89f843d223
The candidate matcher rejected valid downloads of titles with a '/' or ':' (e.g.
Sawano's "You See Big Girl / T:T") because the unified normalize() removed those
chars ("t:t" -> "tt") while keeping the '_' that source filenames substitute for
them ("T_T" -> "t_t") — the asymmetry tanked the similarity score. Now '/ \ : _'
all map to spaces before the strip, so "/ T:T" and "_ T_T" both normalize to "t t".
Verified on the real library: similarity for the Sawano pair 0.927 -> 1.000; only
348/40786 strings (0.85%, all containing those separators) change; worst-case
joined-variant match (e.g. "12:05" vs "1205") stays 0.889, well above the 0.70
title threshold — no match regressions. Fixes the matching half of #851.
24 lines
959 B
Python
24 lines
959 B
Python
"""#851: a '/' or ':' in a title must normalize the same as a source filename
|
|
that substituted '_' for them, so the candidate matcher stops rejecting valid
|
|
downloads (e.g. Sawano's "You See Big Girl / T:T" vs on-disk "..._ T_T")."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from core.matching.audio_verification import normalize, similarity
|
|
|
|
|
|
def test_slash_colon_title_matches_underscore_source():
|
|
assert normalize("You See Big Girl / T:T") == normalize("You See Big Girl _ T_T")
|
|
assert similarity("You See Big Girl / T:T", "You See Big Girl _ T_T") == 1.0
|
|
|
|
|
|
def test_separators_become_word_boundaries():
|
|
assert normalize("Re:Zero") == "re zero"
|
|
assert normalize("AC/DC") == "ac dc"
|
|
assert normalize("T_T") == "t t"
|
|
|
|
|
|
def test_joined_variant_stays_above_title_threshold():
|
|
# Spacing a separator must not drop a joined-variant match below 0.70.
|
|
assert similarity("AC/DC", "ACDC") >= 0.70
|
|
assert similarity("12:05", "1205") >= 0.70
|