summaryrefslogtreecommitdiff
path: root/archaeological_files/data_importer.py
blob: 51809980ff7f34b2bf298c37fbf106b6b0027c10 (plain)
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
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# Copyright (C) 2013-2014  Étienne Loks  <etienne.loks_AT_peacefrogsDOTnet>

# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero 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 Affero General Public License for more details.

# You should have received a copy of the GNU Affero General Public License
# along with this program.  If not, see <http://www.gnu.org/licenses/>.

# See the file COPYING for details.

import unicodecsv

from django.conf import settings
from django.utils.translation import ugettext_lazy as _

from ishtar_common.data_importer import *
from ishtar_common.models import Person, OrganizationType
from ishtar_common.unicode_csv import unicode_csv_reader

from archaeological_operations.data_importer import *

from archaeological_files import models

class ImportClosingFormater(ImportFormater):
    def post_process(self, obj, context, value, owner=None):
        value = self.formater.format(value)
        if not value:
            return
        open_date = obj.reception_date or obj.creation_date
        if not open_date:
            return
        obj.end_date = open_date + datetime.timedelta(30)
        obj.save()

class FileImporterSraPdL(Importer):
    DESC = u"Exports dossiers SRA PdL : importeur Filemaker dossiers"
    LINE_FORMAT = []
    OBJECT_CLS = models.File
    DEFAULTS = {('responsible_town_planning_service', 'attached_to'):{
                    'organization_type':OrganizationType.objects.get(
                                             txt_idx="planning_service")},
                ('general_contractor', 'attached_to'):{
                    'organization_type':OrganizationType.objects.get(
                                             txt_idx="general_contractor")},
                tuple():{
                    'file_type': models.FileType.objects.get(
                                             txt_idx='undefined'),
                },
                ('in_charge',):{'attached_to':None}, # initialized in __init__
               }

    def _init_line_format(self):
        tf = TownFormater()
        tf.town_dct_init()
        self.line_format = [
        None, # A, 1
        ImportFormater(['address', 'postal_code', ['main_town', 'parcels__town']], # B, 2
                    [UnicodeFormater(500, clean=True),
                     UnicodeFormater(5, re_filter=RE_CD_POSTAL_FILTER),
                     tf],
                    regexp=RE_ADD_CD_POSTAL_TOWN,
                    regexp_formater_args=[[0], [1], [2, 1]], required=False,
                    comment=u"Dossier - adresse"),
        ImportFormater('general_contractor__raw_name', # C, 3 TODO - extraire nom_prenom_titre
                       UnicodeFormater(200),
                       comment=u"Aménageur - nom brut",
                       duplicate_fields=['general_contractor__attached_to__name'],
                       required=False),
        ImportFormater(['general_contractor__attached_to__address', # D, 4
                        'general_contractor__attached_to__postal_code',
                        'general_contractor__attached_to__town'],
                    [UnicodeFormater(500, clean=True),
                     UnicodeFormater(5, re_filter=RE_CD_POSTAL_FILTER),
                     TownFormater(town_full_dct=tf._town_full_dct,
                                  town_dct=tf._town_dct)],
                    regexp=RE_ADD_CD_POSTAL_TOWN,
                    regexp_formater_args=[[0], [1], [2, 1]], required=False,
                    comment=u"Aménageur - adresse"),
        ImportFormater("general_contractor__title", # E, 5
                        StrChoiceFormater(Person.TYPE, cli=True),
                        required=False,
                        comment=u"Aménageur - titre"),
        None, # F, 6
        None, # G, 7
        None, # H, 8
        ImportFormater("parcels__year", # I, 9
                        YearNoFuturFormater(),
                        required=False),
        ImportParcelFormater('', required=False, post_processing=True), # J, 10
        None, # K, 11
        ImportFormater([['main_town', 'parcels__town']], # L, 12
                       tf,
                       required=False,
                       comment=u"Commune (si non définie avant)"),
        ImportFormater([['main_town', 'parcels__town']], # M, 13
                       tf,
                       required=False,
                       comment=u"Commune (si non définie avant)"),
        ImportFormater('saisine_type', # N, 14
                        TypeFormater(models.SaisineType),
                        required=False,
                        comment=u"Type de saisine"),
        None, # O, 15
        ImportFormater('comment', # P, 16
                       UnicodeFormater(2000),
                       comment=u"Commentaire",
                       concat=True, required=False),
        None, # Q, 17
        ImportFormater([
                    'responsible_town_planning_service__raw_name', # R, 18 service instructeur
                    'responsible_town_planning_service__attached_to__address',
                    'responsible_town_planning_service__attached_to__postal_code',
                    'responsible_town_planning_service__attached_to__town',],
                    [UnicodeFormater(300, clean=True),
                     UnicodeFormater(300, clean=True),
                     UnicodeFormater(5, re_filter=RE_CD_POSTAL_FILTER),
                     TownFormater(town_full_dct=tf._town_full_dct,
                                  town_dct=tf._town_dct)],
                    regexp=RE_NAME_ADD_CD_POSTAL_TOWN,
                    regexp_formater_args=[[0], [1], [2], [3, 2]],
                    comment=u"Aménageur - adresse",
                    required=False),
        ImportFormater('comment', # S, 19
                       UnicodeFormater(2000),
                       comment=u"Commentaire",
                       concat=True, required=False),
        ImportYearFormater('reception_date', # T, 20
                       DateFormater(),
                       comment=u"Date de création",
                       required=False,
                       duplicate_fields=['creation_date']),
        None, # U, 21
        None, # V, 22
        None, # W, 23
        None, # X, 24
        None, # Y, 25
        None, # Z, 26
        None, # AA, 27
        None, # AB, 28
        None, # AC, 29
        None, # AD, 30
        None, # AE, 31
        None, # AF, 32
        None, # AG, 33
        None, # AH, 34
        ImportFormater('creation_date', # AI, 35
                       DateFormater(),
                       force_value=True,
                       comment=u"Date de création",
                       required=False,),
        None, # AJ, 36
        ImportFormater('comment', # AK, 37
                       UnicodeFormater(2000),
                       comment=u"Commentaire",
                       concat=True, required=False),
        None, # AL, 38
        None, # AM, 39
        None, # AN, 40
        None, # AO, 41
        ImportFormater('comment', # AP, 42
                       UnicodeFormater(2000),
                       comment=u"Commentaire",
                       concat=True, required=False),
        None, # AQ, 43
        None, # AR, 44
        None, # AS, 45
        None, # AT, 46
        ImportFormater('comment', # AU, 47
                       UnicodeFormater(2000),
                       comment=u"Commentaire",
                       concat=True, required=False),
        None, # AV, 48
        ImportFormater('permit_reference', # AW, 49
                       UnicodeFormater(300, clean=True),
                       regexp=RE_PERMIT_REFERENCE,
                       comment=u"Réf. du permis de construire",
                       required=False),
        None, # AX, 50
        None, # AY, 51
        None, # AZ, 52
        None, # BA, 53
        None, # BB, 54
        None, # BC, 55
        None, # BD, 56
        ImportFormater([['main_town', 'parcels__town']], # BE, 57
                       TownINSEEFormater(),
                       required=False,
                       comment=u"Commune (si non définie avant)"),
        ImportFormater('comment', # BF, 58
                       UnicodeFormater(2000),
                       comment=u"Commentaire",
                       concat=True, required=False),
        None, # BG, 59
        None, # BH, 60
        None, # BI, 61
        None, # BJ, 62
        None, # BK, 63
        None, # BL, 64
        None, # BM, 65
        None, # BN, 66
        None, # BO, 67
        None, # BP, 68
        None, # BQ, 69
        None, # BR, 70
        None, # BS, 71
        ImportFormater(
                    'responsible_town_planning_service__attached_to__name', # BT, 72 service instructeur
                    UnicodeFormater(300, clean=True),
                    regexp=RE_ORGA,
                    comment=u"Service instructeur - nom",
                    required=False),
        None, # BU, 73
        ImportClosingFormater('', StrToBoolean(cli=True),
                              post_processing=True, required=False,
                              comment=u'Dossier clos'), # BV, 74, end date
        ImportClosingFormater('in_charge__raw_name', # BW, 75 responsable
                       UnicodeFormater(200),
                       comment=u"Responsable - nom brut",
                       required=False),
        ImportFormater('total_surface', # BX, 76 surface totale
                       SurfaceFormater(),
                       comment=u"Surface totale",
                       required=False),
        ImportFormater('total_developed_surface', # BY, 77 surface totale aménagée
                       SurfaceFormater(),
                       comment=u"Surface totale aménagée",
                       required=False),
        None, # BZ, 78
        None, # CA, 79
        None, # CB, 80
        None, # CC, 81
        None, # CD, 82
        None, # CE, 83
        None, # CF, 84
        ImportFormater('permit_type',
                        TypeFormater(models.PermitType),
                        required=False,
                        comment=u"Type de permis"), # CG, 85
        None, # CH, 85
        ]

    def __init__(self, *args, **kwargs):
        super(FileImporterSraPdL, self).__init__(*args, **kwargs)
        self.DEFAULTS[('in_charge',)]['attached_to'], created = \
          models.Organization.objects.get_or_create(name='SRA Pays de la Loire',
              defaults={
              'organization_type':OrganizationType.objects.get(
                                                  txt_idx='sra')})
        self._init_line_format()
        if tuple() not in self._defaults:
            self._defaults[tuple()] = {}
        self._defaults[tuple()]['history_modifier'] = self.history_modifier

def test(filename):
    importer = FileImporterSraPdL(skip_first_line=True, output=True)
    with open(filename) as csv_file:
        encodings = [settings.ENCODING, settings.ALT_ENCODING, 'utf-8']
        for encoding in encodings:
            try:
                importer.importation([line for line in
                        unicodecsv.reader(csv_file, encoding='utf-8')])
                #importer.importation(unicode_csv_reader(
                #        [line.decode(encoding)
                #         for line in csv_file.readlines()])
                print importer.get_csv_errors()
                break
            except ImporterError, e:
                print(unicode(e))
                if e.type == ImporterError.HEADER and encoding != encodings[-1]:
                    csv_file.seek(0)
                    continue
            except UnicodeDecodeError:
                if encoding != encodings[-1]:
                    csv_file.seek(0)
                    continue