PocketVeto/backend/app/api/members.py

import logging
import re
from datetime import datetime, timezone
from typing import Optional

_FIPS_TO_STATE = {
    "01": "AL", "02": "AK", "04": "AZ", "05": "AR", "06": "CA",
    "08": "CO", "09": "CT", "10": "DE", "11": "DC", "12": "FL",
    "13": "GA", "15": "HI", "16": "ID", "17": "IL", "18": "IN",
    "19": "IA", "20": "KS", "21": "KY", "22": "LA", "23": "ME",
    "24": "MD", "25": "MA", "26": "MI", "27": "MN", "28": "MS",
    "29": "MO", "30": "MT", "31": "NE", "32": "NV", "33": "NH",
    "34": "NJ", "35": "NM", "36": "NY", "37": "NC", "38": "ND",
    "39": "OH", "40": "OK", "41": "OR", "42": "PA", "44": "RI",
    "45": "SC", "46": "SD", "47": "TN", "48": "TX", "49": "UT",
    "50": "VT", "51": "VA", "53": "WA", "54": "WV", "55": "WI",
    "56": "WY", "60": "AS", "66": "GU", "69": "MP", "72": "PR", "78": "VI",
}

import httpx
from fastapi import APIRouter, Depends, HTTPException, Query
from sqlalchemy import desc, func, or_, select
from sqlalchemy.ext.asyncio import AsyncSession
from sqlalchemy.orm import selectinload

from app.database import get_db
from app.models import Bill, Member, MemberTrendScore, MemberNewsArticle
from app.schemas.schemas import (
    BillSchema, MemberSchema, MemberTrendScoreSchema,
    MemberNewsArticleSchema, PaginatedResponse,
)
from app.services import congress_api

logger = logging.getLogger(__name__)

router = APIRouter()


@router.get("/by-zip/{zip_code}", response_model=list[MemberSchema])
async def get_members_by_zip(zip_code: str, db: AsyncSession = Depends(get_db)):
    """Return the House rep and senators for a ZIP code.
    Step 1: Nominatim (OpenStreetMap) — ZIP → lat/lng.
    Step 2: TIGERweb Legislative identify — lat/lng → congressional district.
    """
    if not re.fullmatch(r"\d{5}", zip_code):
        raise HTTPException(status_code=400, detail="ZIP code must be 5 digits")

    state_code: str | None = None
    district_num: str | None = None

    try:
        async with httpx.AsyncClient(timeout=20.0) as client:
            # Step 1: ZIP → lat/lng
            r1 = await client.get(
                "https://nominatim.openstreetmap.org/search",
                params={"postalcode": zip_code, "country": "US", "format": "json", "limit": "1"},
                headers={"User-Agent": "PocketVeto/1.0"},
            )
            places = r1.json() if r1.status_code == 200 else []
            if not places:
                logger.warning("Nominatim: no result for ZIP %s", zip_code)
                return []

            lat = places[0]["lat"]
            lng = places[0]["lon"]

            # Step 2: lat/lng → congressional district via TIGERweb identify (all layers)
            half = 0.5
            r2 = await client.get(
                "https://tigerweb.geo.census.gov/arcgis/rest/services/TIGERweb/Legislative/MapServer/identify",
                params={
                    "f": "json",
                    "geometry": f"{lng},{lat}",
                    "geometryType": "esriGeometryPoint",
                    "sr": "4326",
                    "layers": "all",
                    "tolerance": "2",
                    "mapExtent": f"{float(lng)-half},{float(lat)-half},{float(lng)+half},{float(lat)+half}",
                    "imageDisplay": "100,100,96",
                },
            )
            if r2.status_code != 200:
                logger.warning("TIGERweb returned %s for ZIP %s", r2.status_code, zip_code)
                return []

            identify_results = r2.json().get("results", [])
            logger.info(
                "TIGERweb ZIP %s layers: %s",
                zip_code, [r.get("layerName") for r in identify_results],
            )

            for item in identify_results:
                if "Congressional" not in (item.get("layerName") or ""):
                    continue
                attrs = item.get("attributes", {})

                # GEOID / GEOID20 — 2-char state FIPS + 2-char district (e.g. "0618" = CA-18)
                # 119th Congress layers use GEOID20 (2020 Census vintage)
                geoid = str(attrs.get("GEOID") or attrs.get("GEOID20") or "").strip()
                if len(geoid) == 4 and geoid.isdigit():
                    state_fips = geoid[:2]
                    district_fips = geoid[2:]
                    state_code = _FIPS_TO_STATE.get(state_fips)
                    district_num = str(int(district_fips)) if district_fips.strip("0") else None
                    if state_code:
                        break

                # Fallback: explicit field names (e.g. CD119FP + STATEFP20)
                cd_field = next((k for k in attrs if re.match(r"CD\d+FP$", k)), None)
                state_field = next((k for k in attrs if "STATEFP" in k.upper()), None)
                if cd_field and state_field:
                    try:
                        state_fips = str(attrs[state_field]).zfill(2)
                        district_fips = str(attrs[cd_field]).zfill(2)
                        state_code = _FIPS_TO_STATE.get(state_fips)
                        district_num = str(int(district_fips)) if district_fips.strip("0") else None
                        if state_code:
                            break
                    except (ValueError, TypeError):
                        pass

                logger.debug(
                    "ZIP %s: could not parse layer %r — attrs: %s",
                    zip_code, item.get("layerName"), list(attrs.keys()),
                )

            if not state_code:
                logger.warning(
                    "ZIP %s: no CD found. Layers: %s",
                    zip_code, [r.get("layerName") for r in identify_results],
                )

    except Exception as exc:
        logger.warning("ZIP lookup error for %s: %s", zip_code, exc)
        return []

    if not state_code:
        return []

    members: list[MemberSchema] = []
    seen: set[str] = set()

    if district_num:
        result = await db.execute(
            select(Member).where(
                Member.state == state_code,
                Member.district == district_num,
                Member.chamber == "House of Representatives",
            )
        )
        member = result.scalar_one_or_none()
        if member:
            seen.add(member.bioguide_id)
            members.append(MemberSchema.model_validate(member))
    else:
        # At-large states (AK, DE, MT, ND, SD, VT, WY)
        result = await db.execute(
            select(Member).where(
                Member.state == state_code,
                Member.chamber == "House of Representatives",
            ).limit(1)
        )
        member = result.scalar_one_or_none()
        if member:
            seen.add(member.bioguide_id)
            members.append(MemberSchema.model_validate(member))

    result = await db.execute(
        select(Member).where(
            Member.state == state_code,
            Member.chamber == "Senate",
        )
    )
    for member in result.scalars().all():
        if member.bioguide_id not in seen:
            seen.add(member.bioguide_id)
            members.append(MemberSchema.model_validate(member))

    return members


@router.get("", response_model=PaginatedResponse[MemberSchema])
async def list_members(
    chamber: Optional[str] = Query(None),
    party: Optional[str] = Query(None),
    state: Optional[str] = Query(None),
    q: Optional[str] = Query(None),
    page: int = Query(1, ge=1),
    per_page: int = Query(50, ge=1, le=250),
    db: AsyncSession = Depends(get_db),
):
    query = select(Member)
    if chamber:
        query = query.where(Member.chamber == chamber)
    if party:
        query = query.where(Member.party == party)
    if state:
        query = query.where(Member.state == state)
    if q:
        # name is stored as "Last, First" — also match "First Last" order
        first_last = func.concat(
            func.split_part(Member.name, ", ", 2), " ",
            func.split_part(Member.name, ", ", 1),
        )
        query = query.where(or_(
            Member.name.ilike(f"%{q}%"),
            first_last.ilike(f"%{q}%"),
        ))

    total = await db.scalar(select(func.count()).select_from(query.subquery())) or 0
    query = query.order_by(Member.last_name, Member.first_name).offset((page - 1) * per_page).limit(per_page)

    result = await db.execute(query)
    members = result.scalars().all()

    return PaginatedResponse(
        items=members,
        total=total,
        page=page,
        per_page=per_page,
        pages=max(1, (total + per_page - 1) // per_page),
    )


@router.get("/{bioguide_id}", response_model=MemberSchema)
async def get_member(bioguide_id: str, db: AsyncSession = Depends(get_db)):
    member = await db.get(Member, bioguide_id)
    if not member:
        raise HTTPException(status_code=404, detail="Member not found")

    # Kick off member interest on first view — single combined task avoids duplicate API calls
    if member.detail_fetched is None:
        try:
            from app.workers.member_interest import sync_member_interest
            sync_member_interest.delay(bioguide_id)
        except Exception:
            pass

    # Lazy-enrich with detail data from Congress.gov on first view
    if member.detail_fetched is None:
        try:
            detail_raw = congress_api.get_member_detail(bioguide_id)
            enriched = congress_api.parse_member_detail_from_api(detail_raw)
            for field, value in enriched.items():
                if value is not None:
                    setattr(member, field, value)
            member.detail_fetched = datetime.now(timezone.utc)
            await db.commit()
            await db.refresh(member)
        except Exception as e:
            logger.warning(f"Could not enrich member detail for {bioguide_id}: {e}")

    # Attach latest trend score
    result_schema = MemberSchema.model_validate(member)
    latest_trend = (
        await db.execute(
            select(MemberTrendScore)
            .where(MemberTrendScore.member_id == bioguide_id)
            .order_by(desc(MemberTrendScore.score_date))
            .limit(1)
        )
    )
    trend = latest_trend.scalar_one_or_none()
    if trend:
        result_schema.latest_trend = MemberTrendScoreSchema.model_validate(trend)
    return result_schema


@router.get("/{bioguide_id}/trend", response_model=list[MemberTrendScoreSchema])
async def get_member_trend(
    bioguide_id: str,
    days: int = Query(30, ge=7, le=365),
    db: AsyncSession = Depends(get_db),
):
    from datetime import date, timedelta
    cutoff = date.today() - timedelta(days=days)
    result = await db.execute(
        select(MemberTrendScore)
        .where(MemberTrendScore.member_id == bioguide_id, MemberTrendScore.score_date >= cutoff)
        .order_by(MemberTrendScore.score_date)
    )
    return result.scalars().all()


@router.get("/{bioguide_id}/news", response_model=list[MemberNewsArticleSchema])
async def get_member_news(bioguide_id: str, db: AsyncSession = Depends(get_db)):
    result = await db.execute(
        select(MemberNewsArticle)
        .where(MemberNewsArticle.member_id == bioguide_id)
        .order_by(desc(MemberNewsArticle.published_at))
        .limit(20)
    )
    return result.scalars().all()


@router.get("/{bioguide_id}/bills", response_model=PaginatedResponse[BillSchema])
async def get_member_bills(
    bioguide_id: str,
    page: int = Query(1, ge=1),
    per_page: int = Query(20, ge=1, le=100),
    db: AsyncSession = Depends(get_db),
):
    query = select(Bill).options(selectinload(Bill.briefs), selectinload(Bill.sponsor)).where(Bill.sponsor_id == bioguide_id)
    total = await db.scalar(select(func.count()).select_from(query.subquery())) or 0
    query = query.order_by(desc(Bill.introduced_date)).offset((page - 1) * per_page).limit(per_page)

    result = await db.execute(query)
    bills = result.scalars().all()

    items = []
    for bill in bills:
        b = BillSchema.model_validate(bill)
        if bill.briefs:
            b.latest_brief = bill.briefs[0]
        items.append(b)

    return PaginatedResponse(
        items=items,
        total=total,
        page=page,
        per_page=per_page,
        pages=max(1, (total + per_page - 1) // per_page),
    )