AI Implementation feature(1087): Mastodon Post Composition and Publishing (#6)

src/tenbackward/matching.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 import calendar
 import logging
 import re
+import unicodedata
 from dataclasses import dataclass
 from datetime import date, datetime
 from pathlib import Path
@@ -15,6 +16,8 @@ _LOGGER = logging.getLogger("tenbackward.matching")
 
 _FILENAME_PATTERN = re.compile(r"^(\d{4})-(\d{2})-(\d{2})-(.+)$")
 
+_NON_ALNUM_RE = re.compile(r"[^a-z0-9]+")
+
 _DEFAULT_TZ = "Europe/Berlin"
 
 
@@ -26,6 +29,19 @@ class MatchedPost:
     url: str
 
 
+def slugify_title(title: str) -> str:
+    """Return a URL-safe slug derived from ``title``.
+
+    Used by the matcher to derive the slug component of
+    :attr:`MatchedPost.url` from the resolved post title.
+    """
+    normalized = unicodedata.normalize("NFKD", title)
+    ascii_only = normalized.encode("ascii", "ignore").decode("ascii")
+    lowered = ascii_only.lower()
+    dashed = _NON_ALNUM_RE.sub("-", lowered)
+    return dashed.strip("-")
+
+
 def _today_in_berlin(tz_name: str = _DEFAULT_TZ) -> date:
     return datetime.now(ZoneInfo(tz_name)).date()
 
@@ -152,7 +168,7 @@ def _process_file(
         path=rel,
         title=title,
         date=post_date,
-        url=_build_url(site_url, post_date, fn_slug),
+        url=_build_url(site_url, post_date, slugify_title(title)),
     )
 
 
@@ -206,4 +222,5 @@ __all__ = [
     "MatchedPost",
     "find_anniversary_matches",
     "iter_anniversary_paths",
-]
+    "slugify_title",
+]