csv-detective 0.6.7__py3-none-any.whl → 0.9.3.dev2438__py3-none-any.whl

csv_detective-0.6.7.dist-info/METADATA

@@ -1,23 +0,0 @@
-Metadata-Version: 2.1
-Name: csv_detective
-Version: 0.6.7
-Summary: Detect CSV column content
-Home-page: https://github.com/etalab/csv_detective
-Author: Etalab
-Author-email: opendatateam@data.gouv.fr
-License: http://www.fsf.org/licensing/licenses/agpl-3.0.html
-Keywords: CSV data processing encoding guess parser tabular
-Classifier: Development Status :: 2 - Pre-Alpha
-Classifier: License :: OSI Approved :: GNU Affero General Public License v3
-Classifier: Operating System :: POSIX
-Classifier: Programming Language :: Python :: 3
-Classifier: Topic :: Scientific/Engineering :: Information Analysis
-Description-Content-Type: text/markdown
-License-File: LICENSE.AGPL.txt
-Requires-Dist: boto3 ==1.26.65
-Requires-Dist: faust-cchardet ==2.1.19
-Requires-Dist: pandas ==1.5.3
-Requires-Dist: pytest ==7.2.1
-Requires-Dist: python-dateutil ==2.8.2
-Requires-Dist: Unidecode ==1.3.6
-

csv_detective-0.6.7.dist-info/RECORD

@@ -1,150 +0,0 @@
-csv_detective/__init__.py,sha256=GXnXV3cFmzDnIeFijtPpxojjjKDkoNrbwKLQwhYI7RY,22
-csv_detective/all_packages.txt,sha256=MzN0kVnX99LU0PCqrO7JBjrYMngXn7GByhGYwTvbo74,4681
-csv_detective/cli.py,sha256=Ua7SE1wMH2uFUsTmfumh4nJk7O06okpMd2gvjUDO1II,1048
-csv_detective/detection.py,sha256=FDC7gLe4CNWrMf9py78JXv1vpvjTrS7UwdCA7TQ7u_Y,12249
-csv_detective/explore_csv.py,sha256=KBLMKlyc_5bRJLQH9MYAx9VDTeuD5TzTdjflHR4WnPE,14605
-csv_detective/process_text.py,sha256=1KMgoTnfUKghNcmDQp_84ryLwcMP2PR3sTyCnuOeeAI,1236
-csv_detective/s3_utils.py,sha256=1cIVdQUYY2ovErbMwp72Gqtqx2bkB8nfVhn-QaOFTT0,1451
-csv_detective/schema_generation.py,sha256=D1Cq4QRajsKtY8EJSwbRTIB-T_Cb2ZpcmYtCrJ6DvJQ,13135
-csv_detective/utils.py,sha256=0cpPlcgB6oOpxPtVv6cSqwJGYOYt8GN8uxviABxLwd0,8263
-csv_detective/detect_fields/__init__.py,sha256=CchNbi1vrgIGh_uBexXZTzfjBETDY0kQLjI-PAquU8M,921
-csv_detective/detect_fields/FR/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-csv_detective/detect_fields/FR/geo/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-csv_detective/detect_fields/FR/geo/adresse/__init__.py,sha256=s0Tvyjf09DHksFRlbbtHwepIxRJZk328PvZuac7h0Ok,1647
-csv_detective/detect_fields/FR/geo/code_commune_insee/__init__.py,sha256=34ugFPPjduSjH466aw3XcMcCi97kAaJX2RiguEHOW5M,705
-csv_detective/detect_fields/FR/geo/code_commune_insee/code_commune_insee.txt,sha256=DgMtDlS5tX464k0RgSnSmgbIN9Z3BfK7gOt-k1uLfyk,225600
-csv_detective/detect_fields/FR/geo/code_departement/__init__.py,sha256=9jadtQHMDpcdYKEis5BJpQrpWvIubKarUECPcPRyFJY,382
-csv_detective/detect_fields/FR/geo/code_fantoir/__init__.py,sha256=L9poDp6kuZBdpVjVoHqfslDGEXWl8t2U8Hl6FXCz4N4,397
-csv_detective/detect_fields/FR/geo/code_fantoir/code_fantoir.txt,sha256=nMQcnFaoTyLnIOSRnv0e30F1plvHeMEzr_ZfMwoh6bM,130610
-csv_detective/detect_fields/FR/geo/code_postal/__init__.py,sha256=2DDZl-AuDRKJKg2AEsICzupEMf1_w6wEbgNUFGMHyAE,464
-csv_detective/detect_fields/FR/geo/code_postal/code_postal.txt,sha256=J4XyH2TAYqTtBTyk0ySrmIMXpTlu4H7aFnd861gcf2U,220932
-csv_detective/detect_fields/FR/geo/code_region/__init__.py,sha256=tGFxKHl1sVtFBftSWGi1SXXoDPJcuDcZA_c6YXqjStY,333
-csv_detective/detect_fields/FR/geo/commune/__init__.py,sha256=uhWvl6NqI-AfE2mPCFrPfuBUKR_MAZM1kn81UabdjmM,540
-csv_detective/detect_fields/FR/geo/commune/commune.txt,sha256=IiKhO6-1XmcbAjPXLRvPyR3trPbCAHwCrLDJjRhutT8,468480
-csv_detective/detect_fields/FR/geo/departement/__init__.py,sha256=E7BdP-5PEW9N6AVuzr4vfccebuvC9M286RB1YvDdZN0,525
-csv_detective/detect_fields/FR/geo/departement/departement.txt,sha256=rgNc9QO3ahH5Z-FzDnrp8YaMP140KNi2EYFkoreIAhk,1012
-csv_detective/detect_fields/FR/geo/insee_canton/__init__.py,sha256=yBjm694LpLphaLoEaLq1D3J52oHiSjc_FgxW-viMaV0,543
-csv_detective/detect_fields/FR/geo/insee_canton/canton2017.txt,sha256=foCRrjuobtpKqkjaEKLwUzzk467Lo9Z8sOwFFXrmtj8,98052
-csv_detective/detect_fields/FR/geo/insee_canton/cantons.txt,sha256=8eiau0QfU58AWqhl9N8N1kYHWmh1U8D-Nyfb5R7z4kg,25539
-csv_detective/detect_fields/FR/geo/latitude_l93/__init__.py,sha256=gOGelADhufPOuhuAl_m9wsYyJoWBUjqaN1gZttf-qA8,343
-csv_detective/detect_fields/FR/geo/latitude_wgs_fr_metropole/__init__.py,sha256=WjPHg8s0ND6bOwS-yo6FP1dnwD-6SWg9oH1K0avHsbI,344
-csv_detective/detect_fields/FR/geo/longitude_l93/__init__.py,sha256=Gf8IPsjzBYumGuV5-7_eW8s_Gm2tOMgDBKgwDZY3kcw,344
-csv_detective/detect_fields/FR/geo/longitude_wgs_fr_metropole/__init__.py,sha256=d4fLK4IndwllDhsddyTbyRiPfc8O9wT0pLIRI_C3QvQ,344
-csv_detective/detect_fields/FR/geo/pays/__init__.py,sha256=lDTRA4EkbjcFKoOcWaZ0c8OBcwig4Bovj7hIzWipZvI,402
-csv_detective/detect_fields/FR/geo/pays/pays.txt,sha256=prUV8eSVIuxNspIYHDPg9x_MC0DgFnbr29uxFLcGceU,2549
-csv_detective/detect_fields/FR/geo/region/__init__.py,sha256=dDjK_TrsdOKgsiS-5Ofs98ND6v1Of_iw6XrfhSnntn4,400
-csv_detective/detect_fields/FR/geo/region/region.txt,sha256=wv77qAdQ0FSc33kvnhmg4LBBVKE4tvdgpZV_NDz3o-Y,560
-csv_detective/detect_fields/FR/other/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-csv_detective/detect_fields/FR/other/code_csp_insee/__init__.py,sha256=XCegXF9rmf0yYv2_xFt_HemYsEP_GAzk-eNLa1PUVJw,512
-csv_detective/detect_fields/FR/other/code_csp_insee/code_csp_insee.txt,sha256=rbcjtMP6qTZ7BTU6ZegkiXKCruqY_m9Ep6ZgRabFS_E,2486
-csv_detective/detect_fields/FR/other/code_rna/__init__.py,sha256=Z4AFN4BeBFO9OAZ4lkE4mybSDyMd7uu1PwhDjq2It_k,120
-csv_detective/detect_fields/FR/other/code_waldec/__init__.py,sha256=vfCl1ENCTiJUDF4Dlse5tT2LD9k7Ed674a81VrAe1g0,270
-csv_detective/detect_fields/FR/other/csp_insee/__init__.py,sha256=47r_-CJneGX0C4OB_YHOvMn3TCvg4zKULh1ervIEDdQ,442
-csv_detective/detect_fields/FR/other/csp_insee/csp_insee.txt,sha256=kgKaKc-5PHu5U4--ugLjpFyMNtTU9CGdZ9ANU3YAsM4,32879
-csv_detective/detect_fields/FR/other/date_fr/__init__.py,sha256=xJdMpBJoqe_XDkh-WkH8ZtT2AN43vfAEzueK7faL3GM,259
-csv_detective/detect_fields/FR/other/insee_ape700/__init__.py,sha256=G6EliaNJw_RCpHaAGfTTCkdKe_OxPqDUjpcLikmr4eQ,465
-csv_detective/detect_fields/FR/other/insee_ape700/insee_ape700.txt,sha256=nKgslakENwgE7sPkVNHqR23iXuxF02p9-v5MC2_ntx8,4398
-csv_detective/detect_fields/FR/other/sexe/__init__.py,sha256=YkX4vC85oul30H1Qejsnid_WFv2i7CKK8LH83x6SfRk,215
-csv_detective/detect_fields/FR/other/siren/__init__.py,sha256=jjCXN5xJPD_pOGNSOc3XDIm5jMX4YS2Nk0nfwt89GWs,388
-csv_detective/detect_fields/FR/other/siret/__init__.py,sha256=Yo0YwttbJUZCSIamWBmZmVrAiOLABHywcY5b7CJ_14c,653
-csv_detective/detect_fields/FR/other/tel_fr/__init__.py,sha256=8rrNHCs9mjQ7RVpOhjBMMOsgCI3ormvw4LnrUxno4YI,289
-csv_detective/detect_fields/FR/other/uai/__init__.py,sha256=6pbVoU5g3Jok4OrWmVITHazXriTpKRPkrv-PHppklI4,299
-csv_detective/detect_fields/FR/temp/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-csv_detective/detect_fields/FR/temp/jour_de_la_semaine/__init__.py,sha256=jklVG-8Hcv1bjsKLqC6uN0zwmGkPPTgSa0p4iThz6DE,341
-csv_detective/detect_fields/FR/temp/mois_de_annee/__init__.py,sha256=dzk4BAszoKO_FAAPYrocWpKg7zpl8JukQTPkfSmt3H4,527
-csv_detective/detect_fields/geo/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-csv_detective/detect_fields/geo/iso_country_code_alpha2/__init__.py,sha256=rwIqUgW0DUOXevg1I-ah6uhm00QcKde2bc2YOmwZ1Jc,405
-csv_detective/detect_fields/geo/iso_country_code_alpha2/iso_country_code_alpha2.txt,sha256=YyPlDqCdz65ecf4Wes_r0P4rDSJG35niXtjc4MmctXM,1740
-csv_detective/detect_fields/geo/iso_country_code_alpha3/__init__.py,sha256=_xnwOcW2G3tBxHBFGPguK0fo-Kc8j9s_KC6mqTyjrbY,381
-csv_detective/detect_fields/geo/iso_country_code_alpha3/iso_country_code_alpha3.txt,sha256=aYqKSohgXuBtcIBfF52f8JWYDdxL_HV_Ol1srGnWBp4,1003
-csv_detective/detect_fields/geo/iso_country_code_numeric/__init__.py,sha256=GAHzTvbAgG6kCNFzLh6K-m01CbFLgL_mnCP3jWmzWPY,408
-csv_detective/detect_fields/geo/iso_country_code_numeric/iso_country_code_numeric.txt,sha256=2GtEhuporsHYV-pU4q9kfXU5iOtfW5C0GYBTTKQtnnA,1004
-csv_detective/detect_fields/geo/json_geojson/__init__.py,sha256=FPHOfTrfXJs62-NgeOcNGOvwPd7I1fEVp8lTdMNfj3w,433
-csv_detective/detect_fields/geo/latitude_wgs/__init__.py,sha256=ArS6PuYEd0atZwSqNDZhXZz1TwzdiwdV8ovRYTOacpg,327
-csv_detective/detect_fields/geo/latlon_wgs/__init__.py,sha256=yvjNFyiF-xbhsL0LzC_mS3-_m74t47tItNxbd_nrQsM,254
-csv_detective/detect_fields/geo/longitude_wgs/__init__.py,sha256=myGcoTQUhVPyHDDXeWu4yj7vuqVkobbu1MbDaw3wS5Q,323
-csv_detective/detect_fields/other/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-csv_detective/detect_fields/other/booleen/__init__.py,sha256=wfAa0aPOO63SIjQoPXfB50xl7YfEQ8xwYYhv8K-VOkE,256
-csv_detective/detect_fields/other/email/__init__.py,sha256=TDC1XK9a3A-KTAE9hxVy-V3xmMcVoQHjfYSM0NzRt_A,153
-csv_detective/detect_fields/other/float/__init__.py,sha256=P9VdTaRHYOxCcr4r5Om0-BtcdjlKiEdQtUJgPKvuWik,427
-csv_detective/detect_fields/other/int/__init__.py,sha256=pkYmP_DG5wIB6-tVAbbj4jRVSgzGTRdpOftnkVsX0fw,218
-csv_detective/detect_fields/other/json/__init__.py,sha256=CMhfnA0_O3B6FBwsYgjaTPOv_wQB2nBDNWO9jSYyP4Y,527
-csv_detective/detect_fields/other/mongo_object_id/__init__.py,sha256=znlOyispn4k_oFxiVXX7LwhFG5bz63Nhv5_zny7Zbj0,131
-csv_detective/detect_fields/other/twitter/__init__.py,sha256=EoRUXII5aoSrPCSLaKcTjH2g0P5ojF2fOlxeqm5NfQs,129
-csv_detective/detect_fields/other/url/__init__.py,sha256=ihhkhectA73ovpZ42n0VbgXvtUa6TjhHlEKvrsT4pY0,232
-csv_detective/detect_fields/other/uuid/__init__.py,sha256=uqX0DE-KQUHrkhVssU1AeLEFUw-yIisoabQo7uF5a4s,198
-csv_detective/detect_fields/temp/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-csv_detective/detect_fields/temp/date/__init__.py,sha256=Nc-ZYYM-E7Z-MH8flOkG4iBl238l2XcQF95Nh1lFiu8,1891
-csv_detective/detect_fields/temp/datetime_iso/__init__.py,sha256=8LrsbnKea64zSLOV6ENHDLlmCWtEUhGqLsV75ftZHHk,430
-csv_detective/detect_fields/temp/datetime_rfc822/__init__.py,sha256=t7WxeA0ZavES_pvqHoO4JAAErpC-ifGFFncZ-ehjTTM,511
-csv_detective/detect_fields/temp/year/__init__.py,sha256=RjsiIHoplnI4Odi5587TzRhKTDT-FTqGOBpdartuShA,194
-csv_detective/detect_labels/__init__.py,sha256=BJjWlwTnnDe9nomABDUreu9EMu6IFG3T47d7YCJZbRc,878
-csv_detective/detect_labels/FR/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-csv_detective/detect_labels/FR/geo/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-csv_detective/detect_labels/FR/geo/adresse/__init__.py,sha256=r14SVoVJiaabyr6lTahI_Qsk0EH3F8UVSi6TRnDQS7o,1063
-csv_detective/detect_labels/FR/geo/code_commune_insee/__init__.py,sha256=qJKvP6g98ceSxaFtd37-bI-9uFhQvdwFSh1n3MrzrOo,1096
-csv_detective/detect_labels/FR/geo/code_departement/__init__.py,sha256=FtPwHudArmsgkjCT_IM-I4_wALOsKjiK0-TEsYe9tw4,1025
-csv_detective/detect_labels/FR/geo/code_fantoir/__init__.py,sha256=irrBwY_TXAGRhOAcH1Xqi9D7P5Ajk2854ee1qXwuTnA,949
-csv_detective/detect_labels/FR/geo/code_postal/__init__.py,sha256=L74MwxadiT_MVrEEWUlMbhUsE_kk7xz_E2BHrZMUxMs,1070
-csv_detective/detect_labels/FR/geo/code_region/__init__.py,sha256=Di9j-AKCogKxavnPgGjA_P8hy8g6JyJ0GBOO0k4l-qY,1012
-csv_detective/detect_labels/FR/geo/commune/__init__.py,sha256=8Jhx4neUt5iyyK_b1D4WWsdxi3mpz7cNZQ28fFF4xaE,948
-csv_detective/detect_labels/FR/geo/departement/__init__.py,sha256=N8MYMhqhspoLAUgD25pIrsqDKRuwTGnXXm8Chr8wih8,1229
-csv_detective/detect_labels/FR/geo/insee_canton/__init__.py,sha256=8Tcqzjn-dGGjpxzo-2TqmEYpyfEhcqa1XNcQgMnqq88,957
-csv_detective/detect_labels/FR/geo/latitude_l93/__init__.py,sha256=nUT7SL4sKP_q9LTbiMBaCzJ029yBMP_phAD_CiOVHfc,1386
-csv_detective/detect_labels/FR/geo/latitude_wgs_fr_metropole/__init__.py,sha256=DCyN6-k1FH1kfTy4tFZWIH6lyaKeT-vgWnDh8TB7JhU,1381
-csv_detective/detect_labels/FR/geo/longitude_l93/__init__.py,sha256=Lcqc8Agjxy2dPulu65NRel4uxRLPcQrAGrLsBTYT8EQ,1139
-csv_detective/detect_labels/FR/geo/longitude_wgs_fr_metropole/__init__.py,sha256=xd_W-L9pkKpsMT1IZ0fVMdty1dmT75uS8gmekb_InAw,1144
-csv_detective/detect_labels/FR/geo/pays/__init__.py,sha256=HJ3hNV3xeAN46YP6c-tqQgHMNvltm-tgApfofR5FraE,1169
-csv_detective/detect_labels/FR/geo/region/__init__.py,sha256=ZPw8LXIuV8OvFVY_DA3MkvpAFzB6Rs749Ppr0Wc4lao,1164
-csv_detective/detect_labels/FR/other/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-csv_detective/detect_labels/FR/other/code_csp_insee/__init__.py,sha256=rk5S6UGL0vND2X2ty1HJJH3qswUbaV6ZJHHKAywRa6o,939
-csv_detective/detect_labels/FR/other/code_rna/__init__.py,sha256=MBF9qZIGbX1dP3DJBI71pbqrGcgOR1xXAbGdiHX0pc4,1024
-csv_detective/detect_labels/FR/other/code_waldec/__init__.py,sha256=RDU8jDZgutfxnJl5lQkbqymJmGeeGXpR2i4CuGfqU10,934
-csv_detective/detect_labels/FR/other/csp_insee/__init__.py,sha256=-GoB9i83O3_rg81Ry3ZtLOdMhlrMPZ34he4hn9U6qDc,1043
-csv_detective/detect_labels/FR/other/date_fr/__init__.py,sha256=7eV737iM1X9MTHureWiCpnxAUJ2_YjI14Vs41MGEX2Q,975
-csv_detective/detect_labels/FR/other/insee_ape700/__init__.py,sha256=6UDx_6JRG__aSXTKKPq-2oBJR7ZiWg0HhSLDl4pETm4,1124
-csv_detective/detect_labels/FR/other/sexe/__init__.py,sha256=87BcCHmofOMqfHfHzmwZzIplcBMAm1AUMxVNvigigTQ,956
-csv_detective/detect_labels/FR/other/siren/__init__.py,sha256=oWkOquzLLbDwBlAs_hoic_UQu7LFOmFZ76570vwRgdc,1103
-csv_detective/detect_labels/FR/other/siret/__init__.py,sha256=Xx-oajnzxEe6pEAYafsnZo7S-mLfnB0pP3z5gv3kJy0,1040
-csv_detective/detect_labels/FR/other/tel_fr/__init__.py,sha256=WWglp7xmb_Wz8bxrYYmB46cRyCJKNNqguubziMktZZI,1143
-csv_detective/detect_labels/FR/other/uai/__init__.py,sha256=sVcw6fwQi9ocIEmLEJRi9m4WvTLg_ORwaW0KaJqeMB8,1316
-csv_detective/detect_labels/FR/temp/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-csv_detective/detect_labels/FR/temp/jour_de_la_semaine/__init__.py,sha256=a3fKjduxRIMNu7TF124pG--Mb21PIqZYnQwYU4APLBw,1074
-csv_detective/detect_labels/FR/temp/mois_de_annee/__init__.py,sha256=taNWDz1_0KE4cOS4SeJcC8igMSA2LBbv8TvbCg50-TY,934
-csv_detective/detect_labels/geo/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-csv_detective/detect_labels/geo/iso_country_code_alpha2/__init__.py,sha256=ev8w1hySEoNiMcU1IhJy72IB5OliCvoUy-ytKWPG3oI,1065
-csv_detective/detect_labels/geo/iso_country_code_alpha3/__init__.py,sha256=ev8w1hySEoNiMcU1IhJy72IB5OliCvoUy-ytKWPG3oI,1065
-csv_detective/detect_labels/geo/iso_country_code_numeric/__init__.py,sha256=ev8w1hySEoNiMcU1IhJy72IB5OliCvoUy-ytKWPG3oI,1065
-csv_detective/detect_labels/geo/json_geojson/__init__.py,sha256=p6mXMb1GMkrs27WmoqRqPE3wCbs3iPL4FWfcc280bGA,1072
-csv_detective/detect_labels/geo/latitude_wgs/__init__.py,sha256=DCyN6-k1FH1kfTy4tFZWIH6lyaKeT-vgWnDh8TB7JhU,1381
-csv_detective/detect_labels/geo/latlon_wgs/__init__.py,sha256=xfzeQ1KXmEZAkpVQT_qAYsC4RnXKl11dTB9PoFExGgQ,1705
-csv_detective/detect_labels/geo/longitude_wgs/__init__.py,sha256=knv3HnIerZ6oUPrzGkW2GJjsiTnCklqZ9_koNJCG91I,1145
-csv_detective/detect_labels/other/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-csv_detective/detect_labels/other/booleen/__init__.py,sha256=ahxzBUcJYc5f1J8aAeYDhtSc-URJHS6ruGTAbZXaoG8,987
-csv_detective/detect_labels/other/email/__init__.py,sha256=2pf0e8o3L57damyi4BLrqA9Opw0trZl2wWDHY88s41E,1148
-csv_detective/detect_labels/other/float/__init__.py,sha256=9JC0-B-aVqlLe3FeN8uH5HZjIc2V6hZ7JFStkSLsHW0,926
-csv_detective/detect_labels/other/int/__init__.py,sha256=i9xN8TYBy4C5b1vYO1l3Rkvn4uq_tft8Rip_ErSUIt8,933
-csv_detective/detect_labels/other/money/__init__.py,sha256=kBEGuUy6kYkOI3vC_a7waBciG2ipyV9bhC330U8WaoI,279
-csv_detective/detect_labels/other/money/check_col_name.py,sha256=zgp5eUnf3XRQuxgdEGfxPfUnniO8Pzw19uK0ICr2pf8,414
-csv_detective/detect_labels/other/mongo_object_id/__init__.py,sha256=Y-inIGmeH3lZcN9kR6icE3QypS54qJWv8aE4GQUudpc,927
-csv_detective/detect_labels/other/twitter/__init__.py,sha256=D8G4vGsFL9a99OJz-03wp4HbZSvT-y1IxyRJiSsqxFc,959
-csv_detective/detect_labels/other/url/__init__.py,sha256=vqUQvn5o6JZU8iRsSG3AYqggjlhzagozVYWwpuSReV8,1202
-csv_detective/detect_labels/other/uuid/__init__.py,sha256=OdMUxqvqMdGaY5nph7CbIF_Q0LSxljxE72kCMT4m-Zk,931
-csv_detective/detect_labels/temp/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-csv_detective/detect_labels/temp/date/__init__.py,sha256=GrIbo64WVM3hi7ShBRKKyKUZxkZlVKhpgk41FxkM1VI,1281
-csv_detective/detect_labels/temp/datetime_iso/__init__.py,sha256=Ih9l56nBcdmGLyWDavVUWuUUuVZBz9QUDE1hHzADvVg,1157
-csv_detective/detect_labels/temp/datetime_rfc822/__init__.py,sha256=DQ_h4uDW1e6qu2rATEhgGKw6O-vVi7HbDhbEDDCT9uY,1175
-csv_detective/detect_labels/temp/year/__init__.py,sha256=zPF_mvhzhXMAlHPAskS8mhuxjLj2AlKpV4ss8Q4tDms,1150
-csv_detective-0.6.7.data/data/share/csv_detective/CHANGELOG.md,sha256=urZrWA8jhrqctpQke5NPhzYZINE8UXc7AczcqaxbK3U,4465
-csv_detective-0.6.7.data/data/share/csv_detective/LICENSE.AGPL.txt,sha256=2N5ReRelkdqkR9a-KP-y-shmcD5P62XoYiG-miLTAzo,34519
-csv_detective-0.6.7.data/data/share/csv_detective/README.md,sha256=5pxTU1Ljer8Gw0rOZZvi6vyC3QhjFrGaFJloy2N9GMs,9339
-tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tests/test_fields.py,sha256=xu80qwzZVQIH6dVRf1dE1lru4EzM2XtGc7YoMDPRAX4,7439
-tests/test_file.py,sha256=tWULaaHIokkwKXW_9hfbONYDZncbOXCFL0I0sXtQ4YA,3913
-tests/test_labels.py,sha256=6MOKrGznkwU5fjZ_3oiB6Scmb480Eu-9geBJs0UDLds,159
-csv_detective-0.6.7.dist-info/LICENSE.AGPL.txt,sha256=2N5ReRelkdqkR9a-KP-y-shmcD5P62XoYiG-miLTAzo,34519
-csv_detective-0.6.7.dist-info/METADATA,sha256=acU2wBZzO6LDCEuDjR49xqX4N0xmqhDR4pM8Uzm-KKg,871
-csv_detective-0.6.7.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-csv_detective-0.6.7.dist-info/entry_points.txt,sha256=JjweTReFqKJmuvkegzlew2j3D5pZzfxvbEGOtGVGmaY,56
-csv_detective-0.6.7.dist-info/top_level.txt,sha256=M0Nv646VHo-49zWjPkwo2C48UmtfddV8_9mEZeIxy8Q,20
-csv_detective-0.6.7.dist-info/RECORD,,

csv_detective-0.6.7.dist-info/WHEEL

@@ -1,5 +0,0 @@
-Wheel-Version: 1.0
-Generator: bdist_wheel (0.42.0)
-Root-Is-Purelib: true
-Tag: py3-none-any
-

csv_detective-0.6.7.dist-info/top_level.txt

@@ -1,2 +0,0 @@
-csv_detective
-tests

tests/test_fields.py

@@ -1,360 +0,0 @@
-import pandas as pd
-from numpy import random
-
-from csv_detective.detect_fields.FR.other import (
-    code_csp_insee,
-    csp_insee,
-    sexe,
-    siren,
-    tel_fr,
-    code_rna,
-    code_waldec,
-)
-from csv_detective.detect_fields.other import email, url, uuid, mongo_object_id, json
-
-from csv_detective.detect_fields.FR.geo import (
-    adresse,
-    code_commune_insee,
-    commune,
-    departement,
-    pays,
-    region,
-)
-from csv_detective.detect_fields.geo import (
-    iso_country_code_alpha2,
-    iso_country_code_alpha3,
-    iso_country_code_numeric,
-)
-
-from csv_detective.detect_fields.FR.temp import jour_de_la_semaine
-from csv_detective.detect_fields.temp import year, date, datetime_iso, datetime_rfc822
-
-from csv_detective.detection import (
-    detetect_categorical_variable,
-    detect_continuous_variable,
-)
-
-
-# categorical
-def test_detetect_categorical_variable():
-    categorical_col = ["type_a"] * 33 + ["type_b"] * 33 + ["type_c"] * 34
-    not_categorical_col = [i for i in range(100)]
-
-    df_dict = {"cat": categorical_col, "not_cat": not_categorical_col}
-    df = pd.DataFrame(df_dict, dtype="unicode")
-
-    res, _ = detetect_categorical_variable(df)
-    assert res.values and res.values[0] == "cat"
-
-
-# continuous
-def test_detect_continuous_variable():
-    continuous_col = random.random(100)
-    continuous_col_2 = [1.0, 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7, 21, 3] * 10
-    not_continuous_col = ["type_a"] * 33 + ["type_b"] * 33 + ["type_c"] * 34
-
-    df_dict = {"cont": continuous_col, "not_cont": not_continuous_col}
-    df_dict_2 = {"cont": continuous_col_2, "not_cont": not_continuous_col}
-
-    df = pd.DataFrame(df_dict, dtype="unicode")
-    df2 = pd.DataFrame(df_dict_2, dtype="unicode")
-
-    res = detect_continuous_variable(df)
-    res2 = detect_continuous_variable(df2, continuous_th=0.65)
-    assert res.values and res.values[0] == "cont"
-    assert res2.values and res2.values[0] == "cont"
-
-
-# csp_insee
-def test_match_csp_insee():
-    val = "employes de la poste"
-    assert csp_insee._is(val)
-
-
-def test_do_not_match_csp_insee():
-    val = "super-heros"
-    assert not csp_insee._is(val)
-
-
-# code_csp_insee
-def test_match_code_csp_insee():
-    val = "121f"
-    assert code_csp_insee._is(val)
-
-
-def test_do_not_match_code_csp_insee():
-    val = "121x"
-    assert not code_csp_insee._is(val)
-
-
-# sexe
-def test_match_sexe():
-    val = "homme"
-    assert sexe._is(val)
-
-
-def test_do_not_match_sexe():
-    val = "hermaphrodite"
-    assert not sexe._is(val)
-
-
-# tel_fr
-def test_match_tel_fr():
-    val = "0134643467"
-    assert tel_fr._is(val)
-
-
-def test_do_not_match_tel_fr():
-    val = "3345689715"
-    assert not tel_fr._is(val)
-
-
-# email
-def test_match_email():
-    val = "cdo_intern@data.gouv.fr"
-    assert email._is(val)
-
-
-def test_do_not_match_email():
-    val = "cdo@@gouv.sfd"
-    assert not email._is(val)
-
-
-# uuid
-def test_match_uuid():
-    val = "884762be-51f3-44c3-b811-1e14c5d89262"
-    assert uuid._is(val)
-
-
-def test_do_not_match_uuid():
-    val = "0610928327"
-    assert not uuid._is(val)
-
-
-# Mongo ObjectId
-def test_match_mongo_object_id():
-    val = "62320e50f981bc2b57bcc044"
-    assert mongo_object_id._is(val)
-
-
-def test_do_not_match_mongo_object_id():
-    val = "884762be-51f3-44c3-b811-1e14c5d89262"
-    assert not mongo_object_id._is(val)
-
-
-# url
-def test_match_url():
-    val = "www.etalab.data.gouv.fr"
-    assert url._is(val)
-
-
-def test_do_not_match_url():
-    val = "c est une phrase"
-    assert not url._is(val)
-
-
-# adresse
-def test_match_adresse():
-    val = "rue du martyr"
-    assert adresse._is(val)
-
-
-def test_do_not_match_adresse():
-    val = "bonjour les amis"
-    assert not adresse._is(val)
-
-
-# code_commune_insee
-def test_match_code_commune_insee():
-    val = "91471"
-    assert code_commune_insee._is(val)
-
-
-def test_do_not_match_code_commune_insee():
-    val = "914712"
-    assert not code_commune_insee._is(val)
-
-
-# commune
-def test_match_commune():
-    val = "saint denis"
-    assert commune._is(val)
-
-
-def test_do_not_match_commune():
-    val = "new york"
-    assert not commune._is(val)
-
-
-# departement
-def test_match_departement():
-    val = "essonne"
-    assert departement._is(val)
-
-
-def test_do_not_match_departement():
-    val = "new york"
-    assert not departement._is(val)
-
-
-# pays
-def test_match_pays():
-    val = "france"
-    assert pays._is(val)
-
-
-def test_do_not_match_pays():
-    val = "new york"
-    assert not pays._is(val)
-
-
-# region
-def test_match_region():
-    val = "bretagne"
-    assert region._is(val)
-
-
-def test_do_not_match_region():
-    val = "jambon beurre"
-    assert not region._is(val)
-
-
-# iso_country_code
-def test_match_iso_country_code():
-    val = "FR"
-    assert iso_country_code_alpha2._is(val)
-
-
-def test_do_not_match_iso_country_code():
-    val = "XX"
-    assert not iso_country_code_alpha2._is(val)
-
-
-# iso_country_code alpha-3
-def test_match_iso_country_code_alpha3():
-    val = "FRA"
-    assert iso_country_code_alpha3._is(val)
-
-
-def test_do_not_match_iso_country_code_alpha3():
-    val = "ABC"
-    assert not iso_country_code_alpha3._is(val)
-
-
-# iso_country_code numerique
-def test_match_iso_country_code_numeric():
-    val = "250"
-    print(iso_country_code_numeric._is(val))
-    assert iso_country_code_numeric._is(val)
-
-
-def test_do_not_match_iso_country_code_numeric():
-    val = "003"
-    assert not iso_country_code_numeric._is(val)
-
-
-# jour de la semaine
-def test_match_jour_de_la_semaine():
-    val = "lundi"
-    assert jour_de_la_semaine._is(val)
-
-
-def test_do_not_match_jour_de_la_semaine():
-    val = "jour de la biere"
-    assert not jour_de_la_semaine._is(val)
-
-
-# year
-def test_match_year():
-    val = "2015"
-    assert year._is(val)
-
-
-def test_do_not_match_year():
-    val = "20166"
-    assert not year._is(val)
-
-
-# date
-def test_match_date():
-    val = "1960-08-07"
-    assert date._is(val)
-    val = '12/02/2007'
-    assert date._is(val)
-    val = '15 jan 1985'
-    assert date._is(val)
-    val = '15 décembre 1985'
-    assert date._is(val)
-    val = '02052003'
-    assert date._is(val)
-    val = '1993-12/02'
-    assert date._is(val)
-
-
-def test_do_not_match_date():
-    val = "1993-1993-1993"
-    assert not date._is(val)
-    val = '39-10-1993'
-    assert not date._is(val)
-    val = '19-15-1993'
-    assert not date._is(val)
-    val = '15 tambour 1985'
-    assert not date._is(val)
-
-
-# datetime
-def test_match_datetime():
-    val = "2021-06-22T10:20:10"
-    assert datetime_iso._is(val)
-    val = "2021-06-22T30:20:10"
-    assert not datetime_iso._is(val)
-
-    val = "Sun, 06 Nov 1994 08:49:37 GMT"
-    assert datetime_rfc822._is(val)
-
-
-# siren
-def test_match_siren():
-    val = "552 100 554"
-    assert siren._is(val)
-
-
-def test_do_not_match_siren():
-    val = "42"
-    assert not siren._is(val)
-
-
-# rna
-def test_match_rna():
-    val = "W751515517"
-    assert code_rna._is(val)
-
-
-def test_do_not_match_rna():
-    val = "W111111111111111111111111111111111111"
-    assert not code_rna._is(val)
-
-
-def test_match_waldec():
-    val = "751P00188854"
-    assert code_waldec._is(val)
-
-
-def test_do_not_match_waldec():
-    val = "AA751PEE00188854"
-    assert not code_waldec._is(val)
-
-
-# json
-def test_match_json():
-    val = '{"pomme": "fruit", "reponse": 42}'
-    assert json._is(val)
-    val = "[1,2,3,4]"
-    assert json._is(val)
-
-
-def test_do_not_match_json():
-    val = '{"coordinates": [45.783753, 3.049342], "citycode": "63870"}'
-    assert not json._is(val)
-    val = "666"
-    assert not json._is(val)

tests/test_file.py

@@ -1,116 +0,0 @@
-from csv_detective import explore_csv
-import pytest
-
-
-def test_columns_output_on_file():
-    output = explore_csv.routine(
-        csv_file_path="tests/a_test_file.csv",
-        num_rows=-1,
-        output_profile=False,
-        save_results=False,
-    )
-    assert isinstance(output, dict)
-    assert output["separator"] == ";"
-    assert output["header_row_idx"] == 2
-    assert output["header"] == [
-        "NUMCOM",
-        "NOMCOM",
-        "NUMDEP",
-        "NOMDEP",
-        "NUMEPCI",
-        "NOMEPCI",
-        "TXCOUVGLO_COM_2014",
-        "TXCOUVGLO_DEP_2014",
-        "TXCOUVGLO_EPCI_2014",
-        "STRUCTURED_INFO",
-        "GEO_INFO",
-    ]
-    assert output["total_lines"] == 414
-    assert output["nb_duplicates"] == 7
-    assert output["columns"]["NOMCOM"]["format"] == "commune"
-    assert output["columns"]["NOMDEP"]["format"] == "departement"
-    assert output["columns"]["NUMEPCI"]["format"] == "siren"
-    assert output["columns"]["STRUCTURED_INFO"]["python_type"] == "json"
-    assert output["columns"]["STRUCTURED_INFO"]["format"] == "json"
-    assert output["columns"]["GEO_INFO"]["python_type"] == "json"
-    assert output["columns"]["GEO_INFO"]["format"] == "json_geojson"
-    assert output["columns"]["NUMEPCI"]["format"] == "siren"
-
-
-def test_profile_output_on_file():
-    output = explore_csv.routine(
-        csv_file_path="tests/a_test_file.csv",
-        num_rows=-1,
-        output_profile=True,
-        save_results=False,
-    )
-    assert all(
-        [
-            c in list(output["profile"]["NUMCOM"].keys())
-            for c in [
-                "min",
-                "max",
-                "mean",
-                "std",
-                "tops",
-                "nb_distinct",
-                "nb_missing_values",
-            ]
-        ]
-    )
-    assert len(output["profile"]["NOMCOM"].keys()) == 3
-    assert output["profile"]["NUMCOM"]["min"] == 1001
-    assert output["profile"]["NUMCOM"]["max"] == 6125
-    assert round(output["profile"]["NUMCOM"]["mean"]) == 1245
-    assert round(output["profile"]["NUMCOM"]["std"]) == 363
-    assert output["profile"]["TXCOUVGLO_COM_2014"]["nb_distinct"] == 296
-    assert output["profile"]["TXCOUVGLO_COM_2014"]["nb_missing_values"] == 3
-    assert output["profile"]["GEO_INFO"]["nb_distinct"] == 1
-
-
-def test_exception():
-    with pytest.raises(Exception):
-        explore_csv.routine(
-            csv_file_path="tests/a_test_file.csv",
-            num_rows=50,
-            output_profile=True,
-            save_results=False,
-        )
-
-
-def test_code_dep_reg_on_file():
-    output = explore_csv.routine(
-        csv_file_path="tests/b_test_file.csv",
-        num_rows=-1,
-        output_profile=False,
-        save_results=False,
-    )
-    assert isinstance(output, dict)
-    assert output["columns"]["code_departement"]["format"] == "code_departement"
-    assert output["columns"]["code_region"]["format"] == "code_region"
-
-
-def test_schema_on_file():
-    output = explore_csv.routine(
-        csv_file_path="tests/b_test_file.csv",
-        num_rows=-1,
-        output_schema=True,
-    )
-    assert isinstance(output, dict)
-    is_column_dep = False
-    is_column_reg = False
-    for item in output["schema"]["fields"]:
-        if item["name"] == "code_departement":
-            is_column_dep = True
-            assert item["description"] == "Le code INSEE du département"
-            assert item["type"] == "string"
-            assert item["formatFR"] == "code_departement"
-            assert item["constraints"]["pattern"] == "^(([013-9]\\d|2[AB1-9])$|9\\d{2}$)"
-        if item["name"] == "code_region":
-            is_column_reg = True
-            assert item["description"] == "Le code INSEE de la région"
-            assert item["type"] == "string"
-            assert item["formatFR"] == "code_region"
-            assert item["constraints"]["pattern"] == "^\\d{2}$"
-    assert is_column_dep
-    assert is_column_reg

tests/test_labels.py

@@ -1,7 +0,0 @@
-from csv_detective.detect_labels.other import money
-
-
-# money labels
-def test_money_labels():
-    header = "Montant total"
-    assert money._is(header) == 1.0