afiqzudinhadi/zmk-steno-engine
1
0
Fork 0
Code Issues 3 Pull requests Projects Releases Packages Wiki Activity Actions

Parse Plover number strokes: digits = number bar + positional key

Browse source 
parse_stroke silently dropped digit characters, so number strokes
collapsed onto their letter-only bitmasks: "12K" and "K" both parsed
to K → first-wins dedup let "12K"→"12:00" clobber "K"→"can" (and 297
more core entries: -R→are eaten by 12-R→XII, -S→{^s} by 2-S→2s...).
Digits now map per Plover: 1=S- 2=T- 3=P- 4=H- 5=A- 0=O- 6=-F 7=-P
8=-L 9=-T, all implying #. Collisions: 298 → 0; 300 union keys and
161 translations recovered. Verified: all 262,309 entries byte-exact,
42,000-vector host round trip 0 mismatches.
This commit is contained in:
afiqzudinhadi 2026-07-03 20:08:45 +08:00
parent 2e7853aad3
commit 23439a52f7
2 changed files with 44 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

25
tools/compile_mphf.py
View file

@ -31,14 +31,27 @@ STENO_KEYS = {
IMPLICIT_HYPHEN = set('AOEU*')
# Plover number strokes: a digit means the number bar (#) plus the key
# sharing its physical position. Each digit maps to exactly one key.
DIGIT_KEYS = {
'1': 'S-', '2': 'T-', '3': 'P-', '4': 'H-',
'5': 'A-', '0': 'O-',
'6': '-F', '7': '-P', '8': '-L', '9': '-T',
}
def parse_stroke(s):
result = 0
if '#' in s:
result |= STENO_KEYS['#']
s = s.replace('#', '')
if any(c in DIGIT_KEYS for c in s):
result |= STENO_KEYS['#']
has_hyphen = '-' in s
s_clean = s.replace('-', '')
if not has_hyphen and not any(c in IMPLICIT_HYPHEN for c in s_clean):
if (not has_hyphen and
not any(c in IMPLICIT_HYPHEN for c in s_clean) and
not any(c in DIGIT_KEYS for c in s_clean)):
for c in s_clean:
key = c + '-'
if key in STENO_KEYS:
@ -49,7 +62,9 @@ def parse_stroke(s):
for i, c in enumerate(s):
if c == '-':
continue
if c in 'AO':
if c in DIGIT_KEYS:
result |= STENO_KEYS[DIGIT_KEYS[c]]
elif c in 'AO':
result |= STENO_KEYS[c + '-']
elif c in 'EU':
result |= STENO_KEYS['-' + c]
@ -62,7 +77,11 @@ def parse_stroke(s):
else:
past_vowels = False
for c in s_clean:
if c in 'AO':
if c in DIGIT_KEYS:
result |= STENO_KEYS[DIGIT_KEYS[c]]
if c in '5069' or c in '78':
past_vowels = True
elif c in 'AO':
result |= STENO_KEYS[c + '-']
past_vowels = True
elif c in 'EU':

25
tools/compile_v4.py
View file

@ -98,14 +98,27 @@ STENO_KEYS = {
IMPLICIT_HYPHEN = set('AOEU*')
# Plover number strokes: a digit means the number bar (#) plus the key
# sharing its physical position. Each digit maps to exactly one key.
DIGIT_KEYS = {
'1': 'S-', '2': 'T-', '3': 'P-', '4': 'H-',
'5': 'A-', '0': 'O-',
'6': '-F', '7': '-P', '8': '-L', '9': '-T',
}
def parse_stroke(s):
result = 0
if '#' in s:
result |= STENO_KEYS['#']
s = s.replace('#', '')
if any(c in DIGIT_KEYS for c in s):
result |= STENO_KEYS['#']
has_hyphen = '-' in s
s_clean = s.replace('-', '')
if not has_hyphen and not any(c in IMPLICIT_HYPHEN for c in s_clean):
if (not has_hyphen and
not any(c in IMPLICIT_HYPHEN for c in s_clean) and
not any(c in DIGIT_KEYS for c in s_clean)):
for c in s_clean:
key = c + '-'
if key in STENO_KEYS:
@ -116,7 +129,9 @@ def parse_stroke(s):
for i, c in enumerate(s):
if c == '-':
continue
if c in 'AO':
if c in DIGIT_KEYS:
result |= STENO_KEYS[DIGIT_KEYS[c]]
elif c in 'AO':
result |= STENO_KEYS[c + '-']
elif c in 'EU':
result |= STENO_KEYS['-' + c]
@ -129,7 +144,11 @@ def parse_stroke(s):
else:
past_vowels = False
for c in s_clean:
if c in 'AO':
if c in DIGIT_KEYS:
result |= STENO_KEYS[DIGIT_KEYS[c]]
if c in '5069' or c in '78':
past_vowels = True
elif c in 'AO':
result |= STENO_KEYS[c + '-']
past_vowels = True
elif c in 'EU':