liblevenshtein 0.9.1

Levenshtein/Universal Automata for approximate string matching using various dictionary backends
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259

// Cree Base Phonetic Rules
// ========================
// Phonetic rules for Cree (ᓀᐦᐃᔭᐍᐏᐣ / Nēhiyawēwin).
// Spoken by approximately 100,000 people across Canada.
//
// Cree features:
//   - Syllabics script (Canadian Aboriginal Syllabics)
//   - Also written in Standard Roman Orthography (SRO)
//   - Vowel length distinction (short vs long)
//   - No consonant clusters in syllable onset
//   - Complex verb morphology (polysynthetic)
//
// Writing systems:
//   - Cree syllabics: ᓀᐦᐃᔭᐍᐏᐣ
//   - SRO (Standard Roman Orthography): nēhiyawēwin
//   - Long vowels marked with macron (ā, ē, ī, ō) or circumflex (â, ê, î, ô)
//
// Rule IDs: 8000-8199

@name "Cree Phonetic Rules"
@version "1.0.1"
@author "liblevenshtein"
@description "Phonetic normalization rules for Cree (Plains Cree)"
@changelog "1.0.1: Removed identity mappings (a→a, i→i, o→o, p→p, t→t, k→k, s→s, h→h, m→m, n→n, w→w) as they are redundant"

// ============================================================
// SHORT VOWELS
// ============================================================
// Note: Short vowels a, i, o pass through unchanged (no explicit rules needed)

// ============================================================
// LONG VOWELS - macron (weight 0.05)
// ============================================================

[id: 8005, name: "a long macron", weight: 0.05, group: cree_long_vowels, ipa: "/aː/"]
ā -> aː;

[id: 8006, name: "e long", weight: 0.05, group: cree_long_vowels, ipa: "/eː/"]
ē -> eː;

[id: 8007, name: "i long macron", weight: 0.05, group: cree_long_vowels, ipa: "/iː/"]
ī -> iː;

[id: 8008, name: "o long macron", weight: 0.05, group: cree_long_vowels, ipa: "/oː/"]
ō -> oː;

// Long vowels - circumflex (alternative orthography)
[id: 8010, name: "a long circumflex", weight: 0.05, group: cree_long_vowels, ipa: "/aː/"]
â -> aː;

[id: 8011, name: "e long circumflex", weight: 0.05, group: cree_long_vowels, ipa: "/eː/"]
ê -> eː;

[id: 8012, name: "i long circumflex", weight: 0.05, group: cree_long_vowels, ipa: "/iː/"]
î -> iː;

[id: 8013, name: "o long circumflex", weight: 0.05, group: cree_long_vowels, ipa: "/oː/"]
ô -> oː;

// ============================================================
// CONSONANTS (weight 0.05)
// ============================================================
// Note: Basic consonants p, t, k, s, h, m, n, w pass through unchanged

[id: 8023, name: "c affricate", weight: 0.05, group: cree_consonants, ipa: "/t͡s/"]
c -> t͡s;

// Some dialects use ch instead of c
[id: 8024, name: "ch affricate", weight: 0.05, group: cree_consonants, ipa: "/t͡ʃ/"]
ch -> t͡ʃ;

[id: 8030, name: "y", weight: 0.05, group: cree_consonants, ipa: "/j/"]
y -> j;

// ============================================================
// CREE SYLLABICS - E series (ᐁ)
// ============================================================

[id: 8040, name: "syllabic e", weight: 0.05, group: cree_syllabics, ipa: "/eː/"]
ᐁ -> eː;

[id: 8041, name: "syllabic pe", weight: 0.05, group: cree_syllabics, ipa: "/peː/"]
ᐯ -> peː;

[id: 8042, name: "syllabic te", weight: 0.05, group: cree_syllabics, ipa: "/teː/"]
ᑌ -> teː;

[id: 8043, name: "syllabic ke", weight: 0.05, group: cree_syllabics, ipa: "/keː/"]
ᑫ -> keː;

[id: 8044, name: "syllabic ce", weight: 0.05, group: cree_syllabics, ipa: "/t͡seː/"]
ᒉ -> t͡seː;

[id: 8045, name: "syllabic me", weight: 0.05, group: cree_syllabics, ipa: "/meː/"]
ᒣ -> meː;

[id: 8046, name: "syllabic ne", weight: 0.05, group: cree_syllabics, ipa: "/neː/"]
ᓀ -> neː;

[id: 8047, name: "syllabic se", weight: 0.05, group: cree_syllabics, ipa: "/seː/"]
ᓭ -> seː;

[id: 8048, name: "syllabic ye", weight: 0.05, group: cree_syllabics, ipa: "/jeː/"]
ᔦ -> jeː;

[id: 8049, name: "syllabic we", weight: 0.05, group: cree_syllabics, ipa: "/weː/"]
ᐍ -> weː;

// ============================================================
// CREE SYLLABICS - I series (ᐃ)
// ============================================================

[id: 8050, name: "syllabic i", weight: 0.05, group: cree_syllabics, ipa: "/i/"]
ᐃ -> i;

[id: 8051, name: "syllabic pi", weight: 0.05, group: cree_syllabics, ipa: "/pi/"]
ᐱ -> pi;

[id: 8052, name: "syllabic ti", weight: 0.05, group: cree_syllabics, ipa: "/ti/"]
ᑎ -> ti;

[id: 8053, name: "syllabic ki", weight: 0.05, group: cree_syllabics, ipa: "/ki/"]
ᑭ -> ki;

[id: 8054, name: "syllabic ci", weight: 0.05, group: cree_syllabics, ipa: "/t͡si/"]
ᒋ -> t͡si;

[id: 8055, name: "syllabic mi", weight: 0.05, group: cree_syllabics, ipa: "/mi/"]
ᒥ -> mi;

[id: 8056, name: "syllabic ni", weight: 0.05, group: cree_syllabics, ipa: "/ni/"]
ᓂ -> ni;

[id: 8057, name: "syllabic si", weight: 0.05, group: cree_syllabics, ipa: "/si/"]
ᓯ -> si;

[id: 8058, name: "syllabic yi", weight: 0.05, group: cree_syllabics, ipa: "/ji/"]
ᔨ -> ji;

[id: 8059, name: "syllabic wi", weight: 0.05, group: cree_syllabics, ipa: "/wi/"]
ᐏ -> wi;

// ============================================================
// CREE SYLLABICS - O series (ᐅ)
// ============================================================

[id: 8060, name: "syllabic o", weight: 0.05, group: cree_syllabics, ipa: "/o/"]
ᐅ -> o;

[id: 8061, name: "syllabic po", weight: 0.05, group: cree_syllabics, ipa: "/po/"]
ᐳ -> po;

[id: 8062, name: "syllabic to", weight: 0.05, group: cree_syllabics, ipa: "/to/"]
ᑐ -> to;

[id: 8063, name: "syllabic ko", weight: 0.05, group: cree_syllabics, ipa: "/ko/"]
ᑯ -> ko;

[id: 8064, name: "syllabic co", weight: 0.05, group: cree_syllabics, ipa: "/t͡so/"]
ᒍ -> t͡so;

[id: 8065, name: "syllabic mo", weight: 0.05, group: cree_syllabics, ipa: "/mo/"]
ᒧ -> mo;

[id: 8066, name: "syllabic no", weight: 0.05, group: cree_syllabics, ipa: "/no/"]
ᓄ -> no;

[id: 8067, name: "syllabic so", weight: 0.05, group: cree_syllabics, ipa: "/so/"]
ᓱ -> so;

[id: 8068, name: "syllabic yo", weight: 0.05, group: cree_syllabics, ipa: "/jo/"]
ᔪ -> jo;

[id: 8069, name: "syllabic wo", weight: 0.05, group: cree_syllabics, ipa: "/wo/"]
ᐓ -> wo;

// ============================================================
// CREE SYLLABICS - A series (ᐊ)
// ============================================================

[id: 8070, name: "syllabic a", weight: 0.05, group: cree_syllabics, ipa: "/a/"]
ᐊ -> a;

[id: 8071, name: "syllabic pa", weight: 0.05, group: cree_syllabics, ipa: "/pa/"]
ᐸ -> pa;

[id: 8072, name: "syllabic ta", weight: 0.05, group: cree_syllabics, ipa: "/ta/"]
ᑕ -> ta;

[id: 8073, name: "syllabic ka", weight: 0.05, group: cree_syllabics, ipa: "/ka/"]
ᑲ -> ka;

[id: 8074, name: "syllabic ca", weight: 0.05, group: cree_syllabics, ipa: "/t͡sa/"]
ᒐ -> t͡sa;

[id: 8075, name: "syllabic ma", weight: 0.05, group: cree_syllabics, ipa: "/ma/"]
ᒪ -> ma;

[id: 8076, name: "syllabic na", weight: 0.05, group: cree_syllabics, ipa: "/na/"]
ᓇ -> na;

[id: 8077, name: "syllabic sa", weight: 0.05, group: cree_syllabics, ipa: "/sa/"]
ᓴ -> sa;

[id: 8078, name: "syllabic ya", weight: 0.05, group: cree_syllabics, ipa: "/ja/"]
ᔭ -> ja;

[id: 8079, name: "syllabic wa", weight: 0.05, group: cree_syllabics, ipa: "/wa/"]
ᐘ -> wa;

// ============================================================
// CREE SYLLABICS - FINALS (coda consonants)
// ============================================================

[id: 8090, name: "final p", weight: 0.05, group: cree_finals, ipa: "/p/"]
ᑊ -> p;

[id: 8091, name: "final t", weight: 0.05, group: cree_finals, ipa: "/t/"]
ᐟ -> t;

[id: 8092, name: "final k", weight: 0.05, group: cree_finals, ipa: "/k/"]
ᐠ -> k;

[id: 8093, name: "final c", weight: 0.05, group: cree_finals, ipa: "/t͡s/"]
ᐨ -> t͡s;

[id: 8094, name: "final m", weight: 0.05, group: cree_finals, ipa: "/m/"]
ᒼ -> m;

[id: 8095, name: "final n", weight: 0.05, group: cree_finals, ipa: "/n/"]
ᐣ -> n;

[id: 8096, name: "final s", weight: 0.05, group: cree_finals, ipa: "/s/"]
ᐢ -> s;

[id: 8097, name: "final y", weight: 0.05, group: cree_finals, ipa: "/j/"]
ᕀ -> j;

[id: 8098, name: "final w", weight: 0.05, group: cree_finals, ipa: "/w/"]
ᐤ -> w;

[id: 8099, name: "final h", weight: 0.05, group: cree_finals, ipa: "/h/"]
ᐦ -> h;

// ============================================================
// COMMON WORDS
// ============================================================

[id: 8100, name: "nehiyawewin cree language", weight: 0.02, group: cree_common]
nēhiyawēwin -> neːhijaweːwin;

[id: 8101, name: "tanisi hello", weight: 0.02, group: cree_common]
tānisi -> taːnisi;

[id: 8102, name: "ekosi ok goodbye", weight: 0.02, group: cree_common]
ēkosi -> eːkosi;

[id: 8103, name: "kinanaskomitin thank you", weight: 0.02, group: cree_common]
kinanāskomitin -> kinanaːskomitin;