IPSExtractor/services/services-count-facturas-medicas-serving/internal/pipeline/features.go

package pipeline

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

// FeatureCount debe coincidir con models v1.1.0 (services-count-facturas-medicas-ml).
const FeatureCount = 14

var (
	codePattern         = regexp.MustCompile(`^\d{4,6}$`)
	serviceCodePattern  = regexp.MustCompile(`(?i)^(\d{4,8}|\d+-\d+|[A-Z]{2,}\d{2,})$`)
	currencyPattern     = regexp.MustCompile(`^\d{1,3}(,\d{3})+(\.\d+)?$`)
	headerKeywordPattern = regexp.MustCompile(`(?i)\b(FECHA|VALOR|SUBTOTAL|CUFE|RESOLUCION|CONTRATO|FACTURA|NIT|TELEFONO|TOTAL)\b`)
)

type rowFeatures struct {
	Features  [FeatureCount]float32
	TextoFila string
	Cluster   int
	yNorm     float32
	// índices usados en el paso de continuación
	hasServiceTablePattern int
	currencyCount          int
}

func isServiceCode(token string) bool {
	return serviceCodePattern.MatchString(token)
}

func hasHeaderKeyword(text string) bool {
	return headerKeywordPattern.MatchString(text)
}

func firstTokenOf(text string) string {
	parts := strings.Fields(text)
	if len(parts) == 0 {
		return ""
	}
	return parts[0]
}

func extractRowFeatures(group []indexedBox, pageW, pageH int) rowFeatures {
	sort.Slice(group, func(i, j int) bool { return group[i].X < group[j].X })

	texts := make([]string, len(group))
	for i, b := range group {
		texts[i] = b.Text
	}
	textoFila := strings.Join(texts, " ")
	firstToken := ""
	if len(texts) > 0 {
		firstToken = texts[0]
	}

	currencyCount := 0
	integerCount := 0
	for _, t := range texts {
		if currencyPattern.MatchString(t) {
			currencyCount++
		}
		if isDigits(t) {
			integerCount++
		}
	}

	xMin, xMax := group[0].X, group[0].X
	ySum := 0
	for _, b := range group {
		if b.X < xMin {
			xMin = b.X
		}
		if b.X > xMax {
			xMax = b.X
		}
		ySum += b.Y
	}

	xSpanNorm := float32(0)
	if pageW > 0 {
		xSpanNorm = float32(xMax-xMin) / float32(pageW)
	}
	yNorm := float32(0)
	if pageH > 0 {
		yNorm = float32(ySum/len(group)) / float32(pageH)
	}
	firstTokenXNorm := float32(0)
	if pageW > 0 {
		firstTokenXNorm = float32(xMin) / float32(pageW)
	}

	tailStart := 0
	if len(texts) >= 3 {
		tailStart = len(texts) - 3
	}
	currencyAtRowEnd := 0
	for _, t := range texts[tailStart:] {
		if currencyPattern.MatchString(t) {
			currencyAtRowEnd = 1
			break
		}
	}

	totalChars := len(textoFila)
	if totalChars == 0 {
		totalChars = 1
	}
	special := 0
	digits := 0
	for _, c := range textoFila {
		if !unicode.IsLetter(c) && !unicode.IsNumber(c) && !unicode.IsSpace(c) {
			special++
		}
		if unicode.IsDigit(c) {
			digits++
		}
	}

	firstIsCode := 0
	if codePattern.MatchString(firstToken) {
		firstIsCode = 1
	}

	hasTablePattern := 0
	if currencyCount >= 2 && integerCount >= 1 {
		hasTablePattern = 1
	}
	headerKW := 0
	if hasHeaderKeyword(textoFila) {
		headerKW = 1
	}

	return rowFeatures{
		Features: [FeatureCount]float32{
			float32(firstIsCode),
			boolToFloat(isServiceCode(firstToken)),
			float32(hasTablePattern),
			float32(headerKW),
			float32(currencyAtRowEnd),
			firstTokenXNorm,
			0, // is_likely_continuation — segundo paso
			float32(currencyCount),
			float32(integerCount),
			xSpanNorm,
			yNorm,
			float32(len(texts)),
			float32(special) / float32(totalChars),
			float32(digits) / float32(totalChars),
		},
		TextoFila:              textoFila,
		Cluster:                group[0].Cluster,
		yNorm:                  yNorm,
		hasServiceTablePattern: hasTablePattern,
		currencyCount:          currencyCount,
	}
}

func boolToFloat(v bool) float32 {
	if v {
		return 1
	}
	return 0
}

func buildFeatureRows(boxes []indexedBox, pageW, pageH int) []rowFeatures {
	groups := groupByCluster(boxes)
	rows := make([]rowFeatures, 0, len(groups))
	for _, group := range groups {
		rows = append(rows, extractRowFeatures(group, pageW, pageH))
	}
	if len(rows) == 0 {
		return rows
	}

	sort.Slice(rows, func(i, j int) bool { return rows[i].yNorm < rows[j].yNorm })

	for i := 1; i < len(rows); i++ {
		prev := rows[i-1]
		cur := &rows[i]
		firstToken := firstTokenOf(cur.TextoFila)
		if prev.hasServiceTablePattern == 1 &&
			cur.currencyCount == 0 &&
			!isServiceCode(firstToken) &&
			!codePattern.MatchString(firstToken) {
			cur.Features[6] = 1
		}
	}
	return rows
}

func isDigits(s string) bool {
	if s == "" {
		return false
	}
	for _, c := range s {
		if c < '0' || c > '9' {
			return false
		}
	}
	return true
}