def _is(val):
     try:
-        return is_float(val) and float(val) >= -180 and float(val) <= 180
-    except ValueError:
-        return False
-    except OverflowError:
+        return (
+            is_float(val)
+            and -180 <= float(val) <= 180
+            # we ideally would like a certain level of decimal precision
+            # but 1.200 is saved as 1.2 in csv so we just discriminate ints
+            and not is_int(val)
+        )
+    except Exception:
         return False
 
 
 _test_values = {
-    True: ["120", "-20.2"],
-    False: ["-200"],
+    True: ["120.8263", "-20.27", "31.0"],
+    False: ["-200", "20"],
 }

csv_detective/formats/longitude_wgs_fr_metropole.py

@@ -1,34 +1,19 @@
-from csv_detective.formats.float import _is as is_float
+from csv_detective.formats.longitude_wgs import _is as is_longitude, labels  # noqa
 
 proportion = 1
 tags = ["fr", "geo"]
 mandatory_label = True
 python_type = "float"
-labels = [
-    "longitude",
-    "lon",
-    "long",
-    "geocodage x gps",
-    "location longitude",
-    "xlongitude",
-    "lng",
-    "xlong",
-    "x",
-    "xf",
-    "xd",
-]
 
 
 def _is(val):
     try:
-        return is_float(val) and float(val) >= -5.5 and float(val) <= 9.8
-    except ValueError:
-        return False
-    except OverflowError:
+        return is_longitude(val) and -5.5 <= float(val) <= 9.8
+    except Exception:
         return False
 
 
 _test_values = {
-    True: ["-2.5"],
+    True: ["-2.01", "8.0"],
     False: ["12.8"],
 }

csv_detective/formats/lonlat_wgs.py

@@ -6,18 +6,18 @@ proportion = 1
 tags = ["geo"]
 mandatory_label = True
 
-specific = [
-    "lonlat",
-    "lon lat",
-    "y x",
-    "yx",
-]
+specific = {
+    "lonlat": 1,
+    "lon lat": 1,
+    "y x": 0.75,
+    "yx": 0.75,
+}
 
 # we aim wide to catch exact matches if possible for the highest possible score
-words = (
+labels = (
     SHARED_COORDS_LABELS
-    + specific
-    + [w + sep + suf for suf in specific for w in SHARED_COORDS_LABELS for sep in ["", " "]]
+    | specific
+    | {w + sep + suf: 1 for suf in specific for w in SHARED_COORDS_LABELS for sep in ["", " "]}
 )
 
 
@@ -32,6 +32,6 @@ def _is(val):
 
 
 _test_values = {
-    True: ["-22.6,43.2", "140,-10.7", "10.8, -40.7", "[-0.28,12]"],
-    False: ["192,0.1", "92, -102", "[4.1,23.02", "4.1,23.02]", "-27,160.1"],
+    True: ["-22.6,43.012", "140.0,-10.70", "10.829, -40.71", "[-0.28,12.43]"],
+    False: ["192,0.1", "92, -102", "[4.1,23.02", "4.1,23.02]", "-27,160.1", "2,4", "-22, 43.0"],
 }

csv_detective/formats/mois_de_lannee.py

@@ -2,7 +2,7 @@ from unidecode import unidecode
 
 proportion = 1
 tags = ["fr", "temp"]
-labels = ["mois", "month"]
+labels = {"mois": 1, "month": 1}
 
 mois = {
     "janvier",

csv_detective/formats/money.py

@@ -1,7 +1,7 @@
 from csv_detective.formats.float import _is as is_float
 
 proportion = 0.8
-labels = ["budget", "salaire", "euro", "euros", "prêt", "montant"]
+labels = {"budget": 1, "salaire": 1, "euro": 1, "euros": 1, "prêt": 1, "montant": 1}
 
 currencies = {"€", "$", "£", "¥"}
 

csv_detective/formats/mongo_object_id.py

@@ -1,7 +1,7 @@
 import re
 
 proportion = 0.8
-labels = ["id", "objectid"]
+labels = {"id": 1, "objectid": 1}
 
 
 def _is(val):

csv_detective/formats/pays.py

@@ -2,19 +2,17 @@ from frformat import Millesime, Options, Pays
 
 proportion = 0.6
 tags = ["fr", "geo"]
-labels = [
-    "pays",
-    "payslieu",
-    "paysorg",
-    "country",
-    "pays lib",
-    "lieupays",
-    "pays beneficiaire",
-    "nom du pays",
-    "journey start country",
-    "libelle pays",
-    "journey end country",
-]
+labels = {
+    "pays": 1,
+    "payslieu": 1,
+    "paysorg": 1,
+    "country": 1,
+    "pays lib": 1,
+    "lieupays": 1,
+    "pays beneficiaire": 1,
+    "nom du pays": 1,
+    "libelle pays": 1,
+}
 
 _options = Options(
     ignore_case=True,

csv_detective/formats/percent.py

@@ -1,7 +1,7 @@
 from csv_detective.formats.float import _is as is_float
 
 proportion = 0.8
-labels = []
+labels = {"pourcent": 1, "part": 0.75, "pct": 0.75}
 
 
 def _is(val):

csv_detective/formats/region.py

@@ -2,19 +2,19 @@ from frformat import Millesime, Options, Region
 
 proportion = 1
 tags = ["fr", "geo"]
-labels = [
-    "region",
-    "libelle region",
-    "nom region",
-    "libelle reg",
-    "nom reg",
-    "reg libusage",
-    "nom de la region",
-    "regionorg",
-    "regionlieu",
-    "reg",
-    "nom officiel region",
-]
+labels = {
+    "region": 1,
+    "libelle region": 1,
+    "nom region": 1,
+    "libelle reg": 1,
+    "nom reg": 1,
+    "reg libusage": 1,
+    "nom de la region": 1,
+    "regionorg": 1,
+    "regionlieu": 1,
+    "reg": 0.5,
+    "nom officiel region": 1,
+}
 
 _extra_valid_values_set = frozenset(
     {

csv_detective/formats/sexe.py

@@ -2,7 +2,7 @@ from csv_detective.parsing.text import _process_text
 
 proportion = 1
 tags = ["fr"]
-labels = ["sexe", "sex", "civilite", "genre", "id sexe"]
+labels = {"sexe": 1, "sex": 1, "civilite": 1, "genre": 1}
 
 
 def _is(val):

csv_detective/formats/siren.py

@@ -3,16 +3,14 @@ import re
 proportion = 0.9
 tags = ["fr"]
 mandatory_label = True
-labels = [
-    "siren",
-    "siren organisme designe",
-    "siren organisme designant",
-    "n° siren",
-    "siren organisme",
-    "siren titulaire",
-    "numero siren",
-    "epci",
-]
+labels = {
+    "siren": 1,
+    "n° siren": 1,
+    "siren organisme": 1,
+    "siren titulaire": 1,
+    "numero siren": 1,
+    "epci": 1,
+}
 
 
 def _is(val):

csv_detective/formats/siret.py

@@ -3,15 +3,14 @@ import re
 proportion = 0.8
 tags = ["fr"]
 mandatory_label = True
-labels = [
-    "siret",
-    "siret d",
-    "num siret",
-    "siretacheteur",
-    "n° siret",
-    "coll siret",
-    "epci",
-]
+labels = {
+    "siret": 1,
+    "num siret": 1,
+    "siretacheteur": 1,
+    "n° siret": 1,
+    "coll siret": 1,
+    "epci": 1,
+}
 
 
 def _is(val):

csv_detective/formats/tel_fr.py

@@ -2,19 +2,13 @@ import re
 
 proportion = 0.7
 tags = ["fr"]
-labels = [
-    "telephone",
-    "tel",
-    "tel1",
-    "tel2",
-    "phone",
-    "num tel",
-    "tel mob",
-    "telephone sav",
-    "telephone1",
-    "coordinates.phone",
-    "telephone du lieu",
-]
+labels = {
+    "telephone": 1,
+    "tel": 1,
+    "phone": 1,
+    "num tel": 1,
+    "tel mob": 1,
+}
 
 
 def _is(val):

csv_detective/formats/uai.py

@@ -2,24 +2,23 @@ import re
 
 proportion = 0.8
 tags = ["fr"]
-labels = [
-    "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",
-]
+labels = {
+    "uai": 1,
+    "code etablissement": 1,
+    "code uai": 1,
+    "uai - identifiant": 1,
+    "numero uai": 1,
+    "rne": 0.75,
+    "numero de l'etablissement": 1,
+    "code rne": 1,
+    "codeetab": 1,
+    "code uai de l'etablissement": 1,
+    "ref uai": 1,
+    "cd rne": 1,
+    "numerouai": 1,
+    "numero d etablissement": 1,
+    "numero etablissement": 1,
+}
 
 
 def _is(val):