matchmaking-v2/app/engine/board_adapters/adapters.py

"""
Per-board query builders — `ScoutPrefs` (dict) → each Apify actor's input.
See `docs/ENGINE_DESIGN.md` §1.2. Returns the `input` dict you POST to the actor's
`run-sync-get-dataset-items` endpoint.

System knobs (budget / freshness) are arguments with sane defaults, not user inputs.
"""
from __future__ import annotations
from typing import Any
from urllib.parse import urlencode

from . import coerce as C

Prefs = dict[str, Any]


# ── Naukri (India workhorse — richest structured filters) ────────────────────
def build_naukri_input(prefs: Prefs, *, max_jobs: int = 80, freshness: str = "7", recall: bool = False) -> dict:
    # recall=True (retrieve stage): keep keyword + city + work-mode only; drop the
    # narrowing filters (experience/department/industry/salary/stage) — those become
    # ENGINE ranking later, not hard board cuts. Wider freshness for recall.
    if recall:
        freshness = "30"
    locs = C.parsed_locations(prefs)
    cities: list[int] = []
    for lp in locs:
        if lp["city"]:
            cities += C.CITY_NAUKRI.get(lp["city"], [])  # unmapped city → dropped (kept in keyword)

    out: dict[str, Any] = {
        "keyword": C.title_of(prefs) or C.build_keyword(prefs),
        "maxJobs": max_jobs,        # REQUIRED — the budget
        "freshness": freshness,     # liveness gate
        "sortBy": "date",
        "fetchDetails": True,       # → apply redirect / full details
    }
    if cities:
        out["cities"] = [str(c) for c in sorted(set(cities))]   # Naukri select codes are STRINGS

    wm = [C.WORKMODE_NAUKRI[w] for w in (prefs.get("workMode") or []) if w in C.WORKMODE_NAUKRI]
    if C.is_remote(prefs) and "remote" not in wm:
        wm.append("remote")
    if wm:
        out["workMode"] = wm

    if recall:
        return out  # retrieve stage stops here — keyword + cities + work-mode only

    yrs = C.years_of(prefs)
    if yrs is not None:
        out["experience"] = str(yrs)  # numeric-string enum "0".."30"

    depts = [C.ROLE_NAUKRI_DEPT[r] for r in (prefs.get("role") or []) if r in C.ROLE_NAUKRI_DEPT]
    if depts:
        out["department"] = [str(d) for d in sorted(set(depts))]   # codes → strings

    inds = [C.INDUSTRY_NAUKRI[i] for i in (prefs.get("industry") or []) if i in C.INDUSTRY_NAUKRI]
    if inds:
        out["industry"] = [str(i) for i in sorted(set(inds))]      # codes → strings

    if prefs.get("targetComp") in C.COMP_NAUKRI_SALARY:
        out["salaryRange"] = [C.COMP_NAUKRI_SALARY[prefs["targetComp"]]]

    if prefs.get("companyStage") in C.COMPANY_TYPE_NAUKRI:
        out["companyType"] = [C.COMPANY_TYPE_NAUKRI[prefs["companyStage"]]]

    return out


# ── Naukri (blackfalcondata feed — city-precise, real offsite applyRedirectUrl) ──
def build_naukri_feed_input(prefs: Prefs, *, max_jobs: int = 50, fetch_details: bool = True) -> dict:
    # City-filtered at the board (hyper-relevant + cheap). fetch_details=True surfaces the
    # offsite `applyRedirectUrl`; skipReposts dedups WITHIN a run. Narrowing (dept/industry/exp)
    # stays off here — that's engine ranking later.
    # NOTE: no `incremental`/`stateKey` — that put opaque, exhausting, cross-account dedup state on
    # Apify. Cross-deck dedup is the PER-USER seen-net in our DB. (The feed actor has no page/offset.)
    city = next((lp["city"] for lp in C.parsed_locations(prefs) if lp["city"]), "")
    return {
        # Targeted keyword (seniority + industry + a top skill) → fetch RIGHT-level/industry/skill jobs,
        # not bare-title breadth. Text-targeting degrades gracefully (never zeroes); the pool gives breadth.
        "keyword": C.build_keyword(prefs, seniority=True, industry=True, skills=True),
        "location": city,                # precise city, e.g. "New Delhi"
        "maxResults": max_jobs,
        "fetchDetails": fetch_details,
        "skipReposts": True,
        "sortBy": "date",
    }


# Legacy India job boards (Foundit/Monster, TimesJobs) use OLD city names — they return 0 for the
# modern "New Delhi"/"Bengaluru"/"Gurugram". Map to their canonical names. (Verified live: TimesJobs
# returns 0 for "New Delhi", 15 for "Delhi".)
_LEGACY_IN_CITY = {
    "new delhi": "Delhi", "delhi ncr": "Delhi", "bengaluru": "Bangalore",
    "gurugram": "Gurgaon", "mumbai": "Mumbai", "pune": "Pune", "hyderabad": "Hyderabad",
    "chennai": "Chennai", "kolkata": "Kolkata", "noida": "Noida",
}
_FOUNDIT_CITY = _LEGACY_IN_CITY   # back-compat alias


def build_foundit_input(prefs: Prefs, *, results_wanted: int = 50) -> dict:
    city = next((lp["city"] for lp in C.parsed_locations(prefs) if lp["city"]), "")
    city = _FOUNDIT_CITY.get(city.lower(), city)  # alias to Foundit's canonical name
    return {
        "keyword": C.build_keyword(prefs, seniority=True, industry=True, skills=True),  # targeted
        "location": city,
        "results_wanted": results_wanted,
    }


# ── LinkedIn (takes the band, not years; ₹ comp incompatible) ────────────────
def build_linkedin_input(prefs: Prefs, *, max_items: int = 80, posted: str = "week",
                         recall: bool = False, page: int = 1) -> dict:
    # recall=True (retrieve stage): title + COUNTRY-level location only — drop the narrowing
    # filters (easyApply / workplaceType / experienceLevel / industryIds / freshness), which
    # become ENGINE ranking later. City-level location + a wrong industryId zero the actor out.
    # jobTitles is a TITLE field — prepend the seniority band (real titles, e.g. "Senior Sales Manager")
    # to target right-level roles. Industry stays OUT of the title field (it's not part of a job title).
    _title = C.title_of(prefs)
    if C.seniority_band(prefs) in ("Senior", "Lead") and _title:
        _title = f"{C.seniority_band(prefs)} {_title}"
    out: dict[str, Any] = {
        "jobTitles": [_title],
        "maxItems": max_items,
        "sortBy": "date",
        "page": page,                    # Start Page Number — advance per re-run for NEW jobs
    }

    cities: list[str] = []          # bare city names ("New Delhi") — harvestapi's location format
    cities_q: list[str] = []        # city, country ("New Delhi, India") — used outside recall
    countries: list[str] = []
    for lp in C.parsed_locations(prefs):
        if lp["country"] and lp["country"] not in countries:
            countries.append(lp["country"])
        if lp["city"]:
            cities.append(lp["city"])
            cities_q.append(f"{lp['city']}, {lp['country']}" if lp["country"] else lp["city"])

    if recall:
        # City-level for precision (engine ranks finer later). Fall back to country if no city.
        out["locations"] = cities or countries
        return out

    out["postedLimit"] = posted              # freshness
    out["easyApply"] = False                 # favour offsite (auto-applyable) over login-gated easy-apply
    if cities_q or countries:
        out["locations"] = cities_q or countries
    # TODO: geoIds = [lookup(loc)] is more reliable than free-text locations.

    wm = [C.WORKMODE_LINKEDIN[w] for w in (prefs.get("workMode") or []) if w in C.WORKMODE_LINKEDIN]
    if C.is_remote(prefs) and "remote" not in wm:
        wm.append("remote")
    if wm:
        out["workplaceType"] = wm

    band = C.seniority_band(prefs)
    if band in C.SENIORITY_LINKEDIN:
        out["experienceLevel"] = [C.SENIORITY_LINKEDIN[band]]

    ind_ids = [C.INDUSTRY_LINKEDIN_ID[i] for i in (prefs.get("industry") or []) if i in C.INDUSTRY_LINKEDIN_ID]
    if ind_ids:
        out["industryIds"] = ind_ids  # TODO verify IDs; unmapped industries already fall to keyword

    return out


# ── Indeed (blunt: what + where + country only; everything else folds in) ────
def build_indeed_input(prefs: Prefs, *, max_items: int = 80) -> dict:
    # valig~indeed-jobs-scraper: title + location + country(lowercase ISO2) + limit. ~7s/run (vs misceres 52s).
    loc = next((l for l in C.parsed_locations(prefs) if l["city"] or l["country"]), {})
    country_name = loc.get("country") or "India"
    return {
        # Indeed has no work-mode/seniority/industry params → fold them into the title query.
        "title": C.build_keyword(prefs, seniority=True, industry=True),
        "location": loc.get("city") or "",
        "country": C.COUNTRY_ISO2.get(country_name, "IN").lower(),   # valig wants lowercase ("in")
        "limit": max_items,
    }


def build_indeed_searches(prefs: Prefs, *, max_items: int = 80) -> list[dict]:
    """Fan-out: Indeed `position`/`location` are single strings, so multi title×city
    becomes N runs to merge+dedup downstream."""
    titles = (prefs.get("targetTitles") or [])[:3] or [C.title_of(prefs)]
    cities = [l["city"] for l in C.parsed_locations(prefs) if l["city"]] or [None]
    base = build_indeed_input(prefs, max_items=max_items)
    runs = []
    for t in titles:
        for city in cities:
            r = dict(base)
            r["position"] = " ".join(x for x in [t, *(["remote"] if C.is_remote(prefs) else [])] if x)
            if city:
                r["location"] = city
            runs.append(r)
    return runs


# ── Direct-ATS (curated-company lane — `companies` is passed in, NOT from prefs) ──
def build_ats_input(prefs: Prefs, *, companies: list[dict], recent_days: int = 30,
                    max_per_company: int = 50, output_profile: str = "compact",
                    recall: bool = False) -> dict:
    loc = next((l for l in C.parsed_locations(prefs) if l["city"]), {})
    inds = [i for i in (prefs.get("industry") or []) if i and i != "Any"]
    out: dict[str, Any] = {
        "companies": companies,                # curated [{company}] — the lane's identity
        "titleKeyword": C.title_of(prefs),     # filters within those companies (role relevance)
        "remoteOnly": C.is_remote(prefs),
        "keywords": inds,                      # loose industry fold
        "recentWindowDays": recent_days,
        "maxJobsPerCompany": max_per_company,
        "outputProfile": output_profile,       # "compact" = cheaper (enough for display); "full" adds descriptions
    }
    # recall=True: skip the city filter — these curated companies are global/remote, so a
    # city lock ("Bengaluru") empties the deck. Location becomes engine ranking later.
    if not recall:
        out["locationKeyword"] = loc.get("city", "")
    return out


# ── WorkIndia (India blue/grey-collar — the non-tech workhorse: sales, BPO, retail, field, ops) ──
def build_linkedin_cc_input(prefs: Prefs, *, count: int = 30) -> dict:
    # curious_coder~linkedin-jobs-scraper takes LinkedIn SEARCH URLs (structured industry+jobFunction+
    # applicants). NO pagination — the actor only honors start=0 (start>0 returns empty). Every fetch
    # pulls the freshest page-1 by date; the per-user seen-net dedups, and daily board refresh feeds new jobs.
    kw = C.build_keyword(prefs, seniority=True, industry=True)   # targeted search string
    loc = next((f"{lp['city']}, {lp['country']}" if lp["country"] else lp["city"]
                for lp in C.parsed_locations(prefs) if lp["city"]), None) \
        or next((lp["country"] for lp in C.parsed_locations(prefs) if lp["country"]), "India")
    q = urlencode({"keywords": kw, "location": loc, "sortBy": "DD"})  # DD = newest first
    return {"urls": [f"https://www.linkedin.com/jobs/search/?{q}"],
            "count": max(10, count), "scrapeCompany": False}   # count min 10 (actor constraint)


def build_timesjobs_input(prefs: Prefs, *, results_wanted: int = 35) -> dict:
    # shahidirfan/Timesjobs-Scraper — FULL signal (skills+salary+experience+offsite external_job_url).
    # keyword + city + an experience BAND ("5-10") for right-level targeting. Clean keyword input, no page.
    city = next((lp["city"] for lp in C.parsed_locations(prefs) if lp["city"]), "")
    city = _LEGACY_IN_CITY.get(city.lower(), city)   # TimesJobs needs "Delhi" not "New Delhi" (verified)
    out: dict[str, Any] = {
        "keyword": C.build_keyword(prefs, seniority=True, industry=True, skills=True),
        "results_wanted": results_wanted,
    }
    if city:
        out["location"] = city
    yrs = C.years_of(prefs)
    if yrs is not None:
        out["experience"] = f"{max(0, yrs - 2)}-{yrs + 3}"   # a band around the candidate's years
    return out


def build_workindia_input(prefs: Prefs, *, results_wanted: int = 20) -> dict:
    # keyword + city; includeDetails=True pulls the real skills + full description (verified live Phase 0).
    # No page param → per-user seen-net dedups. City is a lowercased name slug ("mumbai", "pune").
    city = next((lp["city"] for lp in C.parsed_locations(prefs) if lp["city"]), "")
    out: dict[str, Any] = {
        "keyword": C.title_of(prefs) or C.build_keyword(prefs),
        "results_wanted": results_wanted,
        "includeDetails": True,
    }
    if city:
        out["city"] = city.lower()
    return out


# ── Wellfound / AngelList (startup roles — equity + skills; remote-friendly for India) ──
def build_wellfound_input(prefs: Prefs, *, max_results: int = 15) -> dict:
    # query=title; city → location slug (lowercase-hyphen); remote honored. enrichDetail=True is
    # REQUIRED — it pulls skills[] + the full description the curator scores on (the core fields
    # alone are thin). No page param → dedup via the per-user seen-net (like Naukri/Foundit).
    city = next((lp["city"] for lp in C.parsed_locations(prefs) if lp["city"]), "")
    out: dict[str, Any] = {
        "query": C.title_of(prefs) or C.build_keyword(prefs),
        "maxResults": max_results,
        "enrichDetail": True,                 # → skills + description (the curator's signal)
        "remote": C.is_remote(prefs),
    }
    if city:
        out["location"] = city.lower().replace(" ", "-")   # "New Delhi" → "new-delhi"
    return out


if __name__ == "__main__":
    import json
    demo: Prefs = {
        "targetTitles": ["Payments PM"], "title": "Associate Product Manager",
        "role": ["Product"], "industry": ["Fintech"],
        "location": ["Bengaluru · India", "Delhi NCR · India"],
        "workMode": ["Hybrid"], "experience": ["Junior"], "years": 2,
        "targetComp": "₹16–22L", "companyStage": "Growth-stage",
        # engine-side only (ignored by adapters): priorities/stretch/intent/availability/dealBreakers/sort
    }
    print("MVQ ok:", C.has_mvq(demo), "\n")
    for name, fn in [("NAUKRI", build_naukri_input), ("LINKEDIN", build_linkedin_input),
                     ("INDEED", build_indeed_input)]:
        print(f"── {name} ──"); print(json.dumps(fn(demo), indent=2, ensure_ascii=False), "\n")
    print("── DIRECT-ATS ──")
    print(json.dumps(build_ats_input(demo, companies=[{"ats": "ashby", "company": "razorpay"}]), indent=2))