Files

111 lines
4.0 KiB
Python

"""§22.4a SLICE-3 — faceted catalog filtering + counts (read).
Pure functions over already-mirrored entries; no I/O, no DB. An "entry" here is
a plain dict carrying at least:
- "state": the lifecycle state column,
- "metadata_malformed": bool,
- "meta": the per-entry metadata mapping (from cached_rfcs.meta_json).
Facetable fields (§5.1, plan decision 1): a collection's declared `enum` and
`tags` fields, in declaration order, plus the built-in `state` facet appended
last — but only when the collection declares a schema (INV-5: a no-`fields:`
collection has no facets at all, so the frontend keeps its legacy chips). `text`
fields are not faceted in v1 (they get a detail control in SLICE-4).
Counts use drill-down semantics (plan decision 2): the count for a value of
field F is taken over entries matching every OTHER field's selection (and the
malformed toggle), not F's own — so within-field values stay switchable (OR
within a field, AND across fields). The returned items list applies ALL
selections.
"""
from __future__ import annotations
from typing import Any
# enum + tags are facetable; text is rendered as a detail control (SLICE-4).
FACETABLE_TYPES = {"enum", "tags"}
def facet_fields(fields: dict[str, dict] | None) -> list[tuple[str, str]]:
"""Ordered `[(name, type), ...]` facetable from the schema, `state` last.
Empty when the collection declares no schema (INV-5)."""
if not fields:
return []
out = [
(name, spec.get("type"))
for name, spec in fields.items()
if spec.get("type") in FACETABLE_TYPES
]
out.append(("state", "enum"))
return out
def allowed_filter_keys(fields: dict[str, dict] | None) -> set[str]:
"""Query-param keys the collection-scoped list accepts (plan decision 6)."""
keys = {name for name, _ in facet_fields(fields)}
keys.update({"unreviewed", "malformed"})
return keys
def _values_for(entry: dict[str, Any], name: str, ftype: str) -> list[str]:
"""The facet value(s) an entry contributes for field `name` (str-cast)."""
if name == "state":
v = entry.get("state")
return [str(v)] if v else []
meta = entry.get("meta") or {}
v = meta.get(name)
if v is None:
return []
if ftype == "tags":
return [str(x) for x in v] if isinstance(v, list) else []
return [str(v)]
def _matches(entry: dict[str, Any], name: str, ftype: str, selected: set[str]) -> bool:
if not selected:
return True
return bool(set(_values_for(entry, name, ftype)) & selected) # OR within field
def filter_and_count(
entries: list[dict[str, Any]],
fields: dict[str, dict] | None,
selections: dict[str, set[str]],
only_malformed: bool = False,
) -> tuple[list[dict[str, Any]], dict[str, dict[str, int]]]:
"""Filter `entries` by `selections` and compute drill-down facet counts.
`selections` maps a facet field name → the set of selected values (OR within
the field; AND across fields). `only_malformed` narrows items and counts to
entries flagged malformed (INV-3). Returns `(items, facets)` where
`facets = {field: {value: count}}`. With no schema → `([all passing], {})`.
"""
facetable = facet_fields(fields)
def passes_malformed(e: dict[str, Any]) -> bool:
return (not only_malformed) or bool(e.get("metadata_malformed"))
items = [
e for e in entries
if passes_malformed(e)
and all(_matches(e, n, t, selections.get(n, set())) for n, t in facetable)
]
facets: dict[str, dict[str, int]] = {}
for name, ftype in facetable:
counts: dict[str, int] = {}
for e in entries:
if not passes_malformed(e):
continue
if not all(
_matches(e, on, ot, selections.get(on, set()))
for on, ot in facetable
if on != name
):
continue
for val in _values_for(e, name, ftype):
counts[val] = counts.get(val, 0) + 1
facets[name] = counts
return items, facets