csv-detective 0.8.1.dev1362__py3-none-any.whl → 0.8.1.dev1416__py3-none-any.whl

csv_detective/detect_labels/FR/geo/longitude_l93/__init__.py

@@ -1,44 +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']
-    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)
+        "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

@@ -1,45 +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/FR/geo/pays/__init__.py

@@ -1,45 +1,20 @@
-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 = [
-        'pays',
-        'payslieu',
-        'paysorg',
-        'country',
-        'pays lib',
-        'lieupays',
-        'pays beneficiaire',
-        'nom du pays',
-        'journey start country',
-        'libelle pays',
-        'journey end country'
+        "pays",
+        "payslieu",
+        "paysorg",
+        "country",
+        "pays lib",
+        "lieupays",
+        "pays beneficiaire",
+        "nom du pays",
+        "journey start country",
+        "libelle pays",
+        "journey end country",
     ]
-    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/geo/region/__init__.py

@@ -1,45 +1,20 @@
-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 = [
-        'region',
-        'libelle region',
-        'nom region',
-        'libelle reg',
-        'nom reg',
-        'reg libusage',
-        'nom de la region',
-        'regionorg',
-        'regionlieu',
-        'reg',
-        'nom officiel region'
+        "region",
+        "libelle region",
+        "nom region",
+        "libelle reg",
+        "nom reg",
+        "reg libusage",
+        "nom de la region",
+        "regionorg",
+        "regionlieu",
+        "reg",
+        "nom officiel region",
     ]
-    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/other/code_csp_insee/__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 = ['code csp insee', 'code csp']
-    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 = ["code csp insee", "code csp"]
+    return header_score(header, words_combinations_list)

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

@@ -1,38 +1,13 @@
-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 = [
-        'code rna',
-        'rna',
-        'n° inscription association',
-        'identifiant association'
+        "code rna",
+        "rna",
+        "n° inscription association",
+        "identifiant association",
     ]
-    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/other/code_waldec/__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 = ['code waldec', 'waldec']
-    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 = ["code waldec", "waldec"]
+    return header_score(header, words_combinations_list)

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

@@ -1,37 +1,13 @@
-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:
     # To improve? No specific header found in data
     words_combinations_list = [
-        'csp insee',
-        'csp',
-        'categorie socioprofessionnelle'
+        "csp insee",
+        "csp",
+        "categorie socioprofessionnelle",
     ]
-    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/other/date_fr/__init__.py

@@ -1,33 +1,9 @@
-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
-    '''
-    # To improve: no header specific to 'fr' found in data
-    words_combinations_list = ['date']
-    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:
+    # 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

@@ -1,40 +1,15 @@
-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 = [
-        'code ape',
-        'code activite (ape)',
-        'code naf',
-        'code naf organisme designe',
-        'code naf organisme designant',
-        'base sirene : code ape de l\'etablissement siege'
+        "code ape",
+        "code activite (ape)",
+        "code naf",
+        "code naf organisme designe",
+        "code naf organisme designant",
+        "base sirene : code ape de l'etablissement siege",
     ]
-    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/other/sexe/__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 = ['sexe', 'sex', 'civilite', 'genre', 'id sexe']
-    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 = ["sexe", "sex", "civilite", "genre", "id sexe"]
+    return header_score(header, words_combinations_list)

csv_detective/detect_labels/FR/other/siren/__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 = [
-        'siren',
-        'siren organisme designe',
-        'siren organisme designant',
-        'n° siren',
-        'siren organisme',
-        'siren titulaire',
-        'numero siren'
+        "siren",
+        "siren organisme designe",
+        "siren organisme designant",
+        "n° siren",
+        "siren organisme",
+        "siren titulaire",
+        "numero siren",
     ]
-    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/other/siret/__init__.py

@@ -1,40 +1,15 @@
-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 = [
-        'siret',
-        'siret d',
-        'num siret',
-        'siretacheteur',
-        'n° siret',
-        'coll siret'
+        "siret",
+        "siret d",
+        "num siret",
+        "siretacheteur",
+        "n° siret",
+        "coll siret",
     ]
-    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)