glost-core 0.5.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +63 -0
- package/LICENSE +21 -0
- package/README.md +199 -0
- package/dist/__benchmarks__/document-creation.bench.d.ts +7 -0
- package/dist/__benchmarks__/document-creation.bench.d.ts.map +1 -0
- package/dist/__benchmarks__/document-creation.bench.js +71 -0
- package/dist/__benchmarks__/document-creation.bench.js.map +1 -0
- package/dist/__benchmarks__/traversal.bench.d.ts +7 -0
- package/dist/__benchmarks__/traversal.bench.d.ts.map +1 -0
- package/dist/__benchmarks__/traversal.bench.js +124 -0
- package/dist/__benchmarks__/traversal.bench.js.map +1 -0
- package/dist/cli/migrate.d.ts +8 -0
- package/dist/cli/migrate.d.ts.map +1 -0
- package/dist/cli/migrate.js +229 -0
- package/dist/cli/migrate.js.map +1 -0
- package/dist/errors.d.ts +168 -0
- package/dist/errors.d.ts.map +1 -0
- package/dist/errors.js +300 -0
- package/dist/errors.js.map +1 -0
- package/dist/guards.d.ts +103 -0
- package/dist/guards.d.ts.map +1 -0
- package/dist/guards.js +264 -0
- package/dist/guards.js.map +1 -0
- package/dist/index.d.ts +9 -0
- package/dist/index.d.ts.map +1 -0
- package/dist/index.js +25 -0
- package/dist/index.js.map +1 -0
- package/dist/nodes.d.ts +227 -0
- package/dist/nodes.d.ts.map +1 -0
- package/dist/nodes.js +243 -0
- package/dist/nodes.js.map +1 -0
- package/dist/types.d.ts +442 -0
- package/dist/types.d.ts.map +1 -0
- package/dist/types.js +51 -0
- package/dist/types.js.map +1 -0
- package/dist/utils.d.ts +247 -0
- package/dist/utils.d.ts.map +1 -0
- package/dist/utils.js +564 -0
- package/dist/utils.js.map +1 -0
- package/dist/validators.d.ts +1876 -0
- package/dist/validators.d.ts.map +1 -0
- package/dist/validators.js +302 -0
- package/dist/validators.js.map +1 -0
- package/package.json +73 -0
- package/src/__benchmarks__/document-creation.bench.ts +92 -0
- package/src/__benchmarks__/traversal.bench.ts +152 -0
- package/src/__tests__/README.md +20 -0
- package/src/__tests__/example.test.ts +43 -0
- package/src/__tests__/example.ts +186 -0
- package/src/__tests__/helpers.test.ts +178 -0
- package/src/__tests__/mock-data.ts +624 -0
- package/src/__tests__/performance.test.ts +317 -0
- package/src/__tests__/traversal.test.ts +170 -0
- package/src/cli/migrate.ts +294 -0
- package/src/errors.ts +394 -0
- package/src/guards.ts +341 -0
- package/src/index.ts +69 -0
- package/src/nodes.ts +409 -0
- package/src/types.ts +633 -0
- package/src/utils.ts +730 -0
- package/src/validators.ts +336 -0
- package/tsconfig.json +9 -0
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"validators.d.ts","sourceRoot":"","sources":["../src/validators.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,CAAC,EAAE,MAAM,KAAK,CAAC;AAMxB;;GAEG;AACH,eAAO,MAAM,qBAAqB,iFAOhC,CAAC;AAEH;;GAEG;AACH,eAAO,MAAM,0BAA0B,0EAMrC,CAAC;AAEH;;GAEG;AACH,eAAO,MAAM,yBAAyB,sNAUpC,CAAC;AAEH;;GAEG;AACH,eAAO,MAAM,kBAAkB,+HAO7B,CAAC;AAEH;;GAEG;AACH,eAAO,MAAM,kBAAkB,yNAU7B,CAAC;AAEH;;GAEG;AACH,eAAO,MAAM,0BAA0B;;;;;;;;;;;;EAIrC,CAAC;AAEH;;GAEG;AACH,eAAO,MAAM,uBAAuB;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;EAOlC,CAAC;AAEH;;GAEG;AACH,eAAO,MAAM,yBAAyB;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAGrC,CAAC;AAEF;;GAEG;AACH,eAAO,MAAM,wBAAwB;IACnC,kDAAkD;;;;;;;;;;;;;;;;;;;;;;;;;;;EASlD,CAAC;AAEH;;GAEG;AACH,eAAO,MAAM,mBAAmB;;;;;;;;;;;;;;;;;;EAM9B,CAAC;AAEH;;GAEG;AACH,eAAO,MAAM,mBAAmB;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;QAzB9B,kDAAkD;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;EAgClD,CAAC;AAEH;;GAEG;AACH,eAAO,MAAM,uBAAuB;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;EAOlC,CAAC;AAEH;;GAEG;AACH,eAAO,MAAM,wBAAwB;;;;;;;;;;;;;;;;;;;;;;EAKnC,CAAC;AAEH;;GAEG;AACH,eAAO,MAAM,mBAAmB;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;EAW9B,CAAC;AAEH;;GAEG;AACH,eAAO,MAAM,eAAe;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;QA3E1B,kDAAkD;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;IAgFlD,CAAC;AAMH;;GAEG;AACH,wBAAgB,qBAAqB,CAAC,IAAI,EAAE,OAAO,GAAG,IAAI,IAAI,CAAC,CAAC,KAAK,CAAC,OAAO,mBAAmB,CAAC,CAGhG;AAED;;GAEG;AACH,wBAAgB,yBAAyB,CAAC,IAAI,EAAE,OAAO,GAAG,IAAI,IAAI,CAAC,CAAC,KAAK,CAAC,OAAO,uBAAuB,CAAC,CAGxG;AAED;;GAEG;AACH,wBAAgB,0BAA0B,CAAC,IAAI,EAAE,OAAO,GAAG,IAAI,IAAI,CAAC,CAAC,KAAK,CAAC,OAAO,wBAAwB,CAAC,CAG1G;AAED;;GAEG;AACH,wBAAgB,qBAAqB,CAAC,IAAI,EAAE,OAAO,GAAG,IAAI,IAAI,CAAC,CAAC,KAAK,CAAC,OAAO,mBAAmB,CAAC,CAGhG;AAED;;GAEG;AACH,wBAAgB,iBAAiB,CAAC,IAAI,EAAE,OAAO,GAAG,IAAI,IAAI,CAAC,CAAC,KAAK,CAAC,OAAO,eAAe,CAAC,CAGxF;AAED;;GAEG;AACH,wBAAgB,cAAc,CAAC,IAAI,EAAE,OAAO;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAE3C;AAED;;GAEG;AACH,wBAAgB,kBAAkB,CAAC,IAAI,EAAE,OAAO;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAE/C;AAED;;GAEG;AACH,wBAAgB,sBAAsB,CAAC,IAAI,EAAE,OAAO;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAEnD;AAED;;GAEG;AACH,wBAAgB,uBAAuB,CAAC,IAAI,EAAE,OAAO;;;;;;;;;;;;;;GAEpD;AAED;;GAEG;AACH,wBAAgB,kBAAkB,CAAC,IAAI,EAAE,OAAO;;;;;;;;;;;;;;;;;;;;;;;;;;GAE/C;AAED;;GAEG;AACH,wBAAgB,iBAAiB,CAAC,IAAI,EAAE,OAAO,GAAG,MAAM,EAAE,CA8CzD;AAMD,eAAO,MAAM,OAAO;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;QAxNlB,kDAAkD;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;YAAlD,kDAAkD;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;YAAlD,kDAAkD;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CAuOnD,CAAC"}
|
|
@@ -0,0 +1,302 @@
|
|
|
1
|
+
import { z } from 'zod';
|
|
2
|
+
// ============================================================================
|
|
3
|
+
// Zod Schemas for GLOST Validation
|
|
4
|
+
// ============================================================================
|
|
5
|
+
/**
|
|
6
|
+
* Linguistic level schema
|
|
7
|
+
*/
|
|
8
|
+
export const LinguisticLevelSchema = z.enum([
|
|
9
|
+
'character',
|
|
10
|
+
'syllable',
|
|
11
|
+
'word',
|
|
12
|
+
'phrase',
|
|
13
|
+
'sentence',
|
|
14
|
+
'paragraph'
|
|
15
|
+
]);
|
|
16
|
+
/**
|
|
17
|
+
* Pronunciation context schema
|
|
18
|
+
*/
|
|
19
|
+
export const PronunciationContextSchema = z.enum([
|
|
20
|
+
'formal',
|
|
21
|
+
'informal',
|
|
22
|
+
'historical',
|
|
23
|
+
'regional',
|
|
24
|
+
'dialectal'
|
|
25
|
+
]);
|
|
26
|
+
/**
|
|
27
|
+
* Transcription system schema
|
|
28
|
+
*/
|
|
29
|
+
export const TranscriptionSystemSchema = z.union([
|
|
30
|
+
z.literal('rtgs'),
|
|
31
|
+
z.literal('aua'),
|
|
32
|
+
z.literal('paiboon'),
|
|
33
|
+
z.literal('romaji'),
|
|
34
|
+
z.literal('furigana'),
|
|
35
|
+
z.literal('ipa'),
|
|
36
|
+
z.literal('pinyin'),
|
|
37
|
+
z.literal('hangul'),
|
|
38
|
+
z.string()
|
|
39
|
+
]);
|
|
40
|
+
/**
|
|
41
|
+
* Language code schema
|
|
42
|
+
*/
|
|
43
|
+
export const LanguageCodeSchema = z.union([
|
|
44
|
+
z.literal('th'),
|
|
45
|
+
z.literal('ja'),
|
|
46
|
+
z.literal('zh'),
|
|
47
|
+
z.literal('ko'),
|
|
48
|
+
z.literal('en'),
|
|
49
|
+
z.string()
|
|
50
|
+
]);
|
|
51
|
+
/**
|
|
52
|
+
* Script system schema
|
|
53
|
+
*/
|
|
54
|
+
export const ScriptSystemSchema = z.union([
|
|
55
|
+
z.literal('thai'),
|
|
56
|
+
z.literal('hiragana'),
|
|
57
|
+
z.literal('katakana'),
|
|
58
|
+
z.literal('kanji'),
|
|
59
|
+
z.literal('hanzi'),
|
|
60
|
+
z.literal('hangul'),
|
|
61
|
+
z.literal('latin'),
|
|
62
|
+
z.literal('mixed'),
|
|
63
|
+
z.string()
|
|
64
|
+
]);
|
|
65
|
+
/**
|
|
66
|
+
* Pronunciation variant schema
|
|
67
|
+
*/
|
|
68
|
+
export const PronunciationVariantSchema = z.object({
|
|
69
|
+
text: z.string(),
|
|
70
|
+
context: PronunciationContextSchema,
|
|
71
|
+
notes: z.string().optional()
|
|
72
|
+
});
|
|
73
|
+
/**
|
|
74
|
+
* Transcription info schema
|
|
75
|
+
*/
|
|
76
|
+
export const TranscriptionInfoSchema = z.object({
|
|
77
|
+
text: z.string(),
|
|
78
|
+
system: TranscriptionSystemSchema,
|
|
79
|
+
variants: z.array(PronunciationVariantSchema).optional(),
|
|
80
|
+
tone: z.number().optional(),
|
|
81
|
+
syllables: z.array(z.string()).optional(),
|
|
82
|
+
phonetic: z.string().optional()
|
|
83
|
+
});
|
|
84
|
+
/**
|
|
85
|
+
* Transliteration data schema
|
|
86
|
+
*/
|
|
87
|
+
export const TransliterationDataSchema = z.record(z.string(), TranscriptionInfoSchema);
|
|
88
|
+
/**
|
|
89
|
+
* Linguistic metadata schema
|
|
90
|
+
*/
|
|
91
|
+
export const LinguisticMetadataSchema = z.object({
|
|
92
|
+
/** @deprecated Use extras.translations instead */
|
|
93
|
+
meaning: z.string().optional(),
|
|
94
|
+
partOfSpeech: z.string(),
|
|
95
|
+
usage: z.string().optional(),
|
|
96
|
+
etymology: z.string().optional(),
|
|
97
|
+
examples: z.array(z.string()).optional(),
|
|
98
|
+
frequency: z.enum(['high', 'medium', 'low']).optional(),
|
|
99
|
+
formality: z.enum(['formal', 'neutral', 'informal']).optional(),
|
|
100
|
+
register: z.string().optional()
|
|
101
|
+
});
|
|
102
|
+
/**
|
|
103
|
+
* Base GLOST node schema
|
|
104
|
+
*/
|
|
105
|
+
export const GLOSTNodeBaseSchema = z.object({
|
|
106
|
+
type: z.string(),
|
|
107
|
+
lang: LanguageCodeSchema.optional(),
|
|
108
|
+
script: ScriptSystemSchema.optional(),
|
|
109
|
+
level: LinguisticLevelSchema.optional(),
|
|
110
|
+
position: z.any().optional()
|
|
111
|
+
});
|
|
112
|
+
/**
|
|
113
|
+
* GLOST word node schema
|
|
114
|
+
*/
|
|
115
|
+
export const GLOSTWordNodeSchema = GLOSTNodeBaseSchema.extend({
|
|
116
|
+
type: z.literal('GLOSTWordNode'),
|
|
117
|
+
value: z.string(),
|
|
118
|
+
transcription: TransliterationDataSchema,
|
|
119
|
+
metadata: LinguisticMetadataSchema,
|
|
120
|
+
level: LinguisticLevelSchema,
|
|
121
|
+
children: z.array(z.any()).default([])
|
|
122
|
+
});
|
|
123
|
+
/**
|
|
124
|
+
* GLOST sentence node schema
|
|
125
|
+
*/
|
|
126
|
+
export const GLOSTSentenceNodeSchema = GLOSTNodeBaseSchema.extend({
|
|
127
|
+
type: z.literal('GLOSTSentenceNode'),
|
|
128
|
+
originalText: z.string(),
|
|
129
|
+
lang: LanguageCodeSchema,
|
|
130
|
+
script: ScriptSystemSchema,
|
|
131
|
+
transcription: TransliterationDataSchema.optional(),
|
|
132
|
+
children: z.array(z.any()).default([])
|
|
133
|
+
});
|
|
134
|
+
/**
|
|
135
|
+
* GLOST paragraph node schema
|
|
136
|
+
*/
|
|
137
|
+
export const GLOSTParagraphNodeSchema = GLOSTNodeBaseSchema.extend({
|
|
138
|
+
type: z.literal('GLOSTParagraphNode'),
|
|
139
|
+
lang: LanguageCodeSchema,
|
|
140
|
+
script: ScriptSystemSchema,
|
|
141
|
+
children: z.array(z.any()).default([])
|
|
142
|
+
});
|
|
143
|
+
/**
|
|
144
|
+
* GLOST root node schema
|
|
145
|
+
*/
|
|
146
|
+
export const GLOSTRootNodeSchema = GLOSTNodeBaseSchema.extend({
|
|
147
|
+
type: z.literal('GLOSTRootNode'),
|
|
148
|
+
lang: LanguageCodeSchema,
|
|
149
|
+
script: ScriptSystemSchema,
|
|
150
|
+
metadata: z.object({
|
|
151
|
+
title: z.string().optional(),
|
|
152
|
+
author: z.string().optional(),
|
|
153
|
+
date: z.string().optional(),
|
|
154
|
+
description: z.string().optional()
|
|
155
|
+
}).optional(),
|
|
156
|
+
children: z.array(z.any()).default([])
|
|
157
|
+
});
|
|
158
|
+
/**
|
|
159
|
+
* Union schema for all GLOST node types
|
|
160
|
+
*/
|
|
161
|
+
export const GLOSTNodeSchema = z.union([
|
|
162
|
+
GLOSTWordNodeSchema,
|
|
163
|
+
GLOSTSentenceNodeSchema,
|
|
164
|
+
GLOSTParagraphNodeSchema,
|
|
165
|
+
GLOSTRootNodeSchema
|
|
166
|
+
]);
|
|
167
|
+
// ============================================================================
|
|
168
|
+
// Validation Functions
|
|
169
|
+
// ============================================================================
|
|
170
|
+
/**
|
|
171
|
+
* Validate an GLOST word node
|
|
172
|
+
*/
|
|
173
|
+
export function validateGLOSTWordNode(data) {
|
|
174
|
+
const result = GLOSTWordNodeSchema.safeParse(data);
|
|
175
|
+
return result.success;
|
|
176
|
+
}
|
|
177
|
+
/**
|
|
178
|
+
* Validate an GLOST sentence node
|
|
179
|
+
*/
|
|
180
|
+
export function validateGLOSTSentenceNode(data) {
|
|
181
|
+
const result = GLOSTSentenceNodeSchema.safeParse(data);
|
|
182
|
+
return result.success;
|
|
183
|
+
}
|
|
184
|
+
/**
|
|
185
|
+
* Validate an GLOST paragraph node
|
|
186
|
+
*/
|
|
187
|
+
export function validateGLOSTParagraphNode(data) {
|
|
188
|
+
const result = GLOSTParagraphNodeSchema.safeParse(data);
|
|
189
|
+
return result.success;
|
|
190
|
+
}
|
|
191
|
+
/**
|
|
192
|
+
* Validate an GLOST root node
|
|
193
|
+
*/
|
|
194
|
+
export function validateGLOSTRootNode(data) {
|
|
195
|
+
const result = GLOSTRootNodeSchema.safeParse(data);
|
|
196
|
+
return result.success;
|
|
197
|
+
}
|
|
198
|
+
/**
|
|
199
|
+
* Validate any GLOST node
|
|
200
|
+
*/
|
|
201
|
+
export function validateGLOSTNode(data) {
|
|
202
|
+
const result = GLOSTNodeSchema.safeParse(data);
|
|
203
|
+
return result.success;
|
|
204
|
+
}
|
|
205
|
+
/**
|
|
206
|
+
* Parse and validate GLOST data with error details
|
|
207
|
+
*/
|
|
208
|
+
export function parseGLOSTNode(data) {
|
|
209
|
+
return GLOSTNodeSchema.safeParse(data);
|
|
210
|
+
}
|
|
211
|
+
/**
|
|
212
|
+
* Parse and validate GLOST word node with error details
|
|
213
|
+
*/
|
|
214
|
+
export function parseGLOSTWordNode(data) {
|
|
215
|
+
return GLOSTWordNodeSchema.safeParse(data);
|
|
216
|
+
}
|
|
217
|
+
/**
|
|
218
|
+
* Parse and validate GLOST sentence node with error details
|
|
219
|
+
*/
|
|
220
|
+
export function parseGLOSTSentenceNode(data) {
|
|
221
|
+
return GLOSTSentenceNodeSchema.safeParse(data);
|
|
222
|
+
}
|
|
223
|
+
/**
|
|
224
|
+
* Parse and validate GLOST paragraph node with error details
|
|
225
|
+
*/
|
|
226
|
+
export function parseGLOSTParagraphNode(data) {
|
|
227
|
+
return GLOSTParagraphNodeSchema.safeParse(data);
|
|
228
|
+
}
|
|
229
|
+
/**
|
|
230
|
+
* Parse and validate GLOST root node with error details
|
|
231
|
+
*/
|
|
232
|
+
export function parseGLOSTRootNode(data) {
|
|
233
|
+
return GLOSTRootNodeSchema.safeParse(data);
|
|
234
|
+
}
|
|
235
|
+
/**
|
|
236
|
+
* Validate an entire GLOST tree/document
|
|
237
|
+
*/
|
|
238
|
+
export function validateGLOSTTree(data) {
|
|
239
|
+
const errors = [];
|
|
240
|
+
// Validate root node
|
|
241
|
+
const rootResult = GLOSTRootNodeSchema.safeParse(data);
|
|
242
|
+
if (!rootResult.success) {
|
|
243
|
+
errors.push(`Root validation failed: ${rootResult.error.message}`);
|
|
244
|
+
return errors;
|
|
245
|
+
}
|
|
246
|
+
const root = rootResult.data;
|
|
247
|
+
// Validate all paragraphs
|
|
248
|
+
for (let i = 0; i < root.children.length; i++) {
|
|
249
|
+
const child = root.children[i];
|
|
250
|
+
if (child.type === 'ParagraphNode') {
|
|
251
|
+
const paragraphResult = GLOSTParagraphNodeSchema.safeParse(child);
|
|
252
|
+
if (!paragraphResult.success) {
|
|
253
|
+
errors.push(`Paragraph ${i} validation failed: ${paragraphResult.error.message}`);
|
|
254
|
+
}
|
|
255
|
+
else {
|
|
256
|
+
// Validate all sentences in paragraph
|
|
257
|
+
for (let j = 0; j < child.children.length; j++) {
|
|
258
|
+
const sentence = child.children[j];
|
|
259
|
+
if (sentence.type === 'SentenceNode') {
|
|
260
|
+
const sentenceResult = GLOSTSentenceNodeSchema.safeParse(sentence);
|
|
261
|
+
if (!sentenceResult.success) {
|
|
262
|
+
errors.push(`Sentence ${i}.${j} validation failed: ${sentenceResult.error.message}`);
|
|
263
|
+
}
|
|
264
|
+
else {
|
|
265
|
+
// Validate all words in sentence
|
|
266
|
+
for (let k = 0; k < sentence.children.length; k++) {
|
|
267
|
+
const word = sentence.children[k];
|
|
268
|
+
if (word.type === 'WordNode') {
|
|
269
|
+
const wordResult = GLOSTWordNodeSchema.safeParse(word);
|
|
270
|
+
if (!wordResult.success) {
|
|
271
|
+
errors.push(`Word ${i}.${j}.${k} validation failed: ${wordResult.error.message}`);
|
|
272
|
+
}
|
|
273
|
+
}
|
|
274
|
+
}
|
|
275
|
+
}
|
|
276
|
+
}
|
|
277
|
+
}
|
|
278
|
+
}
|
|
279
|
+
}
|
|
280
|
+
}
|
|
281
|
+
return errors;
|
|
282
|
+
}
|
|
283
|
+
// ============================================================================
|
|
284
|
+
// Schema Export
|
|
285
|
+
// ============================================================================
|
|
286
|
+
export const schemas = {
|
|
287
|
+
LinguisticLevel: LinguisticLevelSchema,
|
|
288
|
+
PronunciationContext: PronunciationContextSchema,
|
|
289
|
+
TranscriptionSystem: TranscriptionSystemSchema,
|
|
290
|
+
LanguageCode: LanguageCodeSchema,
|
|
291
|
+
ScriptSystem: ScriptSystemSchema,
|
|
292
|
+
PronunciationVariant: PronunciationVariantSchema,
|
|
293
|
+
TranscriptionInfo: TranscriptionInfoSchema,
|
|
294
|
+
TransliterationData: TransliterationDataSchema,
|
|
295
|
+
LinguisticMetadata: LinguisticMetadataSchema,
|
|
296
|
+
GLOSTNode: GLOSTNodeSchema,
|
|
297
|
+
GLOSTWordNode: GLOSTWordNodeSchema,
|
|
298
|
+
GLOSTSentenceNode: GLOSTSentenceNodeSchema,
|
|
299
|
+
GLOSTParagraphNode: GLOSTParagraphNodeSchema,
|
|
300
|
+
GLOSTRootNode: GLOSTRootNodeSchema
|
|
301
|
+
};
|
|
302
|
+
//# sourceMappingURL=validators.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"validators.js","sourceRoot":"","sources":["../src/validators.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,CAAC,EAAE,MAAM,KAAK,CAAC;AAExB,+EAA+E;AAC/E,mCAAmC;AACnC,+EAA+E;AAE/E;;GAEG;AACH,MAAM,CAAC,MAAM,qBAAqB,GAAG,CAAC,CAAC,IAAI,CAAC;IAC1C,WAAW;IACX,UAAU;IACV,MAAM;IACN,QAAQ;IACR,UAAU;IACV,WAAW;CACZ,CAAC,CAAC;AAEH;;GAEG;AACH,MAAM,CAAC,MAAM,0BAA0B,GAAG,CAAC,CAAC,IAAI,CAAC;IAC/C,QAAQ;IACR,UAAU;IACV,YAAY;IACZ,UAAU;IACV,WAAW;CACZ,CAAC,CAAC;AAEH;;GAEG;AACH,MAAM,CAAC,MAAM,yBAAyB,GAAG,CAAC,CAAC,KAAK,CAAC;IAC/C,CAAC,CAAC,OAAO,CAAC,MAAM,CAAC;IACjB,CAAC,CAAC,OAAO,CAAC,KAAK,CAAC;IAChB,CAAC,CAAC,OAAO,CAAC,SAAS,CAAC;IACpB,CAAC,CAAC,OAAO,CAAC,QAAQ,CAAC;IACnB,CAAC,CAAC,OAAO,CAAC,UAAU,CAAC;IACrB,CAAC,CAAC,OAAO,CAAC,KAAK,CAAC;IAChB,CAAC,CAAC,OAAO,CAAC,QAAQ,CAAC;IACnB,CAAC,CAAC,OAAO,CAAC,QAAQ,CAAC;IACnB,CAAC,CAAC,MAAM,EAAE;CACX,CAAC,CAAC;AAEH;;GAEG;AACH,MAAM,CAAC,MAAM,kBAAkB,GAAG,CAAC,CAAC,KAAK,CAAC;IACxC,CAAC,CAAC,OAAO,CAAC,IAAI,CAAC;IACf,CAAC,CAAC,OAAO,CAAC,IAAI,CAAC;IACf,CAAC,CAAC,OAAO,CAAC,IAAI,CAAC;IACf,CAAC,CAAC,OAAO,CAAC,IAAI,CAAC;IACf,CAAC,CAAC,OAAO,CAAC,IAAI,CAAC;IACf,CAAC,CAAC,MAAM,EAAE;CACX,CAAC,CAAC;AAEH;;GAEG;AACH,MAAM,CAAC,MAAM,kBAAkB,GAAG,CAAC,CAAC,KAAK,CAAC;IACxC,CAAC,CAAC,OAAO,CAAC,MAAM,CAAC;IACjB,CAAC,CAAC,OAAO,CAAC,UAAU,CAAC;IACrB,CAAC,CAAC,OAAO,CAAC,UAAU,CAAC;IACrB,CAAC,CAAC,OAAO,CAAC,OAAO,CAAC;IAClB,CAAC,CAAC,OAAO,CAAC,OAAO,CAAC;IAClB,CAAC,CAAC,OAAO,CAAC,QAAQ,CAAC;IACnB,CAAC,CAAC,OAAO,CAAC,OAAO,CAAC;IAClB,CAAC,CAAC,OAAO,CAAC,OAAO,CAAC;IAClB,CAAC,CAAC,MAAM,EAAE;CACX,CAAC,CAAC;AAEH;;GAEG;AACH,MAAM,CAAC,MAAM,0BAA0B,GAAG,CAAC,CAAC,MAAM,CAAC;IACjD,IAAI,EAAE,CAAC,CAAC,MAAM,EAAE;IAChB,OAAO,EAAE,0BAA0B;IACnC,KAAK,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,EAAE;CAC7B,CAAC,CAAC;AAEH;;GAEG;AACH,MAAM,CAAC,MAAM,uBAAuB,GAAG,CAAC,CAAC,MAAM,CAAC;IAC9C,IAAI,EAAE,CAAC,CAAC,MAAM,EAAE;IAChB,MAAM,EAAE,yBAAyB;IACjC,QAAQ,EAAE,CAAC,CAAC,KAAK,CAAC,0BAA0B,CAAC,CAAC,QAAQ,EAAE;IACxD,IAAI,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,EAAE;IAC3B,SAAS,EAAE,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,MAAM,EAAE,CAAC,CAAC,QAAQ,EAAE;IACzC,QAAQ,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,EAAE;CAChC,CAAC,CAAC;AAEH;;GAEG;AACH,MAAM,CAAC,MAAM,yBAAyB,GAAG,CAAC,CAAC,MAAM,CAC/C,CAAC,CAAC,MAAM,EAAE,EACV,uBAAuB,CACxB,CAAC;AAEF;;GAEG;AACH,MAAM,CAAC,MAAM,wBAAwB,GAAG,CAAC,CAAC,MAAM,CAAC;IAC/C,kDAAkD;IAClD,OAAO,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,EAAE;IAC9B,YAAY,EAAE,CAAC,CAAC,MAAM,EAAE;IACxB,KAAK,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,EAAE;IAC5B,SAAS,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,EAAE;IAChC,QAAQ,EAAE,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,MAAM,EAAE,CAAC,CAAC,QAAQ,EAAE;IACxC,SAAS,EAAE,CAAC,CAAC,IAAI,CAAC,CAAC,MAAM,EAAE,QAAQ,EAAE,KAAK,CAAC,CAAC,CAAC,QAAQ,EAAE;IACvD,SAAS,EAAE,CAAC,CAAC,IAAI,CAAC,CAAC,QAAQ,EAAE,SAAS,EAAE,UAAU,CAAC,CAAC,CAAC,QAAQ,EAAE;IAC/D,QAAQ,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,EAAE;CAChC,CAAC,CAAC;AAEH;;GAEG;AACH,MAAM,CAAC,MAAM,mBAAmB,GAAG,CAAC,CAAC,MAAM,CAAC;IAC1C,IAAI,EAAE,CAAC,CAAC,MAAM,EAAE;IAChB,IAAI,EAAE,kBAAkB,CAAC,QAAQ,EAAE;IACnC,MAAM,EAAE,kBAAkB,CAAC,QAAQ,EAAE;IACrC,KAAK,EAAE,qBAAqB,CAAC,QAAQ,EAAE;IACvC,QAAQ,EAAE,CAAC,CAAC,GAAG,EAAE,CAAC,QAAQ,EAAE;CAC7B,CAAC,CAAC;AAEH;;GAEG;AACH,MAAM,CAAC,MAAM,mBAAmB,GAAG,mBAAmB,CAAC,MAAM,CAAC;IAC5D,IAAI,EAAE,CAAC,CAAC,OAAO,CAAC,eAAe,CAAC;IAChC,KAAK,EAAE,CAAC,CAAC,MAAM,EAAE;IACjB,aAAa,EAAE,yBAAyB;IACxC,QAAQ,EAAE,wBAAwB;IAClC,KAAK,EAAE,qBAAqB;IAC5B,QAAQ,EAAE,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,GAAG,EAAE,CAAC,CAAC,OAAO,CAAC,EAAE,CAAC;CACvC,CAAC,CAAC;AAEH;;GAEG;AACH,MAAM,CAAC,MAAM,uBAAuB,GAAG,mBAAmB,CAAC,MAAM,CAAC;IAChE,IAAI,EAAE,CAAC,CAAC,OAAO,CAAC,mBAAmB,CAAC;IACpC,YAAY,EAAE,CAAC,CAAC,MAAM,EAAE;IACxB,IAAI,EAAE,kBAAkB;IACxB,MAAM,EAAE,kBAAkB;IAC1B,aAAa,EAAE,yBAAyB,CAAC,QAAQ,EAAE;IACnD,QAAQ,EAAE,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,GAAG,EAAE,CAAC,CAAC,OAAO,CAAC,EAAE,CAAC;CACvC,CAAC,CAAC;AAEH;;GAEG;AACH,MAAM,CAAC,MAAM,wBAAwB,GAAG,mBAAmB,CAAC,MAAM,CAAC;IACjE,IAAI,EAAE,CAAC,CAAC,OAAO,CAAC,oBAAoB,CAAC;IACrC,IAAI,EAAE,kBAAkB;IACxB,MAAM,EAAE,kBAAkB;IAC1B,QAAQ,EAAE,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,GAAG,EAAE,CAAC,CAAC,OAAO,CAAC,EAAE,CAAC;CACvC,CAAC,CAAC;AAEH;;GAEG;AACH,MAAM,CAAC,MAAM,mBAAmB,GAAG,mBAAmB,CAAC,MAAM,CAAC;IAC5D,IAAI,EAAE,CAAC,CAAC,OAAO,CAAC,eAAe,CAAC;IAChC,IAAI,EAAE,kBAAkB;IACxB,MAAM,EAAE,kBAAkB;IAC1B,QAAQ,EAAE,CAAC,CAAC,MAAM,CAAC;QACjB,KAAK,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,EAAE;QAC5B,MAAM,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,EAAE;QAC7B,IAAI,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,EAAE;QAC3B,WAAW,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,EAAE;KACnC,CAAC,CAAC,QAAQ,EAAE;IACb,QAAQ,EAAE,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,GAAG,EAAE,CAAC,CAAC,OAAO,CAAC,EAAE,CAAC;CACvC,CAAC,CAAC;AAEH;;GAEG;AACH,MAAM,CAAC,MAAM,eAAe,GAAG,CAAC,CAAC,KAAK,CAAC;IACrC,mBAAmB;IACnB,uBAAuB;IACvB,wBAAwB;IACxB,mBAAmB;CACpB,CAAC,CAAC;AAEH,+EAA+E;AAC/E,uBAAuB;AACvB,+EAA+E;AAE/E;;GAEG;AACH,MAAM,UAAU,qBAAqB,CAAC,IAAa;IACjD,MAAM,MAAM,GAAG,mBAAmB,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC;IACnD,OAAO,MAAM,CAAC,OAAO,CAAC;AACxB,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,yBAAyB,CAAC,IAAa;IACrD,MAAM,MAAM,GAAG,uBAAuB,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC;IACvD,OAAO,MAAM,CAAC,OAAO,CAAC;AACxB,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,0BAA0B,CAAC,IAAa;IACtD,MAAM,MAAM,GAAG,wBAAwB,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC;IACxD,OAAO,MAAM,CAAC,OAAO,CAAC;AACxB,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,qBAAqB,CAAC,IAAa;IACjD,MAAM,MAAM,GAAG,mBAAmB,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC;IACnD,OAAO,MAAM,CAAC,OAAO,CAAC;AACxB,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,iBAAiB,CAAC,IAAa;IAC7C,MAAM,MAAM,GAAG,eAAe,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC;IAC/C,OAAO,MAAM,CAAC,OAAO,CAAC;AACxB,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,cAAc,CAAC,IAAa;IAC1C,OAAO,eAAe,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC;AACzC,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,kBAAkB,CAAC,IAAa;IAC9C,OAAO,mBAAmB,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC;AAC7C,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,sBAAsB,CAAC,IAAa;IAClD,OAAO,uBAAuB,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC;AACjD,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,uBAAuB,CAAC,IAAa;IACnD,OAAO,wBAAwB,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC;AAClD,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,kBAAkB,CAAC,IAAa;IAC9C,OAAO,mBAAmB,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC;AAC7C,CAAC;AAED;;GAEG;AACH,MAAM,UAAU,iBAAiB,CAAC,IAAa;IAC7C,MAAM,MAAM,GAAa,EAAE,CAAC;IAE5B,qBAAqB;IACrB,MAAM,UAAU,GAAG,mBAAmB,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC;IACvD,IAAI,CAAC,UAAU,CAAC,OAAO,EAAE,CAAC;QACxB,MAAM,CAAC,IAAI,CAAC,2BAA2B,UAAU,CAAC,KAAK,CAAC,OAAO,EAAE,CAAC,CAAC;QACnE,OAAO,MAAM,CAAC;IAChB,CAAC;IAED,MAAM,IAAI,GAAG,UAAU,CAAC,IAAI,CAAC;IAE7B,0BAA0B;IAC1B,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,IAAI,CAAC,QAAQ,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;QAC9C,MAAM,KAAK,GAAG,IAAI,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC;QAC/B,IAAI,KAAK,CAAC,IAAI,KAAK,eAAe,EAAE,CAAC;YACnC,MAAM,eAAe,GAAG,wBAAwB,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC;YAClE,IAAI,CAAC,eAAe,CAAC,OAAO,EAAE,CAAC;gBAC7B,MAAM,CAAC,IAAI,CAAC,aAAa,CAAC,uBAAuB,eAAe,CAAC,KAAK,CAAC,OAAO,EAAE,CAAC,CAAC;YACpF,CAAC;iBAAM,CAAC;gBACN,sCAAsC;gBACtC,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,KAAK,CAAC,QAAQ,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;oBAC/C,MAAM,QAAQ,GAAG,KAAK,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC;oBACnC,IAAI,QAAQ,CAAC,IAAI,KAAK,cAAc,EAAE,CAAC;wBACrC,MAAM,cAAc,GAAG,uBAAuB,CAAC,SAAS,CAAC,QAAQ,CAAC,CAAC;wBACnE,IAAI,CAAC,cAAc,CAAC,OAAO,EAAE,CAAC;4BAC5B,MAAM,CAAC,IAAI,CAAC,YAAY,CAAC,IAAI,CAAC,uBAAuB,cAAc,CAAC,KAAK,CAAC,OAAO,EAAE,CAAC,CAAC;wBACvF,CAAC;6BAAM,CAAC;4BACN,iCAAiC;4BACjC,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,QAAQ,CAAC,QAAQ,CAAC,MAAM,EAAE,CAAC,EAAE,EAAE,CAAC;gCAClD,MAAM,IAAI,GAAG,QAAQ,CAAC,QAAQ,CAAC,CAAC,CAAC,CAAC;gCAClC,IAAI,IAAI,CAAC,IAAI,KAAK,UAAU,EAAE,CAAC;oCAC7B,MAAM,UAAU,GAAG,mBAAmB,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC;oCACvD,IAAI,CAAC,UAAU,CAAC,OAAO,EAAE,CAAC;wCACxB,MAAM,CAAC,IAAI,CAAC,QAAQ,CAAC,IAAI,CAAC,IAAI,CAAC,uBAAuB,UAAU,CAAC,KAAK,CAAC,OAAO,EAAE,CAAC,CAAC;oCACpF,CAAC;gCACH,CAAC;4BACH,CAAC;wBACH,CAAC;oBACH,CAAC;gBACH,CAAC;YACH,CAAC;QACH,CAAC;IACH,CAAC;IAED,OAAO,MAAM,CAAC;AAChB,CAAC;AAED,+EAA+E;AAC/E,gBAAgB;AAChB,+EAA+E;AAE/E,MAAM,CAAC,MAAM,OAAO,GAAG;IACrB,eAAe,EAAE,qBAAqB;IACtC,oBAAoB,EAAE,0BAA0B;IAChD,mBAAmB,EAAE,yBAAyB;IAC9C,YAAY,EAAE,kBAAkB;IAChC,YAAY,EAAE,kBAAkB;IAChC,oBAAoB,EAAE,0BAA0B;IAChD,iBAAiB,EAAE,uBAAuB;IAC1C,mBAAmB,EAAE,yBAAyB;IAC9C,kBAAkB,EAAE,wBAAwB;IAC5C,SAAS,EAAE,eAAe;IAC1B,aAAa,EAAE,mBAAmB;IAClC,iBAAiB,EAAE,uBAAuB;IAC1C,kBAAkB,EAAE,wBAAwB;IAC5C,aAAa,EAAE,mBAAmB;CACnC,CAAC"}
|
package/package.json
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
1
|
+
{
|
|
2
|
+
"name": "glost-core",
|
|
3
|
+
"version": "0.5.0",
|
|
4
|
+
"description": "Core types, nodes, and utilities for GLOST (Glossed Syntax Tree)",
|
|
5
|
+
"author": "fustilio",
|
|
6
|
+
"license": "MIT",
|
|
7
|
+
"repository": {
|
|
8
|
+
"type": "git",
|
|
9
|
+
"url": "https://github.com/fustilio/glost.git",
|
|
10
|
+
"directory": "packages/core"
|
|
11
|
+
},
|
|
12
|
+
"type": "module",
|
|
13
|
+
"main": "./src/index.ts",
|
|
14
|
+
"types": "./src/index.ts",
|
|
15
|
+
"bin": {
|
|
16
|
+
"glost": "./dist/cli/migrate.js"
|
|
17
|
+
},
|
|
18
|
+
"exports": {
|
|
19
|
+
".": {
|
|
20
|
+
"types": "./src/index.ts",
|
|
21
|
+
"default": "./src/index.ts"
|
|
22
|
+
},
|
|
23
|
+
"./nodes": {
|
|
24
|
+
"types": "./src/nodes.ts",
|
|
25
|
+
"default": "./src/nodes.ts"
|
|
26
|
+
},
|
|
27
|
+
"./utils": {
|
|
28
|
+
"types": "./src/utils.ts",
|
|
29
|
+
"default": "./src/utils.ts"
|
|
30
|
+
},
|
|
31
|
+
"./validators": {
|
|
32
|
+
"types": "./src/validators.ts",
|
|
33
|
+
"default": "./src/validators.ts"
|
|
34
|
+
},
|
|
35
|
+
"./guards": {
|
|
36
|
+
"types": "./src/guards.ts",
|
|
37
|
+
"default": "./src/guards.ts"
|
|
38
|
+
}
|
|
39
|
+
},
|
|
40
|
+
"dependencies": {
|
|
41
|
+
"unist-util-filter": "^5.0.1",
|
|
42
|
+
"unist-util-find": "^3.0.0",
|
|
43
|
+
"unist-util-flatmap": "^1.0.0",
|
|
44
|
+
"unist-util-is": "^6.0.0",
|
|
45
|
+
"unist-util-map": "^4.0.0",
|
|
46
|
+
"unist-util-modify-children": "^4.0.0",
|
|
47
|
+
"unist-util-remove": "^4.0.0",
|
|
48
|
+
"unist-util-select": "^5.1.0",
|
|
49
|
+
"unist-util-visit": "^5.0.0",
|
|
50
|
+
"zod": "^3.23.8",
|
|
51
|
+
"glost-common": "0.2.0"
|
|
52
|
+
},
|
|
53
|
+
"devDependencies": {
|
|
54
|
+
"@types/nlcst": "^2.0.3",
|
|
55
|
+
"typescript": "^5.8.3",
|
|
56
|
+
"vitest": "^3.0.5"
|
|
57
|
+
},
|
|
58
|
+
"keywords": [
|
|
59
|
+
"glost",
|
|
60
|
+
"glossed-syntax-tree",
|
|
61
|
+
"nlcst",
|
|
62
|
+
"multilingual",
|
|
63
|
+
"language-learning",
|
|
64
|
+
"linguistics",
|
|
65
|
+
"syntax-tree",
|
|
66
|
+
"unist"
|
|
67
|
+
],
|
|
68
|
+
"scripts": {
|
|
69
|
+
"build": "tsc",
|
|
70
|
+
"typecheck": "tsc --noEmit",
|
|
71
|
+
"test": "vitest --passWithNoTests"
|
|
72
|
+
}
|
|
73
|
+
}
|
|
@@ -0,0 +1,92 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* Document Creation Performance Benchmarks
|
|
3
|
+
*
|
|
4
|
+
* Compares different approaches to creating GLOST documents
|
|
5
|
+
*/
|
|
6
|
+
|
|
7
|
+
import { bench, describe } from 'vitest';
|
|
8
|
+
import {
|
|
9
|
+
createSimpleDocument,
|
|
10
|
+
createGLOSTWordNode,
|
|
11
|
+
createDocumentFromSentences,
|
|
12
|
+
createSentenceFromWords,
|
|
13
|
+
createParagraphFromSentences,
|
|
14
|
+
createDocumentFromParagraphs,
|
|
15
|
+
} from '../index.js';
|
|
16
|
+
|
|
17
|
+
describe('Document Creation: Comparing Approaches', () => {
|
|
18
|
+
// Setup: Create test data once
|
|
19
|
+
const words100 = Array.from({ length: 100 }, (_, i) =>
|
|
20
|
+
createGLOSTWordNode({ value: `word${i}` })
|
|
21
|
+
);
|
|
22
|
+
|
|
23
|
+
describe('Compare: Simple vs Full Hierarchy (100 words)', () => {
|
|
24
|
+
bench('createSimpleDocument (recommended)', () => {
|
|
25
|
+
createSimpleDocument(words100, "en", "latin");
|
|
26
|
+
});
|
|
27
|
+
|
|
28
|
+
bench('createDocumentFromSentences', () => {
|
|
29
|
+
const sentence = createSentenceFromWords(words100, "en", "latin", "text");
|
|
30
|
+
createDocumentFromSentences([sentence], "en", "latin");
|
|
31
|
+
});
|
|
32
|
+
|
|
33
|
+
bench('createDocumentFromParagraphs (full hierarchy)', () => {
|
|
34
|
+
const sentence = createSentenceFromWords(words100, "en", "latin", "text");
|
|
35
|
+
const paragraph = createParagraphFromSentences([sentence]);
|
|
36
|
+
createDocumentFromParagraphs([paragraph], "en", "latin");
|
|
37
|
+
});
|
|
38
|
+
});
|
|
39
|
+
|
|
40
|
+
describe('Compare: Word Node Creation Approaches', () => {
|
|
41
|
+
bench('minimal word node', () => {
|
|
42
|
+
createGLOSTWordNode({ value: "test" });
|
|
43
|
+
});
|
|
44
|
+
|
|
45
|
+
bench('word with transcription', () => {
|
|
46
|
+
createGLOSTWordNode({
|
|
47
|
+
value: "test",
|
|
48
|
+
transcription: {
|
|
49
|
+
ipa: { text: "test", syllables: ["test"] }
|
|
50
|
+
}
|
|
51
|
+
});
|
|
52
|
+
});
|
|
53
|
+
|
|
54
|
+
bench('word with full metadata', () => {
|
|
55
|
+
createGLOSTWordNode({
|
|
56
|
+
value: "test",
|
|
57
|
+
transcription: {
|
|
58
|
+
ipa: { text: "test", syllables: ["test"] }
|
|
59
|
+
},
|
|
60
|
+
metadata: {
|
|
61
|
+
partOfSpeech: "noun",
|
|
62
|
+
meaning: "a test",
|
|
63
|
+
usage: "testing"
|
|
64
|
+
},
|
|
65
|
+
lang: "en",
|
|
66
|
+
script: "latin",
|
|
67
|
+
extras: {
|
|
68
|
+
translations: { th: "ทดสอบ" },
|
|
69
|
+
metadata: { frequency: "common" }
|
|
70
|
+
}
|
|
71
|
+
});
|
|
72
|
+
});
|
|
73
|
+
});
|
|
74
|
+
|
|
75
|
+
describe('Compare: Sentence Creation Strategies', () => {
|
|
76
|
+
const words10 = Array.from({ length: 10 }, (_, i) =>
|
|
77
|
+
createGLOSTWordNode({ value: `word${i}` })
|
|
78
|
+
);
|
|
79
|
+
|
|
80
|
+
bench('createDocumentFromSentences - multiple small sentences', () => {
|
|
81
|
+
const sentences = Array.from({ length: 10 }, (_, i) => {
|
|
82
|
+
const sentenceWords = words10.slice(i, i + 5);
|
|
83
|
+
return createSentenceFromWords(sentenceWords, "en", "latin", `Sentence ${i}`);
|
|
84
|
+
});
|
|
85
|
+
createDocumentFromSentences(sentences, "en", "latin");
|
|
86
|
+
});
|
|
87
|
+
|
|
88
|
+
bench('createSimpleDocument - single sentence', () => {
|
|
89
|
+
createSimpleDocument(words10, "en", "latin");
|
|
90
|
+
});
|
|
91
|
+
});
|
|
92
|
+
});
|
|
@@ -0,0 +1,152 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* Document Traversal Performance Benchmarks
|
|
3
|
+
*
|
|
4
|
+
* Compares different approaches to traversing and accessing GLOST documents
|
|
5
|
+
*/
|
|
6
|
+
|
|
7
|
+
import { bench, describe } from 'vitest';
|
|
8
|
+
import {
|
|
9
|
+
createSimpleDocument,
|
|
10
|
+
createGLOSTWordNode,
|
|
11
|
+
getAllWords,
|
|
12
|
+
getFirstWord,
|
|
13
|
+
getWordAtPath,
|
|
14
|
+
getAllSentences,
|
|
15
|
+
getAllParagraphs,
|
|
16
|
+
} from '../index.js';
|
|
17
|
+
import { visit } from 'unist-util-visit';
|
|
18
|
+
import { NODE_TYPES } from '../types.js';
|
|
19
|
+
|
|
20
|
+
// Helper to create test documents
|
|
21
|
+
function createTestDocument(wordCount: number) {
|
|
22
|
+
const words = Array.from({ length: wordCount }, (_, i) =>
|
|
23
|
+
createGLOSTWordNode({
|
|
24
|
+
value: `word${i}`,
|
|
25
|
+
transcription: {
|
|
26
|
+
ipa: { text: `wɜːrd${i}`, syllables: [`word${i}`] }
|
|
27
|
+
},
|
|
28
|
+
metadata: { partOfSpeech: i % 2 === 0 ? "noun" : "verb" }
|
|
29
|
+
})
|
|
30
|
+
);
|
|
31
|
+
return createSimpleDocument(words, "en", "latin");
|
|
32
|
+
}
|
|
33
|
+
|
|
34
|
+
describe('Traversal: Comparing Access Patterns', () => {
|
|
35
|
+
const doc1000 = createTestDocument(1000);
|
|
36
|
+
|
|
37
|
+
describe('Compare: Getting All Words', () => {
|
|
38
|
+
bench('getAllWords (helper)', () => {
|
|
39
|
+
getAllWords(doc1000);
|
|
40
|
+
});
|
|
41
|
+
|
|
42
|
+
bench('visit with type filter', () => {
|
|
43
|
+
const words: any[] = [];
|
|
44
|
+
visit(doc1000, NODE_TYPES.WORD, (node) => {
|
|
45
|
+
words.push(node);
|
|
46
|
+
});
|
|
47
|
+
});
|
|
48
|
+
|
|
49
|
+
bench('manual recursive traversal', () => {
|
|
50
|
+
const words: any[] = [];
|
|
51
|
+
function traverse(node: any) {
|
|
52
|
+
if (node.type === NODE_TYPES.WORD) {
|
|
53
|
+
words.push(node);
|
|
54
|
+
}
|
|
55
|
+
if (node.children) {
|
|
56
|
+
node.children.forEach(traverse);
|
|
57
|
+
}
|
|
58
|
+
}
|
|
59
|
+
traverse(doc1000);
|
|
60
|
+
});
|
|
61
|
+
});
|
|
62
|
+
|
|
63
|
+
describe('Compare: Finding First Word', () => {
|
|
64
|
+
bench('getFirstWord (optimized with SKIP)', () => {
|
|
65
|
+
getFirstWord(doc1000);
|
|
66
|
+
});
|
|
67
|
+
|
|
68
|
+
bench('getAllWords then [0]', () => {
|
|
69
|
+
getAllWords(doc1000)[0];
|
|
70
|
+
});
|
|
71
|
+
|
|
72
|
+
bench('manual early-exit traversal', () => {
|
|
73
|
+
let found: any;
|
|
74
|
+
function traverse(node: any): boolean {
|
|
75
|
+
if (node.type === NODE_TYPES.WORD) {
|
|
76
|
+
found = node;
|
|
77
|
+
return true; // exit early
|
|
78
|
+
}
|
|
79
|
+
if (node.children) {
|
|
80
|
+
for (const child of node.children) {
|
|
81
|
+
if (traverse(child)) return true;
|
|
82
|
+
}
|
|
83
|
+
}
|
|
84
|
+
return false;
|
|
85
|
+
}
|
|
86
|
+
traverse(doc1000);
|
|
87
|
+
});
|
|
88
|
+
});
|
|
89
|
+
|
|
90
|
+
describe('Compare: Direct Path Access', () => {
|
|
91
|
+
bench('getWordAtPath (direct indexing)', () => {
|
|
92
|
+
getWordAtPath(doc1000, { paragraph: 0, sentence: 0, word: 500 });
|
|
93
|
+
});
|
|
94
|
+
|
|
95
|
+
bench('getAllWords then filter by index', () => {
|
|
96
|
+
getAllWords(doc1000)[500];
|
|
97
|
+
});
|
|
98
|
+
});
|
|
99
|
+
});
|
|
100
|
+
|
|
101
|
+
describe('Traversal: Comparing Filter Strategies', () => {
|
|
102
|
+
const doc500 = createTestDocument(500);
|
|
103
|
+
|
|
104
|
+
describe('Compare: Filter by Part of Speech', () => {
|
|
105
|
+
bench('getAllWords + array filter', () => {
|
|
106
|
+
const words = getAllWords(doc500);
|
|
107
|
+
words.filter(w => w.metadata?.partOfSpeech === "noun");
|
|
108
|
+
});
|
|
109
|
+
|
|
110
|
+
bench('visit with conditional push', () => {
|
|
111
|
+
const nouns: any[] = [];
|
|
112
|
+
visit(doc500, NODE_TYPES.WORD, (node: any) => {
|
|
113
|
+
if (node.metadata?.partOfSpeech === "noun") {
|
|
114
|
+
nouns.push(node);
|
|
115
|
+
}
|
|
116
|
+
});
|
|
117
|
+
});
|
|
118
|
+
});
|
|
119
|
+
|
|
120
|
+
describe('Compare: Extract Word Text', () => {
|
|
121
|
+
const words = getAllWords(doc500);
|
|
122
|
+
|
|
123
|
+
bench('map with type guard', () => {
|
|
124
|
+
words.map(w => {
|
|
125
|
+
const textNode = w.children[0];
|
|
126
|
+
return textNode && 'value' in textNode ? textNode.value : '';
|
|
127
|
+
});
|
|
128
|
+
});
|
|
129
|
+
|
|
130
|
+
bench('reduce to array', () => {
|
|
131
|
+
words.reduce((acc, w) => {
|
|
132
|
+
const textNode = w.children[0];
|
|
133
|
+
if (textNode && 'value' in textNode) {
|
|
134
|
+
acc.push(textNode.value);
|
|
135
|
+
}
|
|
136
|
+
return acc;
|
|
137
|
+
}, [] as string[]);
|
|
138
|
+
});
|
|
139
|
+
});
|
|
140
|
+
|
|
141
|
+
describe('Compare: Count with Condition', () => {
|
|
142
|
+
const words = getAllWords(doc500);
|
|
143
|
+
|
|
144
|
+
bench('filter then length', () => {
|
|
145
|
+
words.filter(w => w.transcription !== undefined).length;
|
|
146
|
+
});
|
|
147
|
+
|
|
148
|
+
bench('reduce with counter', () => {
|
|
149
|
+
words.reduce((count, w) => count + (w.transcription ? 1 : 0), 0);
|
|
150
|
+
});
|
|
151
|
+
});
|
|
152
|
+
});
|
|
@@ -0,0 +1,20 @@
|
|
|
1
|
+
# Test Fixtures
|
|
2
|
+
|
|
3
|
+
This directory contains mock data and fixtures for testing purposes only.
|
|
4
|
+
|
|
5
|
+
**Important:** Files in this directory should **NOT** be imported by production code to avoid bundling test data with the main library.
|
|
6
|
+
|
|
7
|
+
## Usage in Tests
|
|
8
|
+
|
|
9
|
+
```typescript
|
|
10
|
+
// In your test files
|
|
11
|
+
import { thaiDocumentWithExtras, japaneseDocumentWithExtras } from '../__fixtures__/mock-data';
|
|
12
|
+
```
|
|
13
|
+
|
|
14
|
+
## Available Fixtures
|
|
15
|
+
|
|
16
|
+
- `mock-data.ts` - Sample GLOST documents with enhanced Thai and Japanese examples including:
|
|
17
|
+
- Word-level annotations with multiple transcription systems
|
|
18
|
+
- Translations in multiple languages
|
|
19
|
+
- Cultural notes and metadata
|
|
20
|
+
- Example sentences and usage patterns
|