AI Implementation feature(1083): Environment Configuration and Logging Baseline (#2)

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