fix(places): submit and link the phase variants
PR Checks / Frontend Typecheck + Tests (pull_request) Successful in 1m3s
PR Checks / Backend Smoke (pull_request) Successful in 8s
PR Checks / Build Backend (no push) (pull_request) Successful in 17s
PR Checks / Build Frontend (no push) (pull_request) Successful in 45s
PR Checks / Build Pipeline (no push) (pull_request) Successful in 10s
PR Checks / AI Code Review (Claude) (pull_request) Failing after 2m39s
PR Checks / Frontend Typecheck + Tests (pull_request) Successful in 1m3s
PR Checks / Backend Smoke (pull_request) Successful in 8s
PR Checks / Build Backend (no push) (pull_request) Successful in 17s
PR Checks / Build Frontend (no push) (pull_request) Successful in 45s
PR Checks / Build Pipeline (no push) (pull_request) Successful in 10s
PR Checks / AI Code Review (Claude) (pull_request) Failing after 2m39s
/schools/[place]/[phase] shipped as routes but reached nothing. The sitemap emitted one URL per registry entry and the registry had no phase dimension, so ~950 pages were absent from every sitemap — and PlaceView did not link them either, leaving them reachable by nothing at all. That is the query shape the baseline actually showed: 'primary schools in beccles', 'secondary schools in brentwood'. Publishing the routes without a path in meant building for the demand and then hiding from it. Place now carries phase_urns so the per-phase threshold can be applied without re-querying, the sitemap emits a variant wherever a phase clears the threshold on its own, and the API exposes the qualifying phases so the place page links only variants that exist. Outcodes are excluded: nobody searches 'primary schools in SW11' and those routes do not exist. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015mWQnpye9F299NVRCCSRvj
This commit is contained in:
1 parent
d3c63ccc6d
commit
6f749ed21f
8 files changed
+148
-11
No files matched your search
+31
-3
@@ -14,7 +14,7 @@ from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import re
|
||||
from dataclasses import dataclass
|
||||
from dataclasses import dataclass, field
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
@@ -30,6 +30,13 @@ class Place:
|
||||
name: str
|
||||
urns: tuple[int, ...]
|
||||
parent_authority: str | None # authority NAME, for the 301 target
|
||||
# URNs per phase, so the per-phase threshold can be applied without
|
||||
# re-querying. A place with 30 primaries and 2 secondaries publishes a
|
||||
# primary variant and no secondary one.
|
||||
phase_urns: dict[str, tuple[int, ...]] = field(default_factory=dict)
|
||||
|
||||
def publishes_phase(self, phase: str) -> bool:
|
||||
return len(self.phase_urns.get(phase, ())) >= MIN_SCHOOLS
|
||||
|
||||
@property
|
||||
def key(self) -> str:
|
||||
@@ -46,6 +53,24 @@ def _publishable_urns(df) -> set[int]:
|
||||
return set(df.loc[df[cols].notna().any(axis=1), "urn"].astype(int))
|
||||
|
||||
|
||||
def _phase_urns(group, publishable: set[int]) -> dict[str, tuple[int, ...]]:
|
||||
"""URNs per phase. All-through schools count toward both, matching the
|
||||
PHASE_GROUPS mapping the search filters already use."""
|
||||
from backend.app import PHASE_GROUPS
|
||||
|
||||
if "phase" not in group.columns:
|
||||
return {}
|
||||
lowered = group["phase"].fillna("").str.lower()
|
||||
out: dict[str, tuple[int, ...]] = {}
|
||||
for phase in ("primary", "secondary"):
|
||||
wanted = PHASE_GROUPS.get(phase, set())
|
||||
subset = group[lowered.isin(wanted)]
|
||||
urns = tuple(sorted({int(u) for u in subset["urn"]} & publishable))
|
||||
if urns:
|
||||
out[phase] = urns
|
||||
return out
|
||||
|
||||
|
||||
def _parent_authority(group) -> str | None:
|
||||
"""The most common authority in a group — the useful 301 target.
|
||||
|
||||
@@ -79,6 +104,7 @@ def _group(df, column: str, kind: str, publishable: set[int]) -> dict[str, Place
|
||||
place = Place(
|
||||
kind=kind, slug=slug, name=name, urns=urns,
|
||||
parent_authority=_parent_authority(group) if kind == "town" else None,
|
||||
phase_urns=_phase_urns(group, publishable),
|
||||
)
|
||||
out[place.key] = place
|
||||
return out
|
||||
@@ -111,7 +137,8 @@ def _outcode_places(df, publishable: set[int]) -> dict[str, Place]:
|
||||
if len(urns) < MIN_SCHOOLS:
|
||||
continue
|
||||
place = Place(kind="outcode", slug=str(oc).lower(), name=str(oc),
|
||||
urns=urns, parent_authority=_parent_authority(group))
|
||||
urns=urns, parent_authority=_parent_authority(group),
|
||||
phase_urns=_phase_urns(group, publishable))
|
||||
out[place.key] = place
|
||||
return out
|
||||
|
||||
@@ -153,7 +180,8 @@ def _locality_places(df, publishable: set[int],
|
||||
slug, ", ".join(outcodes), len(urns), MIN_SCHOOLS)
|
||||
continue
|
||||
place = Place(kind="locality", slug=slug, name=name, urns=urns,
|
||||
parent_authority=_parent_authority(group))
|
||||
parent_authority=_parent_authority(group),
|
||||
phase_urns=_phase_urns(group, publishable))
|
||||
out[place.key] = place
|
||||
return out
|
||||
|
||||
|
||||
Reference in new issue
Block a user