Merge branch 'main' into feature/ecmk-to-ara

This commit is contained in:
Daniel Roth 2026-04-01 16:26:36 +00:00
commit f3ebe122f8
11 changed files with 112 additions and 15 deletions

View file

@ -80,6 +80,8 @@ on:
required: false
TF_VAR_pashub_password:
required: false
TF_VAR_hubspot_api_key:
required: false
jobs:
deploy:
runs-on: ubuntu-latest
@ -146,6 +148,7 @@ jobs:
TF_VAR_social_housing_wave_3_sharepoint_id: ${{ secrets.TF_VAR_social_housing_wave_3_sharepoint_id }}
TF_VAR_pashub_email: ${{ secrets.TF_VAR_pashub_email }}
TF_VAR_pashub_password: ${{ secrets.TF_VAR_pashub_password }}
TF_VAR_hubspot_api_key: ${{ secrets.TF_VAR_hubspot_api_key }}
run: |
ECR_REPO_URL_VAR=""
if [[ -n "${{ inputs.ecr_repo }}" ]]; then
@ -191,6 +194,7 @@ jobs:
TF_VAR_social_housing_wave_3_sharepoint_id: ${{ secrets.TF_VAR_social_housing_wave_3_sharepoint_id }}
TF_VAR_pashub_email: ${{ secrets.TF_VAR_pashub_email }}
TF_VAR_pashub_password: ${{ secrets.TF_VAR_pashub_password }}
TF_VAR_hubspot_api_key: ${{ secrets.TF_VAR_hubspot_api_key }}
run: |
EXTRA_VARS=""
if [[ -n "${{ inputs.ecr_repo }}" ]]; then

View file

@ -518,6 +518,7 @@ jobs:
TF_VAR_db_host: ${{ secrets.DEV_DB_HOST }}
TF_VAR_db_name: ${{ secrets.DEV_DB_NAME }}
TF_VAR_db_port: ${{ secrets.DEV_DB_PORT }}
TF_VAR_hubspot_api_key: ${{ secrets.HUBSPOT_API_KEY }}
AWS_ACCESS_KEY_ID: ${{ secrets.DEV_AWS_ACCESS_KEY_ID }}
AWS_SECRET_ACCESS_KEY: ${{ secrets.DEV_AWS_SECRET_ACCESS_KEY }}
AWS_REGION: ${{ secrets.DEV_AWS_REGION }}

View file

@ -63,6 +63,8 @@ class HubspotDealData(SQLModel, table=True):
surveyor: Optional[str] = Field(default=None)
confirmed_survey_date: Optional[datetime] = Field(default=None)
confirmed_survey_time: Optional[str] = Field(default=None)
surveyed_date: Optional[datetime] = Field(default=None)
design_type: Optional[str] = Field(default=None)
created_at: datetime = Field(
sa_column=Column(

View file

@ -5,7 +5,8 @@ from typing import Callable, Any
from uuid import UUID
import json
from backend.app.db.functions.tasks.Tasks import SubTaskInterface
from backend.app.db.functions.tasks.Tasks import SubTaskInterface, TasksInterface
from utils.logger import setup_logger
def subtask_handler():
@ -93,3 +94,76 @@ def subtask_handler():
return wrapper
return decorator
def task_handler():
"""
Decorator that wraps a Lambda handler and automatically:
- Parses body from the first SQS record (or uses the event dict directly)
- Creates a fresh Task + SubTask in the database
- Marks the subtask as in progress
- Executes the handler, passing the parsed body
- Marks complete on success, failed on exception (and re-raises)
"""
def decorator(func: Callable[..., Any]):
task_source = f"{func.__module__}.{func.__qualname__}"
@wraps(func)
def wrapper(event: dict[str, Any], context: Any, *args, **kwargs):
logger = setup_logger()
# Parse body: Records-style SQS or plain dict event
if "Records" in event:
raw_body = event["Records"][0].get("body", {})
if isinstance(raw_body, str):
try:
body = json.loads(raw_body)
except Exception:
body = {}
else:
body = raw_body or {}
else:
body = event
# Create fresh task + subtask
logger.info("Creating task for source: %s", task_source)
task_id, subtask_id = TasksInterface.create_task(
task_source=task_source,
inputs=body,
)
logger.info("Created task_id=%s subtask_id=%s", task_id, subtask_id)
interface = SubTaskInterface()
interface.update_subtask_status(
subtask_id=subtask_id,
status="in progress",
)
try:
result = func(body, context, *args, **kwargs)
interface.update_subtask_status(
subtask_id=subtask_id,
status="complete",
outputs={"result": result} if result else None,
)
logger.info("Task %s completed successfully", task_id)
return result
except Exception as e:
logger.exception("Task %s failed: %s", task_id, e)
interface.update_subtask_status(
subtask_id=subtask_id,
status="failed",
outputs={"error": str(e)},
)
raise
return wrapper
return decorator

View file

@ -231,6 +231,8 @@ class HubspotClient:
"surveyor",
"confirmed_survey_date",
"confirmed_survey_time",
"surveyed_date",
"design_type",
],
)

View file

@ -257,6 +257,14 @@ class HubspotDataToDb:
deal_in_db.confirmed_survey_time == hs_deal.get("confirmed_survey_time"),
"confirmed_survey_time mismatch",
),
soft_assert(
deal_in_db.surveyed_date == self._parse_hs_date(hs_deal.get("surveyed_date")),
"surveyed_date mismatch",
),
soft_assert(
deal_in_db.design_type == hs_deal.get("design_type"),
"design_type mismatch",
),
]
# If discrepancies found, update from HubSpot
@ -380,6 +388,8 @@ class HubspotDataToDb:
"surveyor": deal_data.get("surveyor"),
"confirmed_survey_date": self._parse_hs_date(deal_data.get("confirmed_survey_date")),
"confirmed_survey_time": deal_data.get("confirmed_survey_time"),
"surveyed_date": self._parse_hs_date(deal_data.get("surveyed_date")),
"design_type": deal_data.get("design_type"),
}.items():
setattr(existing, attr, value or getattr(existing, attr))
@ -462,6 +472,8 @@ class HubspotDataToDb:
surveyor=deal_data.get("surveyor"),
confirmed_survey_date=self._parse_hs_date(deal_data.get("confirmed_survey_date")),
confirmed_survey_time=deal_data.get("confirmed_survey_time"),
surveyed_date=self._parse_hs_date(deal_data.get("surveyed_date")),
design_type=deal_data.get("design_type"),
)
# Handle upload at insert time

View file

@ -1,6 +1,7 @@
from etl.hubspot.hubspotClient import HubspotClient, Companies, Pipeline
from etl.hubspot.scripts.scraper.main import handler
from tqdm import tqdm
import json
PIPELINE_ID = Pipeline.OPERATIONS_SOCIAL_HOUSING.value
@ -29,7 +30,7 @@ def bulk_load(companies: list[Companies] | None = None) -> None:
continue
deal_bar.set_postfix({"status": "uploading", "deal": deal_id})
handler({"hubspot_deal_id": deal_id}, context=None)
handler({"Records": [{"body": json.dumps({"hubspot_deal_id": deal_id})}]}, context=None)
processed += 1
deal_bar.set_postfix({"status": "done", "deal": deal_id})

View file

@ -9,16 +9,13 @@
from etl.hubspot.hubspotClient import HubspotClient
from etl.hubspot.hubspotDataTodB import HubspotDataToDb
from backend.utils.subtasks import task_handler
from typing import Any
import json
# @subtask_handler() TODO: Do this without subtask_handler but task_handler() that creates task_id and subtask_id
def handler(body: dict[str, Any], context: Any, local: bool = False) -> None:
if local is True:
body = {
"hubspot_deal_id": "254427203793",
}
@task_handler()
def handler(body: dict[str, Any], context: Any) -> None:
hubspot_deal_id = body.get("hubspot_deal_id", "")
if hubspot_deal_id == "":
@ -36,5 +33,3 @@ def handler(body: dict[str, Any], context: Any, local: bool = False) -> None:
else:
deal, company, listing = hubspot.get_deal_info_for_db(hubspot_deal_id)
dbloader.upsert_deal(deal, company, listing, hubspot)
print("Finsihed running")

View file

@ -38,6 +38,7 @@ module "hubspot_deal_etl" {
DB_HOST = var.db_host
DB_NAME = var.db_name
DB_PORT = var.db_port
HUBSPOT_API_KEY = var.hubspot_api_key
}
}

View file

@ -41,6 +41,11 @@ variable "db_host" {
type = string
}
variable "hubspot_api_key" {
type = string
}
variable "db_name" {
type = string
}

View file

@ -26,13 +26,13 @@ from backend.app.db.functions.materials_functions import get_materials
from collections import defaultdict
from sqlalchemy import func
PORTFOLIO_ID = 640
SCENARIOS = [1154]
PORTFOLIO_ID = 656
SCENARIOS = [1177]
scenario_names = {
1154: "EPC - 10k Budget",
1177: "EPC C; Proposed Measures",
}
project_name = "First Charterhouse Investments"
project_name = "Walsall Council | WH:LG"
def get_data(portfolio_id, scenario_ids):