flan/winnow
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor: unify env var helpers and remove magic slice in cache

Browse Source 
- Add _getenv_num as shared core for _getenv_int/_getenv_float
- Add _getenv_optional_float for FRIGATE_SCORE_CEILING (replaces 9-line inline block)
- Add _getenv_bool; replace 11 inline .lower()-in-("true","1","yes") sites
  across config.py, jobs.py, and cli.py with single call site
- _resolve_strategy no-embedding branch: inline try/except → _getenv_int("LIMIT", 30)
- cache.py: final[:-4] → final.removesuffix(".npy") — assumption is now explicit
This commit is contained in:
flan
2026-06-15 02:10:00 +00:00
parent fe5e1574ac
commit de6804226d
6 changed files with 54 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CHANGELOG.md
+14
View File
@@ -7,6 +7,20 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
## [Unreleased]
## [0.5.16] - 2026-06-15
### Changed
- **`_getenv_int` and `_getenv_float` now share a single `_getenv_num` implementation**: the two helpers were structurally identical (read env var, return typed default if absent, try-cast, warn and return default on `ValueError`) with only the cast differing. Both are now thin wrappers around a private `_getenv_num(name, default, cast)`, eliminating the duplicated warning logic.
- **`FRIGATE_SCORE_CEILING` now uses `_getenv_optional_float`**: the previous 9-line inline block (`os.getenv("FRIGATE_SCORE_CEILING", "").strip()` + try/except) has been replaced with a new `_getenv_optional_float(name) -> float | None` helper that encapsulates the "empty-string means None, parse-error means None" semantics, making it consistent with the other numeric env var helpers.
- **Boolean env vars now use `_getenv_bool`**: the `.lower() in ("true", "1", "yes")` pattern was repeated across 11 sites in `config.py`, `jobs.py`, and `cli.py`. A new `_getenv_bool(name, default)` helper centralises the canonical truthy-string set; all sites have been updated to call it.
- **`_resolve_strategy` no-embedding branch uses `_getenv_int`**: the inline `int(custom_limit)` try/except block in `jobs.py` for the time-spread path has been replaced with `_getenv_int("LIMIT", 30)`, matching the pattern used in `config.py`. The smart-mode path retains its own try/except because its fallback is to the strategy map rather than to a numeric default.
- **`cache.py` tmp path uses `str.removesuffix`**: `final[:-4] + ".tmp.npy"` replaced with `final.removesuffix(".npy") + ".tmp.npy"` — the assumption that the cache path ends in `.npy` is now explicit and self-documenting rather than expressed as a magic numeric slice.
## [0.5.15] - 2026-06-15
### Fixed
pyproject.toml
+1 -1
View File
@@ -1,6 +1,6 @@
[project]
name = "winnow"
version = "0.5.15"
version = "0.5.16"
description = "Selects diverse, high-quality photos from Immich as training data for Frigate face recognition."
license = "AGPL-3.0-or-later"
requires-python = ">=3.13"
winnow/cache.py
+1 -1
View File
@@ -85,7 +85,7 @@ class EmbeddingCache:
final = self._path(asset_id, model)
# Insert .tmp before .npy so np.save doesn't auto-append another .npy extension
# (np.save appends .npy to paths that don't already end in .npy).
tmp = final[:-4] + ".tmp.npy"
tmp = final.removesuffix(".npy") + ".tmp.npy"
try:
np.save(tmp, embedding)
os.replace(tmp, final)
winnow/cli.py
+4 -4
View File
@@ -7,7 +7,7 @@ import sys
from rich import print as rprint
from rich.prompt import Confirm
from .config import Config
from .config import Config, _getenv_bool
from .executor import execute_jobs, upload_to_frigate
from .immich_api import get_immich_version, get_people, merge_people
from .jobs import _show_preview, auto_configure, interactive_configure
@@ -145,7 +145,7 @@ _UNSUPPORTED_VARS = [
def main() -> None:
"""Entry point for winnow CLI."""
try:
verbose = os.environ.get("VERBOSE", "").lower() in ("true", "1", "yes")
verbose = _getenv_bool("VERBOSE", False)
setup_logging(verbose=verbose)
trace_size = os.environ.get("TRACE_CROP_SIZE", "").strip()
@@ -232,8 +232,8 @@ def main() -> None:
# Auto mode when no TTY (Docker, cron, pipes) — the primary use case.
# A TTY means local interactive use; AUTO_MODE=true overrides that for scripting.
auto_mode = not sys.stdin.isatty() or os.environ.get("AUTO_MODE", "").lower() in ("true", "1", "yes")
dry_run = os.environ.get("DRY_RUN", "false").lower() in ("true", "1", "yes")
auto_mode = not sys.stdin.isatty() or _getenv_bool("AUTO_MODE", False)
dry_run = _getenv_bool("DRY_RUN", False)
if dry_run:
rprint("[bold yellow]DRY RUN — no images will be downloaded or uploaded[/bold yellow]")
winnow/config.py
+29 -22
View File
@@ -12,26 +12,41 @@ from rich.prompt import Prompt
_LEGACY_CONFIG_FILE = Path(".immich_config.json") # pre-v0.6: lived in process CWD, not on a volume
def _getenv_int(name: str, default: int) -> int:
def _getenv_num(name: str, default, cast):
raw = os.getenv(name)
if raw is None:
return default
try:
return int(raw)
return cast(raw)
except ValueError:
logging.warning("%s=%r is not a valid integer — using default %s", name, raw, default)
logging.warning("%s=%r is not a valid %s — using default %s", name, raw, cast.__name__, default)
return default
def _getenv_int(name: str, default: int) -> int:
return _getenv_num(name, default, int)
def _getenv_float(name: str, default: float) -> float:
raw = os.getenv(name)
if raw is None:
return default
return _getenv_num(name, default, float)
def _getenv_optional_float(name: str) -> float | None:
raw = os.getenv(name, "").strip()
if not raw:
return None
try:
return float(raw)
except ValueError:
logging.warning("%s=%r is not a valid float — using default %s", name, raw, default)
logging.warning("%s=%r is not a valid float — ignoring", name, raw)
return None
def _getenv_bool(name: str, default: bool) -> bool:
raw = os.getenv(name)
if raw is None:
return default
return raw.lower() in ("true", "1", "yes")
class _Config:
@@ -109,25 +124,17 @@ class _Config:
self.YEARS_FILTER = _getenv_int("YEARS_FILTER", 10)
self.MIN_FACE_WIDTH = _getenv_int("MIN_FACE_WIDTH", 90)
self.MIN_FACE_COUNT = _getenv_int("MIN_FACE_COUNT", 3)
self.MERGE_DUPLICATE_PEOPLE = os.getenv("MERGE_DUPLICATE_PEOPLE", "false").lower() in ("true", "1", "yes")
self.MERGE_DUPLICATE_PEOPLE = _getenv_bool("MERGE_DUPLICATE_PEOPLE", False)
self.BLUR_THRESHOLD = _getenv_float("BLUR_THRESHOLD", 120.0)
self.MIN_CONFIDENCE = _getenv_float("MIN_CONFIDENCE", 0.7)
self.MAX_AUTO_IMAGES = _getenv_int("MAX_AUTO_IMAGES", 20)
self.QUALITY_REPLACEMENT = os.getenv("QUALITY_REPLACEMENT", "true").lower() in ("true", "1", "yes")
_ceiling_env = os.getenv("FRIGATE_SCORE_CEILING", "").strip()
if _ceiling_env:
try:
self.FRIGATE_SCORE_CEILING = float(_ceiling_env)
except ValueError:
logging.warning("FRIGATE_SCORE_CEILING=%r is not a valid float — ignoring", _ceiling_env)
self.FRIGATE_SCORE_CEILING = None
else:
self.FRIGATE_SCORE_CEILING = None
self.ENABLE_FRIGATE_SCORES = os.getenv("ENABLE_FRIGATE_SCORES", "true").lower() in ("true", "1", "yes")
self.QUALITY_REPLACEMENT = _getenv_bool("QUALITY_REPLACEMENT", True)
self.FRIGATE_SCORE_CEILING = _getenv_optional_float("FRIGATE_SCORE_CEILING")
self.ENABLE_FRIGATE_SCORES = _getenv_bool("ENABLE_FRIGATE_SCORES", True)
self.FACE_MARGIN = _getenv_float("FACE_MARGIN", 0.15)
self.USE_FULL_RESOLUTION = os.getenv("USE_FULL_RESOLUTION", "true").lower() in ("true", "1", "yes")
self.ENABLE_FACE_ALIGNMENT = os.getenv("ENABLE_FACE_ALIGNMENT", "true").lower() in ("true", "1", "yes")
self.ENABLE_CACHE = os.getenv("ENABLE_CACHE", "true").lower() in ("true", "1", "yes")
self.USE_FULL_RESOLUTION = _getenv_bool("USE_FULL_RESOLUTION", True)
self.ENABLE_FACE_ALIGNMENT = _getenv_bool("ENABLE_FACE_ALIGNMENT", True)
self.ENABLE_CACHE = _getenv_bool("ENABLE_CACHE", True)
_data_dir = os.getenv("DATA_DIR")
_cache_dir_legacy = os.getenv("CACHE_DIR")
if _data_dir:
winnow/jobs.py
+5 -14
View File
@@ -8,7 +8,7 @@ from rich.progress import BarColumn, Progress, SpinnerColumn, TaskProgressColumn
from rich.prompt import Confirm, IntPrompt, Prompt
from rich.table import Table
from .config import Config
from .config import Config, _getenv_bool, _getenv_int
from .diversity import select_diverse_assets
from .embeddings import is_embedding_available, load_embedding_model
from .frigate_api import get_frigate_face_counts
@@ -65,19 +65,10 @@ def _get_strategy_choice(has_embedding: bool) -> tuple[int | str, str]:
def _resolve_strategy(strategy: str, has_embedding: bool) -> tuple[int | str, str]:
"""Resolve env var strategy to (limit, selection_mode) without prompts."""
custom_limit = os.environ.get("LIMIT", "").strip()
if not has_embedding:
if custom_limit:
try:
limit = int(custom_limit)
except ValueError:
logger.warning("LIMIT=%r is not a valid integer — using default 30", custom_limit)
limit = 30
else:
limit = 30
return limit, "time"
return _getenv_int("LIMIT", 30), "time"
custom_limit = os.environ.get("LIMIT", "").strip()
if custom_limit:
try:
return int(custom_limit), "smart"
@@ -168,7 +159,7 @@ def _configure_person(person: dict, people: list[dict]) -> dict | None:
rprint(f" Found [bold]{total_raw}[/bold] total, [bold]{len(recent_assets)}[/bold] in range ({years} years).")
# Ask before strategy so the post-dedup count can inform the choice
retry_env = os.environ.get("RETRY_REJECTED", "false").lower() in ("true", "1", "yes")
retry_env = _getenv_bool("RETRY_REJECTED", False)
retry_rejected = Confirm.ask("Include previously rejected images?", default=retry_env)
before_dedup = len(recent_assets)
@@ -317,7 +308,7 @@ def auto_configure(people: list[dict]) -> list[dict]:
if selection_mode == "skip":
continue
retry_rejected = os.environ.get("RETRY_REJECTED", "false").lower() in ("true", "1", "yes")
retry_rejected = _getenv_bool("RETRY_REJECTED", False)
before_dedup = len(recent_assets)
new_asset_ids = set(filter_already_uploaded([a["id"] for a in recent_assets], retry_rejected=retry_rejected))
recent_assets = [a for a in recent_assets if a["id"] in new_asset_ids]