Date photo uploads from capture metadata

photo-upload/publisher.py

@@ -4,6 +4,7 @@ import json
 import logging
 import os
 from pathlib import Path
+import re
 import shutil
 import subprocess
 import sys
@@ -15,6 +16,13 @@ from posts import publish_post
 log = logging.getLogger("publisher")
 
 
+def entry_date(path):
+    match = re.search(r'^date: "(\d{4}-\d{2}-\d{2})', path.read_text(), re.MULTILINE)
+    if not match:
+        raise ValueError(f"Photo entry has no valid date: {path.name}")
+    return match.group(1)
+
+
 class Publisher:
     def __init__(self):
         self.data = Path(os.environ.get("PHOTO_DATA", "/data"))
@@ -50,6 +58,7 @@ class Publisher:
             self.state(job, "publishing")
         try:
             outcomes = {}
+            replaced_photos = {}
             if not (self.repo / ".git").is_dir():
                 self.git("clone", "--branch", self.branch, "--single-branch", "--",
                          self.remote, str(self.repo), directory=self.work)
@@ -85,6 +94,14 @@ class Publisher:
                     continue
                 entry = Path("_art") / f"{manifest['date'][:10]}-photo-{job}.md"
                 images = Path("img/arts/uploads") / job
+                replaces = manifest.get("replaces", "")
+                if re.fullmatch(r"[a-f0-9]{64}", replaces) and replaces != job:
+                    for previous in (self.repo / "_art").glob(f"*-photo-{replaces}*.md"):
+                        self.git("rm", "--ignore-unmatch", "--",
+                                 str(previous.relative_to(self.repo)))
+                    previous_images = Path("img/arts/uploads") / replaces
+                    self.git("rm", "-r", "--ignore-unmatch", "--", str(previous_images))
+                    replaced_photos[job] = replaces
                 (self.repo / entry).parent.mkdir(parents=True, exist_ok=True)
                 entries = submission / "entries"
                 if entries.is_dir():
@@ -92,7 +109,7 @@ class Publisher:
                     # is republished by a newer service version.
                     self.git("rm", "--ignore-unmatch", "--", str(entry))
                     for source in sorted(entries.glob("*.md")):
-                        destination = Path("_art") / f"{manifest['date'][:10]}-photo-{job}-{source.stem}.md"
+                        destination = Path("_art") / f"{entry_date(source)}-photo-{job}-{source.stem}.md"
                         shutil.copyfile(source, self.repo / destination)
                         self.git("add", "--", str(destination))
                 else:
@@ -106,6 +123,8 @@ class Publisher:
             commit = self.git("rev-parse", "HEAD")
             for job in jobs:
                 self.state(job, "pushed", commit=commit, **outcomes.get(job, {}))
+                if job in replaced_photos:
+                    self.state(replaced_photos[job], "superseded", replaced_by=job)
             # A subsequent revision replaces the old one in the rendered site.
             for job, outcome in outcomes.items():
                 job_date = json.loads((self.data / "submissions" / job / "manifest.json").read_text())["date"]