textmachine/backend/internal/pipeline/miner.go

package pipeline

import "sort"

// miner.go: the WS3 bank-mining detector orchestration (a Go port of the frozen exp16 arm A3 = V-C,
// LEMMATIZER-DEFAULT-B). Default B drops the pymorphy3-backed sub-channels the ratified §10-14 default
// removes: the spread multiplier (λ=0 already zeroed it), the dst-variants co-occurrence, and the
// Palladius ru-side name confirmation (+56 bonus). The dst (WHAT) is delivered by the banknote (WS4),
// never by co-occurrence, so exact rank is not a product value — the invariant guarantees are the
// candidate SET (membership), recall@proposed, and the catastrophe screen (∈top-50); dropping the
// Palladius sub-channel moves ONLY 古月's exact rank (21→22 vs the pymorphy3 reference), screen still
// PASS. Pure and deterministic ($0, no LLM, no network, no time/rand).

// MinerConfig is the frozen miner-v1 config (thresholds tuned on chapters 1–15, §D1). Values mirror
// arms.FROZEN; the pymorphy3-dependent knobs (lam, spread_freq_min) are absent by default-B design.
type MinerConfig struct {
	FreqFloor          int
	SubsumeAlpha       float64
	FormantMinPartners int
	FormantMinOverRep  float64
	Bonus              map[string]float64 // typ → base bonus (name/place/title/term)
	PatternWeight      map[string]float64 // evidence-source → weight (max over a candidate's evidence)
	SubfloorFreqScale  float64
	TopK               int
	PackVersion        string
}

// frozenMinerConfig is the ratified default-B config (versionable — a threshold edit is a mining-config
// bump the caller folds; a ±50% sweep is invariant, A3@f≥3=1.0 holds by floor/over_rep/subsume/partners).
func frozenMinerConfig() MinerConfig {
	return MinerConfig{
		FreqFloor:          minerFreqFloor,
		SubsumeAlpha:       minerSubsumeAlpha,
		FormantMinPartners: 3,
		FormantMinOverRep:  15.0,
		Bonus:              map[string]float64{"name": 140.0, "place": 140.0, "title": 120.0, "term": 80.0},
		PatternWeight: map[string]float64{
			"surname": 1.0, "ordinal_title": 1.0, "title_suffix": 0.9, "topo_suffix": 0.9,
			"rank_grade": 1.0, "formant_suffix": 0.6, "formant_prefix": 0.5, "title_bare": 0.4,
			"palladius": 0.8, // retained for parity of the weight table; the sub-channel is off in default B
		},
		SubfloorFreqScale: 40.0,
		TopK:              90,
		PackVersion:       minerPackVersion,
	}
}

// ScoredCand is one candidate after the V-C arm assembly (arms.ScoredCand, minus the default-B-dropped
// dst_variants/spread). types/evidence are in deterministic first-seen order; fromPattern marks a
// pattern-channel contribution.
type ScoredCand struct {
	Src         string
	Score       float64
	Freq        int
	Types       []string
	Evidence    []string
	FromPattern bool
}

// mineResult carries the detector outputs the alias/emit layers consume.
type mineResult struct {
	ranked   []ScoredCand    // A3 ranking, sorted (-score,-freq,src)
	subsumed map[string]bool // V-A ranking-dropped boundary fragments
	formants map[rune]formantInfo
	cfg      MinerConfig
}

// mineDetect runs V-A → V-C (arm A3, default B) over the normalized chunks and returns the ranked
// candidate list. contrast is the general-zh reference (loaded once). Deterministic.
func mineDetect(chunks []MinerChunk, contrast *Contrast, cfg MinerConfig) mineResult {
	va := runVA(chunks, contrast, cfg.FreqFloor, cfg.SubsumeAlpha)
	pats, formants := patternCandidates(chunks, va.candFreq, contrast, cfg.FormantMinPartners, cfg.FormantMinOverRep)

	merged := make(map[string]*ScoredCand, len(va.ranked)+len(pats))
	for _, c := range va.ranked {
		merged[c.src] = &ScoredCand{Src: c.src, Score: c.score, Freq: c.freq} // score·(1+λ·sp) with λ=0
	}
	for cand, info := range pats {
		pw := 0.3
		for _, ev := range info.evidence {
			if w, ok := cfg.PatternWeight[evSource(ev)]; ok && w > pw {
				pw = w
			}
		}
		typ := "term"
		if len(info.types) > 0 {
			typ = info.types[0]
		}
		base, ok := cfg.Bonus[typ]
		if !ok {
			base = cfg.Bonus["term"]
		}
		bonus := base * pw
		if sc, ok := merged[cand]; ok {
			sc.Score += bonus
			for _, t := range info.types {
				if !containsStr(sc.Types, t) {
					sc.Types = append(sc.Types, t)
				}
			}
			sc.Evidence = append(sc.Evidence, firstN(info.evidence, 3)...)
			sc.FromPattern = true
		} else {
			f := countOccurrences(cand, chunks)
			merged[cand] = &ScoredCand{
				Src: cand, Score: bonus + cfg.SubfloorFreqScale*float64(f)*pw, Freq: f,
				Types: append([]string(nil), info.types...), Evidence: firstN(info.evidence, 3),
				FromPattern: true,
			}
		}
	}
	// Palladius ru-side confirmation loop is INTENTIONALLY OMITTED (default B — it needs dst_variants +
	// is_name_lemma, both pymorphy3; it only shifts 古月's exact rank, which is not a product value).

	ranked := make([]ScoredCand, 0, len(merged))
	for _, sc := range merged {
		ranked = append(ranked, *sc)
	}
	sortScored(ranked)
	return mineResult{ranked: ranked, subsumed: va.subsumed, formants: formants, cfg: cfg}
}

// sortScored orders the arm ranking by (-score, -freq, src) — the frozen key.
func sortScored(cs []ScoredCand) {
	sort.Slice(cs, func(i, j int) bool {
		if cs[i].Score != cs[j].Score {
			return cs[i].Score > cs[j].Score
		}
		if cs[i].Freq != cs[j].Freq {
			return cs[i].Freq > cs[j].Freq
		}
		return cs[i].Src < cs[j].Src
	})
}

// evSource is the pattern-weight key: the evidence tag before its ':' (arms' ev.split(":")[0]).
func evSource(ev string) string {
	for i := 0; i < len(ev); i++ {
		if ev[i] == ':' {
			return ev[:i]
		}
	}
	return ev
}

// firstN returns up to n elements of ss (a fresh slice, never aliasing the input).
func firstN(ss []string, n int) []string {
	if len(ss) < n {
		n = len(ss)
	}
	return append([]string(nil), ss[:n]...)
}