8a0eef60b7
code_family_index(families) builds a code -> family key map once so a restamp run of ~1.15M chunks doesn't rescan every family per code. anchor_metadata gains an optional code_index kwarg that looks family membership up through it instead. Ruling A5: families with fewer than two codes are excluded from the index and from the default unindexed scan — the derived registry is ~17,187 keys and all but a handful are single-code stem families, where a 'families' anchor would just echo the code already in 'codes'. Only real groupings (today: ACP, CCM, PCM, TCM, APCM) get a families anchor.
56 lines
2.0 KiB
Python
56 lines
2.0 KiB
Python
"""pfs.anchors — metadata for chunks: codes, families, and element slugs."""
|
|
|
|
from pfs.anchors import anchor_metadata, code_family_index
|
|
from pfs.families import FAMILIES, Family
|
|
|
|
|
|
def test_codes_families_elements():
|
|
md = anchor_metadata(
|
|
"Use 99439 in conjunction with 99490; consent; per calendar month"
|
|
)
|
|
assert md["codes"] == "99439 99490"
|
|
assert md["families"] == "CCM"
|
|
assert (
|
|
"activity=consent" in md["elements"].split()
|
|
and "period=calendar-month" in md["elements"].split()
|
|
)
|
|
assert "relation=addon-of" in md["elements"].split() # detail dropped
|
|
|
|
|
|
def test_empty_and_unknown():
|
|
assert anchor_metadata("nothing here") == {
|
|
"codes": "",
|
|
"families": "",
|
|
"elements": "",
|
|
}
|
|
fams = {"X": Family("X", "X fam", ("12345", "23456"), ("x fam",))}
|
|
assert anchor_metadata("code 12345", families=fams)["families"] == "X"
|
|
|
|
|
|
def test_code_index_matches_unindexed_scan():
|
|
text = "Use 99439 in conjunction with 99490; consent; per calendar month"
|
|
index = code_family_index(FAMILIES)
|
|
assert anchor_metadata(text, code_index=index) == anchor_metadata(text)
|
|
|
|
|
|
def test_code_index_keeps_first_family_on_collision():
|
|
fams = {
|
|
"A": Family("A", "A fam", ("12345", "23456"), ("a fam",)),
|
|
"B": Family("B", "B fam", ("12345", "34567"), ("b fam",)),
|
|
}
|
|
index = code_family_index(fams)
|
|
assert index["12345"] == "A"
|
|
|
|
|
|
def test_single_code_family_never_stamped():
|
|
"""A stem-derived family of exactly one code (~17,182 of 17,187
|
|
derived keys) is not a grouping worth its own anchor — it would just
|
|
echo the code already in 'codes' (Ruling A5)."""
|
|
fams = {"SOLO": Family("SOLO", "Solo", ("54321",), ("solo",))}
|
|
assert "SOLO" not in code_family_index(fams)
|
|
assert anchor_metadata("code 54321", families=fams)["families"] == ""
|
|
index = code_family_index(fams)
|
|
assert (
|
|
anchor_metadata("code 54321", families=fams, code_index=index)["families"] == ""
|
|
)
|