forked from osm-fr/osmose-backend
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathanalyser_merge_public_services_FR.py
392 lines (340 loc) · 19.9 KB
/
analyser_merge_public_services_FR.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
#!/usr/bin/env python
#-*- coding: utf-8 -*-
###########################################################################
## ##
## Copyrights Noémie Lehuby 2023 ##
## ##
## This program is free software: you can redistribute it and/or modify ##
## it under the terms of the GNU General Public License as published by ##
## the Free Software Foundation, either version 3 of the License, or ##
## (at your option) any later version. ##
## ##
## This program is distributed in the hope that it will be useful, ##
## but WITHOUT ANY WARRANTY; without even the implied warranty of ##
## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ##
## GNU General Public License for more details. ##
## ##
## You should have received a copy of the GNU General Public License ##
## along with this program. If not, see <http://www.gnu.org/licenses/>. ##
## ##
###########################################################################
from modules.OsmoseTranslation import T_
from modules import downloader
from .Analyser_Merge import Analyser_Merge_Point, Source, CSV, Load_XY, Conflate, Select, Mapping
from io import BytesIO
import json
import csv
import datetime
import tarfile
class _Generic_Analyser_Merge_Public_Services_FR_(Analyser_Merge_Point):
def __init__(self, config, logger, osmose_class, public_service_category, osm_select_tags, osm_default_tags):
Analyser_Merge_Point.__init__(self, config, logger)
self.def_class_missing_official(item = 8110, id = osmose_class, level = 3, tags = ['merge', 'fix:imagery', 'fix:survey', 'fix:picture'],
title = T_('Public service not integrated'))
self.init(
"https://www.data.gouv.fr/fr/datasets/service-public-fr-annuaire-de-l-administration-base-de-donnees-locales/",
"Service-Public.fr",
CSV(Public_Services_Source(Source(attribution = "Service-Public.fr",
fileUrl="https://www.data.gouv.fr/fr/datasets/r/73302880-e4df-4d4c-8676-1a61bb997f3d"))),
Load_XY("longitude", "latitude",
select = {"categorie": public_service_category}),
Conflate(
select = Select(
types = ["nodes", "ways", "relations"],
tags = osm_select_tags),
conflationDistance = 500,
mapping = Mapping(
static1 = osm_default_tags,
mapping1 = dict({
"name": "name",
"wheelchair": "wheelchair",
"wheelchair:description": lambda feature: feature["wheelchair:description"] if feature["wheelchair"] == "limited" else None,
"contact:email": "contact:email",
"contact:website": "contact:website",
"ref:FR:SIRET": "ref:FR:SIRET",
"branch": "branch",
"opening_hours": "opening_hours",
"contact:phone": "contact:phone"
}),
mapping2 = dict({
"source": lambda feature: "Service-Public.fr - " + feature["millesime"]
}),
text = lambda tags, fields: {"en": "{0}, {1}".format(fields["official_name"], fields["address_txt"])} )))
class Analyser_Merge_Public_Services_Mairie(_Generic_Analyser_Merge_Public_Services_FR_):
def __init__(self, config, logger=None):
_Generic_Analyser_Merge_Public_Services_FR_.__init__(self, config, logger, 1, ["mairie", "mairie_com"], {"amenity": "townhall"}, {"amenity": "townhall"})
class Analyser_Merge_ServicePublic_FR_EPCI(_Generic_Analyser_Merge_Public_Services_FR_):
def __init__(self, config, logger = None):
_Generic_Analyser_Merge_Public_Services_FR_.__init__(self, config, logger, 2, "epci",
{"office": "government", "government": "local_authority"},
{"office": "government", "government": "local_authority"})
class Analyser_Merge_ServicePublic_FR_PMI(_Generic_Analyser_Merge_Public_Services_FR_):
def __init__(self, config, logger = None):
_Generic_Analyser_Merge_Public_Services_FR_.__init__(self, config, logger, 3, "pmi",
{"amenity": "social_facility", "social_facility:for": "child"},
{"amenity": "social_facility", "social_facility:for": "child", "social_facility": "ambulatory_care", "short_name": "PMI"})
class Analyser_Merge_ServicePublic_FR_CIJ(_Generic_Analyser_Merge_Public_Services_FR_):
def __init__(self, config, logger = None):
_Generic_Analyser_Merge_Public_Services_FR_.__init__(self, config, logger, 4, ["cij", "cio", "mission_locale"],
{"amenity": "social_facility", "social_facility:for": "juvenile"},
{"amenity": "social_facility", "social_facility:for": "juvenile", "social_facility": "outreach"})
class Analyser_Merge_ServicePublic_FR_Pole_Emploi(_Generic_Analyser_Merge_Public_Services_FR_):
def __init__(self, config, logger = None):
_Generic_Analyser_Merge_Public_Services_FR_.__init__(self, config, logger, 5, "pole_emploi",
{"office": "employment_agency"},
{"office": "employment_agency", "brand": "Pôle Emploi", "brand:wikidata": "Q8901192"})
class Analyser_Merge_ServicePublic_FR_Tribunal(_Generic_Analyser_Merge_Public_Services_FR_):
def __init__(self, config, logger = None):
_Generic_Analyser_Merge_Public_Services_FR_.__init__(self, config, logger, 6, ["ta", "ti", "tribunal_commerce", "tgi", "te", "cour_appel"], {"amenity": "courthouse"}, {"amenity": "courthouse"})
class Analyser_Merge_ServicePublic_FR_Prison(_Generic_Analyser_Merge_Public_Services_FR_):
def __init__(self, config, logger = None):
_Generic_Analyser_Merge_Public_Services_FR_.__init__(self, config, logger, 7, ["maison_centrale", "maison_arret", "centre_penitentiaire", "centre_detention", "csl", "esm"], {"amenity": "prison"}, {"amenity": "prison"})
class Analyser_Merge_ServicePublic_FR_Prefecture(_Generic_Analyser_Merge_Public_Services_FR_):
def __init__(self, config, logger = None):
_Generic_Analyser_Merge_Public_Services_FR_.__init__(self, config, logger, 8, ["prefecture", "sous_pref"],
{"office": "government", "government": "prefecture"},
{"office": "government", "government": "prefecture"})
class Analyser_Merge_ServicePublic_FR_CG(_Generic_Analyser_Merge_Public_Services_FR_):
def __init__(self, config, logger = None):
_Generic_Analyser_Merge_Public_Services_FR_.__init__(self, config, logger, 9, "cg",
{"office": "government", "government": "parliament"},
{"office": "government", "government": "parliament", "admin_level": "6"})
class Analyser_Merge_ServicePublic_FR_Impots(_Generic_Analyser_Merge_Public_Services_FR_):
def __init__(self, config, logger = None):
_Generic_Analyser_Merge_Public_Services_FR_.__init__(self, config, logger, 10, "sip",
[{"office": "tax"}, {"office": "government", "government": "tax"}],
{"office": "government", "government": "tax"})
class Analyser_Merge_ServicePublic_FR_CAF(_Generic_Analyser_Merge_Public_Services_FR_):
def __init__(self, config, logger = None):
_Generic_Analyser_Merge_Public_Services_FR_.__init__(self, config, logger, 11, "caf",
{"office": "government", "government": "social_welfare", "operator": "Caisse d'Allocations Familiales"},
{"office": "government", "government": "social_welfare", "operator": "Caisse d'Allocations Familiales", "operator:wikidata":"Q1395254"})
class Analyser_Merge_ServicePublic_FR_CPAM(_Generic_Analyser_Merge_Public_Services_FR_):
def __init__(self, config, logger = None):
_Generic_Analyser_Merge_Public_Services_FR_.__init__(self, config, logger, 12, "cpam",
{"office": "government", "government": "social_security", "operator": "Caisse Primaire d'Assurance Maladie"},
{"office": "government", "government": "social_security", "operator": "Caisse Primaire d'Assurance Maladie", "operator:wikidata":"Q2110238"})
class Analyser_Merge_ServicePublic_FR_URSSAF(_Generic_Analyser_Merge_Public_Services_FR_):
def __init__(self, config, logger = None):
_Generic_Analyser_Merge_Public_Services_FR_.__init__(self, config, logger, 13, "urssaf",
[{"office": "tax"}, {"office": "government", "government": "tax"}],
{"office": "government", "government": "tax", "operator": "URSSAF", "operator:wikidata":"Q3550086"})
class Analyser_Merge_ServicePublic_FR_CCI(_Generic_Analyser_Merge_Public_Services_FR_):
def __init__(self, config, logger = None):
_Generic_Analyser_Merge_Public_Services_FR_.__init__(self, config, logger, 14, ["chambre_agriculture", "chambre_metier", "cci"],
{"office": "government", "government": "chamber_of_commerce"},
{"office": "government", "government": "chamber_of_commerce"})
class Analyser_Merge_ServicePublic_FR_CR(_Generic_Analyser_Merge_Public_Services_FR_):
def __init__(self, config, logger = None):
_Generic_Analyser_Merge_Public_Services_FR_.__init__(self, config, logger, 15, "cr",
{"office": "government", "government": "parliament"},
{"office": "government", "government": "parliament", "admin_level": "4"})
class Analyser_Merge_ServicePublic_FR_MSAP(_Generic_Analyser_Merge_Public_Services_FR_):
def __init__(self, config, logger = None):
_Generic_Analyser_Merge_Public_Services_FR_.__init__(self, config, logger, 16, "msap",
{"office": "government", "government": "public_service", "operator": "France Services"},
{"office": "government", "government": "public_service", "operator": "France Services", "operator:wikidata":"Q24931343"})
class Analyser_Merge_ServicePublic_FR_CLIC(_Generic_Analyser_Merge_Public_Services_FR_):
def __init__(self, config, logger = None):
_Generic_Analyser_Merge_Public_Services_FR_.__init__(self, config, logger, 16, "clic",
{"amenity": "social_facility", "social_facility:for": "senior"},
{"amenity": "social_facility", "social_facility:for": "senior", "social_facility": "outreach"})
class Public_Services_Source(Source):
def __init__(self, source):
self.source = source
def __getattr__(self, name):
return getattr(self.source, name)
def open(self):
return open(downloader.update_cache('parse://' + self.source.fileUrl, 15, fetch=self.fetch))
def fetch(self, url, tmp_file, date_string=None):
dataset_dl = downloader.request_get(self.source.fileUrl)
with tarfile.open(fileobj=BytesIO(dataset_dl.raw.read())) as archive:
for content in archive.getmembers():
if content.name.endswith("data.gouv_local.json"):
date_and_blabla = content.name.split("/")[1]
millesime = datetime.datetime.strptime(date_and_blabla[0:10], '%Y-%m-%d').strftime('%m/%Y')
json_file = archive.extractfile(content.name)
data = json.load(json_file)
export = []
wheelchair_mapping = {
"ACC": "yes",
"DEM": "limited",
"NAC": "no",
"": None
}
for feature in data["service"]:
elem = {}
if not feature.get("pivot"):
continue
elem["categorie"] = feature["pivot"][0]["type_service_local"]
elem["official_name"] = feature["nom"]
elem['branch'] = None
if elem["categorie"] in ["mairie", "mairie_com"]:
elem["name"] = retreat_townhall_name(feature["nom"])
elif elem["categorie"] in ["esm"]:
elem["name"] = retreat_prison_name(feature["nom"])
elif elem["categorie"] in ["sous_pref"]:
elem["name"] = retreat_sous_prefecture_name(feature["nom"])
elif elem["categorie"] in ["cpam"]:
elem["name"] = retreat_CPAM_name(feature["nom"])
elif elem["categorie"] in ["caf"]:
elem["name"] = retreat_Caf_name(feature["nom"])
elif elem["categorie"] in ["cio"]:
elem["name"] = retreat_CIO_name(feature["nom"])
elif elem["categorie"] in ["pmi"]:
elem["name"] = retreat_PMI_name(feature["nom"])
elif elem["categorie"] in ["mission_locale"]:
elem["name"] = retreat_Mission_Locale_name(feature["nom"])
elif elem["categorie"] in ["pole_emploi"]:
elem["name"], elem["branch"] = retreat_Pole_Emploi_name(feature["nom"])
elif elem["categorie"] in ["msap"]:
elem["name"], elem["branch"] = retreat_France_Services_name(feature["nom"])
elif elem["categorie"] in ["ti", "tribunal_commerce", "tgi",
"te", "cour_appel", "maison_centrale", "maison_arret",
"centre_penitentiaire", "centre_detention", "csl"]:
elem["name"] = feature["nom"]
elif elem["categorie"] in ["urssaf"]:
elem["name"] = retreat_Urssaf_name(feature["nom"])
else:
elem["name"] = None
elem["contact:phone"] = None
if feature.get("telephone"):
elem["contact:phone"] = retreat_phone_number(feature["code_insee_commune"], feature["telephone"][0]["valeur"])
elem["contact:website"] = None
if feature.get("site_internet"):
elem["contact:website"] = feature.get("site_internet")[0]["valeur"]
elem["contact:email"] = None
if feature.get("adresse_courriel"):
elem["contact:email"] = feature.get("adresse_courriel")[0]
elem["ref:FR:SIRET"] = feature["siret"]
if not feature.get("adresse"):
continue
feature_address = feature["adresse"][0]
elem["longitude"] = feature_address["longitude"]
elem["latitude"] = feature_address["latitude"]
elem["address_txt"] = "{} {} {} {} {}".format(
feature_address["complement1"],
feature_address["complement2"],
feature_address["numero_voie"],
feature_address["code_postal"],
feature_address["nom_commune"],
)
elem["wheelchair"] = wheelchair_mapping[feature_address["accessibilite"]]
elem["wheelchair:description"] = feature_address["note_accessibilite"]
elem["opening_hours"] = parse_opening_hours(feature["plage_ouverture"])
elem["millesime"] = millesime
export.append(elem)
with open(tmp_file, 'w') as out_file:
csv_writer = csv.DictWriter(out_file, delimiter=',', fieldnames=export[0].keys())
csv_writer.writeheader()
for row in export:
csv_writer.writerow(row)
return out_file
def parse_opening_hours(txt):
if txt is None:
return None
osm_days = {"Lundi": "Mo", "Mardi": "Tu", "Mercredi":"We", "Jeudi": "Th", "Vendredi":"Fr", "Samedi":"Sa", "Dimanche":"Su", "jours_feries": "PH"}
opening_hours = ""
for plage in txt:
if not plage["nom_jour_fin"] or not plage["nom_jour_debut"]:
return
if not plage["valeur_heure_debut_1"] or not plage["valeur_heure_fin_1"]:
return
opening_hours += osm_days[plage["nom_jour_debut"]]
if plage["nom_jour_debut"] != plage["nom_jour_fin"]:
opening_hours += "-{}".format(osm_days[plage["nom_jour_fin"]])
opening_hours += " "
opening_hours += "{}-{}".format(plage['valeur_heure_debut_1'][0:5], plage['valeur_heure_fin_1'][0:5])
if plage['valeur_heure_debut_2']:
opening_hours += ",{}-{}".format(plage['valeur_heure_debut_2'][0:5], plage['valeur_heure_fin_2'][0:5])
opening_hours += "; "
return opening_hours[:-2]
def _retreat_name(official_name):
zz = official_name.split(" - ")
if len(zz) != 2:
return
city_name = zz[1]
if city_name.startswith("A"):
return official_name.replace(" - ", " d'")
if city_name.startswith("E"):
return official_name.replace(" - ", " d'")
if city_name.startswith("I"):
return official_name.replace(" - ", " d'")
if city_name.startswith("O"):
return official_name.replace(" - ", " d'")
if city_name.startswith("U"):
return official_name.replace(" - ", " d'")
if city_name.startswith("É"):
return official_name.replace(" - ", " d'")
if city_name.startswith("È"):
return official_name.replace(" - ", " d'")
if city_name.startswith("Ê"):
return official_name.replace(" - ", " d'")
if city_name.startswith("Î"):
return official_name.replace(" - ", " d'")
if city_name.startswith("Le "):
return official_name.replace(" - Le ", " du ")
if city_name.startswith("Les "):
return official_name.replace(" - Les ", " des ")
if city_name.startswith("H"):
return official_name.replace(" - ", " d'")
return official_name.replace(" - ", " de ")
def retreat_sous_prefecture_name(official_name):
name = _retreat_name(official_name)
if name:
return name.replace("préfecture","Préfecture")
return
def retreat_townhall_name(official_name):
return _retreat_name(official_name)
def retreat_prison_name(official_name):
if not official_name.startswith("Etablissement"):
return
return "É" + official_name[1:]
def retreat_CPAM_name(official_name):
return official_name.replace("Caisse primaire d'assurance maladie (CPAM)", "CPAM").split(" - ")[0]
def retreat_Caf_name(official_name):
return official_name.replace("Caisse d'allocations familiales (Caf)", "Caf").split(" - ")[0]
def retreat_PMI_name(official_name):
return official_name.replace("Centre de protection maternelle et infantile (PMI)", "PMI").split(" - ")[0]
def retreat_CIO_name(official_name):
return official_name.replace("Centre d’information et d’orientation (CIO)", "CIO").replace("Centre d'information et d'orientation (CIO)","CIO").split(" - ")[0]
def retreat_Mission_Locale_name(official_name):
return official_name.replace("Mission locale pour l'insertion professionnelle et sociale des jeunes (16-25 ans)", "Mission locale").split(" - ")[0]
def retreat_Pole_Emploi_name(official_name):
return "Pôle Emploi", official_name.replace("Pôle emploi - ", "")
def retreat_France_Services_name(official_name):
return "France Services", official_name.replace("France Services - ", "")
def retreat_Urssaf_name(official_name):
if not official_name.startswith("Urssaf"):
return
return official_name.split(" - ")[0]
def retreat_phone_number(insee, phone_number):
if len(phone_number) < 9:
return
if '(' in phone_number:
return
if not phone_number.startswith("0"):
return
if insee.startswith("971"):
return "+590 " + phone_number[1:]
if insee.startswith("972"):
return "+596 " + phone_number[1:]
if insee.startswith("973"):
return "+594 " + phone_number[1:]
if insee.startswith("974"):
return "+262 " + phone_number[1:]
if insee.startswith("975"):
return "+508 " + phone_number[1:]
if insee.startswith("976"):
return "+262 " + phone_number[1:]
if insee.startswith("977"):
return "+590 " + phone_number[1:]
if insee.startswith("978"):
return "+590 " + phone_number[1:]
if insee.startswith("986"):
return "+681 " + phone_number[1:]
if insee.startswith("987"):
return "+689 " + phone_number[1:]
if insee.startswith("988"):
return "+687 " + phone_number[1:]
return "+33 " + phone_number[1:]