glost 0.1.0

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.
@@ -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 +1,67 @@
1
+ {
2
+ "name": "glost",
3
+ "version": "0.1.0",
4
+ "description": "GLOST - Glossed Syntax Tree for augmenting text with language learning metadata",
5
+ "type": "module",
6
+ "main": "./src/index.ts",
7
+ "types": "./src/index.ts",
8
+ "exports": {
9
+ ".": {
10
+ "types": "./src/index.ts",
11
+ "default": "./src/index.ts"
12
+ },
13
+ "./nodes": {
14
+ "types": "./src/nodes.ts",
15
+ "default": "./src/nodes.ts"
16
+ },
17
+ "./utils": {
18
+ "types": "./src/utils.ts",
19
+ "default": "./src/utils.ts"
20
+ },
21
+ "./validators": {
22
+ "types": "./src/validators.ts",
23
+ "default": "./src/validators.ts"
24
+ },
25
+ "./guards": {
26
+ "types": "./src/guards.ts",
27
+ "default": "./src/guards.ts"
28
+ }
29
+ },
30
+ "dependencies": {
31
+ "unist-util-filter": "^5.0.1",
32
+ "unist-util-find": "^3.0.0",
33
+ "unist-util-flatmap": "^1.0.0",
34
+ "unist-util-is": "^6.0.0",
35
+ "unist-util-map": "^4.0.0",
36
+ "unist-util-modify-children": "^4.0.0",
37
+ "unist-util-remove": "^4.0.0",
38
+ "unist-util-select": "^5.1.0",
39
+ "unist-util-visit": "^5.0.0",
40
+ "zod": "^3.23.8",
41
+ "glost-common": "0.1.0"
42
+ },
43
+ "devDependencies": {
44
+ "@types/nlcst": "^2.0.3",
45
+ "typescript": "^5.8.3",
46
+ "vitest": "^3.0.5"
47
+ },
48
+ "keywords": [
49
+ "glost",
50
+ "glossed-syntax-tree",
51
+ "nlcst",
52
+ "multilingual",
53
+ "language-learning",
54
+ "linguistics",
55
+ "thai",
56
+ "japanese",
57
+ "chinese",
58
+ "korean",
59
+ "syntax-tree",
60
+ "unist"
61
+ ],
62
+ "scripts": {
63
+ "build": "tsc",
64
+ "typecheck": "tsc --noEmit",
65
+ "test": "vitest"
66
+ }
67
+ }
package/src/example.ts ADDED
@@ -0,0 +1,186 @@
1
+ // Example usage of the GLOST package
2
+ import {
3
+ createThaiWord,
4
+ createJapaneseWord,
5
+ createSentenceFromWords,
6
+ createParagraphFromSentences,
7
+ createDocumentFromParagraphs,
8
+ getAllWords,
9
+ getWordTranscription,
10
+ validateGLOSTTree,
11
+ getWordText
12
+ } from './index';
13
+
14
+ // ============================================================================
15
+ // Thai Example: "สวัสดีครับ ผมชื่อสมชาย" (Hello, my name is Somchai)
16
+ // ============================================================================
17
+
18
+ const thaiWords = [
19
+ createThaiWord(
20
+ 'สวัสดี',
21
+ 'sà-wàt-dii',
22
+ 'interjection',
23
+ 2, // tone
24
+ ['sa', 'wat', 'dii']
25
+ ),
26
+ createThaiWord(
27
+ 'ครับ',
28
+ 'khráp',
29
+ 'particle',
30
+ 2,
31
+ ['khrap']
32
+ ),
33
+ createThaiWord(
34
+ 'ผม',
35
+ 'phǒm',
36
+ 'pronoun',
37
+ 3,
38
+ ['phom']
39
+ ),
40
+ createThaiWord(
41
+ 'ชื่อ',
42
+ 'chûue',
43
+ 'noun',
44
+ 3,
45
+ ['chue']
46
+ ),
47
+ createThaiWord(
48
+ 'สมชาย',
49
+ 'sǒm-chaai',
50
+ 'proper noun',
51
+ 3,
52
+ ['som', 'chaai']
53
+ )
54
+ ];
55
+
56
+ const thaiSentence = createSentenceFromWords(
57
+ thaiWords,
58
+ 'th',
59
+ 'thai',
60
+ 'สวัสดีครับ ผมชื่อสมชาย'
61
+ );
62
+
63
+ // ============================================================================
64
+ // Japanese Example: "私の名前は田中です。" (My name is Tanaka)
65
+ // ============================================================================
66
+
67
+ const japaneseWords = [
68
+ createJapaneseWord(
69
+ '私',
70
+ 'watashi',
71
+ 'pronoun',
72
+ 'わたし'
73
+ ),
74
+ createJapaneseWord(
75
+ 'の',
76
+ 'no',
77
+ 'particle'
78
+ ),
79
+ createJapaneseWord(
80
+ '名前',
81
+ 'namae',
82
+ 'noun',
83
+ 'なまえ'
84
+ ),
85
+ createJapaneseWord(
86
+ 'は',
87
+ 'wa',
88
+ 'particle'
89
+ ),
90
+ createJapaneseWord(
91
+ '田中',
92
+ 'tanaka',
93
+ 'proper noun',
94
+ 'たなか'
95
+ ),
96
+ createJapaneseWord(
97
+ 'です',
98
+ 'desu',
99
+ 'copula'
100
+ )
101
+ ];
102
+
103
+ const japaneseSentence = createSentenceFromWords(
104
+ japaneseWords,
105
+ 'ja',
106
+ 'mixed',
107
+ '私の名前は田中です。'
108
+ );
109
+
110
+ // ============================================================================
111
+ // Create Document Structure
112
+ // ============================================================================
113
+
114
+ const thaiParagraph = createParagraphFromSentences([thaiSentence]);
115
+ const japaneseParagraph = createParagraphFromSentences([japaneseSentence]);
116
+
117
+ const document = createDocumentFromParagraphs(
118
+ [thaiParagraph, japaneseParagraph],
119
+ 'mixed',
120
+ 'mixed',
121
+ {
122
+ title: 'Multilingual Greeting Examples',
123
+ description: 'Examples of greetings in Thai and Japanese with transcriptions'
124
+ }
125
+ );
126
+
127
+ // ============================================================================
128
+ // Demonstrate Utilities
129
+ // ============================================================================
130
+
131
+ export function demonstrateUtilities() {
132
+ console.log('=== GLOST Package Demo ===\n');
133
+
134
+ // Get all words from the document
135
+ const allWords = getAllWords(document);
136
+ console.log(`Total words: ${allWords.length}`);
137
+
138
+ // Show Thai words with RTGS transcriptions
139
+ const thaiWordsOnly = allWords.filter(word => word.lang === 'th');
140
+ console.log('\n=== Thai Words ===');
141
+ thaiWordsOnly.forEach(word => {
142
+ const rtgs = getWordTranscription(word, 'rtgs');
143
+ console.log(`${getWordText(word)} → ${rtgs} (${word.metadata.partOfSpeech})`);
144
+ });
145
+
146
+ // Show Japanese words with romaji
147
+ const japaneseWordsOnly = allWords.filter(word => word.lang === 'ja');
148
+ console.log('\n=== Japanese Words ===');
149
+ japaneseWordsOnly.forEach(word => {
150
+ const romaji = getWordTranscription(word, 'romaji');
151
+ console.log(`${getWordText(word)} → ${romaji} (${word.metadata.partOfSpeech})`);
152
+ });
153
+
154
+ // Validate the tree
155
+ const validationErrors = validateGLOSTTree(document);
156
+ if (validationErrors.length === 0) {
157
+ console.log('\n✅ Document is valid!');
158
+ } else {
159
+ console.log('\n❌ Validation errors:');
160
+ validationErrors.forEach((error: string) => console.log(` - ${error}`));
161
+ }
162
+
163
+ // Show document structure
164
+ console.log('\n=== Document Structure ===');
165
+ console.log(`Language: ${document.lang}`);
166
+ console.log(`Script: ${document.script}`);
167
+ console.log(`Paragraphs: ${document.children.length}`);
168
+ console.log(`Sentences: ${document.children.reduce((acc, p) => {
169
+ if (p.type === 'ParagraphNode') {
170
+ return acc + (p.children?.length || 0);
171
+ }
172
+ return acc;
173
+ }, 0)}`);
174
+ console.log(`Words: ${allWords.length}`);
175
+ }
176
+
177
+ // Export for use in other files
178
+ export {
179
+ thaiWords,
180
+ japaneseWords,
181
+ thaiSentence,
182
+ japaneseSentence,
183
+ thaiParagraph,
184
+ japaneseParagraph,
185
+ document
186
+ };