"""Microsoft Research — RSS feed (blog posts and publication announcements) → ANNOUNCEMENT events.

Items categorised as publications (category "Publication" or a /research/publication/ URL) additionally become `paper` entities
(title, authors, date, abstract, URL). Blog posts stay events only; release-like posts are queued for LLM extraction.
"""
from __future__ import annotations

import re

from aiatlas.registry import org_ref
from aiatlas.sdk.connector import BaseConnector, Parsed, RunContext
from aiatlas.sdk.extract.feeds import FeedItem
from aiatlas.sdk.facts import EntityRef, Facts, Target
from aiatlas.sdk.fetch import FetchResult

from ._common import announcement_events

FEED = "https://www.microsoft.com/en-us/research/feed/"


class MicrosoftResearchConnector(BaseConnector):
    name = "microsoft_research"
    label = "Microsoft Research — blog & publications feed"
    description = "Microsoft Research RSS feed: research blog posts (events) and publications (paper entities)."
    source_key = "microsoft.com/research"
    version = "1"
    parser_version = "1"
    interval_seconds = 7200
    min_interval_seconds = 3600
    rate_per_min = 10
    tier = 1
    priority = 1
    expected_min_records = 1
    concurrency = 1

    async def discover(self, ctx: RunContext) -> list[Target]:
        return [Target(url=FEED, doc_type="feed", key="feed", min_bytes=1000)]

    async def extract(self, ctx: RunContext, target: Target, res: FetchResult, parsed: Parsed) -> Facts:
        facts = Facts()
        org = org_ref("microsoft")
        facts.entities.append(org)
        if parsed.kind != "feed":
            return facts
        announcement_events(facts, org, parsed.feed_items, source_name="microsoft.com/research", max_follow=10)
        for it in parsed.feed_items:
            if is_publication(it):
                paper_entity(facts, org, it)
        facts.document_title, facts.document_entity = "Microsoft Research feed", org
        return facts


def is_publication(it: FeedItem) -> bool:
    cats = {c.lower() for c in it.categories}
    return "publication" in cats or "publications" in cats or "/research/publication/" in it.url


def paper_entity(facts: Facts, org: EntityRef, it: FeedItem) -> EntityRef:
    paper = facts.entity("paper", it.title, identifiers={"url": it.url}, organization=org)
    facts.claim(paper, "published_at", it.published_at.date().isoformat() if it.published_at else None)
    facts.claim(paper, "abstract", (it.summary or "")[:2000] or None)
    authors = [a.strip() for chunk in it.authors for a in re.split(r",|\band\b", chunk) if a.strip()]
    facts.claim(paper, "authors", authors or None)
    facts.claim(paper, "paper_url", it.url)
    facts.relate(paper, "published_by", org)
    return paper


CONNECTORS = [MicrosoftResearchConnector]