google_cloud_credentials_file_path = args.google_cloud_credentials_file_path
pipeline_configuration_file_path = args.pipeline_configuration_file_path
avf_uuid_file_path = args.avf_uuid_file_path
log.info("Loading Pipeline Configuration File...")
with open(pipeline_configuration_file_path) as f:
pipeline_configuration = PipelineConfiguration.from_configuration_file(
f)
Logger.set_project_name(pipeline_configuration.pipeline_name)
log.debug(f"Pipeline name is {pipeline_configuration.pipeline_name}")
log.info("Downloading Rapid Pro access token...")
rapid_pro_token = google_cloud_utils.download_blob_to_string(
google_cloud_credentials_file_path, rapid_pro_token_url).strip()
rapid_pro = RapidProClient(rapid_pro_domain, rapid_pro_token)
log.info("Downloading Firestore UUID Table credentials...")
firestore_uuid_table_credentials = json.loads(
google_cloud_utils.download_blob_to_string(
google_cloud_credentials_file_path, pipeline_configuration.
phone_number_uuid_table.firebase_credentials_file_url))
phone_number_uuid_table = FirestoreUuidTable(
pipeline_configuration.phone_number_uuid_table.table_name,
firestore_uuid_table_credentials, "avf-phone-uuid-")
log.info("Initialised the Firestore UUID table")
log.info(f"Loading the uuids that are safe to send to")
with open(avf_uuid_file_path) as f:
safe_uuids = json.load(f)
def fetch_from_rapid_pro(user, google_cloud_credentials_file_path,
raw_data_dir, phone_number_uuid_table,
rapid_pro_source):
log.info("Fetching data from Rapid Pro...")
log.info("Downloading Rapid Pro access token...")
rapid_pro_token = google_cloud_utils.download_blob_to_string(
google_cloud_credentials_file_path,
rapid_pro_source.token_file_url).strip()
rapid_pro = RapidProClient(rapid_pro_source.domain, rapid_pro_token)
# Load the previous export of contacts if it exists, otherwise fetch all contacts from Rapid Pro.
raw_contacts_path = f"{raw_data_dir}/{rapid_pro_source.contacts_file_name}_raw.json"
contacts_log_path = f"{raw_data_dir}/{rapid_pro_source.contacts_file_name}_log.jsonl"
try:
log.info(f"Loading raw contacts from file '{raw_contacts_path}'...")
with open(raw_contacts_path) as raw_contacts_file:
raw_contacts = [
Contact.deserialize(contact_json)
for contact_json in json.load(raw_contacts_file)
]
log.info(f"Loaded {len(raw_contacts)} contacts")
except FileNotFoundError:
log.info(
f"File '{raw_contacts_path}' not found, will fetch all contacts from the Rapid Pro server"
)
with open(contacts_log_path, "a") as contacts_log_file:
raw_contacts = rapid_pro.get_raw_contacts(
raw_export_log_file=contacts_log_file)
# Download all the runs for each of the radio shows
for flow in rapid_pro_source.activation_flow_names + rapid_pro_source.survey_flow_names:
runs_log_path = f"{raw_data_dir}/{flow}_log.jsonl"
raw_runs_path = f"{raw_data_dir}/{flow}_raw.json"
traced_runs_output_path = f"{raw_data_dir}/{flow}.jsonl"
log.info(f"Exporting flow '{flow}' to '{traced_runs_output_path}'...")
flow_id = rapid_pro.get_flow_id(flow)
# Load the previous export of runs for this flow, and update them with the newest runs.
# If there is no previous export for this flow, fetch all the runs from Rapid Pro.
with open(runs_log_path, "a") as raw_runs_log_file:
try:
log.info(f"Loading raw runs from file '{raw_runs_path}'...")
with open(raw_runs_path) as raw_runs_file:
raw_runs = [
Run.deserialize(run_json)
for run_json in json.load(raw_runs_file)
]
log.info(f"Loaded {len(raw_runs)} runs")
raw_runs = rapid_pro.update_raw_runs_with_latest_modified(
flow_id,
raw_runs,
raw_export_log_file=raw_runs_log_file,
ignore_archives=True)
except FileNotFoundError:
log.info(
f"File '{raw_runs_path}' not found, will fetch all runs from the Rapid Pro server for flow '{flow}'"
)
raw_runs = rapid_pro.get_raw_runs_for_flow_id(
flow_id, raw_export_log_file=raw_runs_log_file)
# Fetch the latest contacts from Rapid Pro.
with open(contacts_log_path, "a") as raw_contacts_log_file:
raw_contacts = rapid_pro.update_raw_contacts_with_latest_modified(
raw_contacts, raw_export_log_file=raw_contacts_log_file)
# Convert the runs to TracedData.
traced_runs = rapid_pro.convert_runs_to_traced_data(
user, raw_runs, raw_contacts, phone_number_uuid_table,
rapid_pro_source.test_contact_uuids)
log.info(f"Saving {len(raw_runs)} raw runs to {raw_runs_path}...")
with open(raw_runs_path, "w") as raw_runs_file:
json.dump([run.serialize() for run in raw_runs], raw_runs_file)
log.info(f"Saved {len(raw_runs)} raw runs")
log.info(
f"Saving {len(traced_runs)} traced runs to {traced_runs_output_path}..."
)
IOUtils.ensure_dirs_exist_for_file(traced_runs_output_path)
with open(traced_runs_output_path, "w") as traced_runs_output_file:
TracedDataJsonIO.export_traced_data_iterable_to_jsonl(
traced_runs, traced_runs_output_file)
log.info(f"Saved {len(traced_runs)} traced runs")
log.info(
f"Saving {len(raw_contacts)} raw contacts to file '{raw_contacts_path}'..."
)
with open(raw_contacts_path, "w") as raw_contacts_file:
json.dump([contact.serialize() for contact in raw_contacts],
raw_contacts_file)
log.info(f"Saved {len(raw_contacts)} contacts")
if project.flow_definitions_upload_url_prefix is None:
log.info(
f"Not archiving flow definitions for project {project.project_name} because its "
f"'flow_definitions_upload_url_prefix' is unspecified.")
continue
log.info(
f"Archiving the latest flow definitions for project {project.project_name}..."
)
log.info(
"Downloading the Rapid Pro token file and initialising the Rapid Pro client..."
)
rapid_pro_token = google_cloud_utils.download_blob_to_string(
google_cloud_credentials_file_path,
project.rapid_pro_token_url).strip()
rapid_pro = RapidProClient(project.rapid_pro_domain, rapid_pro_token)
log.info("Downloading all the flow definitions for this instance...")
flow_ids = rapid_pro.get_all_flow_ids()
flow_definitions_request_timestamp = TimeUtils.utc_now_as_iso_string()
flow_definitions = rapid_pro.get_flow_definitions_for_flow_ids(
flow_ids)
log.info("Uploading the flow definitions to a cloud bucket...")
upload_url = f"{project.flow_definitions_upload_url_prefix}{flow_definitions_request_timestamp}.json"
flow_definitions_json = json.dumps(flow_definitions.serialize())
google_cloud_utils.upload_string_to_blob(
google_cloud_credentials_file_path, upload_url,
flow_definitions_json)
help="GS URLs of a text file containing the authorisation token for the Rapid Pro server")
parser.add_argument("output_file_path", metavar="output-file-path",
help="Output CSV file to write the phone numbers to")
args = parser.parse_args()
google_cloud_credentials_file_path = args.google_cloud_credentials_file_path
rapid_pro_domain = args.rapid_pro_domain
rapid_pro_token_file_url = args.rapid_pro_token_file_url
output_file_path = args.output_file_path
log.info("Downloading the Rapid Pro access token...")
rapid_pro_token = google_cloud_utils.download_blob_to_string(
google_cloud_credentials_file_path, rapid_pro_token_file_url).strip()
rapid_pro = RapidProClient(rapid_pro_domain, rapid_pro_token)
all_messages = rapid_pro.get_raw_messages()
inbound_messages = [msg for msg in all_messages if msg.direction == "in"]
inbound_phone_numbers = set()
for msg in inbound_messages:
if msg.urn.startswith("tel:"):
phone_number = msg.urn.split(":")[1]
inbound_phone_numbers.add(phone_number)
else:
log.warning(f"Skipped non-telephone URN type {msg.urn.split(':')[0]}")
log.warning(f"Exporting {len(inbound_phone_numbers)} inbound phone numbers to {output_file_path}...")
with open(output_file_path, "w") as f:
writer = csv.DictWriter(f, fieldnames=["URN:Tel", "Name"])
"GS URL to the organisation access token file for authenticating to the target instance"
)
args = parser.parse_args()
google_cloud_credentials_file_path = args.google_cloud_credentials_file_path
source_domain = args.source_domain
source_credentials_url = args.source_credentials_url
target_domain = args.target_domain
target_credentials_url = args.target_credentials_url
# Initialise the source/target instances
log.info("Downloading the source instance access token...")
source_token = google_cloud_utils.download_blob_to_string(
google_cloud_credentials_file_path, source_credentials_url).strip()
source_instance = RapidProClient(source_domain, source_token)
log.info("Downloading the target instance access token...")
target_token = google_cloud_utils.download_blob_to_string(
google_cloud_credentials_file_path, target_credentials_url).strip()
target_instance = RapidProClient(target_domain, target_token)
# For each contact field in the source instance, create a matching contact field in the target instance if it
# does not already exist
log.info("Copying contact fields...")
source_fields = source_instance.get_fields()
target_field_keys = {f.key for f in target_instance.get_fields()}
for field in source_fields:
if field.key not in target_field_keys:
target_instance.create_field(field.label)
log.info("Contact fields copied")
args = parser.parse_args()
google_cloud_credentials_file_path = args.google_cloud_credentials_file_path
force_update = args.force
instance_1_domain = args.instance_1_domain
instance_1_credentials_url = args.instance_1_credentials_url
instance_2_domain = args.instance_2_domain
instance_2_credentials_url = args.instance_2_credentials_url
# Initialise the two instances
log.info("Downloading the access token for instance 1...")
instance_1_token = google_cloud_utils.download_blob_to_string(
google_cloud_credentials_file_path,
instance_1_credentials_url).strip()
instance_1 = RapidProClient(instance_1_domain, instance_1_token)
log.info("Downloading the target instance access token...")
instance_2_token = google_cloud_utils.download_blob_to_string(
google_cloud_credentials_file_path,
instance_2_credentials_url).strip()
instance_2 = RapidProClient(instance_2_domain, instance_2_token)
# Synchronise the contact fields
log.info("Synchronising contact fields...")
instance_1_fields = instance_1.get_fields()
instance_2_fields = instance_2.get_fields()
for field in instance_1_fields:
if field.key not in {f.key for f in instance_2_fields}:
instance_2.create_field(field.label)
for field in instance_2_fields:
def fetch_from_rapid_pro(user, google_cloud_credentials_file_path, raw_data_dir, phone_number_uuid_table,
rapid_pro_source):
log.info("Fetching data from Rapid Pro...")
log.info("Downloading Rapid Pro access token...")
rapid_pro_token = google_cloud_utils.download_blob_to_string(
google_cloud_credentials_file_path, rapid_pro_source.token_file_url).strip()
rapid_pro = RapidProClient(rapid_pro_source.domain, rapid_pro_token)
# Load the previous export of contacts if it exists, otherwise fetch all contacts from Rapid Pro.
raw_contacts_path = f"{raw_data_dir}/{rapid_pro_source.contacts_file_name}_raw.json"
contacts_log_path = f"{raw_data_dir}/{rapid_pro_source.contacts_file_name}_log.jsonl"
try:
log.info(f"Loading raw contacts from file '{raw_contacts_path}'...")
with open(raw_contacts_path) as raw_contacts_file:
raw_contacts = [Contact.deserialize(contact_json) for contact_json in json.load(raw_contacts_file)]
log.info(f"Loaded {len(raw_contacts)} contacts")
except FileNotFoundError:
log.info(f"File '{raw_contacts_path}' not found, will fetch all contacts from the Rapid Pro server")
with open(contacts_log_path, "a") as contacts_log_file:
raw_contacts = rapid_pro.get_raw_contacts(raw_export_log_file=contacts_log_file)
# Download all the runs for each of the radio shows
for flow in rapid_pro_source.activation_flow_names + rapid_pro_source.survey_flow_names:
runs_log_path = f"{raw_data_dir}/{flow}_log.jsonl"
raw_runs_path = f"{raw_data_dir}/{flow}_raw.json"
traced_runs_output_path = f"{raw_data_dir}/{flow}.jsonl"
log.info(f"Exporting flow '{flow}' to '{traced_runs_output_path}'...")
flow_id = rapid_pro.get_flow_id(flow)
# Load the previous export of runs for this flow, and update them with the newest runs.
# If there is no previous export for this flow, fetch all the runs from Rapid Pro.
with open(runs_log_path, "a") as raw_runs_log_file:
try:
log.info(f"Loading raw runs from file '{raw_runs_path}'...")
with open(raw_runs_path) as raw_runs_file:
raw_runs = [Run.deserialize(run_json) for run_json in json.load(raw_runs_file)]
log.info(f"Loaded {len(raw_runs)} runs")
raw_runs = rapid_pro.update_raw_runs_with_latest_modified(
flow_id, raw_runs, raw_export_log_file=raw_runs_log_file, ignore_archives=True)
except FileNotFoundError:
log.info(f"File '{raw_runs_path}' not found, will fetch all runs from the Rapid Pro server for flow '{flow}'")
raw_runs = rapid_pro.get_raw_runs_for_flow_id(flow_id, raw_export_log_file=raw_runs_log_file)
# Fetch the latest contacts from Rapid Pro.
with open(contacts_log_path, "a") as raw_contacts_log_file:
raw_contacts = rapid_pro.update_raw_contacts_with_latest_modified(raw_contacts,
raw_export_log_file=raw_contacts_log_file)
# Convert the runs to TracedData.
traced_runs = rapid_pro.convert_runs_to_traced_data(
user, raw_runs, raw_contacts, phone_number_uuid_table, rapid_pro_source.test_contact_uuids)
if flow in rapid_pro_source.activation_flow_names:
# Append the Rapid Pro source name to each run.
# Only do this for activation flows because this is the only place where this is interesting.
# Also, demogs may come from either instance, which causes problems downstream.
for td in traced_runs:
td.append_data({
"source_raw": rapid_pro_source.source_name,
"source_coded": CleaningUtils.make_label_from_cleaner_code(
CodeSchemes.SOURCE, CodeSchemes.SOURCE.get_code_with_match_value(rapid_pro_source.source_name),
Metadata.get_call_location()
).to_dict()
}, Metadata(user, Metadata.get_call_location(), TimeUtils.utc_now_as_iso_string()))
log.info(f"Saving {len(raw_runs)} raw runs to {raw_runs_path}...")
with open(raw_runs_path, "w") as raw_runs_file:
json.dump([run.serialize() for run in raw_runs], raw_runs_file)
log.info(f"Saved {len(raw_runs)} raw runs")
log.info(f"Saving {len(traced_runs)} traced runs to {traced_runs_output_path}...")
IOUtils.ensure_dirs_exist_for_file(traced_runs_output_path)
with open(traced_runs_output_path, "w") as traced_runs_output_file:
TracedDataJsonIO.export_traced_data_iterable_to_jsonl(traced_runs, traced_runs_output_file)
log.info(f"Saved {len(traced_runs)} traced runs")
log.info(f"Saving {len(raw_contacts)} raw contacts to file '{raw_contacts_path}'...")
with open(raw_contacts_path, "w") as raw_contacts_file:
json.dump([contact.serialize() for contact in raw_contacts], raw_contacts_file)
log.info(f"Saved {len(raw_contacts)} contacts")
google_cloud_credentials_file_path = args.google_cloud_credentials_file_path
workspace_1_domain = args.workspace_1_domain
workspace_1_credentials_url = args.workspace_1_credentials_url
workspace_2_domain = args.workspace_2_domain
workspace_2_credentials_url = args.workspace_2_credentials_url
raw_data_log_directory = args.raw_data_log_directory
if dry_run:
log.info("Performing a dry-run")
# Initialise the two Rapid Pro clients
log.info("Downloading the access token for workspace 1...")
workspace_1_token = google_cloud_utils.download_blob_to_string(
google_cloud_credentials_file_path,
workspace_1_credentials_url).strip()
workspace_1 = RapidProClient(workspace_1_domain, workspace_1_token)
workspace_1_name = workspace_1.get_workspace_name()
log.info(f"Done. workspace 1 is called {workspace_1_name}")
log.info("Downloading the access token for workspace 2...")
workspace_2_token = google_cloud_utils.download_blob_to_string(
google_cloud_credentials_file_path,
workspace_2_credentials_url).strip()
workspace_2 = RapidProClient(workspace_2_domain, workspace_2_token)
workspace_2_name = workspace_2.get_workspace_name()
log.info(f"Done. workspace 2 is called {workspace_2_name}")
# Download the data from Rapid Pro
log.info("Downloading contact fields...")
log.info(f"Downloading all fields from {workspace_1_name}...")
workspace_1_fields = workspace_1.get_fields()
google_cloud_credentials_file_path, pipeline_configuration.rapid_pro_token_file_url).strip()
log.info("Downloading Firestore UUID Table credentials...")
firestore_uuid_table_credentials = json.loads(google_cloud_utils.download_blob_to_string(
google_cloud_credentials_file_path,
pipeline_configuration.phone_number_uuid_table.firebase_credentials_file_url
))
phone_number_uuid_table = FirestoreUuidTable(
pipeline_configuration.phone_number_uuid_table.table_name,
firestore_uuid_table_credentials,
"avf-phone-uuid-"
)
log.info("Initialised the Firestore UUID table")
rapid_pro = RapidProClient(pipeline_configuration.rapid_pro_domain, rapid_pro_token)
# Load the previous export of contacts if it exists, otherwise fetch all contacts from Rapid Pro.
raw_contacts_path = f"{raw_data_dir}/contacts_raw.json"
contacts_log_path = f"{raw_data_dir}/contacts_log.jsonl"
try:
log.info(f"Loading raw contacts from file '{raw_contacts_path}'...")
with open(raw_contacts_path) as raw_contacts_file:
raw_contacts = [Contact.deserialize(contact_json) for contact_json in json.load(raw_contacts_file)]
log.info(f"Loaded {len(raw_contacts)} contacts")
except FileNotFoundError:
log.info(f"File '{raw_contacts_path}' not found, will fetch all contacts from the Rapid Pro server")
with open(contacts_log_path, "a") as contacts_log_file:
raw_contacts = rapid_pro.get_raw_contacts(raw_export_log_file=contacts_log_file)
# Download all the runs for each of the radio shows