refactor(watcher): extract register_new_files for targeted ingest
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Cameron CordesandClaude Opus 5.5 authored and 
cameron committed
1 parent
7b1d252e75
commit
21920e8608
1 file changed
+130
-113
+130
-113
@@ -740,6 +740,135 @@ pub fn playlist_needs_generation(video_path: &Path, playlist_path: &Path) -> boo
|
||||
true
|
||||
}
|
||||
|
||||
/// Register files in `image_exif` (hash, perceptual hashes, EXIF, resolved
|
||||
/// date). Returns the `(absolute, rel_path)` pairs whose row was written.
|
||||
/// Shared by the watcher tick and the targeted ingest after an Enhance
|
||||
/// approval (#192).
|
||||
pub fn register_new_files(
|
||||
library: &libraries::Library,
|
||||
files_needing_row: Vec<(PathBuf, String)>,
|
||||
exif_dao: &Arc<Mutex<Box<dyn ExifDao>>>,
|
||||
) -> Vec<(PathBuf, String)> {
|
||||
let mut newly_registered: Vec<(PathBuf, String)> = Vec::new();
|
||||
if files_needing_row.is_empty() {
|
||||
return newly_registered;
|
||||
}
|
||||
info!(
|
||||
"Registering {} new files in image_exif",
|
||||
files_needing_row.len()
|
||||
);
|
||||
|
||||
for (file_path, relative_path) in files_needing_row {
|
||||
let registered_file = (file_path.clone(), relative_path.clone());
|
||||
let timestamp = Utc::now().timestamp();
|
||||
|
||||
// Hash + size from filesystem metadata — always attempted so
|
||||
// every file gets a content_hash, even when EXIF is absent.
|
||||
let (content_hash, size_bytes) = match content_hash::compute(&file_path) {
|
||||
Ok(id) => (Some(id.content_hash), Some(id.size_bytes)),
|
||||
Err(e) => {
|
||||
warn!("Failed to hash {}: {:?}", file_path.display(), e);
|
||||
(None, None)
|
||||
}
|
||||
};
|
||||
|
||||
// Perceptual hashes (pHash + dHash). Best-effort — None for
|
||||
// videos and decode failures. Drives near-duplicate detection
|
||||
// in the Apollo duplicates surface; failure here is non-fatal
|
||||
// and never blocks indexing.
|
||||
let perceptual = perceptual_hash::compute(&file_path);
|
||||
|
||||
// EXIF is best-effort enrichment. When extraction fails (or the
|
||||
// file type doesn't support EXIF) we still store a row with all
|
||||
// EXIF fields NULL; the file remains visible to sort-by-date
|
||||
// and tag queries via its rel_path and filesystem timestamps.
|
||||
let exif_fields = if exif::supports_exif(&file_path) {
|
||||
match exif::extract_exif_from_path(&file_path) {
|
||||
Ok(data) => Some(data),
|
||||
Err(e) => {
|
||||
debug!(
|
||||
"No EXIF or parse error for {}: {:?}",
|
||||
file_path.display(),
|
||||
e
|
||||
);
|
||||
None
|
||||
}
|
||||
}
|
||||
} else {
|
||||
None
|
||||
};
|
||||
|
||||
// Canonical date_taken via the waterfall — kamadak-exif (already
|
||||
// computed above) → exiftool fallback for videos / MakerNote /
|
||||
// QuickTime → filename regex → earliest_fs_time. Source is
|
||||
// recorded so the per-tick backfill drain can re-run weak
|
||||
// resolutions later. The EXIF branch additionally runs the
|
||||
// camera-offset cascade to produce the new-contract columns
|
||||
// (date_utc / camera_offset_minutes / date_taken_tz_source,
|
||||
// ADR-0001) while the legacy date_taken stays byte-identical.
|
||||
let resolved_date = date_resolver::resolve_date_taken(
|
||||
&file_path,
|
||||
exif_fields
|
||||
.as_ref()
|
||||
.and_then(date_resolver::exif_prior_from)
|
||||
.as_ref(),
|
||||
);
|
||||
|
||||
let insert_exif = InsertImageExif {
|
||||
library_id: library.id,
|
||||
file_path: relative_path.clone(),
|
||||
camera_make: exif_fields.as_ref().and_then(|e| e.camera_make.clone()),
|
||||
camera_model: exif_fields.as_ref().and_then(|e| e.camera_model.clone()),
|
||||
lens_model: exif_fields.as_ref().and_then(|e| e.lens_model.clone()),
|
||||
width: exif_fields.as_ref().and_then(|e| e.width),
|
||||
height: exif_fields.as_ref().and_then(|e| e.height),
|
||||
orientation: exif_fields.as_ref().and_then(|e| e.orientation),
|
||||
gps_latitude: exif_fields
|
||||
.as_ref()
|
||||
.and_then(|e| e.gps_latitude.map(|v| v as f32)),
|
||||
gps_longitude: exif_fields
|
||||
.as_ref()
|
||||
.and_then(|e| e.gps_longitude.map(|v| v as f32)),
|
||||
gps_altitude: exif_fields
|
||||
.as_ref()
|
||||
.and_then(|e| e.gps_altitude.map(|v| v as f32)),
|
||||
focal_length: exif_fields
|
||||
.as_ref()
|
||||
.and_then(|e| e.focal_length.map(|v| v as f32)),
|
||||
aperture: exif_fields
|
||||
.as_ref()
|
||||
.and_then(|e| e.aperture.map(|v| v as f32)),
|
||||
shutter_speed: exif_fields.as_ref().and_then(|e| e.shutter_speed.clone()),
|
||||
iso: exif_fields.as_ref().and_then(|e| e.iso),
|
||||
date_taken: resolved_date.map(|r| r.timestamp),
|
||||
created_time: timestamp,
|
||||
last_modified: timestamp,
|
||||
content_hash,
|
||||
size_bytes,
|
||||
phash_64: perceptual.map(|h| h.phash_64),
|
||||
dhash_64: perceptual.map(|h| h.dhash_64),
|
||||
date_taken_source: resolved_date.map(|r| r.source.as_str().to_string()),
|
||||
date_utc: resolved_date.and_then(|r| r.date_utc),
|
||||
camera_offset_minutes: resolved_date.and_then(|r| r.camera_offset_minutes),
|
||||
date_taken_tz_source: resolved_date
|
||||
.and_then(|r| r.tz_source)
|
||||
.map(|t| t.as_str().to_string()),
|
||||
};
|
||||
|
||||
let mut dao = exif_dao.lock().expect("Unable to lock ExifDao");
|
||||
if let Err(e) = dao.store_exif(insert_exif) {
|
||||
error!(
|
||||
"Failed to register {} in image_exif: {:?}",
|
||||
relative_path, e
|
||||
);
|
||||
} else {
|
||||
debug!("Registered {} in image_exif", relative_path);
|
||||
newly_registered.push(registered_file);
|
||||
}
|
||||
}
|
||||
newly_registered
|
||||
}
|
||||
|
||||
pub fn process_new_files(
|
||||
library: &libraries::Library,
|
||||
exif_dao: Arc<Mutex<Box<dyn ExifDao>>>,
|
||||
@@ -834,119 +963,7 @@ pub fn process_new_files(
|
||||
}
|
||||
|
||||
if !files_needing_row.is_empty() {
|
||||
info!(
|
||||
"Registering {} new files in image_exif",
|
||||
files_needing_row.len()
|
||||
);
|
||||
|
||||
for (file_path, relative_path) in files_needing_row {
|
||||
let registered_file = (file_path.clone(), relative_path.clone());
|
||||
let timestamp = Utc::now().timestamp();
|
||||
|
||||
// Hash + size from filesystem metadata — always attempted so
|
||||
// every file gets a content_hash, even when EXIF is absent.
|
||||
let (content_hash, size_bytes) = match content_hash::compute(&file_path) {
|
||||
Ok(id) => (Some(id.content_hash), Some(id.size_bytes)),
|
||||
Err(e) => {
|
||||
warn!("Failed to hash {}: {:?}", file_path.display(), e);
|
||||
(None, None)
|
||||
}
|
||||
};
|
||||
|
||||
// Perceptual hashes (pHash + dHash). Best-effort — None for
|
||||
// videos and decode failures. Drives near-duplicate detection
|
||||
// in the Apollo duplicates surface; failure here is non-fatal
|
||||
// and never blocks indexing.
|
||||
let perceptual = perceptual_hash::compute(&file_path);
|
||||
|
||||
// EXIF is best-effort enrichment. When extraction fails (or the
|
||||
// file type doesn't support EXIF) we still store a row with all
|
||||
// EXIF fields NULL; the file remains visible to sort-by-date
|
||||
// and tag queries via its rel_path and filesystem timestamps.
|
||||
let exif_fields = if exif::supports_exif(&file_path) {
|
||||
match exif::extract_exif_from_path(&file_path) {
|
||||
Ok(data) => Some(data),
|
||||
Err(e) => {
|
||||
debug!(
|
||||
"No EXIF or parse error for {}: {:?}",
|
||||
file_path.display(),
|
||||
e
|
||||
);
|
||||
None
|
||||
}
|
||||
}
|
||||
} else {
|
||||
None
|
||||
};
|
||||
|
||||
// Canonical date_taken via the waterfall — kamadak-exif (already
|
||||
// computed above) → exiftool fallback for videos / MakerNote /
|
||||
// QuickTime → filename regex → earliest_fs_time. Source is
|
||||
// recorded so the per-tick backfill drain can re-run weak
|
||||
// resolutions later. The EXIF branch additionally runs the
|
||||
// camera-offset cascade to produce the new-contract columns
|
||||
// (date_utc / camera_offset_minutes / date_taken_tz_source,
|
||||
// ADR-0001) while the legacy date_taken stays byte-identical.
|
||||
let resolved_date = date_resolver::resolve_date_taken(
|
||||
&file_path,
|
||||
exif_fields
|
||||
.as_ref()
|
||||
.and_then(date_resolver::exif_prior_from)
|
||||
.as_ref(),
|
||||
);
|
||||
|
||||
let insert_exif = InsertImageExif {
|
||||
library_id: library.id,
|
||||
file_path: relative_path.clone(),
|
||||
camera_make: exif_fields.as_ref().and_then(|e| e.camera_make.clone()),
|
||||
camera_model: exif_fields.as_ref().and_then(|e| e.camera_model.clone()),
|
||||
lens_model: exif_fields.as_ref().and_then(|e| e.lens_model.clone()),
|
||||
width: exif_fields.as_ref().and_then(|e| e.width),
|
||||
height: exif_fields.as_ref().and_then(|e| e.height),
|
||||
orientation: exif_fields.as_ref().and_then(|e| e.orientation),
|
||||
gps_latitude: exif_fields
|
||||
.as_ref()
|
||||
.and_then(|e| e.gps_latitude.map(|v| v as f32)),
|
||||
gps_longitude: exif_fields
|
||||
.as_ref()
|
||||
.and_then(|e| e.gps_longitude.map(|v| v as f32)),
|
||||
gps_altitude: exif_fields
|
||||
.as_ref()
|
||||
.and_then(|e| e.gps_altitude.map(|v| v as f32)),
|
||||
focal_length: exif_fields
|
||||
.as_ref()
|
||||
.and_then(|e| e.focal_length.map(|v| v as f32)),
|
||||
aperture: exif_fields
|
||||
.as_ref()
|
||||
.and_then(|e| e.aperture.map(|v| v as f32)),
|
||||
shutter_speed: exif_fields.as_ref().and_then(|e| e.shutter_speed.clone()),
|
||||
iso: exif_fields.as_ref().and_then(|e| e.iso),
|
||||
date_taken: resolved_date.map(|r| r.timestamp),
|
||||
created_time: timestamp,
|
||||
last_modified: timestamp,
|
||||
content_hash,
|
||||
size_bytes,
|
||||
phash_64: perceptual.map(|h| h.phash_64),
|
||||
dhash_64: perceptual.map(|h| h.dhash_64),
|
||||
date_taken_source: resolved_date.map(|r| r.source.as_str().to_string()),
|
||||
date_utc: resolved_date.and_then(|r| r.date_utc),
|
||||
camera_offset_minutes: resolved_date.and_then(|r| r.camera_offset_minutes),
|
||||
date_taken_tz_source: resolved_date
|
||||
.and_then(|r| r.tz_source)
|
||||
.map(|t| t.as_str().to_string()),
|
||||
};
|
||||
|
||||
let mut dao = exif_dao.lock().expect("Unable to lock ExifDao");
|
||||
if let Err(e) = dao.store_exif(insert_exif) {
|
||||
error!(
|
||||
"Failed to register {} in image_exif: {:?}",
|
||||
relative_path, e
|
||||
);
|
||||
} else {
|
||||
debug!("Registered {} in image_exif", relative_path);
|
||||
newly_registered.push(registered_file);
|
||||
}
|
||||
}
|
||||
newly_registered = register_new_files(library, files_needing_row, &exif_dao);
|
||||
}
|
||||
|
||||
// ── Photo versions (#191) ──────────────────────────────────────────
|
||||
|
||||
Reference in new issue
Block a user