// Package missionclass is the pure deterministic mission and labor classifier. It tags federal record
// text with structured mission areas (the missionclass.Codes vocabulary) using a keyword gazetteer, the
// WS2 alias layer, and a curated PSC and NAICS crosswalk, each inference carrying the mechanism and the
// evidence phrase so every tag is traceable. The package is pure: no clock, no randomness, no network,
// and no DB, so its output is byte stable for fixed input. Mission tags are NEVER a scoring input and
// never reference the eeo schema.
package missionclass

import (
	"regexp"
	"sort"
	"strings"
)

// Mechanism records HOW a mission was inferred, so every tag is traceable (the WS7 acceptance criterion).
const (
	MechKeyword = "keyword"
	MechAlias   = "alias"
	MechPSC     = "psc"
	MechNAICS   = "naics"
)

// Hit is one mission inference with its provenance.
type Hit struct {
	Code      string
	Mechanism string
	Evidence  string // the matched phrase or code
}

type form struct {
	code string
	re   *regexp.Regexp
	text string // canonical evidence phrase for this form
}

// wbForm compiles a case insensitive, word boundary anchored matcher for a phrase. Any single space in a
// multi word phrase becomes \s+, so a line break or a double space between tokens still matches. The
// phrase is regex quoted, so a literal containing a metacharacter is matched safely.
func wbForm(code, phrase string) form {
	return form{code: code, text: phrase,
		re: regexp.MustCompile(`(?i)\b` + strings.ReplaceAll(regexp.QuoteMeta(phrase), " ", `\s+`) + `\b`)}
}

// missionForms is iterated in Codes order. Keep in sync with ai/mission.go missionVocabulary.
var missionForms = []form{
	wbForm("SIGINT", "sigint"), wbForm("SIGINT", "signals intelligence"),
	wbForm("GEOINT", "geoint"), wbForm("GEOINT", "geospatial intelligence"),
	wbForm("HUMINT", "humint"), wbForm("HUMINT", "human intelligence"),
	wbForm("MASINT", "masint"), wbForm("MASINT", "measurement and signature intelligence"),
	wbForm("OSINT", "osint"), wbForm("OSINT", "open source intelligence"),
	wbForm("SAT_C2", "satellite c2"), wbForm("SAT_C2", "satellite command and control"),
	wbForm("CDS", "cross domain solution"), wbForm("CDS", "cross domain solutions"),
	wbForm("COMSEC", "comsec"), wbForm("COMSEC", "communications security"),
	wbForm("TEMPEST", "tempest"),
	wbForm("EW", "electronic warfare"),
}

// ClassifyKeyword returns one Hit per mission code whose keyword form appears in text, in Codes order.
func ClassifyKeyword(text string) []Hit {
	if strings.TrimSpace(text) == "" {
		return nil
	}
	found := map[string]Hit{}
	for _, f := range missionForms {
		if _, ok := found[f.code]; ok {
			continue
		}
		if f.re.MatchString(text) {
			found[f.code] = Hit{Code: f.code, Mechanism: MechKeyword, Evidence: f.text}
		}
	}
	return ordered(found)
}

// AliasIndex maps a lowercased mission bearing phrase to a mission code. It is built from the curated WS2
// alias rows and the category 'mission_area' skills, so the alias layer (not a cosine threshold) carries
// acronym and synonym knowledge. Phrases are matched on a word boundary, whitespace tolerant.
type AliasIndex struct {
	forms []form
}

// NewAliasIndex builds an AliasIndex from a phrase to code map. The forms are appended in sorted key
// order so the build is deterministic and the resulting index iterates the same way every run.
func NewAliasIndex(phraseToCode map[string]string) AliasIndex {
	keys := make([]string, 0, len(phraseToCode))
	for k := range phraseToCode {
		keys = append(keys, k)
	}
	sort.Strings(keys) // deterministic build order
	ai := AliasIndex{}
	for _, k := range keys {
		ai.forms = append(ai.forms, wbForm(phraseToCode[k], k))
	}
	return ai
}

// ClassifyAlias returns one Hit per mission code whose alias phrase appears in text, in Codes order.
func ClassifyAlias(text string, idx AliasIndex) []Hit {
	if strings.TrimSpace(text) == "" {
		return nil
	}
	found := map[string]Hit{}
	for _, f := range idx.forms {
		if _, ok := found[f.code]; ok {
			continue
		}
		if f.re.MatchString(text) {
			found[f.code] = Hit{Code: f.code, Mechanism: MechAlias, Evidence: f.text}
		}
	}
	return ordered(found)
}

// ordered returns the hits sorted by the canonical Codes order, for byte stable output.
func ordered(m map[string]Hit) []Hit {
	rank := map[string]int{}
	for i, c := range Codes {
		rank[c] = i
	}
	out := make([]Hit, 0, len(m))
	for _, h := range m {
		out = append(out, h)
	}
	sort.Slice(out, func(i, j int) bool { return rank[out[i].Code] < rank[out[j].Code] })
	return out
}