Parent: [b4023f] (diff)

Child: [c4f76a] (diff)

Download this file

project-import.py    277 lines (236 with data), 10.8 kB

  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
import bson
import datetime
import json
import logging
import multiprocessing
import re
import sys
import colander as col
from ming.orm import session, ThreadLocalORMSession
from pylons import c, g
from tg import config
from allura import model as M
from allura.lib import helpers as h
log = logging.getLogger(__name__)
class TroveCategory():
def __init__(self, root_type=''):
self.root_type = root_type
def deserialize(self, node, cstruct):
if cstruct is col.null:
return col.null
cat = M.TroveCategory.query.get(fullpath=cstruct)
if not cat:
cat = M.TroveCategory.query.get(fullname=cstruct)
if not cat:
raise col.Invalid(node,
'"%s" is not a valid trove category.' % cstruct)
if not cat.fullpath.startswith(self.root_type):
raise col.Invalid(node,
'"%s" is not a valid "%s" trove category.' %
(cstruct, self.root_type))
return cat
class User():
def deserialize(self, node, cstruct):
if cstruct is col.null:
return col.null
user = M.User.by_username(cstruct)
if not user:
raise col.Invalid(node,
'Invalid username "%s".' % cstruct)
return user
class ProjectName(object):
def __init__(self, name, shortname):
self.name = name
self.shortname = shortname
class ProjectNameType():
def deserialize(self, node, cstruct):
if cstruct is col.null:
return col.null
name = cstruct
shortname = re.sub("[^A-Za-z0-9 ]", "", name).lower()
shortname = re.sub(" ", "-", shortname)
return ProjectName(name, shortname)
class ProjectShortnameType():
def deserialize(self, node, cstruct):
if cstruct is col.null:
return col.null
col.Length(min=3, max=15)(node, cstruct)
col.Regex(r'^[A-z][-A-z0-9]{2,}$',
msg='Project shortname must begin with a letter, can '
'contain letters, numbers, and dashes, and must be '
'3-15 characters in length.')(node, cstruct)
return cstruct.lower()
class Award():
def __init__(self, nbhd):
self.nbhd = nbhd
def deserialize(self, node, cstruct):
if cstruct is col.null:
return col.null
award = M.Award.query.find(dict(short=cstruct,
created_by_neighborhood_id=self.nbhd._id)).first()
if not award:
# try to look up the award by _id
award = M.Award.query.find(dict(_id=bson.ObjectId(cstruct),
created_by_neighborhood_id=self.nbhd._id)).first()
if not award:
raise col.Invalid(node,
'Invalid award "%s".' % cstruct)
return award
class TroveTopics(col.SequenceSchema):
trove_topics = col.SchemaNode(TroveCategory("Topic"))
class TroveLicenses(col.SequenceSchema):
trove_license = col.SchemaNode(TroveCategory("License"))
class TroveDatabases(col.SequenceSchema):
trove_databases = col.SchemaNode(TroveCategory("Database Environment"))
class TroveStatuses(col.SequenceSchema):
trove_statuses = col.SchemaNode(TroveCategory("Development Status"))
class TroveAudiences(col.SequenceSchema):
trove_audience = col.SchemaNode(TroveCategory("Intended Audience"))
class TroveOSes(col.SequenceSchema):
trove_oses = col.SchemaNode(TroveCategory("Operating System"))
class TroveLanguages(col.SequenceSchema):
trove_languages = col.SchemaNode(TroveCategory("Programming Language"))
class TroveTranslations(col.SequenceSchema):
trove_translations = col.SchemaNode(TroveCategory("Translations"))
class TroveUIs(col.SequenceSchema):
trove_uis = col.SchemaNode(TroveCategory("User Interface"))
class Labels(col.SequenceSchema):
label = col.SchemaNode(col.Str())
class Project(col.MappingSchema):
name = col.SchemaNode(ProjectNameType())
shortname = col.SchemaNode(ProjectShortnameType(), missing=None)
summary = col.SchemaNode(col.Str(), missing='')
description = col.SchemaNode(col.Str(), missing='')
admin = col.SchemaNode(User())
private = col.SchemaNode(col.Bool(), missing=False)
labels = Labels(missing=[])
external_homepage = col.SchemaNode(col.Str(), missing='')
trove_root_databases = TroveDatabases(missing=None)
trove_developmentstatuses = TroveStatuses(validator=col.Length(max=6), missing=None)
trove_audiences = TroveAudiences(validator=col.Length(max=6), missing=None)
trove_licenses = TroveLicenses(validator=col.Length(max=6), missing=None)
trove_oses = TroveOSes(missing=None)
trove_languages = TroveLanguages(validator=col.Length(max=6), missing=None)
trove_topics = TroveTopics(validator=col.Length(max=3), missing=None)
trove_natlanguages = TroveTranslations(missing=None)
trove_environments = TroveUIs(missing=None)
def valid_shortname(project):
if project.shortname:
# already validated in ProjectShortnameType validator
return True
elif 3 <= len(project.name.shortname) <= 15:
return True
else:
return 'Project shortname "%s" must be between 3 and 15 characters' \
% project.name.shortname
class Projects(col.SequenceSchema):
project = Project(validator=col.Function(valid_shortname))
class Object(object):
def __init__(self, d):
self.__dict__.update(d)
def trove_ids(orig, new_):
if new_ is None: return orig
return list(set(t._id for t in list(new_)))
def create_project(p, nbhd, user, options):
worker_name = multiprocessing.current_process().name
M.session.artifact_orm_session._get().skip_mod_date = True
shortname = p.shortname or p.name.shortname
project = M.Project.query.get(shortname=shortname,
neighborhood_id=nbhd._id)
if project and not (options.update and p.shortname):
log.warning('[%s] Skipping existing project "%s". To update an existing '
'project you must provide the project shortname and run '
'this script with --update.' % (worker_name, shortname))
return 0
if not project:
log.info('[%s] Creating project "%s".' % (worker_name, shortname))
try:
project = nbhd.register_project(shortname,
p.admin,
project_name=p.name.name,
private_project=p.private)
except Exception, e:
log.error('[%s] %s' % (worker_name, str(e)))
return 0
else:
log.info('[%s] Updating project "%s".' % (worker_name, shortname))
project.notifications_disabled = True
project.summary = p.summary
project.short_description = p.description
project.external_homepage = p.external_homepage
project.last_updated = datetime.datetime.utcnow()
# These properties may have been populated by nbhd template defaults in
# register_project(). Overwrite if we have data, otherwise keep defaults.
project.labels = p.labels or project.labels
project.trove_root_database = trove_ids(project.trove_root_database, p.trove_root_databases)
project.trove_developmentstatus = trove_ids(project.trove_developmentstatus, p.trove_developmentstatuses)
project.trove_audience = trove_ids(project.trove_audience, p.trove_audiences)
project.trove_license = trove_ids(project.trove_license, p.trove_licenses)
project.trove_os = trove_ids(project.trove_os, p.trove_oses)
project.trove_language = trove_ids(project.trove_language, p.trove_languages)
project.trove_topic = trove_ids(project.trove_topic, p.trove_topics)
project.trove_natlanguage = trove_ids(project.trove_natlanguage, p.trove_natlanguages)
project.trove_environment = trove_ids(project.trove_environment, p.trove_environments)
for a in p.awards:
M.AwardGrant(app_config_id=bson.ObjectId(),
tool_version=dict(neighborhood='0'), award_id=a._id,
granted_to_project_id=project._id,
granted_by_neighborhood_id=nbhd._id)
project.notifications_disabled = False
with h.push_config(c, project=project, user=user):
ThreadLocalORMSession.flush_all()
g.post_event('project_updated')
session(project).clear()
return 0
def create_projects(projects, nbhd, user, options):
for p in projects:
r = create_project(Object(p), nbhd, user, options)
if r != 0:
sys.exit(r)
def main(options):
log.addHandler(logging.StreamHandler(sys.stdout))
log.setLevel(getattr(logging, options.log_level.upper()))
log.debug(options)
nbhd = M.Neighborhood.query.get(name=options.neighborhood)
if not nbhd:
return 'Invalid neighborhood "%s".' % options.neighborhood
admin = M.User.query.get(username=config.get('sfx.api.siteadmin', 'sf-robot'))
data = json.load(open(options.file, 'r'))
project = Project()
project.add(col.SchemaNode(col.Sequence(),
col.SchemaNode(Award(nbhd)),
name='awards', missing=[]))
schema = col.SchemaNode(col.Sequence(), project, name='project')
projects = schema.deserialize(data)
log.debug(projects)
chunks = [projects[i::options.nprocs] for i in range(options.nprocs)]
jobs = []
for i in range(options.nprocs):
p = multiprocessing.Process(target=create_projects,
args=(chunks[i], nbhd, admin, options), name='worker-' + str(i+1))
jobs.append(p)
p.start()
for j in jobs:
j.join()
if j.exitcode <> 0: return j.exitcode
return 0
def parse_options():
import argparse
parser = argparse.ArgumentParser(
description='Import Allura project(s) from JSON file')
parser.add_argument('file', metavar='JSON_FILE', type=str,
help='Path to JSON file containing project data.')
parser.add_argument('neighborhood', metavar='NEIGHBORHOOD', type=str,
help='Destination Neighborhood shortname.')
parser.add_argument('--log', dest='log_level', default='INFO',
help='Log level (DEBUG, INFO, WARNING, ERROR, CRITICAL).')
parser.add_argument('--update', dest='update', default=False,
action='store_true',
help='Update existing projects. Without this option, existing '
'projects will be skipped.')
parser.add_argument('--nprocs', '-n', action='store', dest='nprocs', type=int,
help='Number of processes to divide the work among.',
default=multiprocessing.cpu_count())
return parser.parse_args()
if __name__ == '__main__':
sys.exit(main(parse_options()))