def test_column_task(klass):
# Ensure every column task runs and produces some kind of independent
# metadata.
# TODO: test columnstasks that have params
if klass.get_param_names():
raise SkipTest("Cannot test ColumnsTask with params")
task = klass()
runtask(task)
assert_greater(current_session().query(OBSColumn).filter(OBSColumn.id.startswith(classpath(task))).count(), 0)
def test_column_task(klass):
# Ensure every column task runs and produces some kind of independent
# metadata.
# TODO: test columnstasks that have params
if klass.get_param_names():
raise SkipTest('Cannot test ColumnsTask with params')
task = klass()
runtask(task)
assert_greater(
current_session().query(OBSColumn).filter(
OBSColumn.id.startswith(classpath(task))).count(), 0)
def load_sumlevels():
'''
Load summary levels from JSON. Returns a dict by sumlevel number.
'''
with open(os.path.join(os.path.dirname(__file__), 'summary_levels.json')) as fhandle:
sumlevels_list = json.load(fhandle)
sumlevels = {}
for slevel in sumlevels_list:
# Replace pkey ancestors with paths to columns
# We subtract 1 from the pkey because it's 1-indexed, unlike python
fields = slevel['fields']
for i, ancestor in enumerate(fields['ancestors']):
colpath = os.path.join('columns', classpath(load_sumlevels),
sumlevels_list[ancestor - 1]['fields']['slug'])
fields['ancestors'][i] = colpath
if fields['parent']:
fields['parent'] = os.path.join(
'columns', classpath(load_sumlevels),
sumlevels_list[fields['parent'] - 1]['fields']['slug'])
sumlevels[fields['summary_level']] = fields
return sumlevels
def load_sumlevels():
'''
Load summary levels from JSON. Returns a dict by sumlevel number.
'''
with open(os.path.join(os.path.dirname(__file__), 'summary_levels.json')) as fhandle:
sumlevels_list = json.load(fhandle)
sumlevels = {}
for slevel in sumlevels_list:
# Replace pkey ancestors with paths to columns
# We subtract 1 from the pkey because it's 1-indexed, unlike python
fields = slevel['fields']
for i, ancestor in enumerate(fields['ancestors']):
colpath = os.path.join('columns', classpath(load_sumlevels),
sumlevels_list[ancestor - 1]['fields']['slug'])
fields['ancestors'][i] = colpath
if fields['parent']:
fields['parent'] = os.path.join(
'columns', classpath(load_sumlevels),
sumlevels_list[fields['parent'] - 1]['fields']['slug'])
sumlevels[fields['summary_level']] = fields
return sumlevels
def run(self):
shapefiles = shell(
'ls {dir}/*.shp'.format(dir=os.path.join('tmp', classpath(
self), str(self.year), self.geography))).strip().split('\n')
cmd = 'ogrinfo {shpfile_path}'.format(shpfile_path=shapefiles[0])
resp = shell(cmd)
if 'Polygon' in resp:
nlt = '-nlt MultiPolygon'
else:
nlt = ''
cmd = 'PG_USE_COPY=yes PGCLIENTENCODING=latin1 ' \
'ogr2ogr -f PostgreSQL "PG:dbname=$PGDATABASE active_schema={schema}" ' \
'-t_srs "EPSG:4326" {nlt} -nln {tablename} ' \
'-lco OVERWRITE=yes ' \
'-lco SCHEMA={schema} {shpfile_path} '.format(
tablename=self.output().tablename,
schema=self.output().schema, nlt=nlt,
shpfile_path=shapefiles.pop())
shell(cmd)
# chunk into 500 shapefiles at a time.
for i, shape_group in enumerate(grouper(shapefiles, 500)):
shell('export PG_USE_COPY=yes PGCLIENTENCODING=latin1; '
'echo \'{shapefiles}\' | xargs -P 16 -I shpfile_path '
'ogr2ogr -f PostgreSQL "PG:dbname=$PGDATABASE '
'active_schema={schema}" -append '
'-t_srs "EPSG:4326" {nlt} -nln {tablename} '
'shpfile_path '.format(shapefiles='\n'.join(
[shp for shp in shape_group if shp]),
tablename=self.output().tablename,
nlt=nlt,
schema=self.output().schema))
print('imported {} shapefiles'.format((i + 1) * 500))
session = current_session()
# Spatial index
session.execute(
'ALTER TABLE {qualified_table} RENAME COLUMN '
'wkb_geometry TO geom'.format(qualified_table=self.output().table))
session.execute(
'CREATE INDEX ON {qualified_table} USING GIST (geom)'.format(
qualified_table=self.output().table))
def run(self):
shapefiles = shell('ls {dir}/*.shp'.format(
dir=os.path.join('tmp', classpath(self), str(self.year), self.geography)
)).strip().split('\n')
cmd = 'PG_USE_COPY=yes PGCLIENTENCODING=latin1 ' \
'ogr2ogr -f PostgreSQL "PG:dbname=$PGDATABASE active_schema={schema}" ' \
'-t_srs "EPSG:4326" -nlt MultiPolygon -nln {tablename} ' \
'-lco OVERWRITE=yes ' \
'-lco SCHEMA={schema} {shpfile_path} '.format(
tablename=self.output().tablename,
schema=self.output().schema,
shpfile_path=shapefiles.pop())
shell(cmd)
# chunk into 500 shapefiles at a time.
for i, shape_group in enumerate(grouper(shapefiles, 500)):
shell(
'export PG_USE_COPY=yes PGCLIENTENCODING=latin1; '
'echo \'{shapefiles}\' | xargs -P 16 -I shpfile_path '
'ogr2ogr -f PostgreSQL "PG:dbname=$PGDATABASE '
'active_schema={schema}" -append '
'-t_srs "EPSG:4326" -nlt MultiPolygon -nln {tablename} '
'shpfile_path '.format(
shapefiles='\n'.join([shp for shp in shape_group if shp]),
tablename=self.output().tablename,
schema=self.output().schema))
print 'imported {} shapefiles'.format((i + 1) * 500)
session = current_session()
# Spatial index
session.execute('ALTER TABLE {qualified_table} RENAME COLUMN '
'wkb_geometry TO geom'.format(
qualified_table=self.output().table))
session.execute('CREATE INDEX ON {qualified_table} USING GIST (geom)'.format(
qualified_table=self.output().table))
def directory(self):
return os.path.join('tmp', classpath(self), str(self.year), self.geography)
def directory(self):
return os.path.join('tmp', classpath(self), str(self.year), self.geography)
def output(self):
return LocalTarget(os.path.join('tmp', classpath(self), self.task_id) +
'_' + underscore_slugify(self.last_time) + '.csv')
def output(self):
return LocalTarget(
path=os.path.join('tmp', classpath(self), self.filename()))
def output(self):
return LocalTarget(
os.path.join('tmp', classpath(self),
unqualified_task_id(self.task_id) + '.dump'))
def output(self):
return LocalTarget(
os.path.join('tmp', classpath(self), self.task_id) + '_' +
underscore_slugify(self.last_time) + '.csv')
def output(self):
return LocalTarget(
os.path.join('tmp', classpath(self), self.seq).lower())
def output(self):
return LocalTarget(os.path.join('tmp', classpath(self), self.task_id, 'au_mb_all_merged.shp'))
def output(self):
return LocalTarget(path=os.path.join(classpath(self), self.filename()))
def output(self):
return LocalTarget(os.path.join('tmp', classpath(self), self.task_id))
def output(self):
return LocalTarget(os.path.join('tmp', classpath(self), self.task_id))
def __init__(self, task):
self.path = os.path.join('tmp', classpath(task), task.task_id)
self._target = LocalTarget(self.path)