consolidated shared types from calls_from_preds.go into calls_from_common.go

quietlight

May 19, 2026, 3:06 AM

T6CPEI47HGJNIRCG2FYTDJPDWZGQM6VVSQJDUPEAUX4THFOAKJAAC

Dependencies

[2] 3DVPQOKB big tidy up of tools/
[3] XU7FTYK3 third phase of utils refactor, wav/
[4] V2HX6HEB claude going nuts all over the place
[*] KZKLAINJ run out of space on nest, cleaned out

Change contents

edit in tools/calls/calls_from_preds.go at line 28

[2.164179]→[2.164179:164455](∅→∅)

// ClusteredCall represents a clustered bird call detection
type ClusteredCall struct {
File string `json:"file"`
StartTime float64 `json:"start_time"`
EndTime float64 `json:"end_time"`
EbirdCode string `json:"ebird_code"`
Segments int `json:"segments"`
}
edit in tools/calls/calls_from_preds.go at line 55

[2.165820]→[2.165820:165983](∅→∅)

}

// AviaNZ .data file types

// predFileSpeciesKey groups detections by file and ebird code
type predFileSpeciesKey struct {
File string
EbirdCode string
edit in tools/calls/calls_from_preds.go at line 228

[2.171094]→[2.171094:171912](∅→∅)

}
}
}

// clusterDetections groups detections into clusters and produces sorted ClusteredCalls
func clusterDetections(detections map[predFileSpeciesKey][]float64, clipDuration, gapThreshold float64, minDetections int) ([]ClusteredCall, map[string]int) {
var allCalls []ClusteredCall
speciesCount := make(map[string]int)

for key, startTimes := range detections {
sort.Float64s(startTimes)

clusters := clusterStartTimes(startTimes, gapThreshold)

for _, cluster := range clusters {
if len(cluster) <= minDetections {
continue
}

call := ClusteredCall{
File: key.File,
StartTime: cluster[0],
EndTime: cluster[len(cluster)-1] + clipDuration,
EbirdCode: key.EbirdCode,
Segments: len(cluster),
}
allCalls = append(allCalls, call)
speciesCount[key.EbirdCode]++
edit in tools/calls/calls_from_preds.go at line 230

[2.171919]→[2.171919:172149](∅→∅)

sort.Slice(allCalls, func(i, j int) bool {
if allCalls[i].File != allCalls[j].File {
return allCalls[i].File < allCalls[j].File
}
return allCalls[i].StartTime < allCalls[j].StartTime
})

return allCalls, speciesCount
edit in tools/calls/calls_from_preds.go at line 232

[2.172152]→[2.172152:174676](∅→∅)

// DirCache caches directory entries for fast WAV file lookup.
// Scans the directory once and builds a map from lowercased basename to full filename.
// Safe for concurrent read-only use after construction.
type DirCache struct {
dir string
wavMap map[string]string // lowercase basename -> filename with original case (e.g. "20230610_150000" -> "20230610_150000.WAV")
dirMap map[string]string // lowercase basename -> filename for any file (used by from-raven for .selections.txt etc.)
}

// NewDirCache creates a DirCache by scanning the directory once.
func NewDirCache(dir string) *DirCache {
entries, err := os.ReadDir(dir)
if err != nil {
return &DirCache{dir: dir, wavMap: make(map[string]string), dirMap: make(map[string]string)}
}
wavMap := make(map[string]string, len(entries))
dirMap := make(map[string]string, len(entries))
for _, entry := range entries {
if entry.IsDir() {
continue
}
name := entry.Name()
ext := filepath.Ext(name)
base := strings.TrimSuffix(name, ext)
dirMap[strings.ToLower(base)] = name
if strings.EqualFold(ext, ".wav") {
wavMap[strings.ToLower(base)] = name
}
}
return &DirCache{dir: dir, wavMap: wavMap, dirMap: dirMap}
}

// FindWAV looks up a WAV file by basename (case-insensitive).
// Returns the full path with correct case, or empty string if not found.
func (dc *DirCache) FindWAV(baseName string) string {
if name, ok := dc.wavMap[strings.ToLower(baseName)]; ok {
return filepath.Join(dc.dir, name)
}
return ""
}

// FindFile looks up any file by basename (case-insensitive).
// Returns the full path with correct case, or empty string if not found.
func (dc *DirCache) FindFile(baseName string) string {
if name, ok := dc.dirMap[strings.ToLower(baseName)]; ok {
return filepath.Join(dc.dir, name)
}
return ""
}

// findWAVFile finds a WAV file in the directory with case-insensitive matching.
// baseName is the filename without extension (e.g., "20230610_150000").
// Returns the full path with correct case, or empty string if not found.
// Deprecated: Use DirCache.FindWAV for batch operations to avoid repeated directory scans.
func findWAVFile(dir, baseName string) string {
entries, err := os.ReadDir(dir)
if err != nil {
return ""
}
for _, entry := range entries {
if entry.IsDir() {
continue
}
name := entry.Name()
ext := filepath.Ext(name)
nameNoExt := strings.TrimSuffix(name, ext)
if nameNoExt == baseName && strings.EqualFold(ext, ".wav") {
return filepath.Join(dir, name)
}
}
return ""
}
edit in tools/calls/calls_from_preds.go at line 547

[2.183648]→[2.183648:184859](∅→∅)

// ParseFilterFromFilename extracts filter name from preds CSV filename
// "predsST_opensoundscape-kiwi-1.2_2025-11-12.csv" -> "opensoundscape-kiwi-1.2"
// Returns empty string if parsing fails
func ParseFilterFromFilename(csvPath string) string {
filename := filepath.Base(csvPath)
// Remove .csv extension
name := strings.TrimSuffix(filename, ".csv")

// Split on underscore
parts := strings.Split(name, "_")
if len(parts) == 3 {
return parts[1]
}

return ""
}

// clusterStartTimes groups consecutive start times into clusters
// where the gap between consecutive times is <= gapThreshold
func clusterStartTimes(startTimes []float64, gapThreshold float64) [][]float64 {
if len(startTimes) == 0 {
return nil
}

var clusters [][]float64
currentCluster := []float64{startTimes[0]}

for i := 1; i < len(startTimes); i++ {
gap := startTimes[i] - startTimes[i-1]
if gap <= gapThreshold {
// Same cluster
currentCluster = append(currentCluster, startTimes[i])
} else {
// New cluster
clusters = append(clusters, currentCluster)
currentCluster = []float64{startTimes[i]}
}
}
// Don't forget the last cluster
clusters = append(clusters, currentCluster)

return clusters
}
edit in tools/calls/calls_from_common.go at line 8

[2.184968]

[2.184968]

"strings"
edit in tools/calls/calls_from_common.go at line 286

[2.192600]

[2.192600]

}
}
}

// ClusteredCall represents a clustered bird call detection.
// Shared by all call source implementations (preds, birda, raven).
type ClusteredCall struct {
File string `json:"file"`
StartTime float64 `json:"start_time"`
EndTime float64 `json:"end_time"`
EbirdCode string `json:"ebird_code"`
Segments int `json:"segments"`
}

// DirCache caches directory entries for fast WAV file lookup.
// Scans the directory once and builds a map from lowercased basename to full filename.
// Safe for concurrent read-only use after construction.
type DirCache struct {
dir string
wavMap map[string]string // lowercase basename -> filename with original case (e.g. "20230610_150000" -> "20230610_150000.WAV")
dirMap map[string]string // lowercase basename -> filename for any file (used by from-raven for .selections.txt etc.)
}

// NewDirCache creates a DirCache by scanning the directory once.
func NewDirCache(dir string) *DirCache {
entries, err := os.ReadDir(dir)
if err != nil {
return &DirCache{dir: dir, wavMap: make(map[string]string), dirMap: make(map[string]string)}
}
wavMap := make(map[string]string, len(entries))
dirMap := make(map[string]string, len(entries))
for _, entry := range entries {
if entry.IsDir() {
continue
}
name := entry.Name()
ext := filepath.Ext(name)
base := strings.TrimSuffix(name, ext)
dirMap[strings.ToLower(base)] = name
if strings.EqualFold(ext, ".wav") {
wavMap[strings.ToLower(base)] = name
}
}
return &DirCache{dir: dir, wavMap: wavMap, dirMap: dirMap}
}

// FindWAV looks up a WAV file by basename (case-insensitive).
// Returns the full path with correct case, or empty string if not found.
func (dc *DirCache) FindWAV(baseName string) string {
if name, ok := dc.wavMap[strings.ToLower(baseName)]; ok {
return filepath.Join(dc.dir, name)
}
return ""
}

// FindFile looks up any file by basename (case-insensitive).
// Returns the full path with correct case, or empty string if not found.
func (dc *DirCache) FindFile(baseName string) string {
if name, ok := dc.dirMap[strings.ToLower(baseName)]; ok {
return filepath.Join(dc.dir, name)
}
return ""
}

// findWAVFile finds a WAV file in the directory with case-insensitive matching.
// baseName is the filename without extension (e.g., "20230610_150000").
// Returns the full path with correct case, or empty string if not found.
// Deprecated: Use DirCache.FindWAV for batch operations to avoid repeated directory scans.
func findWAVFile(dir, baseName string) string {
entries, err := os.ReadDir(dir)
if err != nil {
return ""
}
for _, entry := range entries {
if entry.IsDir() {
continue
}
name := entry.Name()
ext := filepath.Ext(name)
nameNoExt := strings.TrimSuffix(name, ext)
if nameNoExt == baseName && strings.EqualFold(ext, ".wav") {
return filepath.Join(dir, name)
}
}
return ""
}

// ParseFilterFromFilename extracts filter name from preds CSV filename.
// "predsST_opensoundscape-kiwi-1.2_2025-11-12.csv" -> "opensoundscape-kiwi-1.2"
// Returns empty string if parsing fails.
func ParseFilterFromFilename(csvPath string) string {
filename := filepath.Base(csvPath)
// Remove .csv extension
name := strings.TrimSuffix(filename, ".csv")

// Split on underscore
parts := strings.Split(name, "_")
if len(parts) == 3 {
return parts[1]
}

return ""
}

// clusterStartTimes groups consecutive start times into clusters
// where the gap between consecutive times is <= gapThreshold.
func clusterStartTimes(startTimes []float64, gapThreshold float64) [][]float64 {
if len(startTimes) == 0 {
return nil
}

var clusters [][]float64
currentCluster := []float64{startTimes[0]}

for i := 1; i < len(startTimes); i++ {
gap := startTimes[i] - startTimes[i-1]
if gap <= gapThreshold {
// Same cluster
currentCluster = append(currentCluster, startTimes[i])
} else {
// New cluster
clusters = append(clusters, currentCluster)
currentCluster = []float64{startTimes[i]}
}
}
// Don't forget the last cluster
clusters = append(clusters, currentCluster)

return clusters
}

// predFileSpeciesKey groups detections by file and ebird code.
// Used by clusterDetections in calls_from_preds.go.
type predFileSpeciesKey struct {
File string
EbirdCode string
}

// clusterDetections groups detections into clusters and produces sorted ClusteredCalls.
func clusterDetections(detections map[predFileSpeciesKey][]float64, clipDuration, gapThreshold float64, minDetections int) ([]ClusteredCall, map[string]int) {
var allCalls []ClusteredCall
speciesCount := make(map[string]int)

for key, startTimes := range detections {
sort.Float64s(startTimes)

clusters := clusterStartTimes(startTimes, gapThreshold)

for _, cluster := range clusters {
if len(cluster) <= minDetections {
continue
}

call := ClusteredCall{
File: key.File,
StartTime: cluster[0],
EndTime: cluster[len(cluster)-1] + clipDuration,
EbirdCode: key.EbirdCode,
Segments: len(cluster),
}
allCalls = append(allCalls, call)
speciesCount[key.EbirdCode]++
edit in tools/calls/calls_from_common.go at line 450

[2.192607]

[2.192607]

sort.Slice(allCalls, func(i, j int) bool {
if allCalls[i].File != allCalls[j].File {
return allCalls[i].File < allCalls[j].File
}
return allCalls[i].StartTime < allCalls[j].StartTime
})

return allCalls, speciesCount
edit in me.txt at line 18

[6.726837]

[6.726837]

- Rename `tools/import/` → `tools/ingest/` and `package imp` → `package ingest`. High churn, low semantic gain. Consider only if the name starts causing confusion in daily work.