Minor updates to overlap detection and segment coalescing logic

internal/filler/filler.go

@@ -3,6 +3,7 @@ package filler
 import (
 	"regexp"
 	"strings"
+	"unicode"
 
 	"gitea.maximumdirect.net/eric/seriatim/internal/model"
 )
@@ -15,10 +16,10 @@ var patterns = []*regexp.Regexp{
 }
 
 // Apply tags short filler segments.
-func Apply(in model.MergedTranscript) (model.MergedTranscript, int) {
+func Apply(in model.MergedTranscript, maxDuration float64) (model.MergedTranscript, int) {
 	tagged := 0
 	for index := range in.Segments {
-		if !matches(in.Segments[index]) || hasCategory(in.Segments[index], Category) {
+		if !matches(in.Segments[index], maxDuration) || hasCategory(in.Segments[index], Category) {
 			continue
 		}
 		in.Segments[index].Categories = append(in.Segments[index].Categories, Category)
@@ -27,15 +28,15 @@ func Apply(in model.MergedTranscript) (model.MergedTranscript, int) {
 	return in, tagged
 }
 
-func matches(segment model.Segment) bool {
-	text := strings.TrimSpace(segment.Text)
+func matches(segment model.Segment, maxDuration float64) bool {
+	text := normalizeForMatching(segment.Text)
 	if text == "" {
 		return false
 	}
 	if len(strings.Fields(text)) > 3 {
 		return false
 	}
-	if segment.End-segment.Start > 1.0 {
+	if segment.End-segment.Start > maxDuration {
 		return false
 	}
 	for _, pattern := range patterns {
@@ -46,6 +47,16 @@ func matches(segment model.Segment) bool {
 	return false
 }
 
+func normalizeForMatching(text string) string {
+	text = strings.Map(func(r rune) rune {
+		if unicode.IsPunct(r) {
+			return ' '
+		}
+		return r
+	}, text)
+	return strings.Join(strings.Fields(text), " ")
+}
+
 func hasCategory(segment model.Segment, category string) bool {
 	for _, existing := range segment.Categories {
 		if existing == category {