92 lines
3.1 KiB
Python
92 lines
3.1 KiB
Python
|
"""The place registry: what places the site publishes, and what is in each.
|
||
|
|
|
||
|
|
One module owns this question. The pages, the sitemap and the internal-link
|
||
|
|
modules all read from here, so the threshold and the collision rules exist in
|
||
|
|
exactly one place and are testable without a browser or a database.
|
||
|
|
|
||
|
|
Two namespaces, never one. 67 viable town names collide with a local
|
||
|
|
authority name, and the authority is the larger set in only 43 of them —
|
||
|
|
postal towns cross authority boundaries, so neither can absorb the other.
|
||
|
|
Keys are "<kind>:<slug>" so the collision cannot reappear in the dict.
|
||
|
|
"""
|
||
|
|
|
||
|
|
from __future__ import annotations
|
||
|
|
|
||
|
|
from dataclasses import dataclass
|
||
|
|
|
||
|
|
# Five schools with publishable data. Below this a place has nothing to say
|
||
|
|
# that a list of schools does not, and publishing it is index bloat.
|
||
|
|
MIN_SCHOOLS = 5
|
||
|
|
|
||
|
|
|
||
|
|
@dataclass(frozen=True)
|
||
|
|
class Place:
|
||
|
|
kind: str # "town" | "locality" | "authority" | "outcode"
|
||
|
|
slug: str
|
||
|
|
name: str
|
||
|
|
urns: tuple[int, ...]
|
||
|
|
parent_authority: str | None # authority NAME, for the 301 target
|
||
|
|
|
||
|
|
@property
|
||
|
|
def key(self) -> str:
|
||
|
|
return f"{self.kind}:{self.slug}"
|
||
|
|
|
||
|
|
|
||
|
|
def _publishable_urns(df) -> set[int]:
|
||
|
|
"""URNs with something a page could state, deduplicated across years."""
|
||
|
|
from backend.app import _PUBLISHABLE_FIELDS
|
||
|
|
|
||
|
|
cols = [c for c in _PUBLISHABLE_FIELDS if c in df.columns]
|
||
|
|
if not cols:
|
||
|
|
return set()
|
||
|
|
return set(df.loc[df[cols].notna().any(axis=1), "urn"].astype(int))
|
||
|
|
|
||
|
|
|
||
|
|
def _parent_authority(group) -> str | None:
|
||
|
|
"""The most common authority in a group — the useful 301 target.
|
||
|
|
|
||
|
|
A town spanning several authorities has no single parent, so the mode is
|
||
|
|
the honest answer rather than an arbitrary first row.
|
||
|
|
"""
|
||
|
|
if "local_authority" not in group.columns:
|
||
|
|
return None
|
||
|
|
top = group["local_authority"].dropna()
|
||
|
|
return str(top.mode().iloc[0]) if not top.empty else None
|
||
|
|
|
||
|
|
|
||
|
|
def _group(df, column: str, kind: str, publishable: set[int]) -> dict[str, Place]:
|
||
|
|
"""One Place per distinct value of `column` that clears the threshold."""
|
||
|
|
from backend.app import _slugify
|
||
|
|
|
||
|
|
if column not in df.columns:
|
||
|
|
return {}
|
||
|
|
|
||
|
|
out: dict[str, Place] = {}
|
||
|
|
for name, group in df.groupby(column, dropna=True):
|
||
|
|
name = str(name).strip()
|
||
|
|
if not name:
|
||
|
|
continue
|
||
|
|
urns = tuple(sorted({int(u) for u in group["urn"]} & publishable))
|
||
|
|
if len(urns) < MIN_SCHOOLS:
|
||
|
|
continue
|
||
|
|
slug = _slugify(name)
|
||
|
|
if not slug:
|
||
|
|
continue
|
||
|
|
place = Place(
|
||
|
|
kind=kind, slug=slug, name=name, urns=urns,
|
||
|
|
parent_authority=_parent_authority(group) if kind == "town" else None,
|
||
|
|
)
|
||
|
|
out[place.key] = place
|
||
|
|
return out
|
||
|
|
|
||
|
|
|
||
|
|
def build_place_registry(df) -> dict[str, Place]:
|
||
|
|
"""Every place the site publishes, keyed by "<kind>:<slug>"."""
|
||
|
|
if df.empty or "urn" not in df.columns:
|
||
|
|
return {}
|
||
|
|
|
||
|
|
publishable = _publishable_urns(df)
|
||
|
|
registry: dict[str, Place] = {}
|
||
|
|
registry.update(_group(df, "local_authority", "authority", publishable))
|
||
|
|
registry.update(_group(df, "town", "town", publishable))
|
||
|
|
return registry
|