docs: compress prose/module docstrings, em-dash->hyphen (de-bloat wave 1)

Signed-off-by: disqualifier <dev@disqualifier.me>
This commit is contained in:
2026-07-03 00:32:56 -04:00
parent 93994da9d6
commit 4d1acc3a47
6 changed files with 107 additions and 182 deletions
+2 -2
View File
@@ -13,12 +13,12 @@ and emit; their records flow into the handlers `log_setup` wired.
## Install
```
log_setup @ git+ssh://git@git.rethinkstudios.io/rethink-public/log_setup.git@v0.6.0
log_setup @ git+ssh://git@git.rethinkstudios.io/rethink-public/log_setup.git@v0.6.1
```
No dependencies — stdlib only.
Drop the `@v0.6.0` suffix from the line above to install the latest unpinned.
Drop the `@v0.6.1` suffix from the line above to install the latest unpinned.
## Quick start
+1 -1
View File
@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
[project]
name = "log_setup"
version = "0.6.0"
version = "0.6.1"
description = "stdlib app-entry-point logging setup: live run.log, rotation, gzip, retention, consistent format"
requires-python = ">=3.10"
dependencies = []
+3 -9
View File
@@ -1,8 +1,4 @@
"""log_setup app-entry-point logging configuration (sync, stdlib only).
call once at an application's entry point to configure the whole process: a live
run.log, rotation (daily/size/on_start), gzip of rolled files, retention, optional
console output, and a consistent `time | module | level | message` format.
"""log_setup - app-entry-point logging configuration (sync, stdlib only). see README.
from log_setup import setup_logging
@@ -10,13 +6,11 @@ console output, and a consistent `time | module | level | message` format.
log = logging.getLogger(__name__)
log.info("up") # -> run.log (add console=True for stdout too)
reusable libraries do NOT call this they only `logging.getLogger(__name__)` and
emit; the application owns this setup. shipping logs to a backend is out of scope
(that's Promtail's job against the produced files).
reusable libraries do NOT call this; the application owns setup, libraries only emit.
"""
from .setup import setup_logging
__all__ = ["setup_logging"]
__version__ = "0.6.0"
__version__ = "0.6.1"
+11 -18
View File
@@ -1,10 +1,8 @@
"""log formats for the app-wide setup: human-readable text + structured JSON lines.
two output formats, two proven needs. `text` (default) is the human `tail -f` format
(`time | module | level | message`, local time). `json` is the Grafana/Loki path
one JSON object per line (JSON Lines), fields parsed into labels natively, UTC
timestamps so logs aggregated from many machines/containers sort unambiguously.
`%(name)s` is the getLogger name the emitting module used, so each module shows.
`text` (default) is the human `tail -f` format (`time | module | level | message`,
local time). `json` is the Grafana/Loki path - one JSON object per line, UTC
timestamps so logs aggregated from many machines sort unambiguously. see README.
"""
import datetime
@@ -15,7 +13,7 @@ DEFAULT_FORMAT = "%(asctime)s | %(name)s | %(levelname)s | %(message)s"
DEFAULT_DATEFMT = "%Y-%m-%d %H:%M:%S"
_RESERVED = frozenset(vars(logging.makeLogRecord({})).keys()) | {"message", "asctime"}
# this formatter's own canonical output keys stdlib's LogRecord rejects `extra` keys
# this formatter's own canonical output keys - stdlib's LogRecord rejects `extra` keys
# colliding with real attribute names (e.g. `module`), but `time`/`level`/`ts` are NOT
# LogRecord attrs, so a caller's extra={"time":...}/{"ts":...} would otherwise overwrite
# the UTC timestamp / epoch. guard them explicitly
@@ -26,14 +24,10 @@ class JsonLinesFormatter(logging.Formatter):
"""format each record as a single-line JSON object (JSON Lines / .jsonl)
emits at minimum time/ts/level/module/message. `time` is UTC ISO-8601 with a `Z`
suffix (e.g. 2026-06-28T14:03:11Z); `ts` (added v0.6.0) is the same instant as a
unix epoch int (`int(record.created)`, second resolution) for a consumer that wants
a sortable number instead of parsing the ISO string — both sort unambiguously
across machines/containers; Grafana converts to local for display. any field
passed via logging `extra={...}` lands as a top-level JSON field (how a caller
stamps monitor/service/request-id for Loki labels without the lib knowing those
domain concepts). a traceback (exc_info) is rendered into an `exc_info` string
field rather than dropped.
suffix; `ts` is the same instant as a unix epoch int, both sortable across
machines/containers. any field passed via logging `extra={...}` lands as a
top-level JSON field. a traceback (exc_info) is rendered into an `exc_info`
string field rather than dropped.
"""
def format(self, record: logging.LogRecord) -> str:
@@ -49,8 +43,7 @@ class JsonLinesFormatter(logging.Formatter):
if key not in _RESERVED and key not in _OUTPUT_KEYS and not key.startswith("_"):
payload[key] = value
if record.exc_info:
# cache the rendered traceback on the record (as stdlib Formatter does) so a
# second handler/format() of the same record doesn't re-render it
# cache the rendered traceback on the record, like stdlib Formatter does
if not record.exc_text:
record.exc_text = self.formatException(record.exc_info)
payload["exc_info"] = record.exc_text
@@ -66,9 +59,9 @@ def build_formatter(output: str = "text", fmt=None, datefmt=None) -> logging.For
`output="text"` (default) returns the human-readable text formatter, honoring
the raw `fmt`/`datefmt` format-string overrides. `output="json"` returns the
structured `JsonLinesFormatter` (which ignores `fmt`/`datefmt` it builds
structured `JsonLinesFormatter` (which ignores `fmt`/`datefmt` - it builds
fields, not a format string). an unrecognized `output` falls back to text and
warns, never raising a bad format arg must not take the app down.
warns, never raising - a bad format arg must not take the app down.
"""
if output == "json":
return JsonLinesFormatter()
+46 -63
View File
@@ -5,11 +5,12 @@ the namer/rotator so rolled files land in `log_dir` and are gzipped when asked,
the live file at its stable path, and handle the on-start and prune paths the handlers
don't manage themselves.
gzip writes are crash-safe: `_gzip_file` writes to a `.tmp` sibling and atomically
`os.replace`s it onto the final `.gz` path, so a crash/OOM/power-loss mid-write never
leaves a truncated `.gz` where retention would trust it. `retier`'s plain/gz dedupe
additionally verifies a `.gz` decompresses cleanly (`_gz_intact`) before removing its
plain twin, so a corrupt `.gz` is never preferred over an intact plain copy.
FOOTGUN: gzip writes are crash-safe - `_gzip_file` writes to a `.tmp` sibling and
atomically `os.replace`s it onto the final `.gz` path, so a crash/OOM/power-loss
mid-write never leaves a truncated `.gz` where retention would trust it. `retier`'s
plain/gz dedupe additionally verifies a `.gz` decompresses cleanly (`_gz_intact`)
before removing its plain twin, so a corrupt `.gz` is never preferred over an intact
plain copy.
"""
import gzip
@@ -22,13 +23,10 @@ from typing import Callable, Optional, Tuple
def _move(source: str, dest: str) -> None:
"""rename source to dest, falling back to copy+unlink across filesystems
os.replace is atomic but raises OSError(EXDEV) across filesystems the container
bind-mount / separate-logs-volume case this lib targets. falls back to shutil.move
(copy+unlink) so the roll still lands instead of failing rotation silently.
precondition: `dest` is a free, non-directory path (every call site generates a
unique timestamped/dated dest) — not safe for arbitrary dests that may already
exist as a directory.
FOOTGUN: os.replace is atomic but raises OSError(EXDEV) across filesystems (the
container bind-mount / separate-logs-volume case) - falls back to shutil.move so
the roll still lands instead of failing rotation silently. precondition: `dest` is
a free, non-directory path.
"""
try:
os.replace(source, dest)
@@ -39,9 +37,8 @@ def _move(source: str, dest: str) -> None:
def _free_dest(dest: str) -> str:
"""return `dest`, or a `.N`-suffixed variant if it (or its .gz twin) already exists
used by the tiered rotator so a second roll landing on the same dated/stamped name
(two daily rolls in one day) doesn't clobber the earlier file. checks both the plain
and .gz forms of each candidate.
used by the tiered rotator so a second same-stamp roll doesn't clobber the earlier
file; checks both the plain and .gz forms of each candidate.
"""
if not os.path.exists(dest) and not os.path.exists(dest + ".gz"):
return dest
@@ -56,14 +53,14 @@ def _free_dest(dest: str) -> str:
def _gzip_file(source: str, dest: str) -> None:
"""gzip source into dest then remove source (the rolled-file compression idiom)
writes to `dest + ".tmp"` and atomically `os.replace`s it onto `dest` once
complete, so a crash/OOM/power-loss mid-write never leaves a truncated `.gz` at
`dest` the partial write stays quarantined in `.tmp` and source is untouched
(safe to retry).
FOOTGUN (crash-safe): writes to `dest + ".tmp"` and atomically `os.replace`s it
onto `dest` once complete, so a crash/OOM/power-loss mid-write never leaves a
truncated `.gz` at `dest` - the partial write stays quarantined in `.tmp` and
source is untouched (safe to retry).
the source mtime is carried onto dest so a file keeps its tier position when it
crosses the plain->gz boundary — retier ranks by mtime, and a fresh write would
otherwise make a just-compressed file look newest and reshuffle tiers.
crosses the plain->gz boundary - a fresh write would otherwise make a
just-compressed file look newest and reshuffle tiers.
"""
mtime = _safe_mtime(source)
tmp_dest = dest + ".tmp"
@@ -88,9 +85,8 @@ def _gz_intact(path: str) -> bool:
"""return True if the gzip file at path decompresses cleanly end to end
belt-and-suspenders check before a dedupe site removes a plain twin in favor of its
.gz a truncated/corrupt .gz must never be trusted over an intact plain copy. reads
the whole stream (gzip.open only validates end-of-stream on a full read); any
failure is treated as "not intact" so the caller keeps the plain source.
.gz - a corrupt .gz must never be trusted over an intact plain copy. reads the
whole stream; any failure means "not intact" so the caller keeps the plain source.
"""
try:
with gzip.open(path, "rb") as handle:
@@ -121,8 +117,8 @@ def make_history_namer(
"""namer minting historic rolled files `<stem>.<Y-m-d_H-M-S>.log[.gz]` in log_dir
used by size and daily (and their tiered variants). `stem` is the HISTORY stem (the
project namespace), independent of the live file's name. FOOTGUN: prune/retier must
glob this same stem or nothing matches and retention silently never fires.
project namespace), independent of the live file's name. FOOTGUN: prune/retier's
`stem` must match this one or nothing matches and retention silently never fires.
ignores the stdlib handler's own rolled name (`.N` for size, `.log.<date>` for
daily) in favor of a uniform timestamped name so all modes converge on one shape
@@ -151,15 +147,15 @@ def make_rotator(
"""rotator: move (or gzip) the source live file to the destination rolled path
legacy mode (default): gzip on roll when `compress`, then prune `log_dir` to
`backup_count` newest rolled files the stdlib handler's own retention only scans
`backup_count` newest rolled files - the stdlib handler's own retention only scans
the live file's directory, so it never sees files redirected into `log_dir`; pruning
here is what bounds retention for daily/size. FOOTGUN: `backup_count <= 0` means
"keep no rolled history", but `prune()` itself no-ops at `<= 0` (its own sentinel for
"don't touch history") so a zero-retention roll is deleted by the rotator directly
"don't touch history") - so a zero-retention roll is deleted by the rotator directly
right after landing, rather than relying on prune to do it.
tiered mode (when `keep_uncompressed`/`keep_compressed` are given): land the rolled
file PLAIN and re-tier `log_dir` newest `keep_uncompressed` stay uncompressed, next
file PLAIN and re-tier `log_dir` - newest `keep_uncompressed` stay uncompressed, next
`keep_compressed` gzipped, rest deleted. `compress`/`backup_count` are ignored.
"""
tiered = keep_uncompressed is not None or keep_compressed is not None
@@ -168,10 +164,8 @@ def make_rotator(
if not os.path.exists(source):
return
if tiered:
# dest carries the namer's .gz suffix in compress mode; strip it so the roll
# lands plain and retier decides its tier. disambiguate a dest that already
# exists (a second same-interval daily roll reuses the same dated name) with
# a counter, checking both .log and .log.gz forms.
# strip the namer's .gz suffix so the roll lands plain and retier decides
# its tier; disambiguate a same-interval collision via _free_dest
plain_dest = _free_dest(dest[:-3] if dest.endswith(".gz") else dest)
_move(source, plain_dest)
if log_dir is not None and prune_stem is not None:
@@ -207,7 +201,7 @@ def rotate_on_start(
tiered mode (`keep_uncompressed`/`keep_compressed` given): the rolled file always
lands PLAIN (so it can occupy the newest uncompressed tier) and `retier` decides
compression/deletion across the whole stem `compress` is ignored here.
compression/deletion across the whole stem - `compress` is ignored here.
"""
if not os.path.exists(live_path):
return
@@ -217,11 +211,9 @@ def rotate_on_start(
stamp = time.strftime("%Y-%m-%d_%H-%M-%S", clock())
suffix = ".log.gz" if (compress and not tiered) else ".log"
# the 1-second stamp resolution means two starts in the same second collide;
# disambiguate with a counter so a rapid crash-restart loop doesn't lose the
# earlier roll. check BOTH .log and .log.gz forms: in tiered mode an earlier
# same-stamp roll may already be compressed, and reusing its bare stem would
# create a second file for the same logical roll and break the tier counts
# a 1-second stamp collision (rapid crash-restart) is disambiguated with a
# counter; check BOTH .log and .log.gz since a tiered same-stamp roll may
# already be compressed
def _taken(path: str) -> bool:
base = path[:-3] if path.endswith(".gz") else path
return os.path.exists(base) or os.path.exists(base + ".gz")
@@ -248,7 +240,7 @@ def retier(log_dir: str, stem: str, keep_uncompressed: int, keep_compressed: int
fail-soft per file (skip on OSError) so retention never crashes setup.
FOOTGUN: `stem` is reduced to its basename to match how rolled files land in
log_dir (namer/rotate_on_start basename them) a `name` containing a directory
log_dir (namer/rotate_on_start basename them) - a `name` containing a directory
(e.g. "sub/run") must be matched by "run." here or nothing matches and retention
silently never fires (unbounded pileup).
@@ -266,10 +258,8 @@ def retier(log_dir: str, stem: str, keep_uncompressed: int, keep_compressed: int
return
entries = [os.path.join(log_dir, name) for name in names]
# dedupe plain/gz twins FIRST (a crash between _gzip_file's write and its os.remove
# can leave <x>.log beside <x>.log.gz) so the phantom twin never occupies a
# retention slot and evicts a distinct older roll — but ONLY once the .gz is
# verified to decompress cleanly (_gz_intact): a pre-existing corrupt .gz must never
# win over an intact plain copy, which would delete the only good copy.
# can leave <x>.log beside <x>.log.gz), but ONLY once the .gz is verified intact -
# a pre-existing corrupt .gz must never win over an intact plain copy
present = set(entries)
kept = []
for p in entries:
@@ -278,13 +268,12 @@ def retier(log_dir: str, stem: str, keep_uncompressed: int, keep_compressed: int
try:
os.remove(p)
except OSError:
kept.append(p) # couldn't remove keep it in the accounting
kept.append(p) # couldn't remove - keep it in the accounting
continue
# .gz twin is corrupt keep the intact plain untouched; a later retier
# retries the compress once it's re-gzipped cleanly
# .gz twin is corrupt - keep the intact plain, a later retier retries
kept.append(p)
files = [(p, _safe_mtime(p), _roll_counter(p)) for p in kept if os.path.isfile(p)]
# newest-first: higher mtime first, tied second broken by higher roll counter (later)
# newest-first: higher mtime first, ties broken by higher (later) roll counter
files.sort(key=lambda t: (t[1], t[2]), reverse=True)
keep = keep_uncompressed + keep_compressed
@@ -297,17 +286,14 @@ def retier(log_dir: str, stem: str, keep_uncompressed: int, keep_compressed: int
elif index >= keep_uncompressed and not path.endswith(".gz"):
dest = path + ".gz"
if os.path.exists(dest):
# a crash between _gzip_file's write and its os.remove can leave a plain
# source beside a fresh .gz — drop the redundant plain twin, but ONLY
# once the .gz is verified intact (a corrupt .gz must never win)
# drop the redundant plain twin, but ONLY once the .gz is intact
if _gz_intact(dest):
try:
os.remove(path)
except OSError:
pass
continue
# .gz is corrupt fall through and re-gzip the plain over the bad dest
# (atomic write replaces it only once a valid archive exists)
# .gz is corrupt - fall through and re-gzip the plain over the bad dest
try:
_gzip_file(path, dest)
except OSError:
@@ -318,12 +304,9 @@ def _roll_counter(path: str) -> int:
"""parse the same-second disambiguation counter out of a rolled filename
only the on_start / size-namer shape carries a counter: `<stem>.<stamp>[.<counter>].log`
(optionally `.gz`), where a colliding same-second roll gets `.1`, `.2`, ... and a higher
counter is the later (newer) roll. the first roll of a second has no counter (0).
daily's dated names (`<stem>.log.<Y-m-d>`) do NOT end in `.log` and are second+-granular
(distinct mtimes), so they never need the counter tie-break — return 0 for them rather
than misparsing the trailing date component as a counter.
(optionally `.gz`); a higher counter is the later roll, first roll of a second is 0.
daily's dated names (`<stem>.log.<Y-m-d>`) don't end in `.log`, so they never need
the tie-break - return 0 rather than misparsing the trailing date as a counter.
"""
base = path[:-3] if path.endswith(".gz") else path
if not base.endswith(".log"):
@@ -337,11 +320,11 @@ def prune(log_dir: str, stem: str, backup_count: int) -> None:
"""keep only the newest `backup_count` rolled files for a given stem in log_dir
matches files beginning with `<stem>.` (e.g. run.*), sorted newest-first by mtime
then roll counter (mirrors retier's ordering see _roll_counter), deleting the
then roll counter (mirrors retier's ordering, see _roll_counter), deleting the
oldest beyond the count. used for on_start, which the handlers don't auto-prune.
FOOTGUN: `stem` is reduced to its basename so a `name` containing a directory (e.g.
"sub/run") still matches the basenamed rolled files in log_dir else nothing
"sub/run") still matches the basenamed rolled files in log_dir - else nothing
matches and old files pile up forever.
"""
if backup_count <= 0:
@@ -380,9 +363,9 @@ def attach_rolling(
) -> Tuple[Callable, Callable]:
"""wire the custom namer + rotator onto a rotating handler; return them
rolled files are named off `prune_stem` (the HISTORY stem the project namespace),
rolled files are named off `prune_stem` (the HISTORY stem - the project namespace),
independent of the live file name, via make_history_namer: `<stem>.<stamp>.log[.gz]`
uniform across size and daily replacing the stdlib handler's own rolled-name
uniform across size and daily - replacing the stdlib handler's own rolled-name
scheme (`.N` for size, `.log.<date>` for daily), which can't inject a project stem
and (for size) can't be managed once files are redirected into log_dir.
+44 -89
View File
@@ -1,15 +1,13 @@
"""app-entry-point logging setup (sync, stdlib only).
"""app-entry-point logging setup (sync, stdlib only). see README.
`setup_logging` configures the root logger once for the whole process: a live
run.log at a stable path, rotation (daily/size/on_start/none) into a logs/ dir, gzip
of rolled files, retention, console output, and a consistent format. called by the
APPLICATION, not by reusable libraries (those stay emit-only). idempotent (no
duplicate handlers on repeat calls), never crashes the app over logging, and can
route through a background queue so an async event loop doesn't block on file I/O.
`setup_logging` configures the root logger once for the whole process. called by the
APPLICATION, not by reusable libraries (those stay emit-only). idempotent, never
crashes the app over logging, and can route through a background queue so an async
event loop doesn't block on file I/O.
`rotate="size"` always bounds the live file: the roll fires at `max_bytes` regardless
of `backup_count`, including `backup_count=0` (means "keep zero rolled files", not
"never roll" each roll is deleted right after landing).
"never roll" - each roll is deleted right after landing).
"""
import atexit
@@ -32,21 +30,12 @@ _atexit_registered = False
def _exc_text() -> str:
"""render sys.exc_info() as text, for capturing a traceback into a buffered warning
(log.warning(..., exc_info=True) only works logged live from the except block; setup
warnings are deferred, see _flush_warnings, so render eagerly instead)
"""
"""render sys.exc_info() as text, for capturing a traceback into a buffered warning"""
return "".join(traceback.format_exception(*sys.exc_info())).strip()
def _flush_warnings(warnings: list) -> None:
"""emit buffered setup-time warnings now that handlers are attached
setup-time warnings fire before this call's handlers exist, so logging them
immediately would only reach stderr (logging's lastResort) and never the file being
configured — buffer, then flush once attached so they land like any other record
"""
"""emit buffered setup-time warnings now that handlers are attached"""
for message, *args in warnings:
log.warning(message, *args)
@@ -54,25 +43,19 @@ def _flush_warnings(warnings: list) -> None:
def _level_value(level: Union[int, str]) -> int:
"""coerce a level name or int to a logging level int (defaults to INFO)"""
if isinstance(level, bool):
# bool is an int subclass (True==1, below DEBUG) but is never a real level
# reject it consistently with the per-module path rather than set level 1
# bool is an int subclass (True==1, below DEBUG) but never a real level
return logging.INFO
if isinstance(level, int):
return level
if not isinstance(level, str):
return logging.INFO
resolved = logging.getLevelName(level.upper())
# getLevelName returns the string "Level XXX" for an unknown name, which
# setLevel then rejects — never crash the app over a bad level, fall back to INFO
# getLevelName returns "Level XXX" for an unknown name; fall back to INFO
return resolved if isinstance(resolved, int) else logging.INFO
def _strict_level_value(level: Union[int, str]) -> Optional[int]:
"""coerce a level name or int to a logging level int, or None if invalid
unlike `_level_value` (falls back to INFO for the root `level`), reports invalid as
None so the per-module path can skip + warn instead of silently applying INFO
"""
"""like _level_value but reports invalid as None so the caller can skip + warn"""
if isinstance(level, bool):
return None
if isinstance(level, int):
@@ -84,12 +67,7 @@ def _strict_level_value(level: Union[int, str]) -> Optional[int]:
def _apply_module_levels(module_levels: Optional[Dict[str, Union[int, str]]], warnings: list) -> None:
"""set per-logger level overrides by exact logger name, never crashing
names match exactly (no discovery); stdlib hierarchy still applies, so a parent name
quiets its whole subtree. a bad level is skipped, its warning appended to `warnings`
(no handlers exist yet — see _flush_warnings) rather than emitted directly
"""
"""set per-logger level overrides by exact logger name, never crashing"""
if not module_levels:
return
for mod_name, raw_level in module_levels.items():
@@ -101,17 +79,12 @@ def _apply_module_levels(module_levels: Optional[Dict[str, Union[int, str]]], wa
def _clear_owned(root: logging.Logger, warnings: list) -> None:
"""remove only the handlers this lib previously added; leave app handlers alone
close failures are appended to `warnings`, not logged directly — no handlers exist
yet at this point in setup (see _flush_warnings)
"""
"""remove only the handlers this lib previously added; leave app handlers alone"""
global _listener
if _listener is not None:
_listener.stop()
# listener owns the real file/console handlers (only QueueHandler is root-
# attached + marked); stopping it doesn't close them, so close here rather than
# rely on GC finalizers across a re-setup
# listener owns the real file/console handlers; stopping it doesn't close
# them, so close here rather than rely on GC finalizers across a re-setup
for wrapped in getattr(_listener, "handlers", ()):
try:
wrapped.close()
@@ -138,10 +111,8 @@ def _tag(handler: logging.Handler) -> logging.Handler:
def _normalize_name(name: str) -> str:
"""strip one trailing '.log' (case-insensitive) so the stem is extension-free
`name` is allowed to be passed with or without the extension — "latest" and
"latest.log" both yield stem "latest" (live file latest.log), never latest.log.log.
only one level is stripped: "app.log.log" -> "app.log" so a legit ".log" inside a
name survives.
"latest" and "latest.log" both yield stem "latest" (never latest.log.log); only
one level is stripped, so "app.log.log" -> "app.log".
"""
if name.lower().endswith(".log"):
return name[:-4]
@@ -149,12 +120,7 @@ def _normalize_name(name: str) -> str:
def _history_stem() -> str:
"""the project namespace for historic files: the cwd basename
a service run from bestbuy/ gives historic files bestbuy.<stamp>.log[.gz]. falls back
to an empty string only for a degenerate cwd (e.g. "/"), which the caller resolves to
the live stem.
"""
"""the project namespace for historic files: the cwd basename, "" for a degenerate cwd"""
try:
return os.path.basename(os.getcwd().rstrip(os.sep))
except OSError:
@@ -168,21 +134,14 @@ def _file_handler(
) -> logging.Handler:
"""build the configured file handler with custom rolling into log_dir
`name` is the LIVE stem (drives live_path); `history_stem` is the PROJECT stem that
rolled/historic files are named off + the retention glob keys on — decoupled: the
live file keeps its defined name, historic files carry the project namespace. an
unknown `rotate` is appended to `warnings` rather than logged directly (see
_flush_warnings — no handlers exist yet at this point).
`name` is the LIVE stem; `history_stem` is the PROJECT stem that rolled/historic
files are named off, decoupled from the live file's own name.
"""
tiered = keep_uncompressed is not None or keep_compressed is not None
if rotate == "size":
# stdlib doRollover no-ops at backupCount==0, and its numbered .1/.2 shift can't
# manage files redirected into log_dir — force nonzero so the roll always fires,
# and let attach_rolling's namer + retier/prune bound retention instead. the
# REAL backup_count (maybe 0) still flows to attach_rolling below: make_rotator
# treats <=0 there as "keep no rolled history" and deletes each roll right after
# landing, rather than passing 0 to prune() (whose own <=0 is a "leave history
# alone" no-op — that mismatch is what silently disabled rotation before)
# stdlib doRollover no-ops at backupCount==0 - force nonzero so the roll
# always fires; the REAL backup_count still flows to attach_rolling, whose
# make_rotator treats <=0 as "keep no rolled history" and deletes each roll
size_backup = max(backup_count, 1)
handler = logging.handlers.RotatingFileHandler(
live_path, maxBytes=max_bytes, backupCount=size_backup, encoding="utf-8",
@@ -212,10 +171,10 @@ def _file_handler(
rotate_on_start(live_path, log_dir, compress, history_stem=history_stem)
prune(log_dir, history_stem, backup_count)
elif rotate is not None:
# a typo'd value (e.g. "hourly") would otherwise silently fall through to a
# non-rotating FileHandler and grow forever warn instead of degrade silently
# a typo'd value would otherwise silently fall through to a non-rotating
# FileHandler and grow forever - warn instead of degrade silently
warnings.append((
"log_setup: unknown rotate %r; expected 'daily'/'size'/'on_start'/None "
"log_setup: unknown rotate %r; expected 'daily'/'size'/'on_start'/None - "
"no rotation applied (single growing file)", rotate,
))
handler = logging.FileHandler(live_path, encoding="utf-8")
@@ -248,8 +207,8 @@ def setup_logging(
`history_name` names the rolled/historic files (`<history_name>.<timestamp>.log[.gz]`),
independent of the live file: defaults to the PROJECT namespace = the cwd basename
(run from bestbuy/ -> historic files bestbuy.<stamp>...), settable explicitly. the
live file always keeps `name`; only historic files carry the project name.
(run from bestbuy/ -> historic files bestbuy.<stamp>...). the live file always keeps
`name`; only historic files carry the project name.
`keep_uncompressed`/`keep_compressed` (default None) enable TIERED retention: when
either is given, rolled files are kept as the newest `keep_uncompressed` uncompressed
@@ -258,29 +217,28 @@ def setup_logging(
IGNORED in tiered mode. pass NEITHER knob and rotation behaves exactly as before.
`level` is the root default every logger inherits. `module_levels` is an optional
map of exact logger name -> level applied after the root is set the ergonomic way
to quiet noisy dependencies (e.g. {"motor": "WARNING"}) from the one setup call
instead of scattering `getLogger(...).setLevel(...)` afterwards (stdlib hierarchy
under the hood, not new capability). names match EXACTLY (no discovery: a typo'd
name silently configures an unused logger), but hierarchy applies, so naming a
parent ("aiohttp") quiets its whole subtree. str or int per entry; a bad value is
skipped with a warning and never aborts the others or the setup.
map of exact logger name -> level applied after the root is set, the ergonomic way
to quiet noisy dependencies (e.g. {"motor": "WARNING"}) from one call instead of
scattering `getLogger(...).setLevel(...)` calls. names match EXACTLY (no discovery:
a typo'd name silently configures an unused logger), but hierarchy applies, so
naming a parent ("aiohttp") quiets its whole subtree. str or int per entry; a bad
value is skipped with a warning and never aborts the others or the setup.
`rotate` is "daily" (default), "size", "on_start", or None. for `rotate="size"`, the
live file always rolls at `max_bytes` regardless of `backup_count`: `backup_count=0`
means "keep zero rolled files" (each roll lands then is deleted immediately), NOT
"disable rotation". `backup_count>=1` keeps that many rolled files as before.
`console=True` adds a stdout handler (off by default the file is the output).
`console=True` adds a stdout handler (off by default - the file is the output).
`queue=True` routes records through a background QueueListener so file I/O never
blocks the caller (stopped at exit). `output` is "text" (default, human `time |
module | level | message`, local time) or "json" (structured JSON Lines for the
Grafana/Loki path, UTC timestamps + a unix-epoch `ts`, `extra=` fields surfaced as
top-level keys); file and console use the same format, live-file name unaffected.
`fmt`/`datefmt` apply to text output only.
module | level | message`, local time) or "json" (structured JSON Lines, UTC
timestamps + a unix-epoch `ts`, `extra=` fields surfaced as top-level keys); file
and console use the same format, live-file name unaffected. `fmt`/`datefmt` apply
to text output only.
idempotent: a repeat call clears only the handlers this function added. never
raises over logging an unwritable `log_dir` falls back to console-only with a
raises over logging - an unwritable `log_dir` falls back to console-only with a
warning even when `console` is off; an unknown `output` falls back to text.
"""
global _listener, _atexit_registered
@@ -295,9 +253,8 @@ def setup_logging(
formatter = build_formatter(output, fmt, datefmt)
stem = _normalize_name(name)
live_path = f"{stem}.log"
# historic/rolled files are named off the project namespace: history_name if given,
# else the cwd basename. normalized + basenamed like `name`; falls back to the live
# stem for a degenerate cwd so naming/retention never break.
# history_name if given, else the cwd basename; falls back to the live stem for a
# degenerate cwd so naming/retention never break
history_source = history_name if history_name is not None else _history_stem()
history_stem = os.path.basename(_normalize_name(history_source)) or stem
@@ -332,8 +289,7 @@ def setup_logging(
_listener = logging.handlers.QueueListener(record_queue, *handlers, respect_handler_level=True)
_listener.start()
if not _atexit_registered:
# register once atexit doesn't dedupe; repeated re-setups would otherwise
# stack identical callbacks
# register once - atexit doesn't dedupe, repeated re-setups would stack
atexit.register(_stop_listener)
_atexit_registered = True
else:
@@ -343,8 +299,7 @@ def setup_logging(
if not file_ok:
warnings.append(("log_setup: log_dir %r not writable; logging to console only", log_dir))
# flush now that handlers are attached, so setup-time warnings actually land in the
# configured log rather than being lost to stderr before any handler existed
# flush now that handlers are attached, so warnings land in the configured log
_flush_warnings(warnings)
return root