jobhunt-platform/packages/matching/tests/conftest.py

"""Shared fixtures for matching tests.

Provides agency-repost fixture triples and a legit-different-jobs-same-agency
negative case.
"""

from __future__ import annotations

import pytest


# ---------------------------------------------------------------------------
# Agency-repost fixture triples.
# Three realistic scenarios where agencies repost the same job.
# Each triple is a list of 3 posting dicts that should all cluster together.
# ---------------------------------------------------------------------------

# Triple 1: Same role, two agencies + direct employer posting.
# All three have the same title and nearly identical description, but
# different employer names (the two agencies vs the actual company).
TRIPLE_1_AGENCY_REPOST = [
    {
        "id": "t1-a",
        "employer": "TechCorp AB",
        "title": "Senior Python Developer",
        "description": (
            "We are looking for a Senior Python Developer to join our backend team. "
            "You will work with Fast API, PostgreSQL, and Docker in a cloud-native "
            "environment. 5+ years of Python experience required. "
            "Experience with AWS and Kubernetes is a plus."
        ),
    },
    {
        "id": "t1-b",
        "employer": "Nordic IT Consulting AB",
        "title": "Senior Python Developer",
        "description": (
            "We are looking for a Senior Python Developer to join our backend team. "
            "You will work with Fast API, PostgreSQL, and Docker in a cloud-native "
            "environment. 5+ years of Python experience required. "
            "Experience with AWS and Kubernetes is a plus."
        ),
    },
    {
        "id": "t1-c",
        "employer": "Acme Recruitment Group",
        "title": "Senior Python Developer",
        "description": (
            "We are looking for a Senior Python Developer to join our backend team. "
            "You will work with Fast API, PostgreSQL, and Docker in a cloud-native "
            "environment. 5+ years of Python experience required. "
            "Experience with AWS and Kubernetes is a plus."
        ),
    },
]

# Triple 2: Same role reposted by same agency with minor wording variations.
TRIPLE_2_SAME_AGENCY_REPOST = [
    {
        "id": "t2-a",
        "employer": "Stockholm Tech Staffing AB",
        "title": "Fullstack Engineer",
        "description": (
            "Fullstack Engineer wanted for a fintech startup in Stockholm. "
            "Tech stack: React, TypeScript, Node.js, PostgreSQL. "
            "You will build customer-facing features and internal tools. "
            "Must have experience with CI/CD pipelines."
        ),
    },
    {
        "id": "t2-b",
        "employer": "Stockholm Tech Staffing AB",
        "title": "Fullstack Engineer",
        "description": (
            "Fullstack Engineer wanted for a fintech startup in Stockholm. "
            "Tech stack: React, TypeScript, Node.js, PostgreSQL. "
            "You will build customer-facing features and internal tools. "
            "Must have experience with CI/CD pipelines."
        ),
    },
    {
        "id": "t2-c",
        "employer": "Stockholm Tech Staffing",
        "title": "Fullstack Engineer",
        "description": (
            "Fullstack Engineer wanted for a fintech startup in Stockholm. "
            "Tech stack: React, TypeScript, Node.js, PostgreSQL. "
            "You will build customer-facing features and internal tools. "
            "Must have experience with CI/CD pipelines."
        ),
    },
]

# Triple 3: Same role, slightly different title but same description body.
# Different employers (agencies), high title + desc similarity.
TRIPLE_3_CROSS_AGENCY = [
    {
        "id": "t3-a",
        "employer": "Data Recruiting Solutions",
        "title": "Data Engineer",
        "description": (
            "We seek a Data Engineer to build and maintain ETL pipelines using "
            "Python, Airflow, dbt, and Snowflake. You will design data models, "
            "optimize queries, and ensure data quality. Experience with "
            "distributed systems and Spark is required."
        ),
    },
    {
        "id": "t3-b",
        "employer": "Cloud Talent Partners",
        "title": "Data Engineer",
        "description": (
            "We seek a Data Engineer to build and maintain ETL pipelines using "
            "Python, Airflow, dbt, and Snowflake. You will design data models, "
            "optimize queries, and ensure data quality. Experience with "
            "distributed systems and Spark is required."
        ),
    },
    {
        "id": "t3-c",
        "employer": "Analytics Staffing Ltd",
        "title": "Data Engineer",
        "description": (
            "We seek a Data Engineer to build and maintain ETL pipelines using "
            "Python, Airflow, dbt, and Snowflake. You will design data models, "
            "optimize queries, and ensure data quality. Experience with "
            "distributed systems and Spark is required."
        ),
    },
]

# ---------------------------------------------------------------------------
# NEGATIVE case: legit different jobs at same agency -- must NOT cluster.
# Same agency employer but different titles and different descriptions.
# ---------------------------------------------------------------------------

NEGATIVE_DIFFERENT_JOBS_SAME_AGENCY = [
    {
        "id": "neg-a",
        "employer": "Nordic IT Consulting AB",
        "title": "Frontend Developer",
        "description": (
            "We are looking for a Frontend Developer with expertise in React "
            "and TypeScript. You will build responsive web applications and "
            "work closely with our design team. Experience with CSS-in-JS and "
            "accessibility standards is required."
        ),
    },
    {
        "id": "neg-b",
        "employer": "Nordic IT Consulting AB",
        "title": "DevOps Engineer",
        "description": (
            "We need a DevOps Engineer to manage our Kubernetes clusters and "
            "CI/CD pipelines. You will work with Terraform, ArgoCD, and "
            "Prometheus monitoring. Strong Linux and networking background "
            "is required. AWS certification is a plus."
        ),
    },
]


@pytest.fixture
def triple1():
    """Agency repost triple 1: same role, two agencies + employer."""
    return [dict(p) for p in TRIPLE_1_AGENCY_REPOST]


@pytest.fixture
def triple2():
    """Agency repost triple 2: same agency reposts same job."""
    return [dict(p) for p in TRIPLE_2_SAME_AGENCY_REPOST]


@pytest.fixture
def triple3():
    """Agency repost triple 3: cross-agency same role same description."""
    return [dict(p) for p in TRIPLE_3_CROSS_AGENCY]


@pytest.fixture
def negative_same_agency():
    """Negative case: different jobs at same agency, must NOT cluster."""
    return [dict(p) for p in NEGATIVE_DIFFERENT_JOBS_SAME_AGENCY]