eric/seriatim
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 4 Wiki Activity

Minor updates to overlap detection and segment coalescing logic

Browse Source
This commit is contained in:
Eric Rakestraw
2026-04-28 14:11:38 -05:00
parent 28c2eea340
commit a3ca6665a9
14 changed files with 662 additions and 95 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
internal/filler/filler_test.go
View File

@@ -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)
}