Minor updates to overlap detection and segment coalescing logic
This commit is contained in:
@@ -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 {
|
||||
|
||||
@@ -10,7 +10,7 @@ import (
|
||||
func TestApplyTagsVerySafeFillers(t *testing.T) {
|
||||
for _, text := range []string{"um", "uhhh", "ER", "ermm", "ah", "eh", "hmmm", "mm", "mmm"} {
|
||||
t.Run(text, func(t *testing.T) {
|
||||
got, tagged := Apply(transcript(segment(text, 1, 1.5)))
|
||||
got, tagged := Apply(transcript(segment(text, 1, 1.5)), 1.0)
|
||||
if tagged != 1 {
|
||||
t.Fatalf("tagged = %d, want 1", tagged)
|
||||
}
|
||||
@@ -20,7 +20,7 @@ func TestApplyTagsVerySafeFillers(t *testing.T) {
|
||||
}
|
||||
|
||||
func TestApplyTagsRepeatedFillers(t *testing.T) {
|
||||
got, tagged := Apply(transcript(segment("um uh hmm", 1, 1.8)))
|
||||
got, tagged := Apply(transcript(segment("um uh hmm", 1, 1.8)), 1.0)
|
||||
if tagged != 1 {
|
||||
t.Fatalf("tagged = %d, want 1", tagged)
|
||||
}
|
||||
@@ -28,17 +28,29 @@ func TestApplyTagsRepeatedFillers(t *testing.T) {
|
||||
}
|
||||
|
||||
func TestApplyMatchesTrimAwareCaseInsensitive(t *testing.T) {
|
||||
got, tagged := Apply(transcript(segment(" UM uh ", 1, 1.5)))
|
||||
got, tagged := Apply(transcript(segment(" UM uh ", 1, 1.5)), 1.0)
|
||||
if tagged != 1 {
|
||||
t.Fatalf("tagged = %d, want 1", tagged)
|
||||
}
|
||||
assertCategories(t, got.Segments[0], []string{Category})
|
||||
}
|
||||
|
||||
func TestApplyIgnoresPunctuationWhenMatching(t *testing.T) {
|
||||
for _, text := range []string{"um.", "uh?!", "um, uh... hmm!", "hmm--mm"} {
|
||||
t.Run(text, func(t *testing.T) {
|
||||
got, tagged := Apply(transcript(segment(text, 1, 1.8)), 1.0)
|
||||
if tagged != 1 {
|
||||
t.Fatalf("tagged = %d, want 1", tagged)
|
||||
}
|
||||
assertCategories(t, got.Segments[0], []string{Category})
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestApplyDoesNotTagNonMatches(t *testing.T) {
|
||||
for _, text := range []string{"um okay", "uh-huh", "hmm, okay"} {
|
||||
t.Run(text, func(t *testing.T) {
|
||||
got, tagged := Apply(transcript(segment(text, 1, 1.5)))
|
||||
got, tagged := Apply(transcript(segment(text, 1, 1.5)), 1.0)
|
||||
if tagged != 0 {
|
||||
t.Fatalf("tagged = %d, want 0", tagged)
|
||||
}
|
||||
@@ -48,15 +60,29 @@ func TestApplyDoesNotTagNonMatches(t *testing.T) {
|
||||
}
|
||||
|
||||
func TestApplyRejectsWordCountOverThree(t *testing.T) {
|
||||
got, tagged := Apply(transcript(segment("um uh er ah", 1, 1.5)))
|
||||
got, tagged := Apply(transcript(segment("um uh er ah", 1, 1.5)), 1.0)
|
||||
if tagged != 0 {
|
||||
t.Fatalf("tagged = %d, want 0", tagged)
|
||||
}
|
||||
assertCategories(t, got.Segments[0], nil)
|
||||
}
|
||||
|
||||
func TestApplyRejectsDurationOverOneSecond(t *testing.T) {
|
||||
got, tagged := Apply(transcript(segment("um", 1, 2.1)))
|
||||
func TestApplyUsesConfiguredMaxDuration(t *testing.T) {
|
||||
got, tagged := Apply(transcript(segment("um", 1, 2.2)), 1.25)
|
||||
if tagged != 1 {
|
||||
t.Fatalf("tagged = %d, want 1", tagged)
|
||||
}
|
||||
assertCategories(t, got.Segments[0], []string{Category})
|
||||
|
||||
got, tagged = Apply(transcript(segment("um", 1, 2.3)), 1.25)
|
||||
if tagged != 0 {
|
||||
t.Fatalf("tagged = %d, want 0", tagged)
|
||||
}
|
||||
assertCategories(t, got.Segments[0], nil)
|
||||
}
|
||||
|
||||
func TestApplyRejectsDurationOverConfiguredMax(t *testing.T) {
|
||||
got, tagged := Apply(transcript(segment("um", 1, 2.1)), 1.0)
|
||||
if tagged != 0 {
|
||||
t.Fatalf("tagged = %d, want 0", tagged)
|
||||
}
|
||||
@@ -67,7 +93,7 @@ func TestApplyPreservesExistingCategoriesAndAvoidsDuplicate(t *testing.T) {
|
||||
existing := segment("um", 1, 1.2)
|
||||
existing.Categories = []string{"manual", Category}
|
||||
|
||||
got, tagged := Apply(transcript(existing))
|
||||
got, tagged := Apply(transcript(existing), 1.0)
|
||||
if tagged != 0 {
|
||||
t.Fatalf("tagged = %d, want 0", tagged)
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user