@magda/semantic-indexer-framework 5.2.0

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.
Files changed (64) hide show
  1. package/dist/MinioClient.d.ts +7 -0
  2. package/dist/MinioClient.js +37 -0
  3. package/dist/MinioClient.js.map +1 -0
  4. package/dist/SkipError.d.ts +1 -0
  5. package/dist/SkipError.js +1 -0
  6. package/dist/SkipError.js.map +1 -0
  7. package/dist/chunker.d.ts +32 -0
  8. package/dist/chunker.js +84 -0
  9. package/dist/chunker.js.map +1 -0
  10. package/dist/commonYargs.d.ts +43 -0
  11. package/dist/commonYargs.js +61 -0
  12. package/dist/commonYargs.js.map +1 -0
  13. package/dist/createEmbeddingText.d.ts +18 -0
  14. package/dist/createEmbeddingText.js +1 -0
  15. package/dist/createEmbeddingText.js.map +1 -0
  16. package/dist/helpers.d.ts +1 -0
  17. package/dist/helpers.js +10 -0
  18. package/dist/helpers.js.map +1 -0
  19. package/dist/index.d.ts +8 -0
  20. package/dist/index.js +4 -0
  21. package/dist/index.js.map +1 -0
  22. package/dist/indexEmbeddingText.d.ts +22 -0
  23. package/dist/indexEmbeddingText.js +216 -0
  24. package/dist/indexEmbeddingText.js.map +1 -0
  25. package/dist/indexSchema.d.ts +105 -0
  26. package/dist/indexSchema.js +98 -0
  27. package/dist/indexSchema.js.map +1 -0
  28. package/dist/onRecordFoundRegistryRecord.d.ts +7 -0
  29. package/dist/onRecordFoundRegistryRecord.js +47 -0
  30. package/dist/onRecordFoundRegistryRecord.js.map +1 -0
  31. package/dist/onRecordFoundStorageObject.d.ts +9 -0
  32. package/dist/onRecordFoundStorageObject.js +145 -0
  33. package/dist/onRecordFoundStorageObject.js.map +1 -0
  34. package/dist/semanticIndexer.d.ts +2 -0
  35. package/dist/semanticIndexer.js +86 -0
  36. package/dist/semanticIndexer.js.map +1 -0
  37. package/dist/semanticIndexerOptions.d.ts +19 -0
  38. package/dist/semanticIndexerOptions.js +26 -0
  39. package/dist/semanticIndexerOptions.js.map +1 -0
  40. package/dist/test/BaseSemanticIndexerTest.d.ts +41 -0
  41. package/dist/test/BaseSemanticIndexerTest.js +167 -0
  42. package/dist/test/BaseSemanticIndexerTest.js.map +1 -0
  43. package/dist/test/chunker.spec.d.ts +1 -0
  44. package/dist/test/chunker.spec.js +154 -0
  45. package/dist/test/chunker.spec.js.map +1 -0
  46. package/dist/test/embeddingApiClient.spec.d.ts +1 -0
  47. package/dist/test/embeddingApiClient.spec.js +43 -0
  48. package/dist/test/embeddingApiClient.spec.js.map +1 -0
  49. package/dist/test/helpers.d.ts +4 -0
  50. package/dist/test/helpers.js +34 -0
  51. package/dist/test/helpers.js.map +1 -0
  52. package/dist/test/indexEmbeddingText.spec.d.ts +1 -0
  53. package/dist/test/indexEmbeddingText.spec.js +238 -0
  54. package/dist/test/indexEmbeddingText.spec.js.map +1 -0
  55. package/dist/test/mockEmbeddingApi.d.ts +1 -0
  56. package/dist/test/mockEmbeddingApi.js +25 -0
  57. package/dist/test/mockEmbeddingApi.js.map +1 -0
  58. package/dist/test/onRecordFoundRegistryRecord.spec.d.ts +1 -0
  59. package/dist/test/onRecordFoundRegistryRecord.spec.js +155 -0
  60. package/dist/test/onRecordFoundRegistryRecord.spec.js.map +1 -0
  61. package/dist/test/onRecordFoundStorageObject.spec.d.ts +1 -0
  62. package/dist/test/onRecordFoundStorageObject.spec.js +490 -0
  63. package/dist/test/onRecordFoundStorageObject.spec.js.map +1 -0
  64. package/package.json +78 -0
@@ -0,0 +1,490 @@
1
+ import { expect } from "chai";
2
+ import sinon from "sinon";
3
+ import { onRecordFoundStorageObject } from "../onRecordFoundStorageObject.js";
4
+ import { createRecord, expectNoThrowsAsync } from "./helpers.js";
5
+ import { BaseSemanticIndexerTest } from "./BaseSemanticIndexerTest.js";
6
+ import fs from "fs";
7
+ import nock from "nock";
8
+ import { tmpdir } from "os";
9
+ import { join } from "path";
10
+ describe("onRecordFoundStorageObject", () => {
11
+ let testEnv;
12
+ beforeEach(() => {
13
+ testEnv = new BaseSemanticIndexerTest({
14
+ suppressConsoleLogs: true
15
+ });
16
+ });
17
+ afterEach(() => {
18
+ testEnv.cleanup();
19
+ });
20
+ it("should handle and index storage object with expected formatType, with autoDownloadFile disabled", async () => {
21
+ testEnv.createEmbeddingTextStub.resolves({
22
+ text: "embedding text: test1"
23
+ });
24
+ const userConfig = testEnv.updateUserConfig({
25
+ itemType: "storageObject",
26
+ formatTypes: ["csv"],
27
+ autoDownloadFile: false
28
+ });
29
+ testEnv.chunker.chunk
30
+ .withArgs("embedding text: test1")
31
+ .returns([{ text: "test1", length: 5, position: 0, overlap: 0 }]);
32
+ testEnv.embeddingApiClient.get
33
+ .withArgs(["test1"])
34
+ .resolves([[0.1, 0.2, 0.3]]);
35
+ const record = createRecord({
36
+ id: "id1",
37
+ aspects: {
38
+ "dataset-format": { format: "csv" },
39
+ "dcat-distribution-strings": {
40
+ format: "csv",
41
+ downloadURL: "http://test.com/file.csv"
42
+ }
43
+ }
44
+ });
45
+ const onRecordFound = onRecordFoundStorageObject(userConfig, testEnv.chunker, testEnv.embeddingApiClient, testEnv.opensearchApiClient, testEnv.minioClient, testEnv.registry);
46
+ await onRecordFound(record, testEnv.registry);
47
+ const expectedDocs = [
48
+ {
49
+ itemType: userConfig.itemType,
50
+ recordId: "id1",
51
+ parentRecordId: testEnv.DEFAULT_PARENT_RECORD_ID,
52
+ fileFormat: "csv",
53
+ index_text_chunk: "test1",
54
+ embedding: [0.1, 0.2, 0.3],
55
+ only_one_index_text_chunk: true,
56
+ index_text_chunk_length: 5,
57
+ index_text_chunk_position: 0,
58
+ index_text_chunk_overlap: 0,
59
+ indexerId: userConfig.id,
60
+ createTime: testEnv.getCurrentTimeString(),
61
+ updateTime: testEnv.getCurrentTimeString()
62
+ }
63
+ ];
64
+ testEnv.expectSuccessCalls({
65
+ createEmbeddingTextCallCount: 1,
66
+ chunkCallCount: 1,
67
+ embeddingApiCallCount: 1,
68
+ bulkIndexCallCount: 1,
69
+ deleteByQueryCallCount: 1
70
+ });
71
+ testEnv.expectCalledWith(testEnv.createEmbeddingTextStub, 0, {
72
+ record,
73
+ format: "csv",
74
+ filePath: null,
75
+ url: "http://test.com/file.csv",
76
+ readonlyRegistry: testEnv.registry
77
+ });
78
+ testEnv.expectIndexedDocs(expectedDocs);
79
+ });
80
+ it("should handle and index storage object with expected formatType, with autoDownloadFile enabled", async () => {
81
+ const fileContent = "test1";
82
+ nock("http://test.com").get("/file.csv").reply(200, fileContent);
83
+ const record = createRecord({
84
+ id: "id1",
85
+ aspects: {
86
+ "dataset-format": { format: "csv" },
87
+ "dcat-distribution-strings": {
88
+ format: "csv",
89
+ downloadURL: "http://test.com/file.csv"
90
+ }
91
+ }
92
+ });
93
+ let usedFilePath = null;
94
+ testEnv.createEmbeddingTextStub.callsFake(async ({ record, format, filePath, url }) => {
95
+ expect(record).to.deep.equal(record);
96
+ expect(format).to.equal("csv");
97
+ expect(fs.existsSync(filePath)).to.be.true;
98
+ expect(url).to.equal("http://test.com/file.csv");
99
+ const content = fs.readFileSync(filePath, "utf-8");
100
+ expect(content).to.equal("test1");
101
+ usedFilePath = filePath;
102
+ return { text: "embedding text: test1" };
103
+ });
104
+ testEnv.chunker.chunk
105
+ .withArgs("embedding text: test1")
106
+ .returns([{ text: "test1", length: 5, position: 0, overlap: 0 }]);
107
+ testEnv.embeddingApiClient.get
108
+ .withArgs(["test1"])
109
+ .resolves([[0.1, 0.2, 0.3]]);
110
+ const userConfig = testEnv.updateUserConfig({
111
+ itemType: "storageObject",
112
+ formatTypes: ["csv"],
113
+ autoDownloadFile: true
114
+ });
115
+ const expectedDocs = [
116
+ {
117
+ itemType: userConfig.itemType,
118
+ recordId: "id1",
119
+ parentRecordId: testEnv.DEFAULT_PARENT_RECORD_ID,
120
+ fileFormat: "csv",
121
+ index_text_chunk: "test1",
122
+ embedding: [0.1, 0.2, 0.3],
123
+ only_one_index_text_chunk: true,
124
+ index_text_chunk_length: 5,
125
+ index_text_chunk_position: 0,
126
+ index_text_chunk_overlap: 0,
127
+ indexerId: userConfig.id,
128
+ createTime: testEnv.getCurrentTimeString(),
129
+ updateTime: testEnv.getCurrentTimeString()
130
+ }
131
+ ];
132
+ const onRecordFound = onRecordFoundStorageObject(userConfig, testEnv.chunker, testEnv.embeddingApiClient, testEnv.opensearchApiClient, testEnv.minioClient, testEnv.registry);
133
+ await onRecordFound(record, testEnv.registry);
134
+ testEnv.expectSuccessCalls({
135
+ createEmbeddingTextCallCount: 1,
136
+ chunkCallCount: 1,
137
+ embeddingApiCallCount: 1,
138
+ bulkIndexCallCount: 1,
139
+ deleteByQueryCallCount: 1
140
+ });
141
+ testEnv.expectIndexedDocs(expectedDocs);
142
+ if (usedFilePath) {
143
+ expect(fs.existsSync(usedFilePath)).to.be.false;
144
+ }
145
+ nock.cleanAll();
146
+ });
147
+ it("should successfully download file from minio", async () => {
148
+ const fileContent = "test1";
149
+ const downloadUrl = "magda://storage-api/fake-parent-record-id/id1/file.csv";
150
+ const tempDir = tmpdir();
151
+ const tempFilePath = join(tempDir, "file.csv");
152
+ testEnv.minioClient.downloadFile
153
+ .withArgs(downloadUrl)
154
+ .callsFake(async () => {
155
+ fs.writeFileSync(tempFilePath, fileContent);
156
+ return tempFilePath;
157
+ });
158
+ const record = createRecord({
159
+ id: "id1",
160
+ aspects: {
161
+ "dataset-format": { format: "csv" },
162
+ "dcat-distribution-strings": {
163
+ format: "csv",
164
+ downloadURL: downloadUrl
165
+ }
166
+ }
167
+ });
168
+ let usedFilePath = null;
169
+ testEnv.createEmbeddingTextStub.callsFake(async ({ record, format, filePath, url }) => {
170
+ expect(record).to.deep.equal(record);
171
+ expect(format).to.equal("csv");
172
+ expect(fs.existsSync(filePath)).to.be.true;
173
+ expect(url).to.equal(downloadUrl);
174
+ const content = fs.readFileSync(filePath, "utf-8");
175
+ expect(content).to.equal("test1");
176
+ usedFilePath = filePath;
177
+ return { text: "embedding text: test1" };
178
+ });
179
+ testEnv.chunker.chunk
180
+ .withArgs("embedding text: test1")
181
+ .returns([{ text: "test1", length: 5, position: 0, overlap: 0 }]);
182
+ testEnv.embeddingApiClient.get
183
+ .withArgs(["test1"])
184
+ .resolves([[0.1, 0.2, 0.3]]);
185
+ const userConfig = testEnv.updateUserConfig({
186
+ itemType: "storageObject",
187
+ formatTypes: ["csv"],
188
+ autoDownloadFile: true
189
+ });
190
+ const expectedDocs = [
191
+ {
192
+ itemType: userConfig.itemType,
193
+ recordId: "id1",
194
+ parentRecordId: testEnv.DEFAULT_PARENT_RECORD_ID,
195
+ fileFormat: "csv",
196
+ index_text_chunk: "test1",
197
+ embedding: [0.1, 0.2, 0.3],
198
+ only_one_index_text_chunk: true,
199
+ index_text_chunk_length: 5,
200
+ index_text_chunk_position: 0,
201
+ index_text_chunk_overlap: 0,
202
+ indexerId: userConfig.id,
203
+ createTime: testEnv.getCurrentTimeString(),
204
+ updateTime: testEnv.getCurrentTimeString()
205
+ }
206
+ ];
207
+ const onRecordFound = onRecordFoundStorageObject(userConfig, testEnv.chunker, testEnv.embeddingApiClient, testEnv.opensearchApiClient, testEnv.minioClient, testEnv.registry);
208
+ await onRecordFound(record, testEnv.registry);
209
+ testEnv.expectSuccessCalls({
210
+ createEmbeddingTextCallCount: 1,
211
+ chunkCallCount: 1,
212
+ embeddingApiCallCount: 1,
213
+ bulkIndexCallCount: 1,
214
+ deleteByQueryCallCount: 1
215
+ });
216
+ testEnv.expectIndexedDocs(expectedDocs);
217
+ if (usedFilePath) {
218
+ expect(fs.existsSync(usedFilePath)).to.be.false;
219
+ }
220
+ nock.cleanAll();
221
+ });
222
+ it("should filter out records with unexpected formatType", async () => {
223
+ testEnv.createEmbeddingTextStub.resolves({
224
+ text: "embedding text: test1"
225
+ });
226
+ const userConfig = testEnv.updateUserConfig({
227
+ itemType: "storageObject",
228
+ formatTypes: ["csv"],
229
+ autoDownloadFile: false
230
+ });
231
+ testEnv.chunker.chunk
232
+ .withArgs("embedding text: test1")
233
+ .returns([{ text: "test1", length: 5, position: 0, overlap: 0 }]);
234
+ testEnv.embeddingApiClient.get
235
+ .withArgs(["test1"])
236
+ .resolves([[0.1, 0.2, 0.3]]);
237
+ const record = createRecord({
238
+ id: "id1",
239
+ aspects: {
240
+ "dataset-format": { format: "json" },
241
+ "dcat-distribution-strings": {
242
+ format: "json",
243
+ downloadURL: "http://test.com/file.json"
244
+ }
245
+ }
246
+ });
247
+ const onRecordFound = onRecordFoundStorageObject(userConfig, testEnv.chunker, testEnv.embeddingApiClient, testEnv.opensearchApiClient, testEnv.minioClient, testEnv.registry);
248
+ await onRecordFound(record, testEnv.registry);
249
+ testEnv.expectSuccessCalls({
250
+ createEmbeddingTextCallCount: 0,
251
+ chunkCallCount: 0,
252
+ embeddingApiCallCount: 0,
253
+ bulkIndexCallCount: 0,
254
+ deleteByQueryCallCount: 0
255
+ });
256
+ });
257
+ it("should handle and index storage object with multiple expected format types", async () => {
258
+ const userConfig = testEnv.updateUserConfig({
259
+ itemType: "storageObject",
260
+ formatTypes: ["csv", "json"],
261
+ autoDownloadFile: false
262
+ });
263
+ const record = createRecord({
264
+ id: "id1",
265
+ aspects: {
266
+ "dataset-format": { format: "csv" },
267
+ "dcat-distribution-strings": {
268
+ format: "csv",
269
+ downloadURL: "http://test.com/file.csv"
270
+ }
271
+ }
272
+ });
273
+ testEnv.chunker.chunk
274
+ .withArgs("embedding text: test1")
275
+ .returns([{ text: "test1", length: 5, position: 0, overlap: 0 }]);
276
+ testEnv.embeddingApiClient.get
277
+ .withArgs(["test1"])
278
+ .resolves([[0.1, 0.2, 0.3]]);
279
+ testEnv.createEmbeddingTextStub
280
+ .withArgs({
281
+ record,
282
+ format: "csv",
283
+ filePath: null,
284
+ url: "http://test.com/file.csv",
285
+ readonlyRegistry: testEnv.registry
286
+ })
287
+ .resolves({ text: "embedding text: test1" });
288
+ const onRecordFound = onRecordFoundStorageObject(userConfig, testEnv.chunker, testEnv.embeddingApiClient, testEnv.opensearchApiClient, testEnv.minioClient, testEnv.registry);
289
+ await onRecordFound(record, testEnv.registry);
290
+ const expectedDocs1 = [
291
+ {
292
+ itemType: userConfig.itemType,
293
+ recordId: "id1",
294
+ parentRecordId: testEnv.DEFAULT_PARENT_RECORD_ID,
295
+ fileFormat: "csv",
296
+ index_text_chunk: "test1",
297
+ embedding: [0.1, 0.2, 0.3],
298
+ only_one_index_text_chunk: true,
299
+ index_text_chunk_length: 5,
300
+ index_text_chunk_position: 0,
301
+ index_text_chunk_overlap: 0,
302
+ indexerId: userConfig.id,
303
+ createTime: testEnv.getCurrentTimeString(),
304
+ updateTime: testEnv.getCurrentTimeString()
305
+ }
306
+ ];
307
+ testEnv.expectSuccessCalls({
308
+ createEmbeddingTextCallCount: 1,
309
+ chunkCallCount: 1,
310
+ embeddingApiCallCount: 1,
311
+ bulkIndexCallCount: 1,
312
+ deleteByQueryCallCount: 1
313
+ });
314
+ testEnv.expectIndexedDocs(expectedDocs1);
315
+ });
316
+ it("should skip this record when embeddingApiClient throws an error", async () => {
317
+ const userConfig = testEnv.updateUserConfig({
318
+ itemType: "storageObject",
319
+ formatTypes: ["csv"]
320
+ });
321
+ const record = createRecord({
322
+ id: "id1",
323
+ aspects: {
324
+ "dataset-format": { format: "csv" },
325
+ "dcat-distribution-strings": {
326
+ format: "csv",
327
+ downloadURL: "http://test.com/file.csv"
328
+ }
329
+ }
330
+ });
331
+ testEnv.embeddingApiClient.get
332
+ .withArgs(["test1"])
333
+ .rejects(new Error("throw test error"));
334
+ const onRecordFound = onRecordFoundStorageObject(userConfig, testEnv.chunker, testEnv.embeddingApiClient, testEnv.opensearchApiClient, testEnv.minioClient, testEnv.registry);
335
+ await expectNoThrowsAsync(() => onRecordFound(record, testEnv.registry));
336
+ });
337
+ it("should skip this record when opensearchApiClient throws an error", async () => {
338
+ const userConfig = testEnv.updateUserConfig({
339
+ itemType: "storageObject",
340
+ formatTypes: ["csv"]
341
+ });
342
+ const record = createRecord({
343
+ id: "id1",
344
+ aspects: {
345
+ "dataset-format": { format: "csv" },
346
+ "dcat-distribution-strings": {
347
+ format: "csv",
348
+ downloadURL: "http://test.com/file.csv"
349
+ }
350
+ }
351
+ });
352
+ testEnv.opensearchApiClient.bulkIndexDocument
353
+ .withArgs(record, null)
354
+ .rejects(new Error("throw test error"));
355
+ const onRecordFound = onRecordFoundStorageObject(userConfig, testEnv.chunker, testEnv.embeddingApiClient, testEnv.opensearchApiClient, testEnv.minioClient, testEnv.registry);
356
+ await expectNoThrowsAsync(() => onRecordFound(record, testEnv.registry));
357
+ });
358
+ it("should skip this record when createEmbeddingText throws an error", async () => {
359
+ const userConfig = testEnv.updateUserConfig({
360
+ itemType: "storageObject",
361
+ formatTypes: ["csv"],
362
+ createEmbeddingText: sinon
363
+ .stub()
364
+ .rejects(new Error("throw test error"))
365
+ });
366
+ const record = createRecord({
367
+ id: "id1",
368
+ aspects: {
369
+ "dataset-format": { format: "csv" },
370
+ "dcat-distribution-strings": {
371
+ format: "csv",
372
+ downloadURL: "http://test.com/file.csv"
373
+ }
374
+ }
375
+ });
376
+ const onRecordFound = onRecordFoundStorageObject(userConfig, testEnv.chunker, testEnv.embeddingApiClient, testEnv.opensearchApiClient, testEnv.minioClient, testEnv.registry);
377
+ await expectNoThrowsAsync(() => onRecordFound(record, testEnv.registry));
378
+ });
379
+ it("should skip this record when dataset-distributions aspect not exist", async () => {
380
+ const userConfig = testEnv.updateUserConfig({
381
+ itemType: "storageObject",
382
+ formatTypes: ["csv"]
383
+ });
384
+ const record = createRecord({
385
+ id: "id1",
386
+ aspects: {}
387
+ });
388
+ const onRecordFound = onRecordFoundStorageObject(userConfig, testEnv.chunker, testEnv.embeddingApiClient, testEnv.opensearchApiClient, testEnv.minioClient, testEnv.registry);
389
+ await expectNoThrowsAsync(() => onRecordFound(record, testEnv.registry));
390
+ });
391
+ it("should skip this record when dcat-distribution-strings is missing downloadURL", async () => {
392
+ const userConfig = testEnv.updateUserConfig({
393
+ itemType: "storageObject",
394
+ formatTypes: ["csv"]
395
+ });
396
+ const record = createRecord({
397
+ id: "id1",
398
+ aspects: {
399
+ "dataset-format": { format: "csv" },
400
+ "dcat-distribution-strings": {
401
+ format: "csv",
402
+ downloadURL: "http://test.com/test.csv"
403
+ }
404
+ }
405
+ });
406
+ const onRecordFound = onRecordFoundStorageObject(userConfig, testEnv.chunker, testEnv.embeddingApiClient, testEnv.opensearchApiClient, testEnv.minioClient, testEnv.registry);
407
+ await expectNoThrowsAsync(() => onRecordFound(record, testEnv.registry));
408
+ });
409
+ it("should use format from dcat-distribution-strings when dataset-format is missing", async () => {
410
+ const userConfig = testEnv.updateUserConfig({
411
+ itemType: "storageObject",
412
+ formatTypes: ["csv"],
413
+ autoDownloadFile: false
414
+ });
415
+ const record = createRecord({
416
+ id: "id1",
417
+ aspects: {
418
+ "dataset-format": {},
419
+ "dcat-distribution-strings": {
420
+ format: "csv",
421
+ downloadURL: "http://test.com/test.csv"
422
+ }
423
+ }
424
+ });
425
+ const onRecordFound = onRecordFoundStorageObject(userConfig, testEnv.chunker, testEnv.embeddingApiClient, testEnv.opensearchApiClient, testEnv.minioClient, testEnv.registry);
426
+ await expectNoThrowsAsync(() => onRecordFound(record, testEnv.registry));
427
+ expect(testEnv.createEmbeddingTextStub.firstCall.args[0]).to.deep.equal({
428
+ record,
429
+ format: "csv",
430
+ filePath: null,
431
+ url: "http://test.com/test.csv",
432
+ readonlyRegistry: testEnv.registry
433
+ });
434
+ });
435
+ it("should call deleteByQuery after indexing", async () => {
436
+ testEnv.createEmbeddingTextStub.resolves({
437
+ text: "embedding text: test1"
438
+ });
439
+ const userConfig = testEnv.updateUserConfig({
440
+ itemType: "storageObject",
441
+ formatTypes: ["csv"],
442
+ autoDownloadFile: false
443
+ });
444
+ testEnv.chunker.chunk
445
+ .withArgs("embedding text: test1")
446
+ .returns([{ text: "test1", length: 5, position: 0, overlap: 0 }]);
447
+ testEnv.embeddingApiClient.get
448
+ .withArgs(["test1"])
449
+ .resolves([[0.1, 0.2, 0.3]]);
450
+ const record = createRecord({
451
+ id: "id1",
452
+ aspects: {
453
+ "dataset-format": { format: "csv" },
454
+ "dcat-distribution-strings": {
455
+ format: "csv",
456
+ downloadURL: "http://test.com/file.csv"
457
+ }
458
+ }
459
+ });
460
+ const onRecordFound = onRecordFoundStorageObject(userConfig, testEnv.chunker, testEnv.embeddingApiClient, testEnv.opensearchApiClient, testEnv.minioClient, testEnv.registry);
461
+ await onRecordFound(record, testEnv.registry);
462
+ testEnv.expectSuccessCalls({
463
+ deleteByQueryCallCount: 1
464
+ });
465
+ testEnv.expectCalledWith(testEnv.opensearchApiClient.deleteByQuery, 0, {
466
+ index: userConfig.argv.semanticIndexerConfig.fullIndexName,
467
+ body: {
468
+ query: {
469
+ bool: {
470
+ filter: [
471
+ { term: { indexerId: userConfig.id } },
472
+ { term: { recordId: "id1" } },
473
+ {
474
+ range: {
475
+ createTime: {
476
+ lt: testEnv.getCurrentTimeString()
477
+ }
478
+ }
479
+ }
480
+ ]
481
+ }
482
+ }
483
+ },
484
+ wait_for_completion: true,
485
+ conflicts: "proceed",
486
+ timeout: userConfig.timeout
487
+ });
488
+ });
489
+ });
490
+ //# sourceMappingURL=onRecordFoundStorageObject.spec.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"onRecordFoundStorageObject.spec.js","sourceRoot":"","sources":["../../src/test/onRecordFoundStorageObject.spec.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,MAAM,EAAE,MAAM,MAAM,CAAC;AAC9B,OAAO,KAAK,MAAM,OAAO,CAAC;AAC1B,OAAO,EAAE,0BAA0B,EAAE,MAAM,kCAAkC,CAAC;AAC9E,OAAO,EAAE,YAAY,EAAE,mBAAmB,EAAE,MAAM,cAAc,CAAC;AACjE,OAAO,EAAE,uBAAuB,EAAE,MAAM,8BAA8B,CAAC;AACvE,OAAO,EAAE,MAAM,IAAI,CAAC;AACpB,OAAO,IAAI,MAAM,MAAM,CAAC;AACxB,OAAO,EAAE,MAAM,EAAE,MAAM,IAAI,CAAC;AAC5B,OAAO,EAAE,IAAI,EAAE,MAAM,MAAM,CAAC;AAE5B,QAAQ,CAAC,4BAA4B,EAAE,GAAG,EAAE;IACxC,IAAI,OAAgC,CAAC;IAErC,UAAU,CAAC,GAAG,EAAE;QACZ,OAAO,GAAG,IAAI,uBAAuB,CAAC;YAClC,mBAAmB,EAAE,IAAI;SAC5B,CAAC,CAAC;IACP,CAAC,CAAC,CAAC;IAEH,SAAS,CAAC,GAAG,EAAE;QACX,OAAO,CAAC,OAAO,EAAE,CAAC;IACtB,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,iGAAiG,EAAE,KAAK,IAAI,EAAE;QAC7G,OAAO,CAAC,uBAAuB,CAAC,QAAQ,CAAC;YACrC,IAAI,EAAE,uBAAuB;SAChC,CAAC,CAAC;QACH,MAAM,UAAU,GAAG,OAAO,CAAC,gBAAgB,CAAC;YACxC,QAAQ,EAAE,eAAe;YACzB,WAAW,EAAE,CAAC,KAAK,CAAC;YACpB,gBAAgB,EAAE,KAAK;SAC1B,CAAC,CAAC;QAEH,OAAO,CAAC,OAAO,CAAC,KAAK;aAChB,QAAQ,CAAC,uBAAuB,CAAC;aACjC,OAAO,CAAC,CAAC,EAAE,IAAI,EAAE,OAAO,EAAE,MAAM,EAAE,CAAC,EAAE,QAAQ,EAAE,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,CAAC,CAAC,CAAC;QACtE,OAAO,CAAC,kBAAkB,CAAC,GAAG;aACzB,QAAQ,CAAC,CAAC,OAAO,CAAC,CAAC;aACnB,QAAQ,CAAC,CAAC,CAAC,GAAG,EAAE,GAAG,EAAE,GAAG,CAAC,CAAC,CAAC,CAAC;QAEjC,MAAM,MAAM,GAAG,YAAY,CAAC;YACxB,EAAE,EAAE,KAAK;YACT,OAAO,EAAE;gBACL,gBAAgB,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE;gBACnC,2BAA2B,EAAE;oBACzB,MAAM,EAAE,KAAK;oBACb,WAAW,EAAE,0BAA0B;iBAC1C;aACJ;SACJ,CAAC,CAAC;QAEH,MAAM,aAAa,GAAG,0BAA0B,CAC5C,UAAU,EACV,OAAO,CAAC,OAAO,EACf,OAAO,CAAC,kBAAkB,EAC1B,OAAO,CAAC,mBAAmB,EAC3B,OAAO,CAAC,WAAW,EACnB,OAAO,CAAC,QAAQ,CACnB,CAAC;QACF,MAAM,aAAa,CAAC,MAAM,EAAE,OAAO,CAAC,QAAQ,CAAC,CAAC;QAE9C,MAAM,YAAY,GAAG;YACjB;gBACI,QAAQ,EAAE,UAAU,CAAC,QAAQ;gBAC7B,QAAQ,EAAE,KAAK;gBACf,cAAc,EAAE,OAAO,CAAC,wBAAwB;gBAChD,UAAU,EAAE,KAAK;gBACjB,gBAAgB,EAAE,OAAO;gBACzB,SAAS,EAAE,CAAC,GAAG,EAAE,GAAG,EAAE,GAAG,CAAC;gBAC1B,yBAAyB,EAAE,IAAI;gBAC/B,uBAAuB,EAAE,CAAC;gBAC1B,yBAAyB,EAAE,CAAC;gBAC5B,wBAAwB,EAAE,CAAC;gBAC3B,SAAS,EAAE,UAAU,CAAC,EAAE;gBACxB,UAAU,EAAE,OAAO,CAAC,oBAAoB,EAAE;gBAC1C,UAAU,EAAE,OAAO,CAAC,oBAAoB,EAAE;aAC7C;SACJ,CAAC;QAEF,OAAO,CAAC,kBAAkB,CAAC;YACvB,4BAA4B,EAAE,CAAC;YAC/B,cAAc,EAAE,CAAC;YACjB,qBAAqB,EAAE,CAAC;YACxB,kBAAkB,EAAE,CAAC;YACrB,sBAAsB,EAAE,CAAC;SAC5B,CAAC,CAAC;QAEH,OAAO,CAAC,gBAAgB,CAAC,OAAO,CAAC,uBAAuB,EAAE,CAAC,EAAE;YACzD,MAAM;YACN,MAAM,EAAE,KAAK;YACb,QAAQ,EAAE,IAAI;YACd,GAAG,EAAE,0BAA0B;YAC/B,gBAAgB,EAAE,OAAO,CAAC,QAAQ;SACrC,CAAC,CAAC;QAEH,OAAO,CAAC,iBAAiB,CAAC,YAAY,CAAC,CAAC;IAC5C,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,gGAAgG,EAAE,KAAK,IAAI,EAAE;QAC5G,MAAM,WAAW,GAAG,OAAO,CAAC;QAC5B,IAAI,CAAC,iBAAiB,CAAC,CAAC,GAAG,CAAC,WAAW,CAAC,CAAC,KAAK,CAAC,GAAG,EAAE,WAAW,CAAC,CAAC;QAEjE,MAAM,MAAM,GAAG,YAAY,CAAC;YACxB,EAAE,EAAE,KAAK;YACT,OAAO,EAAE;gBACL,gBAAgB,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE;gBACnC,2BAA2B,EAAE;oBACzB,MAAM,EAAE,KAAK;oBACb,WAAW,EAAE,0BAA0B;iBAC1C;aACJ;SACJ,CAAC,CAAC;QAEH,IAAI,YAAY,GAAG,IAAI,CAAC;QACxB,OAAO,CAAC,uBAAuB,CAAC,SAAS,CACrC,KAAK,EAAE,EAAE,MAAM,EAAE,MAAM,EAAE,QAAQ,EAAE,GAAG,EAAE,EAAE,EAAE;YACxC,MAAM,CAAC,MAAM,CAAC,CAAC,EAAE,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC;YACrC,MAAM,CAAC,MAAM,CAAC,CAAC,EAAE,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC;YAC/B,MAAM,CAAC,EAAE,CAAC,UAAU,CAAC,QAAQ,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,CAAC,IAAI,CAAC;YAC3C,MAAM,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC,KAAK,CAAC,0BAA0B,CAAC,CAAC;YACjD,MAAM,OAAO,GAAG,EAAE,CAAC,YAAY,CAAC,QAAQ,EAAE,OAAO,CAAC,CAAC;YACnD,MAAM,CAAC,OAAO,CAAC,CAAC,EAAE,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC;YAClC,YAAY,GAAG,QAAQ,CAAC;YACxB,OAAO,EAAE,IAAI,EAAE,uBAAuB,EAAE,CAAC;QAC7C,CAAC,CACJ,CAAC;QAEF,OAAO,CAAC,OAAO,CAAC,KAAK;aAChB,QAAQ,CAAC,uBAAuB,CAAC;aACjC,OAAO,CAAC,CAAC,EAAE,IAAI,EAAE,OAAO,EAAE,MAAM,EAAE,CAAC,EAAE,QAAQ,EAAE,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,CAAC,CAAC,CAAC;QACtE,OAAO,CAAC,kBAAkB,CAAC,GAAG;aACzB,QAAQ,CAAC,CAAC,OAAO,CAAC,CAAC;aACnB,QAAQ,CAAC,CAAC,CAAC,GAAG,EAAE,GAAG,EAAE,GAAG,CAAC,CAAC,CAAC,CAAC;QAEjC,MAAM,UAAU,GAAG,OAAO,CAAC,gBAAgB,CAAC;YACxC,QAAQ,EAAE,eAAe;YACzB,WAAW,EAAE,CAAC,KAAK,CAAC;YACpB,gBAAgB,EAAE,IAAI;SACzB,CAAC,CAAC;QAEH,MAAM,YAAY,GAAG;YACjB;gBACI,QAAQ,EAAE,UAAU,CAAC,QAAQ;gBAC7B,QAAQ,EAAE,KAAK;gBACf,cAAc,EAAE,OAAO,CAAC,wBAAwB;gBAChD,UAAU,EAAE,KAAK;gBACjB,gBAAgB,EAAE,OAAO;gBACzB,SAAS,EAAE,CAAC,GAAG,EAAE,GAAG,EAAE,GAAG,CAAC;gBAC1B,yBAAyB,EAAE,IAAI;gBAC/B,uBAAuB,EAAE,CAAC;gBAC1B,yBAAyB,EAAE,CAAC;gBAC5B,wBAAwB,EAAE,CAAC;gBAC3B,SAAS,EAAE,UAAU,CAAC,EAAE;gBACxB,UAAU,EAAE,OAAO,CAAC,oBAAoB,EAAE;gBAC1C,UAAU,EAAE,OAAO,CAAC,oBAAoB,EAAE;aAC7C;SACJ,CAAC;QAEF,MAAM,aAAa,GAAG,0BAA0B,CAC5C,UAAU,EACV,OAAO,CAAC,OAAO,EACf,OAAO,CAAC,kBAAkB,EAC1B,OAAO,CAAC,mBAAmB,EAC3B,OAAO,CAAC,WAAW,EACnB,OAAO,CAAC,QAAQ,CACnB,CAAC;QACF,MAAM,aAAa,CAAC,MAAM,EAAE,OAAO,CAAC,QAAQ,CAAC,CAAC;QAE9C,OAAO,CAAC,kBAAkB,CAAC;YACvB,4BAA4B,EAAE,CAAC;YAC/B,cAAc,EAAE,CAAC;YACjB,qBAAqB,EAAE,CAAC;YACxB,kBAAkB,EAAE,CAAC;YACrB,sBAAsB,EAAE,CAAC;SAC5B,CAAC,CAAC;QAEH,OAAO,CAAC,iBAAiB,CAAC,YAAY,CAAC,CAAC;QAExC,IAAI,YAAY,EAAE,CAAC;YACf,MAAM,CAAC,EAAE,CAAC,UAAU,CAAC,YAAY,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,CAAC,KAAK,CAAC;QACpD,CAAC;QACD,IAAI,CAAC,QAAQ,EAAE,CAAC;IACpB,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,8CAA8C,EAAE,KAAK,IAAI,EAAE;QAC1D,MAAM,WAAW,GAAG,OAAO,CAAC;QAC5B,MAAM,WAAW,GACb,wDAAwD,CAAC;QAC7D,MAAM,OAAO,GAAG,MAAM,EAAE,CAAC;QACzB,MAAM,YAAY,GAAG,IAAI,CAAC,OAAO,EAAE,UAAU,CAAC,CAAC;QAC/C,OAAO,CAAC,WAAW,CAAC,YAAY;aAC3B,QAAQ,CAAC,WAAW,CAAC;aACrB,SAAS,CAAC,KAAK,IAAI,EAAE;YAClB,EAAE,CAAC,aAAa,CAAC,YAAY,EAAE,WAAW,CAAC,CAAC;YAC5C,OAAO,YAAY,CAAC;QACxB,CAAC,CAAC,CAAC;QAEP,MAAM,MAAM,GAAG,YAAY,CAAC;YACxB,EAAE,EAAE,KAAK;YACT,OAAO,EAAE;gBACL,gBAAgB,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE;gBACnC,2BAA2B,EAAE;oBACzB,MAAM,EAAE,KAAK;oBACb,WAAW,EAAE,WAAW;iBAC3B;aACJ;SACJ,CAAC,CAAC;QAEH,IAAI,YAAY,GAAG,IAAI,CAAC;QACxB,OAAO,CAAC,uBAAuB,CAAC,SAAS,CACrC,KAAK,EAAE,EAAE,MAAM,EAAE,MAAM,EAAE,QAAQ,EAAE,GAAG,EAAE,EAAE,EAAE;YACxC,MAAM,CAAC,MAAM,CAAC,CAAC,EAAE,CAAC,IAAI,CAAC,KAAK,CAAC,MAAM,CAAC,CAAC;YACrC,MAAM,CAAC,MAAM,CAAC,CAAC,EAAE,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC;YAC/B,MAAM,CAAC,EAAE,CAAC,UAAU,CAAC,QAAQ,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,CAAC,IAAI,CAAC;YAC3C,MAAM,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC,KAAK,CAAC,WAAW,CAAC,CAAC;YAClC,MAAM,OAAO,GAAG,EAAE,CAAC,YAAY,CAAC,QAAQ,EAAE,OAAO,CAAC,CAAC;YACnD,MAAM,CAAC,OAAO,CAAC,CAAC,EAAE,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC;YAClC,YAAY,GAAG,QAAQ,CAAC;YACxB,OAAO,EAAE,IAAI,EAAE,uBAAuB,EAAE,CAAC;QAC7C,CAAC,CACJ,CAAC;QAEF,OAAO,CAAC,OAAO,CAAC,KAAK;aAChB,QAAQ,CAAC,uBAAuB,CAAC;aACjC,OAAO,CAAC,CAAC,EAAE,IAAI,EAAE,OAAO,EAAE,MAAM,EAAE,CAAC,EAAE,QAAQ,EAAE,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,CAAC,CAAC,CAAC;QACtE,OAAO,CAAC,kBAAkB,CAAC,GAAG;aACzB,QAAQ,CAAC,CAAC,OAAO,CAAC,CAAC;aACnB,QAAQ,CAAC,CAAC,CAAC,GAAG,EAAE,GAAG,EAAE,GAAG,CAAC,CAAC,CAAC,CAAC;QAEjC,MAAM,UAAU,GAAG,OAAO,CAAC,gBAAgB,CAAC;YACxC,QAAQ,EAAE,eAAe;YACzB,WAAW,EAAE,CAAC,KAAK,CAAC;YACpB,gBAAgB,EAAE,IAAI;SACzB,CAAC,CAAC;QAEH,MAAM,YAAY,GAAG;YACjB;gBACI,QAAQ,EAAE,UAAU,CAAC,QAAQ;gBAC7B,QAAQ,EAAE,KAAK;gBACf,cAAc,EAAE,OAAO,CAAC,wBAAwB;gBAChD,UAAU,EAAE,KAAK;gBACjB,gBAAgB,EAAE,OAAO;gBACzB,SAAS,EAAE,CAAC,GAAG,EAAE,GAAG,EAAE,GAAG,CAAC;gBAC1B,yBAAyB,EAAE,IAAI;gBAC/B,uBAAuB,EAAE,CAAC;gBAC1B,yBAAyB,EAAE,CAAC;gBAC5B,wBAAwB,EAAE,CAAC;gBAC3B,SAAS,EAAE,UAAU,CAAC,EAAE;gBACxB,UAAU,EAAE,OAAO,CAAC,oBAAoB,EAAE;gBAC1C,UAAU,EAAE,OAAO,CAAC,oBAAoB,EAAE;aAC7C;SACJ,CAAC;QAEF,MAAM,aAAa,GAAG,0BAA0B,CAC5C,UAAU,EACV,OAAO,CAAC,OAAO,EACf,OAAO,CAAC,kBAAkB,EAC1B,OAAO,CAAC,mBAAmB,EAC3B,OAAO,CAAC,WAAW,EACnB,OAAO,CAAC,QAAQ,CACnB,CAAC;QACF,MAAM,aAAa,CAAC,MAAM,EAAE,OAAO,CAAC,QAAQ,CAAC,CAAC;QAE9C,OAAO,CAAC,kBAAkB,CAAC;YACvB,4BAA4B,EAAE,CAAC;YAC/B,cAAc,EAAE,CAAC;YACjB,qBAAqB,EAAE,CAAC;YACxB,kBAAkB,EAAE,CAAC;YACrB,sBAAsB,EAAE,CAAC;SAC5B,CAAC,CAAC;QAEH,OAAO,CAAC,iBAAiB,CAAC,YAAY,CAAC,CAAC;QAExC,IAAI,YAAY,EAAE,CAAC;YACf,MAAM,CAAC,EAAE,CAAC,UAAU,CAAC,YAAY,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,CAAC,KAAK,CAAC;QACpD,CAAC;QACD,IAAI,CAAC,QAAQ,EAAE,CAAC;IACpB,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,sDAAsD,EAAE,KAAK,IAAI,EAAE;QAClE,OAAO,CAAC,uBAAuB,CAAC,QAAQ,CAAC;YACrC,IAAI,EAAE,uBAAuB;SAChC,CAAC,CAAC;QACH,MAAM,UAAU,GAAG,OAAO,CAAC,gBAAgB,CAAC;YACxC,QAAQ,EAAE,eAAe;YACzB,WAAW,EAAE,CAAC,KAAK,CAAC;YACpB,gBAAgB,EAAE,KAAK;SAC1B,CAAC,CAAC;QAEH,OAAO,CAAC,OAAO,CAAC,KAAK;aAChB,QAAQ,CAAC,uBAAuB,CAAC;aACjC,OAAO,CAAC,CAAC,EAAE,IAAI,EAAE,OAAO,EAAE,MAAM,EAAE,CAAC,EAAE,QAAQ,EAAE,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,CAAC,CAAC,CAAC;QACtE,OAAO,CAAC,kBAAkB,CAAC,GAAG;aACzB,QAAQ,CAAC,CAAC,OAAO,CAAC,CAAC;aACnB,QAAQ,CAAC,CAAC,CAAC,GAAG,EAAE,GAAG,EAAE,GAAG,CAAC,CAAC,CAAC,CAAC;QAEjC,MAAM,MAAM,GAAG,YAAY,CAAC;YACxB,EAAE,EAAE,KAAK;YACT,OAAO,EAAE;gBACL,gBAAgB,EAAE,EAAE,MAAM,EAAE,MAAM,EAAE;gBACpC,2BAA2B,EAAE;oBACzB,MAAM,EAAE,MAAM;oBACd,WAAW,EAAE,2BAA2B;iBAC3C;aACJ;SACJ,CAAC,CAAC;QAEH,MAAM,aAAa,GAAG,0BAA0B,CAC5C,UAAU,EACV,OAAO,CAAC,OAAO,EACf,OAAO,CAAC,kBAAkB,EAC1B,OAAO,CAAC,mBAAmB,EAC3B,OAAO,CAAC,WAAW,EACnB,OAAO,CAAC,QAAQ,CACnB,CAAC;QAEF,MAAM,aAAa,CAAC,MAAM,EAAE,OAAO,CAAC,QAAQ,CAAC,CAAC;QAE9C,OAAO,CAAC,kBAAkB,CAAC;YACvB,4BAA4B,EAAE,CAAC;YAC/B,cAAc,EAAE,CAAC;YACjB,qBAAqB,EAAE,CAAC;YACxB,kBAAkB,EAAE,CAAC;YACrB,sBAAsB,EAAE,CAAC;SAC5B,CAAC,CAAC;IACP,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,4EAA4E,EAAE,KAAK,IAAI,EAAE;QACxF,MAAM,UAAU,GAAG,OAAO,CAAC,gBAAgB,CAAC;YACxC,QAAQ,EAAE,eAAe;YACzB,WAAW,EAAE,CAAC,KAAK,EAAE,MAAM,CAAC;YAC5B,gBAAgB,EAAE,KAAK;SAC1B,CAAC,CAAC;QAEH,MAAM,MAAM,GAAG,YAAY,CAAC;YACxB,EAAE,EAAE,KAAK;YACT,OAAO,EAAE;gBACL,gBAAgB,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE;gBACnC,2BAA2B,EAAE;oBACzB,MAAM,EAAE,KAAK;oBACb,WAAW,EAAE,0BAA0B;iBAC1C;aACJ;SACJ,CAAC,CAAC;QAEH,OAAO,CAAC,OAAO,CAAC,KAAK;aAChB,QAAQ,CAAC,uBAAuB,CAAC;aACjC,OAAO,CAAC,CAAC,EAAE,IAAI,EAAE,OAAO,EAAE,MAAM,EAAE,CAAC,EAAE,QAAQ,EAAE,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,CAAC,CAAC,CAAC;QACtE,OAAO,CAAC,kBAAkB,CAAC,GAAG;aACzB,QAAQ,CAAC,CAAC,OAAO,CAAC,CAAC;aACnB,QAAQ,CAAC,CAAC,CAAC,GAAG,EAAE,GAAG,EAAE,GAAG,CAAC,CAAC,CAAC,CAAC;QAEjC,OAAO,CAAC,uBAAuB;aAC1B,QAAQ,CAAC;YACN,MAAM;YACN,MAAM,EAAE,KAAK;YACb,QAAQ,EAAE,IAAI;YACd,GAAG,EAAE,0BAA0B;YAC/B,gBAAgB,EAAE,OAAO,CAAC,QAAQ;SACrC,CAAC;aACD,QAAQ,CAAC,EAAE,IAAI,EAAE,uBAAuB,EAAE,CAAC,CAAC;QAEjD,MAAM,aAAa,GAAG,0BAA0B,CAC5C,UAAU,EACV,OAAO,CAAC,OAAO,EACf,OAAO,CAAC,kBAAkB,EAC1B,OAAO,CAAC,mBAAmB,EAC3B,OAAO,CAAC,WAAW,EACnB,OAAO,CAAC,QAAQ,CACnB,CAAC;QACF,MAAM,aAAa,CAAC,MAAM,EAAE,OAAO,CAAC,QAAQ,CAAC,CAAC;QAE9C,MAAM,aAAa,GAAG;YAClB;gBACI,QAAQ,EAAE,UAAU,CAAC,QAAQ;gBAC7B,QAAQ,EAAE,KAAK;gBACf,cAAc,EAAE,OAAO,CAAC,wBAAwB;gBAChD,UAAU,EAAE,KAAK;gBACjB,gBAAgB,EAAE,OAAO;gBACzB,SAAS,EAAE,CAAC,GAAG,EAAE,GAAG,EAAE,GAAG,CAAC;gBAC1B,yBAAyB,EAAE,IAAI;gBAC/B,uBAAuB,EAAE,CAAC;gBAC1B,yBAAyB,EAAE,CAAC;gBAC5B,wBAAwB,EAAE,CAAC;gBAC3B,SAAS,EAAE,UAAU,CAAC,EAAE;gBACxB,UAAU,EAAE,OAAO,CAAC,oBAAoB,EAAE;gBAC1C,UAAU,EAAE,OAAO,CAAC,oBAAoB,EAAE;aAC7C;SACJ,CAAC;QAEF,OAAO,CAAC,kBAAkB,CAAC;YACvB,4BAA4B,EAAE,CAAC;YAC/B,cAAc,EAAE,CAAC;YACjB,qBAAqB,EAAE,CAAC;YACxB,kBAAkB,EAAE,CAAC;YACrB,sBAAsB,EAAE,CAAC;SAC5B,CAAC,CAAC;QAEH,OAAO,CAAC,iBAAiB,CAAC,aAAa,CAAC,CAAC;IAC7C,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,iEAAiE,EAAE,KAAK,IAAI,EAAE;QAC7E,MAAM,UAAU,GAAG,OAAO,CAAC,gBAAgB,CAAC;YACxC,QAAQ,EAAE,eAAe;YACzB,WAAW,EAAE,CAAC,KAAK,CAAC;SACvB,CAAC,CAAC;QAEH,MAAM,MAAM,GAAG,YAAY,CAAC;YACxB,EAAE,EAAE,KAAK;YACT,OAAO,EAAE;gBACL,gBAAgB,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE;gBACnC,2BAA2B,EAAE;oBACzB,MAAM,EAAE,KAAK;oBACb,WAAW,EAAE,0BAA0B;iBAC1C;aACJ;SACJ,CAAC,CAAC;QAEH,OAAO,CAAC,kBAAkB,CAAC,GAAG;aACzB,QAAQ,CAAC,CAAC,OAAO,CAAC,CAAC;aACnB,OAAO,CAAC,IAAI,KAAK,CAAC,kBAAkB,CAAC,CAAC,CAAC;QAE5C,MAAM,aAAa,GAAG,0BAA0B,CAC5C,UAAU,EACV,OAAO,CAAC,OAAO,EACf,OAAO,CAAC,kBAAkB,EAC1B,OAAO,CAAC,mBAAmB,EAC3B,OAAO,CAAC,WAAW,EACnB,OAAO,CAAC,QAAQ,CACnB,CAAC;QAEF,MAAM,mBAAmB,CAAC,GAAG,EAAE,CAC3B,aAAa,CAAC,MAAM,EAAE,OAAO,CAAC,QAAQ,CAAC,CAC1C,CAAC;IACN,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,kEAAkE,EAAE,KAAK,IAAI,EAAE;QAC9E,MAAM,UAAU,GAAG,OAAO,CAAC,gBAAgB,CAAC;YACxC,QAAQ,EAAE,eAAe;YACzB,WAAW,EAAE,CAAC,KAAK,CAAC;SACvB,CAAC,CAAC;QAEH,MAAM,MAAM,GAAG,YAAY,CAAC;YACxB,EAAE,EAAE,KAAK;YACT,OAAO,EAAE;gBACL,gBAAgB,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE;gBACnC,2BAA2B,EAAE;oBACzB,MAAM,EAAE,KAAK;oBACb,WAAW,EAAE,0BAA0B;iBAC1C;aACJ;SACJ,CAAC,CAAC;QAEH,OAAO,CAAC,mBAAmB,CAAC,iBAAiB;aACxC,QAAQ,CAAC,MAAM,EAAE,IAAW,CAAC;aAC7B,OAAO,CAAC,IAAI,KAAK,CAAC,kBAAkB,CAAC,CAAC,CAAC;QAE5C,MAAM,aAAa,GAAG,0BAA0B,CAC5C,UAAU,EACV,OAAO,CAAC,OAAO,EACf,OAAO,CAAC,kBAAkB,EAC1B,OAAO,CAAC,mBAAmB,EAC3B,OAAO,CAAC,WAAW,EACnB,OAAO,CAAC,QAAQ,CACnB,CAAC;QACF,MAAM,mBAAmB,CAAC,GAAG,EAAE,CAC3B,aAAa,CAAC,MAAM,EAAE,OAAO,CAAC,QAAQ,CAAC,CAC1C,CAAC;IACN,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,kEAAkE,EAAE,KAAK,IAAI,EAAE;QAC9E,MAAM,UAAU,GAAG,OAAO,CAAC,gBAAgB,CAAC;YACxC,QAAQ,EAAE,eAAe;YACzB,WAAW,EAAE,CAAC,KAAK,CAAC;YACpB,mBAAmB,EAAE,KAAK;iBACrB,IAAI,EAAE;iBACN,OAAO,CAAC,IAAI,KAAK,CAAC,kBAAkB,CAAC,CAAC;SAC9C,CAAC,CAAC;QAEH,MAAM,MAAM,GAAG,YAAY,CAAC;YACxB,EAAE,EAAE,KAAK;YACT,OAAO,EAAE;gBACL,gBAAgB,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE;gBACnC,2BAA2B,EAAE;oBACzB,MAAM,EAAE,KAAK;oBACb,WAAW,EAAE,0BAA0B;iBAC1C;aACJ;SACJ,CAAC,CAAC;QAEH,MAAM,aAAa,GAAG,0BAA0B,CAC5C,UAAU,EACV,OAAO,CAAC,OAAO,EACf,OAAO,CAAC,kBAAkB,EAC1B,OAAO,CAAC,mBAAmB,EAC3B,OAAO,CAAC,WAAW,EACnB,OAAO,CAAC,QAAQ,CACnB,CAAC;QACF,MAAM,mBAAmB,CAAC,GAAG,EAAE,CAC3B,aAAa,CAAC,MAAM,EAAE,OAAO,CAAC,QAAQ,CAAC,CAC1C,CAAC;IACN,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,qEAAqE,EAAE,KAAK,IAAI,EAAE;QACjF,MAAM,UAAU,GAAG,OAAO,CAAC,gBAAgB,CAAC;YACxC,QAAQ,EAAE,eAAe;YACzB,WAAW,EAAE,CAAC,KAAK,CAAC;SACvB,CAAC,CAAC;QAEH,MAAM,MAAM,GAAG,YAAY,CAAC;YACxB,EAAE,EAAE,KAAK;YACT,OAAO,EAAE,EAAE;SACd,CAAC,CAAC;QAEH,MAAM,aAAa,GAAG,0BAA0B,CAC5C,UAAU,EACV,OAAO,CAAC,OAAO,EACf,OAAO,CAAC,kBAAkB,EAC1B,OAAO,CAAC,mBAAmB,EAC3B,OAAO,CAAC,WAAW,EACnB,OAAO,CAAC,QAAQ,CACnB,CAAC;QACF,MAAM,mBAAmB,CAAC,GAAG,EAAE,CAC3B,aAAa,CAAC,MAAM,EAAE,OAAO,CAAC,QAAQ,CAAC,CAC1C,CAAC;IACN,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,+EAA+E,EAAE,KAAK,IAAI,EAAE;QAC3F,MAAM,UAAU,GAAG,OAAO,CAAC,gBAAgB,CAAC;YACxC,QAAQ,EAAE,eAAe;YACzB,WAAW,EAAE,CAAC,KAAK,CAAC;SACvB,CAAC,CAAC;QAEH,MAAM,MAAM,GAAG,YAAY,CAAC;YACxB,EAAE,EAAE,KAAK;YACT,OAAO,EAAE;gBACL,gBAAgB,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE;gBACnC,2BAA2B,EAAE;oBACzB,MAAM,EAAE,KAAK;oBACb,WAAW,EAAE,0BAA0B;iBAC1C;aACJ;SACJ,CAAC,CAAC;QAEH,MAAM,aAAa,GAAG,0BAA0B,CAC5C,UAAU,EACV,OAAO,CAAC,OAAO,EACf,OAAO,CAAC,kBAAkB,EAC1B,OAAO,CAAC,mBAAmB,EAC3B,OAAO,CAAC,WAAW,EACnB,OAAO,CAAC,QAAQ,CACnB,CAAC;QACF,MAAM,mBAAmB,CAAC,GAAG,EAAE,CAC3B,aAAa,CAAC,MAAM,EAAE,OAAO,CAAC,QAAQ,CAAC,CAC1C,CAAC;IACN,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,iFAAiF,EAAE,KAAK,IAAI,EAAE;QAC7F,MAAM,UAAU,GAAG,OAAO,CAAC,gBAAgB,CAAC;YACxC,QAAQ,EAAE,eAAe;YACzB,WAAW,EAAE,CAAC,KAAK,CAAC;YACpB,gBAAgB,EAAE,KAAK;SAC1B,CAAC,CAAC;QAEH,MAAM,MAAM,GAAG,YAAY,CAAC;YACxB,EAAE,EAAE,KAAK;YACT,OAAO,EAAE;gBACL,gBAAgB,EAAE,EAAE;gBACpB,2BAA2B,EAAE;oBACzB,MAAM,EAAE,KAAK;oBACb,WAAW,EAAE,0BAA0B;iBAC1C;aACJ;SACJ,CAAC,CAAC;QAEH,MAAM,aAAa,GAAG,0BAA0B,CAC5C,UAAU,EACV,OAAO,CAAC,OAAO,EACf,OAAO,CAAC,kBAAkB,EAC1B,OAAO,CAAC,mBAAmB,EAC3B,OAAO,CAAC,WAAW,EACnB,OAAO,CAAC,QAAQ,CACnB,CAAC;QAEF,MAAM,mBAAmB,CAAC,GAAG,EAAE,CAC3B,aAAa,CAAC,MAAM,EAAE,OAAO,CAAC,QAAQ,CAAC,CAC1C,CAAC;QACF,MAAM,CAAC,OAAO,CAAC,uBAAuB,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC,CAAC,EAAE,CAAC,IAAI,CAAC,KAAK,CACnE;YACI,MAAM;YACN,MAAM,EAAE,KAAK;YACb,QAAQ,EAAE,IAAI;YACd,GAAG,EAAE,0BAA0B;YAC/B,gBAAgB,EAAE,OAAO,CAAC,QAAQ;SACrC,CACJ,CAAC;IACN,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,0CAA0C,EAAE,KAAK,IAAI,EAAE;QACtD,OAAO,CAAC,uBAAuB,CAAC,QAAQ,CAAC;YACrC,IAAI,EAAE,uBAAuB;SAChC,CAAC,CAAC;QACH,MAAM,UAAU,GAAG,OAAO,CAAC,gBAAgB,CAAC;YACxC,QAAQ,EAAE,eAAe;YACzB,WAAW,EAAE,CAAC,KAAK,CAAC;YACpB,gBAAgB,EAAE,KAAK;SAC1B,CAAC,CAAC;QAEH,OAAO,CAAC,OAAO,CAAC,KAAK;aAChB,QAAQ,CAAC,uBAAuB,CAAC;aACjC,OAAO,CAAC,CAAC,EAAE,IAAI,EAAE,OAAO,EAAE,MAAM,EAAE,CAAC,EAAE,QAAQ,EAAE,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,CAAC,CAAC,CAAC;QACtE,OAAO,CAAC,kBAAkB,CAAC,GAAG;aACzB,QAAQ,CAAC,CAAC,OAAO,CAAC,CAAC;aACnB,QAAQ,CAAC,CAAC,CAAC,GAAG,EAAE,GAAG,EAAE,GAAG,CAAC,CAAC,CAAC,CAAC;QAEjC,MAAM,MAAM,GAAG,YAAY,CAAC;YACxB,EAAE,EAAE,KAAK;YACT,OAAO,EAAE;gBACL,gBAAgB,EAAE,EAAE,MAAM,EAAE,KAAK,EAAE;gBACnC,2BAA2B,EAAE;oBACzB,MAAM,EAAE,KAAK;oBACb,WAAW,EAAE,0BAA0B;iBAC1C;aACJ;SACJ,CAAC,CAAC;QAEH,MAAM,aAAa,GAAG,0BAA0B,CAC5C,UAAU,EACV,OAAO,CAAC,OAAO,EACf,OAAO,CAAC,kBAAkB,EAC1B,OAAO,CAAC,mBAAmB,EAC3B,OAAO,CAAC,WAAW,EACnB,OAAO,CAAC,QAAQ,CACnB,CAAC;QACF,MAAM,aAAa,CAAC,MAAM,EAAE,OAAO,CAAC,QAAQ,CAAC,CAAC;QAE9C,OAAO,CAAC,kBAAkB,CAAC;YACvB,sBAAsB,EAAE,CAAC;SAC5B,CAAC,CAAC;QAEH,OAAO,CAAC,gBAAgB,CAAC,OAAO,CAAC,mBAAmB,CAAC,aAAa,EAAE,CAAC,EAAE;YACnE,KAAK,EAAE,UAAU,CAAC,IAAI,CAAC,qBAAqB,CAAC,aAAa;YAC1D,IAAI,EAAE;gBACF,KAAK,EAAE;oBACH,IAAI,EAAE;wBACF,MAAM,EAAE;4BACJ,EAAE,IAAI,EAAE,EAAE,SAAS,EAAE,UAAU,CAAC,EAAE,EAAE,EAAE;4BACtC,EAAE,IAAI,EAAE,EAAE,QAAQ,EAAE,KAAK,EAAE,EAAE;4BAC7B;gCACI,KAAK,EAAE;oCACH,UAAU,EAAE;wCACR,EAAE,EAAE,OAAO,CAAC,oBAAoB,EAAE;qCACrC;iCACJ;6BACJ;yBACJ;qBACJ;iBACJ;aACJ;YACD,mBAAmB,EAAE,IAAI;YACzB,SAAS,EAAE,SAAS;YACpB,OAAO,EAAE,UAAU,CAAC,OAAO;SAC9B,CAAC,CAAC;IACP,CAAC,CAAC,CAAC;AACP,CAAC,CAAC,CAAC"}
package/package.json ADDED
@@ -0,0 +1,78 @@
1
+ {
2
+ "name": "@magda/semantic-indexer-framework",
3
+ "description": "MAGDA Semantic Indexer Framework",
4
+ "version": "5.2.0",
5
+ "type": "module",
6
+ "exports": {
7
+ ".": "./dist/index.js",
8
+ "./package.json": "./package.json",
9
+ "./dist/*.js": "./dist/*.js"
10
+ },
11
+ "engines": {
12
+ "node": ">=18.19.0"
13
+ },
14
+ "scripts": {
15
+ "prebuild": "rimraf dist tsconfig.tsbuildinfo",
16
+ "build": "yarn run compile",
17
+ "compile": "tsc -b && ts-module-alias-transformer dist",
18
+ "watch": "tsc -b --watch",
19
+ "test": "mocha",
20
+ "release": "npm publish || echo \"Skip releasing npm package @magda/semantic-indexer-framework.\""
21
+ },
22
+ "author": "",
23
+ "license": "Apache-2.0",
24
+ "devDependencies": {
25
+ "@magda/scripts": "^5.2.0",
26
+ "@types/chai": "^4.3.11",
27
+ "@types/mocha": "^10.0.6",
28
+ "@types/uuid": "^8.0.0",
29
+ "@types/yargs": "^12.0.8",
30
+ "chai": "^5.0.0-rc.0",
31
+ "mocha": "^10.2.0",
32
+ "typescript": "~5.3.3"
33
+ },
34
+ "dependencies": {
35
+ "@langchain/core": "^0.3.57",
36
+ "@langchain/textsplitters": "https://gitpkg.vercel.app/JHZhang2736/langchainjs/libs/langchain-textsplitters?textsplitters-build",
37
+ "@magda/esm-utils": "^1.0.1",
38
+ "@magda/minion-framework": "^5.2.0",
39
+ "@magda/typescript-common": "^5.2.0",
40
+ "@types/lodash": "^4.17.17",
41
+ "cross-fetch": "^4.0.0",
42
+ "minio": "^8.0.5",
43
+ "uuid": "^8.2.0",
44
+ "yargs": "^12.0.5"
45
+ },
46
+ "mocha": {
47
+ "import": "tsx/esm",
48
+ "spec": [
49
+ "src/test/**/*.spec.ts"
50
+ ]
51
+ },
52
+ "config": {
53
+ "docker": {
54
+ "include": "node_modules dist package.json"
55
+ }
56
+ },
57
+ "magda": {
58
+ "language": "typescript",
59
+ "categories": {
60
+ "minion": true,
61
+ "library": true,
62
+ "npmPackage": true
63
+ }
64
+ },
65
+ "_moduleMappings": {
66
+ "magda-typescript-common/src": "@magda/typescript-common/dist",
67
+ "magda-minion-framework/src": "@magda/minion-framework/dist"
68
+ },
69
+ "keywords": [
70
+ "Magda",
71
+ "SDK",
72
+ "Semantic",
73
+ "Indexer"
74
+ ],
75
+ "files": [
76
+ "dist"
77
+ ]
78
+ }