loket to op sync with reasoning

This commit is contained in:
Boris De Vloed
2022-11-29 16:00:34 +00:00
parent f236290b62
commit a127ea8060
7 changed files with 582 additions and 65 deletions

View File

@@ -1,7 +1,6 @@
version: '3.4'
version: "3.4"
x-logging:
&default-logging
x-logging: &default-logging
driver: "json-file"
options:
max-size: "10m"
@@ -11,7 +10,7 @@ services:
identifier:
image: semtech/mu-identifier:1.9.1
environment:
DEFAULT_MU_AUTH_ALLOWED_GROUPS_HEADER: "[{\"variables\":[],\"name\":\"public\"}]"
DEFAULT_MU_AUTH_ALLOWED_GROUPS_HEADER: '[{"variables":[],"name":"public"}]'
SESSION_COOKIE_SECURE: "on"
labels:
- "logging=true"
@@ -201,34 +200,38 @@ services:
- db:database
restart: always
logging: *default-logging
################################################################################
# DELTA GENERAL
################################################################################
reasoner:
image: bdevloed/mu-reasoner
volumes:
- ./config/reasoner:/config
################################################################################
# DELTA GENERAL
################################################################################
delta-producer-dump-file-publisher:
image: bdevloed/delta-producer-dump-file-publisher:0.8.0-beta
volumes:
- ./config/delta-producer/dump-file-publisher:/config
- ./data/files:/share
environment:
FILES_GRAPH: 'http://mu.semte.ch/graphs/public' # Note: this will be extracted in a config per job one day
DCAT_DATASET_GRAPH: 'http://mu.semte.ch/graphs/public'
FILES_GRAPH: "http://mu.semte.ch/graphs/public" # Note: this will be extracted in a config per job one day
DCAT_DATASET_GRAPH: "http://mu.semte.ch/graphs/public"
links:
- db:database
restart: always
logging: *default-logging
################################################################################
# DELTA ADMINISTRATIVE-UNITS: START
################################################################################
################################################################################
# DELTA ADMINISTRATIVE-UNITS: START
################################################################################
delta-producer-bg-jobs-initiator-administrative-units:
image: lblod/delta-producer-background-jobs-initiator:0.3.1
environment:
JOBS_GRAPH: "http://mu.semte.ch/graphs/organisatieportaal"
DUMP_FILE_CREATION_JOB_OPERATION: 'http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/deltaDumpFileCreation/administrative-units'
INITIAL_PUBLICATION_GRAPH_SYNC_JOB_OPERATION: 'http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/initialPublicationGraphSyncing/administrative-units'
HEALING_JOB_OPERATION: 'http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/healingOperation/administrative-units'
CRON_PATTERN_DUMP_JOB: '0 0 4 * * 6' # weekly on saturday
CRON_PATTERN_HEALING_JOB: '0 0 4 * * *' # everyday at 4 AM
START_INITIAL_SYNC: 'false' # prefer to disable it now. We want to have feeling with how the DB acts.
DUMP_FILE_CREATION_JOB_OPERATION: "http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/deltaDumpFileCreation/administrative-units"
INITIAL_PUBLICATION_GRAPH_SYNC_JOB_OPERATION: "http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/initialPublicationGraphSyncing/administrative-units"
HEALING_JOB_OPERATION: "http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/healingOperation/administrative-units"
CRON_PATTERN_DUMP_JOB: "0 0 4 * * 6" # weekly on saturday
CRON_PATTERN_HEALING_JOB: "0 0 4 * * *" # everyday at 4 AM
START_INITIAL_SYNC: "false" # prefer to disable it now. We want to have feeling with how the DB acts.
labels:
- "logging=true"
links:
@@ -241,12 +244,12 @@ services:
MAX_BODY_SIZE: "50mb"
JOBS_GRAPH: "http://mu.semte.ch/graphs/organisatieportaal"
RELATIVE_FILE_PATH: "deltas/administrative-units"
PUBLICATION_GRAPH: 'http://redpencil.data.gift/id/deltas/producer/administrative-units'
HEALING_JOB_OPERATION: 'http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/healingOperation/administrative-units'
INITIAL_PUBLICATION_GRAPH_SYNC_JOB_OPERATION: 'http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/initialPublicationGraphSyncing/administrative-units'
PUBLICATION_GRAPH: "http://redpencil.data.gift/id/deltas/producer/administrative-units"
HEALING_JOB_OPERATION: "http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/healingOperation/administrative-units"
INITIAL_PUBLICATION_GRAPH_SYNC_JOB_OPERATION: "http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/initialPublicationGraphSyncing/administrative-units"
QUEUE_POLL_INTERVAL: 3000
USE_VIRTUOSO_FOR_EXPENSIVE_SELECTS: "true" # some queries are just too expensive
SKIP_MU_AUTH_INITIAL_SYNC: 'true'
SKIP_MU_AUTH_INITIAL_SYNC: "true"
HEALING_PATCH_GRAPH_BATCH_SIZE: 500
volumes:
- ./config/delta-producer/administrative-units:/config
@@ -263,7 +266,7 @@ services:
ERROR_GRAPH: "http://mu.semte.ch/graphs/organisatieportaal"
RELATIVE_FILE_PATH: "deltas/administrative-units"
PUBLISHER_URI: "http://data.lblod.info/services/delta-production-json-diff-file-manager/administrative-units"
PUBLICATION_GRAPH: 'http://redpencil.data.gift/id/deltas/producer/administrative-units'
PUBLICATION_GRAPH: "http://redpencil.data.gift/id/deltas/producer/administrative-units"
DELTA_INTERVAL_MS: 10000
PRETTY_PRINT_DIFF_JSON: "true"
volumes:
@@ -274,22 +277,22 @@ services:
- db:database
restart: always
logging: *default-logging
################################################################################
# DELTA ADMINISTRATIVE-UNITS: END
################################################################################
################################################################################
# DELTA ORGANIZATIONS: START
################################################################################
################################################################################
# DELTA ADMINISTRATIVE-UNITS: END
################################################################################
################################################################################
# DELTA ORGANIZATIONS: START
################################################################################
delta-producer-bg-jobs-initiator-organizations:
image: lblod/delta-producer-background-jobs-initiator:0.3.1
environment:
JOBS_GRAPH: "http://mu.semte.ch/graphs/organisatieportaal"
DUMP_FILE_CREATION_JOB_OPERATION: 'http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/deltaDumpFileCreation/organizations'
INITIAL_PUBLICATION_GRAPH_SYNC_JOB_OPERATION: 'http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/initialPublicationGraphSyncing/organizations'
HEALING_JOB_OPERATION: 'http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/healingOperation/organizations'
CRON_PATTERN_DUMP_JOB: '42 * * * *' # At minute 42 every hour
CRON_PATTERN_HEALING_JOB: '0 0 4 * * *' # everyday at 4 AM
START_INITIAL_SYNC: 'false' # prefer to disable it now. We want to have feeling with how the DB acts.
DUMP_FILE_CREATION_JOB_OPERATION: "http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/deltaDumpFileCreation/organizations"
INITIAL_PUBLICATION_GRAPH_SYNC_JOB_OPERATION: "http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/initialPublicationGraphSyncing/organizations"
HEALING_JOB_OPERATION: "http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/healingOperation/organizations"
CRON_PATTERN_DUMP_JOB: "42 * * * *" # At minute 42 every hour
CRON_PATTERN_HEALING_JOB: "0 0 4 * * *" # everyday at 4 AM
START_INITIAL_SYNC: "false" # prefer to disable it now. We want to have feeling with how the DB acts.
labels:
- "logging=true"
links:
@@ -302,12 +305,12 @@ services:
MAX_BODY_SIZE: "50mb"
JOBS_GRAPH: "http://mu.semte.ch/graphs/organisatieportaal"
RELATIVE_FILE_PATH: "deltas/organizations"
PUBLICATION_GRAPH: 'http://redpencil.data.gift/id/deltas/producer/organizations'
HEALING_JOB_OPERATION: 'http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/healingOperation/organizations'
INITIAL_PUBLICATION_GRAPH_SYNC_JOB_OPERATION: 'http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/initialPublicationGraphSyncing/organizations'
PUBLICATION_GRAPH: "http://redpencil.data.gift/id/deltas/producer/organizations"
HEALING_JOB_OPERATION: "http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/healingOperation/organizations"
INITIAL_PUBLICATION_GRAPH_SYNC_JOB_OPERATION: "http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/initialPublicationGraphSyncing/organizations"
QUEUE_POLL_INTERVAL: 3000
USE_VIRTUOSO_FOR_EXPENSIVE_SELECTS: "true" # some queries are just too expensive
SKIP_MU_AUTH_INITIAL_SYNC: 'true'
SKIP_MU_AUTH_INITIAL_SYNC: "true"
HEALING_PATCH_GRAPH_BATCH_SIZE: 500
volumes:
- ./config/delta-producer/organizations:/config
@@ -324,7 +327,7 @@ services:
ERROR_GRAPH: "http://mu.semte.ch/graphs/organisatieportaal"
RELATIVE_FILE_PATH: "deltas/organizations"
PUBLISHER_URI: "http://data.lblod.info/services/delta-production-json-diff-file-manager/organizations"
PUBLICATION_GRAPH: 'http://redpencil.data.gift/id/deltas/producer/organizations'
PUBLICATION_GRAPH: "http://redpencil.data.gift/id/deltas/producer/organizations"
DELTA_INTERVAL_MS: 10000
PRETTY_PRINT_DIFF_JSON: "true"
volumes:
@@ -335,24 +338,23 @@ services:
- db:database
restart: always
logging: *default-logging
################################################################################
# DELTA ORGANIZATIONS: END
################################################################################
################################################################################
# DELTA ORGANIZATIONS: END
################################################################################
################################################################################
# DELTA PUBLIC INFORMATION: START
################################################################################
################################################################################
# DELTA PUBLIC INFORMATION: START
################################################################################
delta-producer-bg-jobs-initiator-public:
image: lblod/delta-producer-background-jobs-initiator:0.3.1
environment:
JOBS_GRAPH: "http://mu.semte.ch/graphs/organisatieportaal"
DUMP_FILE_CREATION_JOB_OPERATION: 'http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/deltaDumpFileCreation/public'
INITIAL_PUBLICATION_GRAPH_SYNC_JOB_OPERATION: 'http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/initialPublicationGraphSyncing/public'
HEALING_JOB_OPERATION: 'http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/healingOperation/public'
CRON_PATTERN_DUMP_JOB: '11 */4 * * *' # At minute 11 every 4 hours
CRON_PATTERN_HEALING_JOB: '0 0 4 * * *' # everyday at 4 AM
START_INITIAL_SYNC: 'false' # prefer to disable it now. We want to have feeling with how the DB acts.
DUMP_FILE_CREATION_JOB_OPERATION: "http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/deltaDumpFileCreation/public"
INITIAL_PUBLICATION_GRAPH_SYNC_JOB_OPERATION: "http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/initialPublicationGraphSyncing/public"
HEALING_JOB_OPERATION: "http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/healingOperation/public"
CRON_PATTERN_DUMP_JOB: "11 */4 * * *" # At minute 11 every 4 hours
CRON_PATTERN_HEALING_JOB: "0 0 4 * * *" # everyday at 4 AM
START_INITIAL_SYNC: "false" # prefer to disable it now. We want to have feeling with how the DB acts.
labels:
- "logging=true"
links:
@@ -365,12 +367,12 @@ services:
MAX_BODY_SIZE: "50mb"
JOBS_GRAPH: "http://mu.semte.ch/graphs/organisatieportaal"
RELATIVE_FILE_PATH: "deltas/public"
PUBLICATION_GRAPH: 'http://redpencil.data.gift/id/deltas/producer/public'
HEALING_JOB_OPERATION: 'http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/healingOperation/public'
INITIAL_PUBLICATION_GRAPH_SYNC_JOB_OPERATION: 'http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/initialPublicationGraphSyncing/public'
PUBLICATION_GRAPH: "http://redpencil.data.gift/id/deltas/producer/public"
HEALING_JOB_OPERATION: "http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/healingOperation/public"
INITIAL_PUBLICATION_GRAPH_SYNC_JOB_OPERATION: "http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/initialPublicationGraphSyncing/public"
QUEUE_POLL_INTERVAL: 3000
USE_VIRTUOSO_FOR_EXPENSIVE_SELECTS: "true" # some queries are just too expensive
SKIP_MU_AUTH_INITIAL_SYNC: 'true'
SKIP_MU_AUTH_INITIAL_SYNC: "true"
HEALING_PATCH_GRAPH_BATCH_SIZE: 500
volumes:
- ./config/delta-producer/public:/config
@@ -387,7 +389,7 @@ services:
ERROR_GRAPH: "http://mu.semte.ch/graphs/organisatieportaal"
RELATIVE_FILE_PATH: "deltas/public"
PUBLISHER_URI: "http://data.lblod.info/services/delta-production-json-diff-file-manager/public"
PUBLICATION_GRAPH: 'http://redpencil.data.gift/id/deltas/producer/public'
PUBLICATION_GRAPH: "http://redpencil.data.gift/id/deltas/producer/public"
DELTA_INTERVAL_MS: 10000
PRETTY_PRINT_DIFF_JSON: "true"
volumes:
@@ -398,14 +400,44 @@ services:
- db:database
restart: always
logging: *default-logging
################################################################################
# DELTA PUBLIC INFORMATION: END
################################################################################
################################################################################
# DELTA PUBLIC INFORMATION: END
################################################################################
################################################################################
# DELTA CONSUMERS
################################################################################
mandatendatabank-consumer:
image: bdevloed/delta-consumer:fetch
environment:
DCR_SERVICE_NAME: "mandatendatabank-consumer"
DCR_SYNC_BASE_URL: "https://loket.lblod.info" # replace with link to Loket API
DCR_SYNC_DATASET_SUBJECT: "http://data.lblod.info/datasets/delta-producer/dumps/MandatarissenCacheGraphDump"
DCR_INITIAL_SYNC_JOB_OPERATION: "http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/consumer/initialSync/mandatarissen"
DCR_DELTA_SYNC_JOB_OPERATION: "http://redpencil.data.gift/id/jobs/concept/JobOperation/deltas/consumer/deltaSync/mandatarissen"
DCR_JOB_CREATOR_URI: "http://data.lblod.info/services/id/mandatendatabank-consumer"
# DISABLE_INITIAL_SYNC: "true"
BYPASS_MU_AUTH_FOR_EXPENSIVE_QUERIES: "true"
DCR_SYNC_FILES_PATH: "/sync/mandatarissen/files"
FILE_SYNC_GRAPH: "http://mu.semte.ch/graphs/temp/original-physical-files-data"
KEEP_DELTA_FILES: "true"
volumes:
- ./config/loket-consumer/mandate-dispatching:/config/triples-dispatching/custom-dispatching
restart: always
labels:
- "logging=true"
links:
- db:database
- triplestore:virtuoso
logging: *default-logging
################################################################################
# MU SEARCH - TODO USE THE CORRECT IMAGE ONCE INHERITANCE IS IN MU SEARCH
################################################################################
################################################################################
# DELTA CONSUMERS: END
################################################################################
################################################################################
# MU SEARCH - TODO USE THE CORRECT IMAGE ONCE INHERITANCE IS IN MU SEARCH
################################################################################
search:
image: nbittich/mu-search:wip-inheritance-alpha2 # Bump to fixed version when merged and release to the original repo
links:
@@ -418,7 +450,7 @@ services:
volumes:
- ./data/elasticsearch/:/usr/share/elasticsearch/data
environment:
- discovery.type=single-node
- discovery.type=single-node
restart: always
error-report-service: