fix(datacenters): report newly tagged features osmium cannot export

A still-tagged feature without exportable geometry already keeps its old
line. A newly tagged one had nowhere to go and was dropped silently; it is
now listed as skipped with a warning, so a refresh never loses a site or
hides a broken one.

scripts/build-datacenters-norway.py

@@ -182,12 +182,13 @@ def feature_line(key, sequence, fresh):
 
 
 def merge(lines, fresh, rings, tagged):
-    out, seen, sequence = [], set(), 0
-    report = {'kept': 0, 'updated': [], 'removed': [], 'added': [], 'unexported': []}
+    out, seen, known, sequence = [], set(), set(), 0
+    report = {'kept': 0, 'updated': [], 'removed': [], 'added': [], 'unexported': [], 'skipped': []}
     for line in lines:
         feature = json.loads(line)
         sequence = max(sequence, feature['properties']['id'])
         key = osm_key(feature)
+        known.add(key)
         if key in fresh:
             seen.add(key)
             old_tags = feature['properties']['tags']
@@ -211,6 +212,8 @@ def merge(lines, fresh, rings, tagged):
         sequence += 1
         out.append(feature_line(key, sequence, fresh[key]))
         report['added'].append(key)
+    # newly tagged, but osmium built no usable geometry: nothing to add yet
+    report['skipped'] = sorted(set(tagged) - set(fresh) - known, key=lambda k: (k[0], int(k[1:])))
     if len({osm_key(json.loads(line)) for line in out}) != len(out):
         raise ValueError('Duplicate OSM identity')
     return out, report
@@ -239,6 +242,9 @@ def main():
     if report['unexported']:
         print('warning: kept the old line of tagged features osmium did not export: %s'
               % ', '.join(report['unexported']), file=sys.stderr)
+    if report['skipped']:
+        print('warning: did not add newly tagged features osmium did not export: %s'
+              % ', '.join(report['skipped']), file=sys.stderr)
     payload = '\n'.join(merged) + '\n'
     if args.verify:
         if payload != DATASET.read_text(encoding='utf-8'):

src/data/datacentersNorwayRefresh.test.mjs

@@ -52,9 +52,10 @@ def line(osm_id, sequence):
                                       'type': 'data_center', 'osm_id': osm_id}})
 norway = [([(0, 0), (20, 0), (20, 80), (0, 80)], False)]
 lines = [line(7, 1), line(8, 2)]
-out, report = merge(lines, {}, norway, {'w7'})
+out, report = merge(lines, {}, norway, {'w7', 'w12'})
 assert out == [lines[0]], out
 assert report['unexported'] == ['w7'] and report['removed'] == ['w8'], report
+assert report['skipped'] == ['w12'] and report['added'] == [], report
 `,
   );
 });

src/data/local_data/datacenters/README.md

@@ -29,7 +29,8 @@ reflects OSM as of the extract below, everything else the original snapshot.
 - Contact tags are dropped as above; unchanged features keep their original
   line, so geometry is only rewritten when tags or rings actually changed.
   A feature is removed only once it is no longer tagged; one still tagged but
-  without an exportable geometry keeps its line and is reported as unexported.
+  without an exportable geometry keeps its line and is reported as unexported,
+  and a newly tagged one osmium cannot export is reported as skipped.
 - Refresh: `python3 scripts/build-datacenters-norway.py --cache <dir>` uses
   Geofabrik's current Norway extract and prints the dated name it used; record
   that name, its OSM timestamp and MD5 here. Requires `osmium-tool`.