How to unwind/merge arrays from hierarchical document structure? - merge

Question

I have a nested document structure and I am able to filter it with pluck to show the relevant parts:
Is there an elegant way to merge all entries of the last level to a single array?
Expected result (entries are not unique on purpose):
[
'3425b91f-f019-4db3-ad56-c336bf55279b',
'3d07946e-183d-4992-9acd-676f5122e1b1',
'3425b91f-f019-4db3-ad56-c336bf55279b',
'3d07946e-183d-4992-9acd-676f5122e1b1',
'2cd652a6-4dcd-4920-9592-d4cdc5a034bf',
'70fe1812-e1de-447b-ac4f-d89fead4756d',
'2cd652a6-4dcd-4920-9592-d4cdc5a034bf',
'70fe1812-e1de-447b-ac4f-d89fead4756d'
]
I tried to use
r.table('periods')['regions']['sites']['plants']['product']['process']['technologies'].run()
but it gives the error "Cannot perform bracket on a sequence of sequences".
=> Is there some alternative operator to get a merged sequence instead a "sequence of sequences" for each step?
Something like
r.table('periods').unwind('regions.sites.plants.product.process.technologies')
Here is some python code to create example data:
from rethinkdb import RethinkDB
r = RethinkDB()
r.connect({}).repl()
r.table_create("periods")
def uniqueid():
return r.uuid().run()
periodid_first = uniqueid()
periodid_second = uniqueid()
companyid_2000 = uniqueid()
companyid_2001 = uniqueid()
technologyid_2000_first = uniqueid()
technologyid_2000_second = uniqueid()
technologyid_2001_first = uniqueid()
technologyid_2001_second = uniqueid()
energy_carrierid_2000_first = uniqueid()
energy_carrierid_2000_second = uniqueid()
energy_carrierid_2001_first = uniqueid()
energy_carrierid_2001_second = uniqueid()
periods = [
{
'id': periodid_first,
'start': 2000,
'end': 2000,
# 'sub_periods': [],
'regions': [
{
'id': 'DE',
# 'sub_regions': [],
'sites': [
{
'id': 'first_site_in_germany',
'company': companyid_2000, # => verweist auf periods => companies
'plants': [
{
'id': 'qux',
'product': {
'id': 'Ammoniak',
'process': {
'id': 'SMR+HB',
'technologies': [
technologyid_2000_first, # => verweist auf periods => technologies
technologyid_2000_second
]
}
}
}
]
}
]
},
{
'id': 'FR',
# 'sub_regions': [],
'sites': [
{
'id': 'first_site_in_france',
'company': companyid_2000, # => verweist auf periods => companies
'plants': [
{
'id': 'qux',
'product': {
'id': 'Ammoniak',
'process': {
'id': 'SMR+HB',
'technologies': [
technologyid_2000_first, # => verweist auf periods => technologies
technologyid_2000_second
]
}
}
}
]
}
]
}
],
'companies': [
{
'id': companyid_2000,
'name': 'international_company'
}
],
'technologies': [
{
'id': technologyid_2000_first,
'name': 'SMR',
'specific_cost_per_year': 123,
'specific_energy_consumptions': [
{
'energy_carrier': energy_carrierid_2000_first,
'specific_consumption': 5555
}, # => verweist auf periods => energy_carriers
{
'energy_carrier': energy_carrierid_2000_second,
'energy_consumption': 2333
}
]
},
{
'id': technologyid_2000_second,
'name': 'HB',
'specific_cost_per_year': 1234,
'specific_energy_consumptions': [
{
'energy_carrier': energy_carrierid_2000_first,
'specific_consumption': 555
}, # => verweist auf periods => energy_carriers
{
'energy_carrier': energy_carrierid_2000_second,
'energy_consumption': 233
}
]
}
],
'energy_carriers': [
{
'id': energy_carrierid_2000_first,
'name': 'oil',
'group': 'fuel'
},
{
'id': energy_carrierid_2000_second,
'name': 'gas',
'group': 'fuel'
},
{
'id': uniqueid(),
'name': 'conventional',
'group': 'electricity'
},
{
'id': uniqueid(),
'name': 'green',
'group': 'electricity'
}
],
'networks': [
{
'id': uniqueid(),
'name': 'gas',
'sub_networks': [],
'pipelines': [
]
},
{
'id': uniqueid(),
'name': 'gas',
'sub_networks': [],
'pipelines': [
]
}
]
},
{
'id': periodid_second,
'start': 2001,
'end': 2001,
# 'sub_periods': [],
'regions': [
{
'id': 'DE',
# 'sub_regions': [],
'sites': [
{
'id': 'first_site_in_germany',
'company': companyid_2001, # => verweist auf periods => companies
'plants': [
{
'id': 'qux',
'product': {
'id': 'Ammoniak',
'process': {
'id': 'SMR+HB',
'technologies': [
technologyid_2001_first, # => verweist auf periods => technologies
technologyid_2001_second
]
}
}
}
]
}
]
},
{
'id': 'FR',
# 'sub_regions': [],
'sites': [
{
'id': 'first_site_in_france',
'company': companyid_2001, # => verweist auf periods => companies
'plants': [
{
'id': 'qux',
'product': {
'id': 'Ammoniak',
'process': {
'id': 'SMR+HB',
'technologies': [
technologyid_2001_first, # => verweist auf periods => technologies
technologyid_2001_second
]
}
}
}
]
}
]
}
],
'companies': [
{
'id': companyid_2001,
'name': 'international_company'
}
],
'technologies': [
{
'id': technologyid_2001_first,
'name': 'SMR',
'specific_cost_per_year': 123,
'specific_energy_consumptions': [
{
'energy_carrier': energy_carrierid_2001_first,
'specific_consumption': 5555
}, # => verweist auf periods => energy_carriers
{
'energy_carrier': energy_carrierid_2001_second,
'energy_consumption': 2333
}
]
},
{
'id': technologyid_2001_second,
'name': 'HB',
'specific_cost_per_year': 1234,
'specific_energy_consumptions': [
{
'energy_carrier': energy_carrierid_2001_first,
'specific_consumption': 555
}, # => verweist auf periods => energy_carriers
{
'energy_carrier': energy_carrierid_2001_second,
'energy_consumption': 233
}
]
}
],
'energy_carrieriers': [
{
'id': energy_carrierid_2001_first,
'name': 'oil',
'group': 'fuel'
},
{
'id': energy_carrierid_2001_second,
'name': 'gas',
'group': 'fuel'
},
{
'id': uniqueid(),
'name': 'conventional',
'group': 'electricity'
},
{
'id': uniqueid(),
'name': 'green',
'group': 'electricity'
}
],
'networks': [
{
'id': uniqueid(),
'name': 'gas',
'sub_networks': [],
'pipelines': [
]
},
{
'id': uniqueid(),
'name': 'gas',
'sub_networks': [],
'pipelines': [
]
}
]
}
]
r.table('periods') \
.insert(periods) \
.run()
Related:
RethinkDB: RqlRuntimeError: Cannot perform bracket on a sequence of sequences

Answer 1

Nested concat_map in combination with r.row operator and bracket drill down does the trick:
r.table('periods') \
.concat_map(r.row['regions']) \
.concat_map(r.row['sites']) \
.concat_map(r.row['plants'])['product']['process'] \
.concat_map(r.row['technologies']) \
.run()