diff --git a/.env.example b/.env.example index 646a5fb..603cb12 100644 --- a/.env.example +++ b/.env.example @@ -2,10 +2,10 @@ MASTODON_BASE_URL=https://mastodon.example MASTODON_ACCESS_TOKEN=replace-me -MASTODON_VISIBILITY=public +VISIBILITY=public SITE_URL=https://blog.example.com HASHTAGS=#throwback,#10backward -THROWBACK_PREFIX=Throwback: -RETRY_COUNT=3 +THROWNBACK_PREFIX=Throwback: +MAX_RETRIES=3 RUN_AT=09:00 TZ=Europe/Berlin diff --git a/build.sh b/build.sh index 5d15a76..5c5453d 100755 --- a/build.sh +++ b/build.sh @@ -2,6 +2,13 @@ set -euo pipefail export DEBIAN_FRONTEND=noninteractive +SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)" +cd "${SCRIPT_DIR}" + +if [ -w /usr/local/bin ] && [ ! -e /usr/local/bin/build.sh ]; then + ln -s "${SCRIPT_DIR}/build.sh" /usr/local/bin/build.sh || true +fi + apt-get update apt-get install -y --no-install-recommends \ bash \ diff --git a/docker-compose.yml b/docker-compose.yml index 381c3a8..297cb54 100644 --- a/docker-compose.yml +++ b/docker-compose.yml @@ -11,11 +11,11 @@ services: environment: MASTODON_BASE_URL: ${MASTODON_BASE_URL:-https://mastodon.example} MASTODON_ACCESS_TOKEN: ${MASTODON_ACCESS_TOKEN:-replace-me} - MASTODON_VISIBILITY: ${MASTODON_VISIBILITY:-public} + VISIBILITY: ${VISIBILITY:-public} SITE_URL: ${SITE_URL:-https://blog.example.com} HASHTAGS: ${HASHTAGS:-#throwback,#10backward} - THROWBACK_PREFIX: ${THROWBACK_PREFIX:-Throwback:} - RETRY_COUNT: ${RETRY_COUNT:-3} + THROWNBACK_PREFIX: ${THROWNBACK_PREFIX:-Throwback:} + MAX_RETRIES: ${MAX_RETRIES:-3} RUN_AT: ${RUN_AT:-09:00} TZ: ${TZ:-Europe/Berlin} volumes: diff --git a/entrypoint.sh b/entrypoint.sh index f385358..e1f4b9e 100755 --- a/entrypoint.sh +++ b/entrypoint.sh @@ -11,9 +11,13 @@ fi required_vars=( MASTODON_BASE_URL MASTODON_ACCESS_TOKEN + VISIBILITY SITE_URL HASHTAGS + THROWNBACK_PREFIX + MAX_RETRIES RUN_AT + TZ ) missing=() diff --git a/src/tenbackward/config.py b/src/tenbackward/config.py index f5c84ae..831b39a 100644 --- a/src/tenbackward/config.py +++ b/src/tenbackward/config.py @@ -4,6 +4,8 @@ import os from dataclasses import dataclass, field from pathlib import Path from typing import Optional +from urllib.parse import urlparse +from zoneinfo import ZoneInfo, ZoneInfoNotFoundError from dotenv import dotenv_values, load_dotenv @@ -11,27 +13,29 @@ from dotenv import dotenv_values, load_dotenv REQUIRED_KEYS = ( "MASTODON_BASE_URL", "MASTODON_ACCESS_TOKEN", + "VISIBILITY", "SITE_URL", "HASHTAGS", + "THROWNBACK_PREFIX", + "MAX_RETRIES", "RUN_AT", -) - -OPTIONAL_KEYS = ( - "MASTODON_VISIBILITY", - "THROWBACK_PREFIX", - "RETRY_COUNT", "TZ", ) +OPTIONAL_KEYS: tuple[str, ...] = () + DEFAULTS = { - "MASTODON_VISIBILITY": "public", - "THROWBACK_PREFIX": "Throwback:", - "RETRY_COUNT": "3", + "VISIBILITY": "public", + "THROWNBACK_PREFIX": "Throwback:", + "MAX_RETRIES": "3", "TZ": "Europe/Berlin", "RUN_AT": "09:00", } +ALLOWED_VISIBILITY = frozenset({"public", "unlisted"}) + + class ConfigError(ValueError): """Raised when required configuration is missing or invalid.""" @@ -40,11 +44,11 @@ class ConfigError(ValueError): class Config: mastodon_base_url: str mastodon_access_token: str - mastodon_visibility: str + visibility: str site_url: str hashtags: str throwback_prefix: str - retry_count: int + max_retries: int run_at: str tz: str data_dir: Path = field(default_factory=lambda: Path("/app/data")) @@ -104,11 +108,11 @@ def load_config(dotenv_path: Optional[Path] = None) -> Config: return Config( mastodon_base_url=merged["MASTODON_BASE_URL"], mastodon_access_token=merged["MASTODON_ACCESS_TOKEN"], - mastodon_visibility=merged["MASTODON_VISIBILITY"], + visibility=merged["VISIBILITY"], site_url=merged["SITE_URL"], hashtags=merged["HASHTAGS"], - throwback_prefix=merged["THROWBACK_PREFIX"], - retry_count=_parse_retry_count(merged["RETRY_COUNT"]), + throwback_prefix=merged["THROWNBACK_PREFIX"], + max_retries=_parse_max_retries(merged["MAX_RETRIES"]), run_at=merged["RUN_AT"], tz=merged["TZ"], data_dir=data_dir, @@ -122,25 +126,47 @@ def apply_defaults(values: dict[str, str]) -> None: def validate_config(values: dict[str, str]) -> None: - missing = [k for k in REQUIRED_KEYS if not values.get(k)] - if missing: - raise ConfigError( - "missing required configuration key(s): " + ", ".join(missing) - ) + errors: list[str] = [] + + for key in REQUIRED_KEYS: + raw = values.get(key, "") + if not raw: + errors.append(f"missing required configuration key: {key}") run_at = values.get("RUN_AT", "") - if not _is_valid_hhmm(run_at): - raise ConfigError( - f"RUN_AT={run_at!r} must be in HH:MM (24-hour) format" + if run_at and not _is_valid_hhmm(run_at): + errors.append(f"RUN_AT={run_at!r} must be in HH:MM (24-hour) format") + + base_url = values.get("MASTODON_BASE_URL", "") + if base_url and not _is_valid_url(base_url): + errors.append(f"MASTODON_BASE_URL={base_url!r} must be a valid http(s) URL") + + site_url = values.get("SITE_URL", "") + if site_url and not _is_valid_url(site_url): + errors.append(f"SITE_URL={site_url!r} must be a valid http(s) URL") + + visibility = values.get("VISIBILITY", "") + if visibility and not _is_valid_visibility(visibility): + errors.append( + f"VISIBILITY={visibility!r} must be one of: {sorted(ALLOWED_VISIBILITY)}" ) - try: - _parse_retry_count(values.get("RETRY_COUNT", "")) - except ConfigError as exc: - raise ConfigError(str(exc)) from exc + tz = values.get("TZ", "") + if tz and not _is_valid_tz(tz): + errors.append(f"TZ={tz!r} must be a valid IANA timezone") + + max_retries = values.get("MAX_RETRIES", "") + if max_retries: + try: + _parse_max_retries(max_retries) + except ConfigError as exc: + errors.append(str(exc)) + + if errors: + raise ConfigError("; ".join(errors)) -def _is_valid_hhmm(value: str) -> bool: +def _is_valid_hhmm(value) -> bool: if not isinstance(value, str): return False parts = value.split(":") @@ -156,11 +182,39 @@ def _is_valid_hhmm(value: str) -> bool: return 0 <= h <= 23 and 0 <= m <= 59 -def _parse_retry_count(value: str) -> int: +def _is_valid_url(value: str) -> bool: + if not isinstance(value, str) or not value: + return False + try: + parsed = urlparse(value) + except (TypeError, ValueError): + return False + return parsed.scheme in {"http", "https"} and bool(parsed.netloc) + + +def _is_valid_visibility(value: str) -> bool: + return isinstance(value, str) and value in ALLOWED_VISIBILITY + + +def _is_valid_tz(value: str) -> bool: + if not isinstance(value, str) or not value: + return False + try: + ZoneInfo(value) + except ZoneInfoNotFoundError: + return False + except Exception: + return False + return True + + +def _parse_max_retries(value) -> int: + if isinstance(value, bool): + raise ConfigError(f"MAX_RETRIES={value!r} must be a non-negative integer") try: count = int(value) except (TypeError, ValueError): - raise ConfigError(f"RETRY_COUNT={value!r} must be a positive integer") + raise ConfigError(f"MAX_RETRIES={value!r} must be a non-negative integer") if count < 0: - raise ConfigError(f"RETRY_COUNT={value!r} must be >= 0") + raise ConfigError(f"MAX_RETRIES={value!r} must be >= 0") return count diff --git a/src/tenbackward/logging_setup.py b/src/tenbackward/logging_setup.py new file mode 100644 index 0000000..39ba10d --- /dev/null +++ b/src/tenbackward/logging_setup.py @@ -0,0 +1,155 @@ +from __future__ import annotations + +import json +import logging +from datetime import datetime, timezone +from typing import Any + +from .config import ConfigError + +_SECRET_KEYS = frozenset( + { + "token", + "access_token", + "mastodon_access_token", + "password", + "secret", + "authorization", + "api_key", + } +) + +_LOGGER_NAME = "tenbackward" + + +class JsonFormatter(logging.Formatter): + """Emit one JSON object per log record. + + Reserved record attributes are mapped to top-level keys; anything passed + via ``extra=`` is merged into the same object. Keys whose name appears in + ``_SECRET_KEYS`` are redacted before formatting. + """ + + _RESERVED = { + "name", + "msg", + "args", + "levelname", + "levelno", + "pathname", + "filename", + "module", + "exc_info", + "exc_text", + "stack_info", + "lineno", + "funcName", + "created", + "msecs", + "relativeCreated", + "thread", + "threadName", + "processName", + "process", + "message", + "asctime", + } + + def format(self, record: logging.LogRecord) -> str: # noqa: A003 + message = record.getMessage() + payload: dict[str, Any] = { + "ts": datetime.fromtimestamp(record.created, tz=timezone.utc).isoformat(), + "level": record.levelname, + "logger": record.name, + "message": message, + } + + for key, value in record.__dict__.items(): + if key in self._RESERVED or key.startswith("_"): + continue + if key in _SECRET_KEYS: + payload[key] = "[REDACTED]" + else: + payload[key] = value + + if record.exc_info: + payload["exc_type"] = record.exc_info[0].__name__ if record.exc_info[0] else None + + return json.dumps(payload, default=str, sort_keys=False) + + +def configure_json_logging(level: int = logging.INFO) -> None: + """Install the JSON formatter on the root logger. + + Idempotent: safe to call multiple times (replaces any existing handler). + """ + handler = logging.StreamHandler() + handler.setFormatter(JsonFormatter()) + handler.setLevel(level) + + root = logging.getLogger() + root.setLevel(level) + for existing in list(root.handlers): + root.removeHandler(existing) + root.addHandler(handler) + + +def _redact_dict(fields: dict[str, Any]) -> dict[str, Any]: + cleaned: dict[str, Any] = {} + for key, value in fields.items(): + if key.lower() in _SECRET_KEYS: + cleaned[key] = "[REDACTED]" + else: + cleaned[key] = value + return cleaned + + +def log_run_summary( + scanned: int, + matched: int, + posted: int, + skipped: int, + posted_ids: list[str], +) -> None: + """Emit a single structured info line on successful completion. + + A run with no matching posts is silent — no log line is emitted. + """ + if scanned == 0 and matched == 0 and posted == 0 and skipped == 0 and not posted_ids: + return + + fields = _redact_dict( + { + "event": "run_complete", + "scanned": scanned, + "matched": matched, + "posted": posted, + "skipped": skipped, + "posted_ids": list(posted_ids), + } + ) + logging.getLogger(_LOGGER_NAME).info("run complete", extra=fields) + + +def log_error(event: str, *, exc: BaseException | None = None, **fields: Any) -> None: + """Emit a single structured error line, redacting any secret-shaped keys.""" + payload = _redact_dict({"event": event, **fields}) + if exc is not None: + payload["exc_type"] = type(exc).__name__ + logging.getLogger(_LOGGER_NAME).error(event, extra=payload) + + +def log_startup(**fields: Any) -> None: + """Emit a single structured info line at startup.""" + payload = _redact_dict({"event": "startup", **fields}) + logging.getLogger(_LOGGER_NAME).info("startup", extra=payload) + + +__all__ = [ + "ConfigError", + "JsonFormatter", + "configure_json_logging", + "log_error", + "log_run_summary", + "log_startup", +] diff --git a/src/tenbackward/main.py b/src/tenbackward/main.py index 7c3da6d..41b6ce9 100644 --- a/src/tenbackward/main.py +++ b/src/tenbackward/main.py @@ -1,47 +1,116 @@ from __future__ import annotations -import logging import sys +import time +from typing import Iterable from . import __version__ -from .config import ConfigError, load_config +from .config import Config, ConfigError, load_config +from .logging_setup import ( + configure_json_logging, + log_error, + log_run_summary, + log_startup, +) from .state import load_posted, save_posted -log = logging.getLogger("tenbackward") +def _iter_candidates(config: Config) -> Iterable[str]: + """Yield candidate post identifiers. + + This is the extension seam for the future blog-clone + matching + pipeline. Job 1083 leaves it empty so the silent-on-no-matches + contract is the default behaviour. + """ + return [] + + +def _run_once(config: Config) -> tuple[int, int, int, int, list[str]]: + """Execute one pipeline pass and return the summary counters. + + Returns ``(scanned, matched, posted, skipped, posted_ids)``. + """ + already_posted = set(load_posted(config.data_dir).keys()) + + scanned = 0 + matched = 0 + posted = 0 + skipped = 0 + posted_ids: list[str] = [] + + state = load_posted(config.data_dir) + + for candidate_id in _iter_candidates(config): + scanned += 1 + matched += 1 + if candidate_id in already_posted: + skipped += 1 + continue + posted_ids.append(candidate_id) + state[candidate_id] = {"posted_at": _now_iso()} + posted += 1 + + if posted_ids: + save_posted(config.data_dir, state) + + return scanned, matched, posted, skipped, posted_ids + + +def _now_iso() -> str: + from datetime import datetime, timezone + + return datetime.now(tz=timezone.utc).isoformat() + + +def _run_with_retry(config: Config) -> tuple[int, int, int, int, list[str]] | None: + """Execute the pipeline with retries. Returns the summary counters on + success or ``None`` when the retry budget is exhausted.""" + attempts = max(1, config.max_retries + 1) + last_exc: BaseException | None = None + for attempt in range(1, attempts + 1): + try: + return _run_once(config) + except Exception as exc: # noqa: BLE001 — broad on purpose + last_exc = exc + log_error( + "pipeline_error", + exc=exc, + attempt=attempt, + max_attempts=attempts, + ) + if attempt < attempts: + time.sleep(0) + assert last_exc is not None + log_error("pipeline_failed", exc=last_exc, attempts=attempts) + return None def main() -> int: - logging.basicConfig( - level=logging.INFO, - format="%(asctime)s %(levelname)s %(name)s: %(message)s", - ) + configure_json_logging() try: config = load_config() except ConfigError as exc: - log.error("configuration error: %s", exc) + log_error("configuration_error", exc=exc) return 2 config.data_dir.mkdir(parents=True, exist_ok=True) - state = load_posted(config.data_dir) - save_posted(config.data_dir, state) - - log.info( - "10backward v%s ready (site=%s, run_at=%s, tz=%s, hashtags=%s, prefix=%r)", - __version__, - config.site_url, - config.run_at, - config.tz, - config.hashtags, - config.throwback_prefix, + log_startup( + version=__version__, + site_url=config.site_url, + run_at=config.run_at, + tz=config.tz, + hashtags=config.hashtags, + throwback_prefix=config.throwback_prefix, ) - log.warning( - "post pipeline is not yet implemented; this run only validates the scaffold. " - "Future job will clone the blog and post a throwback via Mastodon.py." - ) + result = _run_with_retry(config) + if result is None: + return 1 + + scanned, matched, posted, skipped, posted_ids = result + log_run_summary(scanned, matched, posted, skipped, posted_ids) return 0 diff --git a/tests/conftest.py b/tests/conftest.py index 82b0edb..433ae1c 100644 --- a/tests/conftest.py +++ b/tests/conftest.py @@ -16,9 +16,13 @@ def env_setup(monkeypatch: pytest.MonkeyPatch) -> None: """ monkeypatch.setenv("MASTODON_BASE_URL", "https://mastodon.example") monkeypatch.setenv("MASTODON_ACCESS_TOKEN", "test-token") + monkeypatch.setenv("VISIBILITY", "public") monkeypatch.setenv("SITE_URL", "https://blog.example.com") monkeypatch.setenv("HASHTAGS", "#throwback,#10backward") + monkeypatch.setenv("THROWNBACK_PREFIX", "Throwback:") + monkeypatch.setenv("MAX_RETRIES", "3") monkeypatch.setenv("RUN_AT", "09:00") + monkeypatch.setenv("TZ", "Europe/Berlin") @pytest.fixture() diff --git a/tests/test_config.py b/tests/test_config.py index 82f2aa6..7addfc2 100644 --- a/tests/test_config.py +++ b/tests/test_config.py @@ -9,15 +9,30 @@ from tenbackward.config import ConfigError, load_config, validate_config def _populate(env_setup) -> dict[str, str]: - return {k: os.environ[k] for k in os.environ if k.startswith(("MASTODON_", "SITE_", "HASHTAGS", "RUN_AT", "THROWBACK_", "RETRY_", "TZ"))} + return {k: os.environ[k] for k in os.environ if k.startswith(("MASTODON_", "VISIBILITY", "SITE_", "HASHTAGS", "THROWNBACK_", "MAX_RETRIES", "RUN_AT", "TZ"))} + + +def _full_values() -> dict[str, str]: + return { + "MASTODON_BASE_URL": "https://mastodon.example", + "MASTODON_ACCESS_TOKEN": "x", + "VISIBILITY": "public", + "SITE_URL": "https://blog.example.com", + "HASHTAGS": "#throwback", + "THROWNBACK_PREFIX": "Throwback:", + "MAX_RETRIES": "3", + "RUN_AT": "09:00", + "TZ": "Europe/Berlin", + } def test_load_config_succeeds_with_complete_env(env_setup) -> None: config = load_config() assert config.mastodon_base_url == "https://mastodon.example" assert config.run_at == "09:00" - assert config.retry_count == 3 + assert config.max_retries == 3 assert config.throwback_prefix == "Throwback:" + assert config.visibility == "public" def test_validate_config_lists_every_missing_key(env_setup, monkeypatch) -> None: @@ -27,9 +42,13 @@ def test_validate_config_lists_every_missing_key(env_setup, monkeypatch) -> None values = {k: os.environ.get(k, "") for k in [ "MASTODON_BASE_URL", "MASTODON_ACCESS_TOKEN", + "VISIBILITY", "SITE_URL", "HASHTAGS", + "THROWNBACK_PREFIX", + "MAX_RETRIES", "RUN_AT", + "TZ", ]} with pytest.raises(ConfigError) as excinfo: @@ -41,30 +60,63 @@ def test_validate_config_lists_every_missing_key(env_setup, monkeypatch) -> None def test_validate_config_rejects_bad_run_at() -> None: - values = { - "MASTODON_BASE_URL": "https://mastodon.example", - "MASTODON_ACCESS_TOKEN": "x", - "SITE_URL": "https://blog.example.com", - "HASHTAGS": "#x", - "RUN_AT": "25:99", - "MASTODON_VISIBILITY": "public", - "THROWBACK_PREFIX": "Throwback:", - "RETRY_COUNT": "3", - "TZ": "Europe/Berlin", - } + values = _full_values() + values["RUN_AT"] = "25:99" with pytest.raises(ConfigError): validate_config(values) +def test_validate_config_rejects_invalid_url() -> None: + values = _full_values() + values["SITE_URL"] = "not-a-url" + with pytest.raises(ConfigError, match="SITE_URL"): + validate_config(values) + + values = _full_values() + values["MASTODON_BASE_URL"] = "ftp://mastodon.example" + with pytest.raises(ConfigError, match="MASTODON_BASE_URL"): + validate_config(values) + + +def test_validate_config_rejects_invalid_visibility() -> None: + for bad in ("private", "direct", "", "PUBLIC"): + values = _full_values() + values["VISIBILITY"] = bad + with pytest.raises(ConfigError, match="VISIBILITY"): + validate_config(values) + + +def test_validate_config_rejects_invalid_tz() -> None: + values = _full_values() + values["TZ"] = "Not/AZone" + with pytest.raises(ConfigError, match="TZ"): + validate_config(values) + + +def test_validate_config_rejects_negative_max_retries() -> None: + values = _full_values() + values["MAX_RETRIES"] = "-1" + with pytest.raises(ConfigError, match="MAX_RETRIES"): + validate_config(values) + + +def test_validate_config_accepts_zero_max_retries() -> None: + values = _full_values() + values["MAX_RETRIES"] = "0" + validate_config(values) + + def test_load_config_applies_optional_defaults(env_setup, monkeypatch) -> None: - monkeypatch.delenv("THROWBACK_PREFIX", raising=False) - monkeypatch.delenv("RETRY_COUNT", raising=False) + monkeypatch.delenv("VISIBILITY", raising=False) + monkeypatch.delenv("THROWNBACK_PREFIX", raising=False) + monkeypatch.delenv("MAX_RETRIES", raising=False) + monkeypatch.delenv("TZ", raising=False) config = load_config() assert config.throwback_prefix == "Throwback:" - assert config.retry_count == 3 + assert config.max_retries == 3 assert config.tz == "Europe/Berlin" - assert config.mastodon_visibility == "public" + assert config.visibility == "public" def test_load_config_reads_dotenv_file(tmp_path: Path, monkeypatch) -> None: @@ -72,18 +124,35 @@ def test_load_config_reads_dotenv_file(tmp_path: Path, monkeypatch) -> None: dotenv.write_text( "MASTODON_BASE_URL=https://from-file.example\n" "MASTODON_ACCESS_TOKEN=file-token\n" + "VISIBILITY=unlisted\n" "SITE_URL=https://blog.example.com\n" "HASHTAGS=#throwback\n" + "THROWNBACK_PREFIX=Werferückblick:\n" + "MAX_RETRIES=5\n" "RUN_AT=12:34\n" + "TZ=Europe/Berlin\n" ) - for key in ("MASTODON_BASE_URL", "MASTODON_ACCESS_TOKEN", "SITE_URL", "HASHTAGS", "RUN_AT"): + for key in ( + "MASTODON_BASE_URL", + "MASTODON_ACCESS_TOKEN", + "VISIBILITY", + "SITE_URL", + "HASHTAGS", + "THROWNBACK_PREFIX", + "MAX_RETRIES", + "RUN_AT", + "TZ", + ): monkeypatch.delenv(key, raising=False) config = load_config(dotenv_path=dotenv) assert config.mastodon_base_url == "https://from-file.example" assert config.mastodon_access_token == "file-token" assert config.run_at == "12:34" + assert config.visibility == "unlisted" + assert config.throwback_prefix == "Werferückblick:" + assert config.max_retries == 5 def test_env_overrides_dotenv(tmp_path: Path, monkeypatch) -> None: @@ -94,10 +163,19 @@ def test_env_overrides_dotenv(tmp_path: Path, monkeypatch) -> None: for key in ( "MASTODON_BASE_URL", "MASTODON_ACCESS_TOKEN", + "VISIBILITY", "SITE_URL", "HASHTAGS", + "THROWNBACK_PREFIX", + "MAX_RETRIES", + "TZ", ): monkeypatch.setenv(key, "x") + monkeypatch.setenv("MASTODON_BASE_URL", "https://mastodon.example") + monkeypatch.setenv("SITE_URL", "https://blog.example.com") + monkeypatch.setenv("VISIBILITY", "public") + monkeypatch.setenv("TZ", "Europe/Berlin") + monkeypatch.setenv("MAX_RETRIES", "3") config = load_config(dotenv_path=dotenv) assert config.run_at == "23:00" diff --git a/tests/test_cron_render.py b/tests/test_cron_render.py index bcb473d..7c3da24 100644 --- a/tests/test_cron_render.py +++ b/tests/test_cron_render.py @@ -103,8 +103,11 @@ def test_entrypoint_renders_run_at_into_cron() -> None: env = _entrypoint_env({ "MASTODON_BASE_URL": "https://mastodon.example", "MASTODON_ACCESS_TOKEN": "x", + "VISIBILITY": "public", "SITE_URL": "https://blog.example.com", "HASHTAGS": "#throwback", + "THROWNBACK_PREFIX": "Throwback:", + "MAX_RETRIES": "3", "RUN_AT": "09:00", "TZ": "Europe/Berlin", }) diff --git a/tests/test_entrypoint_validation.py b/tests/test_entrypoint_validation.py index d1907b9..04ae681 100644 --- a/tests/test_entrypoint_validation.py +++ b/tests/test_entrypoint_validation.py @@ -39,8 +39,11 @@ def test_entrypoint_rejects_bad_run_at(tmp_path: Path, monkeypatch) -> None: env = _clean_env() env["MASTODON_BASE_URL"] = "https://mastodon.example" env["MASTODON_ACCESS_TOKEN"] = "x" + env["VISIBILITY"] = "public" env["SITE_URL"] = "https://blog.example.com" env["HASHTAGS"] = "#throwback" + env["THROWNBACK_PREFIX"] = "Throwback:" + env["MAX_RETRIES"] = "3" env["RUN_AT"] = "25:99" env["TZ"] = "Europe/Berlin" @@ -61,8 +64,11 @@ def test_entrypoint_fails_fast_when_token_missing(tmp_path: Path, monkeypatch) - """A missing required var must abort before cron is started.""" env = _clean_env() env["MASTODON_BASE_URL"] = "https://mastodon.example" + env["VISIBILITY"] = "public" env["SITE_URL"] = "https://blog.example.com" env["HASHTAGS"] = "#throwback" + env["THROWNBACK_PREFIX"] = "Throwback:" + env["MAX_RETRIES"] = "3" env["RUN_AT"] = "09:00" env["TZ"] = "Europe/Berlin" env.pop("MASTODON_ACCESS_TOKEN", None) diff --git a/tests/test_logging_setup.py b/tests/test_logging_setup.py new file mode 100644 index 0000000..4ff68be --- /dev/null +++ b/tests/test_logging_setup.py @@ -0,0 +1,93 @@ +from __future__ import annotations + +import io +import json +import logging + +from tenbackward.logging_setup import ( + JsonFormatter, + configure_json_logging, + log_error, + log_run_summary, + log_startup, +) + + +def _capture(logger: logging.Logger) -> io.StringIO: + buf = io.StringIO() + handler = logging.StreamHandler(buf) + handler.setFormatter(JsonFormatter()) + logger.handlers = [handler] + logger.setLevel(logging.INFO) + logger.propagate = False + return buf + + +def test_json_formatter_emits_valid_json() -> None: + buf = _capture(logging.getLogger("tenbackward.test")) + logging.getLogger("tenbackward.test").info("hello", extra={"foo": 1}) + line = buf.getvalue().strip() + payload = json.loads(line) + assert payload["message"] == "hello" + assert payload["level"] == "INFO" + assert payload["logger"] == "tenbackward.test" + assert payload["foo"] == 1 + assert "ts" in payload + + +def test_json_formatter_redacts_secret_keys() -> None: + buf = _capture(logging.getLogger("tenbackward.test")) + logging.getLogger("tenbackward.test").info( + "msg", + extra={"access_token": "secret-value", "site_url": "https://x"}, + ) + payload = json.loads(buf.getvalue().strip()) + assert payload["access_token"] == "[REDACTED]" + assert payload["site_url"] == "https://x" + + +def test_log_run_summary_emits_one_line_with_counters() -> None: + buf = _capture(logging.getLogger("tenbackward")) + log_run_summary(3, 2, 1, 1, ["x"]) + lines = [line for line in buf.getvalue().splitlines() if line.strip()] + assert len(lines) == 1 + payload = json.loads(lines[0]) + assert payload["message"] == "run complete" + assert payload["event"] == "run_complete" + assert payload["scanned"] == 3 + assert payload["matched"] == 2 + assert payload["posted"] == 1 + assert payload["skipped"] == 1 + assert payload["posted_ids"] == ["x"] + + +def test_log_run_summary_silent_when_no_matches() -> None: + buf = _capture(logging.getLogger("tenbackward")) + log_run_summary(0, 0, 0, 0, []) + assert buf.getvalue() == "" + + +def test_log_startup_emits_single_info_line() -> None: + buf = _capture(logging.getLogger("tenbackward")) + log_startup(version="0.1.0", site_url="https://x", run_at="09:00", tz="Europe/Berlin") + payload = json.loads(buf.getvalue().strip()) + assert payload["event"] == "startup" + assert payload["version"] == "0.1.0" + + +def test_log_error_redacts_secret_keys_and_exposes_exc_type() -> None: + buf = _capture(logging.getLogger("tenbackward")) + log_error("boom", exc=RuntimeError("x"), access_token="abc") + payload = json.loads(buf.getvalue().strip()) + assert payload["level"] == "ERROR" + assert payload["event"] == "boom" + assert payload["access_token"] == "[REDACTED]" + assert payload["exc_type"] == "RuntimeError" + + +def test_configure_json_logging_is_idempotent() -> None: + configure_json_logging() + configure_json_logging() + root = logging.getLogger() + json_handlers = [h for h in root.handlers if isinstance(h.formatter, JsonFormatter)] + assert len(json_handlers) == 1 diff --git a/tests/test_run_logging.py b/tests/test_run_logging.py new file mode 100644 index 0000000..b4b7549 --- /dev/null +++ b/tests/test_run_logging.py @@ -0,0 +1,117 @@ +from __future__ import annotations + +import io +import json +import logging +import os +from pathlib import Path + +import pytest + +from tenbackward import main as main_module +from tenbackward.logging_setup import JsonFormatter +from tenbackward.main import main + + +@pytest.fixture() +def capture_logger() -> io.StringIO: + buf = io.StringIO() + handler = logging.StreamHandler(buf) + handler.setFormatter(JsonFormatter()) + target = logging.getLogger("tenbackward") + target.handlers = [handler] + target.setLevel(logging.INFO) + target.propagate = False + return buf + + +def _run_lines(buf: io.StringIO) -> list[dict]: + return [json.loads(line) for line in buf.getvalue().splitlines() if line.strip()] + + +def _seed_state(data_dir: Path, ids: list[str]) -> None: + from tenbackward.state import save_posted + + state = {pid: {"posted_at": "2024-01-01T00:00:00+00:00"} for pid in ids} + save_posted(data_dir, state) + + +def test_run_emits_one_info_summary_on_success(env_setup, data_dir, capture_logger, monkeypatch) -> None: + monkeypatch.setenv("DATA_DIR", str(data_dir)) + + monkeypatch.setattr(main_module, "_iter_candidates", lambda config: ["new-1", "already-1"]) + + _seed_state(data_dir, ["already-1"]) + + rc = main() + assert rc == 0 + + lines = _run_lines(capture_logger) + summary = [line for line in lines if line.get("event") == "run_complete"] + assert len(summary) == 1 + payload = summary[0] + assert payload["scanned"] == 2 + assert payload["matched"] == 2 + assert payload["posted"] == 1 + assert payload["skipped"] == 1 + assert payload["posted_ids"] == ["new-1"] + + from tenbackward.state import load_posted + + state = load_posted(data_dir) + assert "new-1" in state + assert "already-1" in state + + +def test_run_silent_when_no_matches(env_setup, data_dir, capture_logger, monkeypatch) -> None: + monkeypatch.setenv("DATA_DIR", str(data_dir)) + monkeypatch.setattr(main_module, "_iter_candidates", lambda config: []) + + rc = main() + assert rc == 0 + + lines = _run_lines(capture_logger) + summary = [line for line in lines if line.get("event") == "run_complete"] + assert summary == [] + + +def test_run_returns_nonzero_on_pipeline_error(env_setup, data_dir, capture_logger, monkeypatch) -> None: + monkeypatch.setenv("DATA_DIR", str(data_dir)) + monkeypatch.setenv("MAX_RETRIES", "1") + + def _boom(config): + raise RuntimeError("boom-token-should-not-appear") + + monkeypatch.setattr(main_module, "_iter_candidates", _boom) + + rc = main() + assert rc == 1 + + lines = _run_lines(capture_logger) + summary = [line for line in lines if line.get("event") == "run_complete"] + assert summary == [] + + error_lines = [line for line in lines if line.get("level") == "ERROR"] + assert any("exc_type" in line for line in error_lines) + assert "boom-token-should-not-appear" not in capture_logger.getvalue() + + +def test_run_distinguishes_posted_from_skipped_via_ids(env_setup, data_dir, capture_logger, monkeypatch) -> None: + monkeypatch.setenv("DATA_DIR", str(data_dir)) + monkeypatch.setattr( + main_module, + "_iter_candidates", + lambda config: ["alpha", "beta", "gamma"], + ) + _seed_state(data_dir, ["beta"]) + + rc = main() + assert rc == 0 + + summary = [line for line in _run_lines(capture_logger) if line.get("event") == "run_complete"] + assert len(summary) == 1 + payload = summary[0] + assert set(payload["posted_ids"]) == {"alpha", "gamma"} + assert "beta" not in payload["posted_ids"] + assert payload["skipped"] == 1 + assert payload["posted"] == 2