"""Signal Producer interface + Normalizer — one signal language, but TWO signal KINDS.

The platform already HAS scanners (website, repo/code, SBOM, security headers, TLS, SPF/DKIM/DMARC,
document analysis, RAG over uploads, product classification). The Silent Pass does not want a
WebsiteScanner or a RepoScanner — it wants their UNIFIED output. So every source (a scanner, a PDF
parser, a tender parser, an OEM spec, an API, or the user) emits the SAME `ProducedSignal`
{signal_id, source_type, kind, confidence, evidence, provenance}, and `normalize_signals` reduces
producer-specific ids to ONE canonical signal via a vocabulary (id + aliases + kind) — exactly the
Requirement-Source / MCAP / regulation-alias pattern. The Silent Pass then never gets per-scanner logic.

CRITICAL — a signal is one of two KINDS, and they NEVER substitute for each other:
  observation = "I SAW X"          — a repo with an SBOM, a published security.txt, a risk-assessment PDF.
  requirement = "someone DEMANDS X" — a tender clause `requires_sbom`, an OEM spec `supplier_requires_psirt`.
A demanded SBOM is NOT a present SBOM. `kind` is carried on the canonical VOCABULARY entry (authoritative),
so even a mislabelled producer signal cannot collapse the two. The Silent Pass consumes ONLY observations;
requirement signals are preserved and feed the required-set / prioritisation later. This Observation-vs-
Requirement split is the very one the Requirements Verification Platform rests on: Observations (reality)
vs Requirements (targets); their comparison IS the delta. Pure, deterministic, no I/O. Python 3.9 compatible.
"""

from __future__ import annotations

from typing import Dict, List, Optional, Sequence

from pydantic import BaseModel, Field

from .silent_intake import IntakeSignal


class ProducedSignal(BaseModel):
    """What ANY signal producer emits — the common interface every source agrees on."""

    signal_id: str                              # raw or canonical id the producer used
    source_type: str = ""                       # website / repository / document / product / tender / oem / user / api
    kind: str = ""                              # "observation" | "requirement"; empty -> resolved from the vocabulary
    confidence: float = 1.0
    evidence: Optional[str] = None              # the artifact found (already in hand)
    provenance: str = ""                        # url / filename / tender clause / "customer statement"


class SignalVocabularyEntry(BaseModel):
    """One canonical signal + its aliases + its KIND (the authoritative observation/requirement label)."""

    id: str
    kind: str = "observation"                   # "observation" (I saw X) | "requirement" (someone DEMANDS X)
    aliases: List[str] = Field(default_factory=list)


def normalize_signals(
    produced: Sequence[ProducedSignal], vocabulary: Sequence[SignalVocabularyEntry]
) -> List[IntakeSignal]:
    """Reduce heterogeneous producer signals to the canonical IntakeSignal stream (alias resolution).

    The canonical vocabulary entry's `kind` is AUTHORITATIVE — a producer cannot relabel a requirement as
    an observation (that is what stops a demanded SBOM from masquerading as a present one). Unknown signal
    ids pass through unchanged (a new producer's signal stays visible, not silently dropped) and keep the
    producer-declared kind (default observation). Deterministic; carries confidence/evidence/provenance.
    """
    alias: Dict[str, str] = {}
    kind_of: Dict[str, str] = {}
    for v in vocabulary:
        alias[v.id] = v.id
        kind_of[v.id] = v.kind
        for a in v.aliases:
            alias[a] = v.id
    out: List[IntakeSignal] = []
    for p in produced:
        canonical = alias.get(p.signal_id, p.signal_id)
        kind = kind_of.get(canonical) or p.kind or "observation"
        out.append(IntakeSignal(
            source=p.source_type, signal=canonical, kind=kind, confidence=p.confidence,
            evidence=p.evidence, provenance=p.provenance))
    return out