HR-ATS-Portal/backend/inbox/plugins.py

"""Inbox helpers — attachment loading, resume text extraction, read-status sync."""

from __future__ import annotations

import base64
import os
import re
import uuid
from pathlib import Path
from urllib.parse import quote

import httpx
from dotenv import load_dotenv
from sqlalchemy.ext.asyncio import AsyncSession
from sqlmodel import select

from inbox.models import AtsResults, Inbox, Inbox_Messages
from job.candidate.models import Candidates, Manual_UPLOAD_CANDIDATE
from job.candidate.views import FileRead

load_dotenv()

EMAIL_URL=os.getenv("EMAIL_URL")
EMAIL_API_TOKEN=os.getenv("EMAIL_API_TOKEN")
BACKEND_URL=os.getenv("BACKEND_URL","http://localhost:8000")

_ATTACHMENTS_DIR=Path(__file__).resolve().parent/"decoded_attachments"
# Prefer +92 / 03xx style numbers; fall back to a looser intl-ish pattern.
_PHONE=re.compile(
    r"(?:\+?92[\s\-]?)?0?3\d{2}[\s\-]?\d{7}"
    r"|(?:\+?\d{1,3}[\s\-]?)?(?:\(?\d{2,4}\)?[\s\-]?)?\d{3,4}[\s\-]?\d{3,4}"
)


async def request_email_confirmation(email):
    """POST /users/confirm-email/resend on this same service -> status code.

    Goes through the endpoint rather than importing Confirmation so the token row,
    resend cooldown and mail send stay on one code path.
    """
    async with httpx.AsyncClient(timeout=20.0) as client:
        response=await client.post(
            f"{BACKEND_URL.rstrip('/')}/users/confirm-email/resend",
            json={"email":email},
        )
    return response.status_code


async def fetch_read_status_delta(folder, since=None, limit=100, max_pages=10, token=None):
    """GET /sync/read-status -> the raw round dict.

    Upstream Email API caps `limit` at 100; keep the default at that ceiling.
    """
    if not EMAIL_URL:
        raise RuntimeError("EMAIL_URL must be set")
    auth_token=token or EMAIL_API_TOKEN
    if not auth_token:
        raise RuntimeError("EMAIL_API_TOKEN must be set")
    params={"folder":folder,"limit":min(int(limit or 100),100),"max_pages":max_pages}
    if since:
        params["since"]=since
    async with httpx.AsyncClient(timeout=15.0) as client:
        response=await client.get(
            f"{EMAIL_URL.rstrip('/')}/sync/read-status",
            params=params,
            headers={"Authorization":f"Bearer {auth_token}"},
        )
    if response.status_code>=400:
        raise httpx.HTTPStatusError(
            response.text,
            request=response.request,
            response=response,
        )
    return response.json()


async def fetch_message_read_status(message_id, token=None):
    """GET /sync/read-status/message/{id} -> record dict, or None on 404."""
    if not EMAIL_URL:
        raise RuntimeError("EMAIL_URL must be set")
    auth_token=token or EMAIL_API_TOKEN
    if not auth_token:
        raise RuntimeError("EMAIL_API_TOKEN must be set")
    encoded_id=quote(str(message_id),safe="")
    async with httpx.AsyncClient(timeout=15.0) as client:
        response=await client.get(
            f"{EMAIL_URL.rstrip('/')}/sync/read-status/message/{encoded_id}",
            headers={"Authorization":f"Bearer {auth_token}"},
        )
    if response.status_code==404:
        return None
    if response.status_code>=400:
        raise httpx.HTTPStatusError(
            response.text,
            request=response.request,
            response=response,
        )
    return response.json()


def resolve_attachment_path(path_str:str) -> Path:
    """Prefer stored path; fall back to basename under decoded_attachments.

    Stored paths may be Windows absolutes written by the host API. The Taskiq
    worker runs in Linux, where ``Path(r"D:\\...\\file.pdf").name`` is the
    whole string (backslash is not a separator), so normalize separators before
    taking the basename for the mounted attachments dir.
    """
    raw=path_str.strip()
    path=Path(raw)
    if path.is_file():
        return path
    basename=Path(raw.replace("\\","/")).name
    fallback=_ATTACHMENTS_DIR/basename
    if fallback.is_file():
        return fallback
    return path


def load_message_files(message:Inbox_Messages) -> list[dict]:
    if not message.file_path:
        return []
    files=[]
    for path_str in message.file_path.split(","):
        path=resolve_attachment_path(path_str)
        if not path.is_file():
            continue
        try:
            raw=path.read_bytes()
        except OSError:
            continue
        files.append({
            "file_name":path.name,
            "content_base64":base64.b64encode(raw).decode("ascii"),
            "size":len(raw),
        })
    return files


def extract_phone(text:str) -> str|None:
    m=_PHONE.search(text or "")
    if not m:
        return None
    return re.sub(r"[\s\-()]+"," ",m.group(0)).strip()


async def extract_resume_text(file_paths:list[str]) -> tuple[str,str]:
    candidates=[resolve_attachment_path(p) for p in (file_paths or []) if p and p.strip()]
    existing=[p for p in candidates if p.is_file() and p.suffix.lower()==".pdf"]
    if not existing:
        return "","no PDF attachment to extract (.doc/.docx not supported)"

    texts=[]
    errors=[]
    for path in existing:
        try:
            raw=path.read_bytes()
            result=await FileRead(session=None,filename=path.name,file=raw).read_file()
            text=(result.get("text") or "").strip()
            if text:
                texts.append(text)
        except Exception as exc:
            errors.append(f"{path.name}: {exc}")

    if not texts:
        return "","; ".join(errors) if errors else "no text extracted from PDF"
    return "\n\n---\n\n".join(texts),""


def _ats_score_payload(row):
    if row is None:
        return None
    return {
        "overall_score":row.overall_score,
        "band":row.band or None,
        "job_post_id":str(row.job_post_id) if row.job_post_id else None,
        "computed_at":row.computed_at.isoformat() if row.computed_at else None,
        "candidate_id":str(row.candidate_id) if row.candidate_id else None,
        "user_id":str(row.user_id) if row.user_id else None,
    }


async def get_ats_score_for_user(session:AsyncSession,user_id,job_post_id=None):
    """Current ats_results overall score for a candidate -> dict, or None.

    Prefer ats_results.user_id (CV email matched that user). Fall back to the
    inbox.user_id join for scores whose email did not match any user, where
    candidate_id is set and user_id is NULL.

    Pass job_post_id to pin one application when a candidate has several;
    without it the newest current score across their applications wins.
    """
    try:
        uid=uuid.UUID(str(user_id))
    except (TypeError,ValueError):
        return None

    direct=(
        select(AtsResults)
        .where(AtsResults.user_id==uid,AtsResults.is_current==True)  # noqa: E712
        .order_by(AtsResults.computed_at.desc())
    )
    if job_post_id:
        try:
            direct=direct.where(AtsResults.job_post_id==uuid.UUID(str(job_post_id)))
        except (TypeError,ValueError):
            return None
    row=(await session.execute(direct)).scalars().first()
    if row is not None:
        return _ats_score_payload(row)

    qry=(
        select(AtsResults)
        .join(Inbox,AtsResults.inbox_id==Inbox.id)
        .join(Inbox_Messages,Inbox.message_id==Inbox_Messages.id)
        .where(
            Inbox.user_id==uid,
            Inbox_Messages.assigned_job_post_id.is_not(None),
            AtsResults.job_post_id==Inbox_Messages.assigned_job_post_id,
            AtsResults.is_current==True,  # noqa: E712
        )
        .order_by(AtsResults.computed_at.desc())
    )
    if job_post_id:
        try:
            qry=qry.where(Inbox_Messages.assigned_job_post_id==uuid.UUID(str(job_post_id)))
        except (TypeError,ValueError):
            return None

    return _ats_score_payload((await session.execute(qry)).scalars().first())


async def get_ats_score_for_manual_user(session:AsyncSession,user_id,job_post_id=None):
    """Current ats_results overall score for an Add Candidate user -> dict, or None.

    Prefer ats_results.user_id (Add Candidate always creates a users row, so a
    later score against that email lands on user_id). Fall back to the
    email+candidate_id join for rows written before user_id existed.
    apply_via=manual_upload is the Add Candidate gate; /import never writes
    that table.

    Pass job_post_id to pin one application when a candidate has several;
    without it the newest current score across their applications wins.
    """
    try:
        uid=uuid.UUID(str(user_id))
    except (TypeError,ValueError):
        return None

    direct=(
        select(AtsResults)
        .where(AtsResults.user_id==uid,AtsResults.is_current==True)  # noqa: E712
        .order_by(AtsResults.computed_at.desc())
    )
    if job_post_id:
        try:
            jid=uuid.UUID(str(job_post_id))
        except (TypeError,ValueError):
            return None
        direct=direct.where(AtsResults.job_post_id==jid)
    row=(await session.execute(direct)).scalars().first()
    if row is not None:
        return _ats_score_payload(row)

    qry=(
        select(AtsResults)
        .join(Candidates,AtsResults.candidate_id==Candidates.id)
        .join(
            Manual_UPLOAD_CANDIDATE,
            (Candidates.job_id==Manual_UPLOAD_CANDIDATE.job_post_id)
            &(Candidates.candidate_email==Manual_UPLOAD_CANDIDATE.candidate_email),
        )
        .where(
            Manual_UPLOAD_CANDIDATE.user_id==uid,
            Manual_UPLOAD_CANDIDATE.apply_via=="manual_upload",
            Candidates.status=="completed",
            AtsResults.job_post_id==Manual_UPLOAD_CANDIDATE.job_post_id,
            AtsResults.is_current==True,  # noqa: E712
        )
        .order_by(AtsResults.computed_at.desc())
    )
    if job_post_id:
        try:
            jid=uuid.UUID(str(job_post_id))
        except (TypeError,ValueError):
            return None
        qry=qry.where(
            Manual_UPLOAD_CANDIDATE.job_post_id==jid,
            AtsResults.job_post_id==jid,
        )

    return _ats_score_payload((await session.execute(qry)).scalars().first())