csv-detective 0.8.1.dev1362__py3-none-any.whl → 0.8.1.dev1380__py3-none-any.whl

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

@@ -1,50 +1,25 @@
-from csv_detective.utils import is_word_in_string
-from csv_detective.parsing.text import _process_text
+from csv_detective.parsing.text import header_score
 
 PROPORTION = 0.5
 
 
-def _is(header):
-    '''
-    Returns 1 if the (processed) header matches one of the expected words combination,
-    else 0
-    '''
-
+def _is(header: str) -> float:
     words_combinations_list = [
-        'uai',
-        'code etablissement',
-        'code uai',
-        'uai - identifiant',
-        'numero uai',
-        'rne',
+        "uai",
+        "code etablissement",
+        "code uai",
+        "uai - identifiant",
+        "numero uai",
+        "rne",
         "numero de l'etablissement",
-        'code rne',
-        'codeetab',
+        "code rne",
+        "codeetab",
         "code uai de l'etablissement",
-        'ref uai',
-        'cd rne',
-        'numerouai',
-        'numero d etablissement',
-        'code etablissement',
-        'numero etablissement'
+        "ref uai",
+        "cd rne",
+        "numerouai",
+        "numero d etablissement",
+        "code etablissement",
+        "numero etablissement",
     ]
-    processed_header = _process_text(header)
-
-    header_matches_words_combination = float(
-        any(
-            [
-                words_combination == processed_header for words_combination in words_combinations_list
-            ]
-        )
-    )
-    words_combination_in_header = 0.5 * float(
-        any(
-            [
-                is_word_in_string(
-                    words_combination, processed_header
-                ) for words_combination in words_combinations_list
-            ]
-        )
-    )
-
-    return max(header_matches_words_combination, words_combination_in_header)
+    return header_score(header, words_combinations_list)

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

@@ -1,41 +1,16 @@
-from csv_detective.utils import is_word_in_string
-from csv_detective.parsing.text import _process_text
+from csv_detective.parsing.text import header_score
 
 PROPORTION = 0.5
 
 
-def _is(header):
-    '''
-    Returns 1 if the (processed) header matches one of the expected words combination,
-    else 0
-    '''
-
+def _is(header: str) -> float:
     words_combinations_list = [
-        'jour semaine',
-        'type jour',
-        'jour de la semaine',
-        'saufjour',
-        'nomjour',
-        'jour',
-        'jour de fermeture'
+        "jour semaine",
+        "type jour",
+        "jour de la semaine",
+        "saufjour",
+        "nomjour",
+        "jour",
+        "jour de fermeture",
     ]
-    processed_header = _process_text(header)
-
-    header_matches_words_combination = float(
-        any(
-            [
-                words_combination == processed_header for words_combination in words_combinations_list
-            ]
-        )
-    )
-    words_combination_in_header = 0.5 * float(
-        any(
-            [
-                is_word_in_string(
-                    words_combination, processed_header
-                ) for words_combination in words_combinations_list
-            ]
-        )
-    )
-
-    return max(header_matches_words_combination, words_combination_in_header)
+    return header_score(header, words_combinations_list)

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

@@ -1,33 +1,8 @@
-from csv_detective.utils import is_word_in_string
-from csv_detective.parsing.text import _process_text
+from csv_detective.parsing.text import header_score
 
 PROPORTION = 0.5
 
 
-def _is(header):
-    '''
-    Returns 1 if the (processed) header matches one of the expected words combination,
-    else 0
-    '''
-
-    words_combinations_list = ['mois de annee', 'mois']
-    processed_header = _process_text(header)
-
-    header_matches_words_combination = float(
-        any(
-            [
-                words_combination == processed_header for words_combination in words_combinations_list
-            ]
-        )
-    )
-    words_combination_in_header = 0.5 * float(
-        any(
-            [
-                is_word_in_string(
-                    words_combination, processed_header
-                ) for words_combination in words_combinations_list
-            ]
-        )
-    )
-
-    return max(header_matches_words_combination, words_combination_in_header)
+def _is(header: str) -> float:
+    words_combinations_list = ["mois de annee", "mois", "month"]
+    return header_score(header, words_combinations_list)

csv_detective/detect_labels/geo/iso_country_code_alpha2/__init__.py

@@ -1,41 +1,16 @@
-from csv_detective.utils import is_word_in_string
-from csv_detective.parsing.text import _process_text
+from csv_detective.parsing.text import header_score
 
 PROPORTION = 0.5
 
 
-def _is(header):
-    '''
-    Returns 1 if the (processed) header matches one of the expected words combination,
-    else 0
-    '''
-
+def _is(header: str) -> float:
     words_combinations_list = [
-        'iso country code',
-        'code pays',
-        'pays',
-        'country',
-        'nation',
-        'pays code',
-        'code pays (iso)'
+        "iso country code",
+        "code pays",
+        "pays",
+        "country",
+        "nation",
+        "pays code",
+        "code pays (iso)",
     ]
-    processed_header = _process_text(header)
-
-    header_matches_words_combination = float(
-        any(
-            [
-                words_combination == processed_header for words_combination in words_combinations_list
-            ]
-        )
-    )
-    words_combination_in_header = 0.5 * float(
-        any(
-            [
-                is_word_in_string(
-                    words_combination, processed_header
-                ) for words_combination in words_combinations_list
-            ]
-        )
-    )
-
-    return max(header_matches_words_combination, words_combination_in_header)
+    return header_score(header, words_combinations_list)

csv_detective/detect_labels/geo/iso_country_code_alpha3/__init__.py

@@ -1,41 +1,16 @@
-from csv_detective.utils import is_word_in_string
-from csv_detective.parsing.text import _process_text
+from csv_detective.parsing.text import header_score
 
 PROPORTION = 0.5
 
 
-def _is(header):
-    '''
-    Returns 1 if the (processed) header matches one of the expected words combination,
-    else 0
-    '''
-
+def _is(header: str) -> float:
     words_combinations_list = [
-        'iso country code',
-        'code pays',
-        'pays',
-        'country',
-        'nation',
-        'pays code',
-        'code pays (iso)'
+        "iso country code",
+        "code pays",
+        "pays",
+        "country",
+        "nation",
+        "pays code",
+        "code pays (iso)",
     ]
-    processed_header = _process_text(header)
-
-    header_matches_words_combination = float(
-        any(
-            [
-                words_combination == processed_header for words_combination in words_combinations_list
-            ]
-        )
-    )
-    words_combination_in_header = 0.5 * float(
-        any(
-            [
-                is_word_in_string(
-                    words_combination, processed_header
-                ) for words_combination in words_combinations_list
-            ]
-        )
-    )
-
-    return max(header_matches_words_combination, words_combination_in_header)
+    return header_score(header, words_combinations_list)

csv_detective/detect_labels/geo/iso_country_code_numeric/__init__.py

@@ -1,41 +1,16 @@
-from csv_detective.utils import is_word_in_string
-from csv_detective.parsing.text import _process_text
+from csv_detective.parsing.text import header_score
 
 PROPORTION = 0.5
 
 
-def _is(header):
-    '''
-    Returns 1 if the (processed) header matches one of the expected words combination,
-    else 0
-    '''
-
+def _is(header: str) -> float:
     words_combinations_list = [
-        'iso country code',
-        'code pays',
-        'pays',
-        'country',
-        'nation',
-        'pays code',
-        'code pays (iso)'
+        "iso country code",
+        "code pays",
+        "pays",
+        "country",
+        "nation",
+        "pays code",
+        "code pays (iso)",
     ]
-    processed_header = _process_text(header)
-
-    header_matches_words_combination = float(
-        any(
-            [
-                words_combination == processed_header for words_combination in words_combinations_list
-            ]
-        )
-    )
-    words_combination_in_header = 0.5 * float(
-        any(
-            [
-                is_word_in_string(
-                    words_combination, processed_header
-                ) for words_combination in words_combinations_list
-            ]
-        )
-    )
-
-    return max(header_matches_words_combination, words_combination_in_header)
+    return header_score(header, words_combinations_list)

csv_detective/detect_labels/geo/json_geojson/__init__.py

@@ -1,42 +1,17 @@
-from csv_detective.utils import is_word_in_string
-from csv_detective.parsing.text import _process_text
+from csv_detective.parsing.text import header_score
 
 PROPORTION = 0.5
 
 
-def _is(header):
-    '''
-    Returns 1 if the (processed) header matches one of the expected words combination,
-    else 0
-    '''
-
+def _is(header: str) -> float:
     words_combinations_list = [
-        'json geojson',
-        'json',
-        'geojson',
-        'geo shape',
-        'geom',
-        'geometry',
-        'geo shape',
-        'geoshape'
+        "json geojson",
+        "json",
+        "geojson",
+        "geo shape",
+        "geom",
+        "geometry",
+        "geo shape",
+        "geoshape",
     ]
-    processed_header = _process_text(header)
-
-    header_matches_words_combination = float(
-        any(
-            [
-                words_combination == processed_header for words_combination in words_combinations_list
-            ]
-        )
-    )
-    words_combination_in_header = 0.5 * float(
-        any(
-            [
-                is_word_in_string(
-                    words_combination, processed_header
-                ) for words_combination in words_combinations_list
-            ]
-        )
-    )
-
-    return max(header_matches_words_combination, words_combination_in_header)
+    return header_score(header, words_combinations_list)

csv_detective/detect_labels/geo/latitude_wgs/__init__.py

@@ -1,55 +1,30 @@
-from csv_detective.utils import is_word_in_string
-from csv_detective.parsing.text import _process_text
+from csv_detective.parsing.text import header_score
 
 PROPORTION = 0.5
 
 
-def _is(header):
-    '''
-    Returns 1 if the (processed) header matches one of the expected words combination,
-    else 0
-    '''
-
+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)'
+        "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)",
     ]
-    processed_header = _process_text(header)
-
-    header_matches_words_combination = float(
-        any(
-            [
-                words_combination == processed_header for words_combination in words_combinations_list
-            ]
-        )
-    )
-    words_combination_in_header = 0.5 * float(
-        any(
-            [
-                is_word_in_string(
-                    words_combination, processed_header
-                ) for words_combination in words_combinations_list
-            ]
-        )
-    )
-
-    return max(header_matches_words_combination, words_combination_in_header)
+    return header_score(header, words_combinations_list)

csv_detective/detect_labels/geo/latlon_wgs/__init__.py

@@ -1,67 +1,43 @@
-from csv_detective.utils import is_word_in_string
-from csv_detective.parsing.text import _process_text
+from csv_detective.parsing.text import header_score
 
 PROPORTION = 0.5
 
 
-def _is(header):
-    '''
-    Returns 1 if the (processed) header matches one of the expected words combination,
-    else 0
-    '''
-
+def _is(header: str) -> float:
     words_combinations_list = [
-        'latlon wgs',
-        'latlon',
-        'geo point',
-        'geo point 2d',
-        'wgs84',
-        'geolocalisation',
-        'geo',
-        'coordonnees finales',
-        'coordonnees',
-        'coordonnees ban',
-        'xy',
-        'geometry x y',
-        'coordonnees insee',
-        'coordonnees geographiques',
-        'position',
-        'coordonnes gps',
-        'geopoint',
-        'geom x y',
-        'coord gps',
-        'latlong',
-        'position geographique',
-        'c geo',
-        'coordonnes geoloc',
-        'lat lon',
-        'code geo',
-        'geo localisation',
-        'coordonnes geo',
-        'geo cp',
-        'x y',
-        'geo coordinates',
-        'point geo',
-        'point geo insee',
-        'coordonnees geoloc',
-        'coordonnees xy'
+        "latlon wgs",
+        "latlon",
+        "geo point",
+        "geo point 2d",
+        "wgs84",
+        "geolocalisation",
+        "geo",
+        "coordonnees finales",
+        "coordonnees",
+        "coordonnees ban",
+        "xy",
+        "geometry x y",
+        "coordonnees insee",
+        "coordonnees geographiques",
+        "position",
+        "coordonnes gps",
+        "geopoint",
+        "geom x y",
+        "coord gps",
+        "latlong",
+        "position geographique",
+        "c geo",
+        "coordonnes geoloc",
+        "lat lon",
+        "code geo",
+        "geo localisation",
+        "coordonnes geo",
+        "geo cp",
+        "x y",
+        "geo coordinates",
+        "point geo",
+        "point geo insee",
+        "coordonnees geoloc",
+        "coordonnees xy",
     ]
-    processed_header = _process_text(header)
-
-    header_matches_words_combination = float(
-        any(
-            [
-                words_combination == processed_header for words_combination in words_combinations_list
-            ]
-        )
-    )
-    words_combination_in_header = 0.5 * float(
-        any(
-            [
-                is_word_in_string(
-                    words_combination, processed_header
-                ) for words_combination in words_combinations_list
-            ]
-        )
-    )
-    return max(header_matches_words_combination, words_combination_in_header)
+    return header_score(header, words_combinations_list)

csv_detective/detect_labels/geo/longitude_wgs/__init__.py

@@ -1,45 +1,21 @@
-from csv_detective.utils import is_word_in_string
-from csv_detective.parsing.text import _process_text
+from csv_detective.parsing.text import header_score
 
 PROPORTION = 0.5
 
 
-def _is(header):
-    '''
-    Returns 1 if the (processed) header matches one of the expected words combination,
-    else 0
-    '''
+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'
+        "longitude",
+        "lon",
+        "long",
+        "geocodage x gps",
+        "location longitude",
+        "xlongitude",
+        "lng",
+        "xlong",
+        "x",
+        "xf",
+        "xd",
     ]
-    processed_header = _process_text(header)
-
-    header_matches_words_combination = float(
-        any(
-            [
-                words_combination == processed_header for words_combination in words_combinations_list
-            ]
-        )
-    )
-    words_combination_in_header = 0.5 * float(
-        any(
-            [
-                is_word_in_string(
-                    words_combination, processed_header
-                ) for words_combination in words_combinations_list
-            ]
-        )
-    )
-
-    return max(header_matches_words_combination, words_combination_in_header)
+    return header_score(header, words_combinations_list)

csv_detective/detect_labels/other/booleen/__init__.py

@@ -1,34 +1,8 @@
-from csv_detective.utils import is_word_in_string
-from csv_detective.parsing.text import _process_text
+from csv_detective.parsing.text import header_score
 
 PROPORTION = 0.5
 
 
-def _is(header):
-    '''
-    Returns 1 if the (processed) header matches one of the expected words combination,
-    else 0
-    '''
-
-    #  Not relevant to make it match with specific words (find other rules)
-    words_combinations_list = []
-    processed_header = _process_text(header)
-
-    header_matches_words_combination = float(
-        any(
-            [
-                words_combination == processed_header for words_combination in words_combinations_list
-            ]
-        )
-    )
-    words_combination_in_header = 0.5 * float(
-        any(
-            [
-                is_word_in_string(
-                    words_combination, processed_header
-                ) for words_combination in words_combinations_list
-            ]
-        )
-    )
-
-    return max(header_matches_words_combination, words_combination_in_header)
+def _is(header: str) -> float:
+    words_combinations_list = ["is_", "has_", "est_"]
+    return header_score(header, words_combinations_list)