Candidates chosen with the arrow-down list are recorded on commit as toneless reading -> phrase with a count. The converter lifts a picked phrase just above the best lexicon entry for that reading (more for more picks), so it comes first next time without overriding longer phrases. Up to 2000 pairs, least recently used evicted. Stored as user-history.json on every platform; the Mac menu's clear item clears it too. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
66 lines
2.4 KiB
Python
66 lines
2.4 KiB
Python
"""Remembers the candidates the user picked. Port of UserHistory.swift.
|
|
|
|
Keys are toneless readings ("ㄊㄧㄢ", "ㄐㄧㄣ-ㄊㄧㄢ"); a picked phrase is boosted only
|
|
where the lexicon has it for the reading being converted, so a toneless key is safe.
|
|
"""
|
|
|
|
|
|
class UserHistory:
|
|
max_entries = 2000 # (reading, phrase) pairs kept; the least recently used go first
|
|
max_count = 10
|
|
|
|
def __init__(self, data=None, on_change=None):
|
|
# reading -> {phrase: [count, last use]}
|
|
self.data = {}
|
|
self.on_change = on_change or (lambda data: None)
|
|
self._clock = 0
|
|
for reading, phrases in (data or {}).items():
|
|
if not isinstance(phrases, dict):
|
|
continue
|
|
for phrase, value in phrases.items():
|
|
try:
|
|
count, used = int(value[0]), int(value[1])
|
|
except (TypeError, ValueError, IndexError):
|
|
continue
|
|
self.data.setdefault(reading, {})[phrase] = [count, used]
|
|
self._clock = max(self._clock, used)
|
|
|
|
@staticmethod
|
|
def key(syllables):
|
|
return "-".join(s.toneless for s in syllables)
|
|
|
|
def record(self, syllables, phrase):
|
|
if not syllables or not phrase:
|
|
return
|
|
self._clock += 1
|
|
entry = self.data.setdefault(self.key(syllables), {}).setdefault(phrase, [0, 0])
|
|
entry[0] = min(self.max_count, entry[0] + 1)
|
|
entry[1] = self._clock
|
|
self._evict()
|
|
self.on_change(self.data)
|
|
|
|
def _evict(self):
|
|
pairs = [(v[1], r, p) for r, ps in self.data.items() for p, v in ps.items()]
|
|
if len(pairs) <= self.max_entries:
|
|
return
|
|
pairs.sort()
|
|
for _, r, p in pairs[:len(pairs) - self.max_entries]:
|
|
del self.data[r][p]
|
|
if not self.data[r]:
|
|
del self.data[r]
|
|
|
|
def clear(self):
|
|
self.data = {}
|
|
self.on_change(self.data)
|
|
|
|
def adjust(self, syllables, entries):
|
|
"""Lexicon entries [(phrase, score)] with picked phrases moved to the top: just above
|
|
the best entry, more so the more often they were picked. Returns a new list."""
|
|
picked = self.data.get(self.key(syllables))
|
|
if not picked or not entries:
|
|
return entries
|
|
top = entries[0][1]
|
|
out = [(p, max(s, top + 0.01 + 0.1 * picked[p][0]) if p in picked else s) for p, s in entries]
|
|
out.sort(key=lambda e: -e[1])
|
|
return out
|