Accept single snippet photos and derive post IDs from titles

photo-upload/posts.py

@@ -1,7 +1,6 @@
 """Markdown import with conservative content matching and explicit ID overrides."""
 from difflib import SequenceMatcher
 from datetime import date, datetime
-import hashlib
 import re
 import unicodedata
 
@@ -28,6 +27,17 @@ def filename_key(filename):
     return unicodedata.normalize("NFC", filename).casefold()
 
 
+def title_id(title):
+    slug = re.sub(r"[\W_]+", "-", unicodedata.normalize("NFKC", title).lower()).strip("-")
+    slug = slug[:80].rstrip("-")
+    # Leave room for the date and prefix in the filesystem's byte-length limit.
+    while len(slug.encode("utf-8")) > 160:
+        slug = slug[:-1].rstrip("-")
+    if not slug:
+        raise ValueError("The post title must contain a letter or number")
+    return slug
+
+
 def parse_upload(filename, raw):
     if not filename or "/" in filename or "\\" in filename or not filename.lower().endswith((".md", ".markdown")):
         raise ValueError("Share one .md or .markdown file with a plain filename")
@@ -69,7 +79,7 @@ def parse_upload(filename, raw):
             raise ValueError("date must be an ISO date or timestamp") from None
         clean["date"] = str(value)
     explicit_id = clean.pop("post_id", None)
-    if explicit_id is not None and not re.fullmatch(r"[a-zA-Z0-9_-]{1,80}", explicit_id):
+    if explicit_id is not None and (not re.fullmatch(r"[\w-]{1,80}", explicit_id) or len(explicit_id.encode()) > 160):
         raise ValueError("post_id must be 1–80 letters, digits, underscores, or hyphens")
     if "permalink" in clean and not re.fullmatch(r"/[\w/-]+/", clean["permalink"]):
         raise ValueError("permalink must be a local path such as /my-post/")
@@ -109,21 +119,22 @@ def publish_post(repo, submission, manifest):
             candidates.append(scored[0][1:])
     if len(candidates) > 1:
         raise ValueError("More than one post matches this post ID")
-    identity = incoming["explicit_id"] or manifest["id"]
+    identity = incoming["explicit_id"] or title_id(incoming["metadata"]["title"])
     if candidates:
         entry, metadata = candidates[0]
-        identity = metadata.get("upload_id", identity)
+        identity = metadata.get("upload_id") or metadata.get("post_id") or title_id(metadata.get("title", entry.stem))
         # Keep the public URL and original publication date during updates.
         metadata.update({key: value for key, value in incoming["metadata"].items() if key not in {"date", "permalink"}})
         permalink = metadata.get("permalink") or "/" + re.sub(r"^\d{4}-\d{2}-\d{2}-", "", entry.stem) + "/"
     else:
         metadata = dict(incoming["metadata"])
         metadata.setdefault("date", manifest["date"])
-        slug = re.sub(r"[^\w-]+", "-", incoming["metadata"]["title"].lower()).strip("-")[:80] or "post"
-        permalink = metadata.get("permalink", f"/{slug}-{identity[:8]}/")
+        permalink = metadata.get("permalink", f"/{identity}/")
         entry = repo / "_posts" / f"{str(metadata['date'])[:10]}-upload-{identity}.md"
         if entry.exists():
             raise ValueError("Post identity conflicts with another file")
+        if any(identity in (record.get("upload_id"), record.get("post_id")) for _, record in records):
+            raise ValueError("Another post already uses this title-derived ID; use a different title or explicit post_id")
         # Avoid taking over another page's URL, including non-post pages.
         for other in list(repo.glob("*.md")) + list(repo.glob("*.html")):
             other_metadata, _ = split_markdown(other.read_text())
@@ -135,7 +146,7 @@ def publish_post(repo, submission, manifest):
             if url and str(url).strip("/") == permalink.strip("/"):
                 raise ValueError("Another page already uses this permalink")
     permalink = "/" + str(permalink).strip("/") + "/"
-    metadata.update(layout="post", permalink=permalink, upload_id=identity,
+    metadata.update(layout="post", permalink=permalink, upload_id=identity, post_id=identity,
                     upload_filename=incoming["key"], upload_revision=manifest["id"],
                     render_with_liquid=False)
     entry.parent.mkdir(parents=True, exist_ok=True)