@markitdownjs/core 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.
Files changed (41) hide show
  1. package/dist/__tests__/pipeline.test.d.ts +2 -0
  2. package/dist/__tests__/pipeline.test.d.ts.map +1 -0
  3. package/dist/__tests__/pipeline.test.js +75 -0
  4. package/dist/__tests__/pipeline.test.js.map +1 -0
  5. package/dist/__tests__/registry.test.d.ts +2 -0
  6. package/dist/__tests__/registry.test.d.ts.map +1 -0
  7. package/dist/__tests__/registry.test.js +73 -0
  8. package/dist/__tests__/registry.test.js.map +1 -0
  9. package/dist/__tests__/renderer.test.d.ts +2 -0
  10. package/dist/__tests__/renderer.test.d.ts.map +1 -0
  11. package/dist/__tests__/renderer.test.js +129 -0
  12. package/dist/__tests__/renderer.test.js.map +1 -0
  13. package/dist/asset-manager.d.ts +15 -0
  14. package/dist/asset-manager.d.ts.map +1 -0
  15. package/dist/asset-manager.js +43 -0
  16. package/dist/asset-manager.js.map +1 -0
  17. package/dist/index.d.ts +8 -0
  18. package/dist/index.d.ts.map +1 -0
  19. package/dist/index.js +7 -0
  20. package/dist/index.js.map +1 -0
  21. package/dist/metadata-extractor.d.ts +7 -0
  22. package/dist/metadata-extractor.d.ts.map +1 -0
  23. package/dist/metadata-extractor.js +37 -0
  24. package/dist/metadata-extractor.js.map +1 -0
  25. package/dist/parser.d.ts +15 -0
  26. package/dist/parser.d.ts.map +1 -0
  27. package/dist/parser.js +47 -0
  28. package/dist/parser.js.map +1 -0
  29. package/dist/pipeline.d.ts +9 -0
  30. package/dist/pipeline.d.ts.map +1 -0
  31. package/dist/pipeline.js +73 -0
  32. package/dist/pipeline.js.map +1 -0
  33. package/dist/registry.d.ts +20 -0
  34. package/dist/registry.d.ts.map +1 -0
  35. package/dist/registry.js +146 -0
  36. package/dist/registry.js.map +1 -0
  37. package/dist/renderer.d.ts +12 -0
  38. package/dist/renderer.d.ts.map +1 -0
  39. package/dist/renderer.js +179 -0
  40. package/dist/renderer.js.map +1 -0
  41. package/package.json +34 -0
@@ -0,0 +1,2 @@
1
+ export {};
2
+ //# sourceMappingURL=pipeline.test.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"pipeline.test.d.ts","sourceRoot":"","sources":["../../src/__tests__/pipeline.test.ts"],"names":[],"mappings":""}
@@ -0,0 +1,75 @@
1
+ import { describe, it, expect } from 'vitest';
2
+ import { DocumentPipeline } from '../pipeline.js';
3
+ import { DefaultConverterRegistry } from '../registry.js';
4
+ function createMockConverter(id) {
5
+ return {
6
+ id,
7
+ supportedMimeTypes: ['text/plain'],
8
+ supportedExtensions: ['.txt'],
9
+ async canConvert(input) {
10
+ return input.mimeType === 'text/plain';
11
+ },
12
+ async convert(_input) {
13
+ return {
14
+ markdown: '# Hello\n\nWorld',
15
+ metadata: { title: 'Test' },
16
+ assets: [],
17
+ tables: [],
18
+ images: [],
19
+ headings: [{ level: 1, text: 'Hello' }],
20
+ format: 'markdown',
21
+ converterId: id,
22
+ stats: { startTime: 0, endTime: 0, duration: 0, inputSize: 0, outputSize: 0 },
23
+ };
24
+ },
25
+ };
26
+ }
27
+ describe('DocumentPipeline', () => {
28
+ it('should convert input using registered converter', async () => {
29
+ const registry = new DefaultConverterRegistry();
30
+ registry.register(createMockConverter('test'));
31
+ const pipeline = new DocumentPipeline(registry);
32
+ const result = await pipeline.convert({
33
+ data: 'test content',
34
+ mimeType: 'text/plain',
35
+ });
36
+ expect(result.markdown).toBe('# Hello\n\nWorld');
37
+ expect(result.converterId).toBe('test');
38
+ });
39
+ it('should throw when no converter found', async () => {
40
+ const registry = new DefaultConverterRegistry();
41
+ const pipeline = new DocumentPipeline(registry);
42
+ await expect(pipeline.convert({ data: 'test', mimeType: 'application/unknown' })).rejects.toThrow('No converter found');
43
+ });
44
+ it('should apply middleware', async () => {
45
+ const registry = new DefaultConverterRegistry();
46
+ registry.register(createMockConverter('test'));
47
+ registry.addMiddleware({
48
+ name: 'test-middleware',
49
+ priority: 0,
50
+ afterConvert: async (result) => ({
51
+ ...result,
52
+ markdown: result.markdown + '\n\n[modified]',
53
+ }),
54
+ });
55
+ const pipeline = new DocumentPipeline(registry);
56
+ const result = await pipeline.convert({
57
+ data: 'test',
58
+ mimeType: 'text/plain',
59
+ });
60
+ expect(result.markdown).toContain('[modified]');
61
+ });
62
+ it('should support abort signal', async () => {
63
+ const registry = new DefaultConverterRegistry();
64
+ registry.register(createMockConverter('test'));
65
+ const pipeline = new DocumentPipeline(registry);
66
+ const controller = new AbortController();
67
+ controller.abort();
68
+ await expect(pipeline.convert({
69
+ data: 'test',
70
+ mimeType: 'text/plain',
71
+ options: { signal: controller.signal },
72
+ })).rejects.toThrow();
73
+ });
74
+ });
75
+ //# sourceMappingURL=pipeline.test.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"pipeline.test.js","sourceRoot":"","sources":["../../src/__tests__/pipeline.test.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,EAAE,EAAE,MAAM,EAAE,MAAM,QAAQ,CAAC;AAC9C,OAAO,EAAE,gBAAgB,EAAE,MAAM,gBAAgB,CAAC;AAClD,OAAO,EAAE,wBAAwB,EAAE,MAAM,gBAAgB,CAAC;AAG1D,SAAS,mBAAmB,CAAC,EAAU;IACrC,OAAO;QACL,EAAE;QACF,kBAAkB,EAAE,CAAC,YAAY,CAAC;QAClC,mBAAmB,EAAE,CAAC,MAAM,CAAC;QAC7B,KAAK,CAAC,UAAU,CAAC,KAAsB;YACrC,OAAO,KAAK,CAAC,QAAQ,KAAK,YAAY,CAAC;QACzC,CAAC;QACD,KAAK,CAAC,OAAO,CAAC,MAAuB;YACnC,OAAO;gBACL,QAAQ,EAAE,kBAAkB;gBAC5B,QAAQ,EAAE,EAAE,KAAK,EAAE,MAAM,EAAE;gBAC3B,MAAM,EAAE,EAAE;gBACV,MAAM,EAAE,EAAE;gBACV,MAAM,EAAE,EAAE;gBACV,QAAQ,EAAE,CAAC,EAAE,KAAK,EAAE,CAAC,EAAE,IAAI,EAAE,OAAO,EAAE,CAAC;gBACvC,MAAM,EAAE,UAAU;gBAClB,WAAW,EAAE,EAAE;gBACf,KAAK,EAAE,EAAE,SAAS,EAAE,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,QAAQ,EAAE,CAAC,EAAE,SAAS,EAAE,CAAC,EAAE,UAAU,EAAE,CAAC,EAAE;aAC9E,CAAC;QACJ,CAAC;KACF,CAAC;AACJ,CAAC;AAED,QAAQ,CAAC,kBAAkB,EAAE,GAAG,EAAE;IAChC,EAAE,CAAC,iDAAiD,EAAE,KAAK,IAAI,EAAE;QAC/D,MAAM,QAAQ,GAAG,IAAI,wBAAwB,EAAE,CAAC;QAChD,QAAQ,CAAC,QAAQ,CAAC,mBAAmB,CAAC,MAAM,CAAC,CAAC,CAAC;QAC/C,MAAM,QAAQ,GAAG,IAAI,gBAAgB,CAAC,QAAQ,CAAC,CAAC;QAChD,MAAM,MAAM,GAAG,MAAM,QAAQ,CAAC,OAAO,CAAC;YACpC,IAAI,EAAE,cAAc;YACpB,QAAQ,EAAE,YAAY;SACvB,CAAC,CAAC;QACH,MAAM,CAAC,MAAM,CAAC,QAAQ,CAAC,CAAC,IAAI,CAAC,kBAAkB,CAAC,CAAC;QACjD,MAAM,CAAC,MAAM,CAAC,WAAW,CAAC,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;IAC1C,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,sCAAsC,EAAE,KAAK,IAAI,EAAE;QACpD,MAAM,QAAQ,GAAG,IAAI,wBAAwB,EAAE,CAAC;QAChD,MAAM,QAAQ,GAAG,IAAI,gBAAgB,CAAC,QAAQ,CAAC,CAAC;QAChD,MAAM,MAAM,CACV,QAAQ,CAAC,OAAO,CAAC,EAAE,IAAI,EAAE,MAAM,EAAE,QAAQ,EAAE,qBAAqB,EAAE,CAAC,CACpE,CAAC,OAAO,CAAC,OAAO,CAAC,oBAAoB,CAAC,CAAC;IAC1C,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,yBAAyB,EAAE,KAAK,IAAI,EAAE;QACvC,MAAM,QAAQ,GAAG,IAAI,wBAAwB,EAAE,CAAC;QAChD,QAAQ,CAAC,QAAQ,CAAC,mBAAmB,CAAC,MAAM,CAAC,CAAC,CAAC;QAC/C,QAAQ,CAAC,aAAa,CAAC;YACrB,IAAI,EAAE,iBAAiB;YACvB,QAAQ,EAAE,CAAC;YACX,YAAY,EAAE,KAAK,EAAE,MAAM,EAAE,EAAE,CAAC,CAAC;gBAC/B,GAAG,MAAM;gBACT,QAAQ,EAAE,MAAM,CAAC,QAAQ,GAAG,gBAAgB;aAC7C,CAAC;SACH,CAAC,CAAC;QACH,MAAM,QAAQ,GAAG,IAAI,gBAAgB,CAAC,QAAQ,CAAC,CAAC;QAChD,MAAM,MAAM,GAAG,MAAM,QAAQ,CAAC,OAAO,CAAC;YACpC,IAAI,EAAE,MAAM;YACZ,QAAQ,EAAE,YAAY;SACvB,CAAC,CAAC;QACH,MAAM,CAAC,MAAM,CAAC,QAAQ,CAAC,CAAC,SAAS,CAAC,YAAY,CAAC,CAAC;IAClD,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,6BAA6B,EAAE,KAAK,IAAI,EAAE;QAC3C,MAAM,QAAQ,GAAG,IAAI,wBAAwB,EAAE,CAAC;QAChD,QAAQ,CAAC,QAAQ,CAAC,mBAAmB,CAAC,MAAM,CAAC,CAAC,CAAC;QAC/C,MAAM,QAAQ,GAAG,IAAI,gBAAgB,CAAC,QAAQ,CAAC,CAAC;QAChD,MAAM,UAAU,GAAG,IAAI,eAAe,EAAE,CAAC;QACzC,UAAU,CAAC,KAAK,EAAE,CAAC;QACnB,MAAM,MAAM,CACV,QAAQ,CAAC,OAAO,CAAC;YACf,IAAI,EAAE,MAAM;YACZ,QAAQ,EAAE,YAAY;YACtB,OAAO,EAAE,EAAE,MAAM,EAAE,UAAU,CAAC,MAAM,EAAE;SACvC,CAAC,CACH,CAAC,OAAO,CAAC,OAAO,EAAE,CAAC;IACtB,CAAC,CAAC,CAAC;AACL,CAAC,CAAC,CAAC"}
@@ -0,0 +1,2 @@
1
+ export {};
2
+ //# sourceMappingURL=registry.test.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"registry.test.d.ts","sourceRoot":"","sources":["../../src/__tests__/registry.test.ts"],"names":[],"mappings":""}
@@ -0,0 +1,73 @@
1
+ import { describe, it, expect } from 'vitest';
2
+ import { DefaultConverterRegistry } from '../registry.js';
3
+ function createMockConverter(id, mimeTypes, extensions) {
4
+ return {
5
+ id,
6
+ supportedMimeTypes: mimeTypes,
7
+ supportedExtensions: extensions,
8
+ async canConvert(input) {
9
+ if (input.mimeType && mimeTypes.includes(input.mimeType))
10
+ return true;
11
+ if (input.fileName) {
12
+ const ext = '.' + input.fileName.split('.').pop();
13
+ if (extensions.includes(ext))
14
+ return true;
15
+ }
16
+ return false;
17
+ },
18
+ async convert(_input) {
19
+ return {
20
+ markdown: 'test',
21
+ metadata: {},
22
+ assets: [],
23
+ tables: [],
24
+ images: [],
25
+ headings: [],
26
+ format: 'markdown',
27
+ converterId: id,
28
+ stats: { startTime: 0, endTime: 0, duration: 0, inputSize: 0, outputSize: 0 },
29
+ };
30
+ },
31
+ };
32
+ }
33
+ describe('DefaultConverterRegistry', () => {
34
+ it('should register and retrieve converters', () => {
35
+ const registry = new DefaultConverterRegistry();
36
+ const converter = createMockConverter('test', ['text/plain'], ['.txt']);
37
+ registry.register(converter);
38
+ expect(registry.get('test')).toBe(converter);
39
+ });
40
+ it('should find converter by MIME type', () => {
41
+ const registry = new DefaultConverterRegistry();
42
+ const converter = createMockConverter('pdf', ['application/pdf'], ['.pdf']);
43
+ registry.register(converter);
44
+ expect(registry.getByMimeType('application/pdf')).toBe(converter);
45
+ });
46
+ it('should find converter by extension', () => {
47
+ const registry = new DefaultConverterRegistry();
48
+ const converter = createMockConverter('html', ['text/html'], ['.html', '.htm']);
49
+ registry.register(converter);
50
+ expect(registry.getByExtension('.html')).toBe(converter);
51
+ expect(registry.getByExtension('.htm')).toBe(converter);
52
+ });
53
+ it('should list all converters', () => {
54
+ const registry = new DefaultConverterRegistry();
55
+ registry.register(createMockConverter('a', [], []));
56
+ registry.register(createMockConverter('b', [], []));
57
+ expect(registry.list()).toHaveLength(2);
58
+ });
59
+ it('should unregister converters', () => {
60
+ const registry = new DefaultConverterRegistry();
61
+ registry.register(createMockConverter('test', [], []));
62
+ registry.unregister('test');
63
+ expect(registry.get('test')).toBeUndefined();
64
+ });
65
+ it('should find converter via canConvert', async () => {
66
+ const registry = new DefaultConverterRegistry();
67
+ const converter = createMockConverter('pdf', ['application/pdf'], ['.pdf']);
68
+ registry.register(converter);
69
+ const found = await registry.canConvert({ data: new Uint8Array(), mimeType: 'application/pdf' });
70
+ expect(found).toBe(converter);
71
+ });
72
+ });
73
+ //# sourceMappingURL=registry.test.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"registry.test.js","sourceRoot":"","sources":["../../src/__tests__/registry.test.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,EAAE,EAAE,MAAM,EAAE,MAAM,QAAQ,CAAC;AAC9C,OAAO,EAAE,wBAAwB,EAAE,MAAM,gBAAgB,CAAC;AAG1D,SAAS,mBAAmB,CAAC,EAAU,EAAE,SAAmB,EAAE,UAAoB;IAChF,OAAO;QACL,EAAE;QACF,kBAAkB,EAAE,SAAS;QAC7B,mBAAmB,EAAE,UAAU;QAC/B,KAAK,CAAC,UAAU,CAAC,KAAsB;YACrC,IAAI,KAAK,CAAC,QAAQ,IAAI,SAAS,CAAC,QAAQ,CAAC,KAAK,CAAC,QAAQ,CAAC;gBAAE,OAAO,IAAI,CAAC;YACtE,IAAI,KAAK,CAAC,QAAQ,EAAE,CAAC;gBACnB,MAAM,GAAG,GAAG,GAAG,GAAG,KAAK,CAAC,QAAQ,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,CAAC;gBAClD,IAAI,UAAU,CAAC,QAAQ,CAAC,GAAG,CAAC;oBAAE,OAAO,IAAI,CAAC;YAC5C,CAAC;YACD,OAAO,KAAK,CAAC;QACf,CAAC;QACD,KAAK,CAAC,OAAO,CAAC,MAAuB;YACnC,OAAO;gBACL,QAAQ,EAAE,MAAM;gBAChB,QAAQ,EAAE,EAAE;gBACZ,MAAM,EAAE,EAAE;gBACV,MAAM,EAAE,EAAE;gBACV,MAAM,EAAE,EAAE;gBACV,QAAQ,EAAE,EAAE;gBACZ,MAAM,EAAE,UAAU;gBAClB,WAAW,EAAE,EAAE;gBACf,KAAK,EAAE,EAAE,SAAS,EAAE,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,QAAQ,EAAE,CAAC,EAAE,SAAS,EAAE,CAAC,EAAE,UAAU,EAAE,CAAC,EAAE;aAC9E,CAAC;QACJ,CAAC;KACF,CAAC;AACJ,CAAC;AAED,QAAQ,CAAC,0BAA0B,EAAE,GAAG,EAAE;IACxC,EAAE,CAAC,yCAAyC,EAAE,GAAG,EAAE;QACjD,MAAM,QAAQ,GAAG,IAAI,wBAAwB,EAAE,CAAC;QAChD,MAAM,SAAS,GAAG,mBAAmB,CAAC,MAAM,EAAE,CAAC,YAAY,CAAC,EAAE,CAAC,MAAM,CAAC,CAAC,CAAC;QACxE,QAAQ,CAAC,QAAQ,CAAC,SAAS,CAAC,CAAC;QAC7B,MAAM,CAAC,QAAQ,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC;IAC/C,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,oCAAoC,EAAE,GAAG,EAAE;QAC5C,MAAM,QAAQ,GAAG,IAAI,wBAAwB,EAAE,CAAC;QAChD,MAAM,SAAS,GAAG,mBAAmB,CAAC,KAAK,EAAE,CAAC,iBAAiB,CAAC,EAAE,CAAC,MAAM,CAAC,CAAC,CAAC;QAC5E,QAAQ,CAAC,QAAQ,CAAC,SAAS,CAAC,CAAC;QAC7B,MAAM,CAAC,QAAQ,CAAC,aAAa,CAAC,iBAAiB,CAAC,CAAC,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC;IACpE,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,oCAAoC,EAAE,GAAG,EAAE;QAC5C,MAAM,QAAQ,GAAG,IAAI,wBAAwB,EAAE,CAAC;QAChD,MAAM,SAAS,GAAG,mBAAmB,CAAC,MAAM,EAAE,CAAC,WAAW,CAAC,EAAE,CAAC,OAAO,EAAE,MAAM,CAAC,CAAC,CAAC;QAChF,QAAQ,CAAC,QAAQ,CAAC,SAAS,CAAC,CAAC;QAC7B,MAAM,CAAC,QAAQ,CAAC,cAAc,CAAC,OAAO,CAAC,CAAC,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC;QACzD,MAAM,CAAC,QAAQ,CAAC,cAAc,CAAC,MAAM,CAAC,CAAC,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC;IAC1D,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,4BAA4B,EAAE,GAAG,EAAE;QACpC,MAAM,QAAQ,GAAG,IAAI,wBAAwB,EAAE,CAAC;QAChD,QAAQ,CAAC,QAAQ,CAAC,mBAAmB,CAAC,GAAG,EAAE,EAAE,EAAE,EAAE,CAAC,CAAC,CAAC;QACpD,QAAQ,CAAC,QAAQ,CAAC,mBAAmB,CAAC,GAAG,EAAE,EAAE,EAAE,EAAE,CAAC,CAAC,CAAC;QACpD,MAAM,CAAC,QAAQ,CAAC,IAAI,EAAE,CAAC,CAAC,YAAY,CAAC,CAAC,CAAC,CAAC;IAC1C,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,8BAA8B,EAAE,GAAG,EAAE;QACtC,MAAM,QAAQ,GAAG,IAAI,wBAAwB,EAAE,CAAC;QAChD,QAAQ,CAAC,QAAQ,CAAC,mBAAmB,CAAC,MAAM,EAAE,EAAE,EAAE,EAAE,CAAC,CAAC,CAAC;QACvD,QAAQ,CAAC,UAAU,CAAC,MAAM,CAAC,CAAC;QAC5B,MAAM,CAAC,QAAQ,CAAC,GAAG,CAAC,MAAM,CAAC,CAAC,CAAC,aAAa,EAAE,CAAC;IAC/C,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,sCAAsC,EAAE,KAAK,IAAI,EAAE;QACpD,MAAM,QAAQ,GAAG,IAAI,wBAAwB,EAAE,CAAC;QAChD,MAAM,SAAS,GAAG,mBAAmB,CAAC,KAAK,EAAE,CAAC,iBAAiB,CAAC,EAAE,CAAC,MAAM,CAAC,CAAC,CAAC;QAC5E,QAAQ,CAAC,QAAQ,CAAC,SAAS,CAAC,CAAC;QAC7B,MAAM,KAAK,GAAG,MAAM,QAAQ,CAAC,UAAU,CAAC,EAAE,IAAI,EAAE,IAAI,UAAU,EAAE,EAAE,QAAQ,EAAE,iBAAiB,EAAE,CAAC,CAAC;QACjG,MAAM,CAAC,KAAK,CAAC,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC;IAChC,CAAC,CAAC,CAAC;AACL,CAAC,CAAC,CAAC"}
@@ -0,0 +1,2 @@
1
+ export {};
2
+ //# sourceMappingURL=renderer.test.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"renderer.test.d.ts","sourceRoot":"","sources":["../../src/__tests__/renderer.test.ts"],"names":[],"mappings":""}
@@ -0,0 +1,129 @@
1
+ import { describe, it, expect } from 'vitest';
2
+ import { MarkdownRenderer } from '../renderer.js';
3
+ import { createNode } from '@markitdownjs/shared';
4
+ describe('MarkdownRenderer', () => {
5
+ const renderer = new MarkdownRenderer();
6
+ it('should render headings', () => {
7
+ const node = createNode({
8
+ type: 'heading',
9
+ level: 1,
10
+ children: [createNode({ type: 'text', value: 'Title' })],
11
+ });
12
+ expect(renderer.renderAst(node)).toBe('# Title');
13
+ });
14
+ it('should render paragraphs', () => {
15
+ const node = createNode({
16
+ type: 'paragraph',
17
+ children: [createNode({ type: 'text', value: 'Hello world' })],
18
+ });
19
+ expect(renderer.renderAst(node)).toBe('Hello world');
20
+ });
21
+ it('should render bold text', () => {
22
+ const node = createNode({
23
+ type: 'strong',
24
+ children: [createNode({ type: 'text', value: 'bold' })],
25
+ });
26
+ expect(renderer.renderAst(node)).toBe('**bold**');
27
+ });
28
+ it('should render italic text', () => {
29
+ const node = createNode({
30
+ type: 'emphasis',
31
+ children: [createNode({ type: 'text', value: 'italic' })],
32
+ });
33
+ expect(renderer.renderAst(node)).toBe('*italic*');
34
+ });
35
+ it('should render links', () => {
36
+ const node = createNode({
37
+ type: 'link',
38
+ href: 'https://example.com',
39
+ children: [createNode({ type: 'text', value: 'Example' })],
40
+ });
41
+ expect(renderer.renderAst(node)).toBe('[Example](https://example.com)');
42
+ });
43
+ it('should render images', () => {
44
+ const node = createNode({
45
+ type: 'image',
46
+ src: 'image.png',
47
+ alt: 'An image',
48
+ });
49
+ expect(renderer.renderAst(node)).toBe('![An image](image.png)');
50
+ });
51
+ it('should render code blocks', () => {
52
+ const node = createNode({
53
+ type: 'code',
54
+ language: 'typescript',
55
+ value: 'const x = 1;',
56
+ });
57
+ expect(renderer.renderAst(node)).toContain('typescript');
58
+ expect(renderer.renderAst(node)).toContain('const x = 1;');
59
+ });
60
+ it('should render tables', () => {
61
+ const node = createNode({
62
+ type: 'table',
63
+ children: [
64
+ createNode({
65
+ type: 'table-row',
66
+ isHeader: true,
67
+ children: [
68
+ createNode({
69
+ type: 'table-cell',
70
+ children: [createNode({ type: 'text', value: 'Name' })],
71
+ }),
72
+ ],
73
+ }),
74
+ createNode({
75
+ type: 'table-row',
76
+ children: [
77
+ createNode({
78
+ type: 'table-cell',
79
+ children: [createNode({ type: 'text', value: 'John' })],
80
+ }),
81
+ ],
82
+ }),
83
+ ],
84
+ });
85
+ const md = renderer.renderAst(node);
86
+ expect(md).toContain('| Name |');
87
+ expect(md).toContain('---');
88
+ expect(md).toContain('| John |');
89
+ });
90
+ it('should render lists', () => {
91
+ const node = createNode({
92
+ type: 'list',
93
+ ordered: false,
94
+ children: [
95
+ createNode({
96
+ type: 'list-item',
97
+ children: [createNode({ type: 'text', value: 'Item 1' })],
98
+ }),
99
+ createNode({
100
+ type: 'list-item',
101
+ children: [createNode({ type: 'text', value: 'Item 2' })],
102
+ }),
103
+ ],
104
+ });
105
+ const md = renderer.renderAst(node);
106
+ expect(md).toContain('- Item 1');
107
+ expect(md).toContain('- Item 2');
108
+ });
109
+ it('should render document nodes', () => {
110
+ const doc = createNode({
111
+ type: 'document',
112
+ children: [
113
+ createNode({
114
+ type: 'heading',
115
+ level: 1,
116
+ children: [createNode({ type: 'text', value: 'Title' })],
117
+ }),
118
+ createNode({
119
+ type: 'paragraph',
120
+ children: [createNode({ type: 'text', value: 'Content' })],
121
+ }),
122
+ ],
123
+ });
124
+ const md = renderer.renderAst(doc);
125
+ expect(md).toContain('# Title');
126
+ expect(md).toContain('Content');
127
+ });
128
+ });
129
+ //# sourceMappingURL=renderer.test.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"renderer.test.js","sourceRoot":"","sources":["../../src/__tests__/renderer.test.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,EAAE,EAAE,MAAM,EAAE,MAAM,QAAQ,CAAC;AAC9C,OAAO,EAAE,gBAAgB,EAAE,MAAM,gBAAgB,CAAC;AAClD,OAAO,EAAE,UAAU,EAAE,MAAM,sBAAsB,CAAC;AAOlD,QAAQ,CAAC,kBAAkB,EAAE,GAAG,EAAE;IAChC,MAAM,QAAQ,GAAG,IAAI,gBAAgB,EAAE,CAAC;IAExC,EAAE,CAAC,wBAAwB,EAAE,GAAG,EAAE;QAChC,MAAM,IAAI,GAAG,UAAU,CAAc;YACnC,IAAI,EAAE,SAAS;YACf,KAAK,EAAE,CAAC;YACR,QAAQ,EAAE,CAAC,UAAU,CAAW,EAAE,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,OAAO,EAAE,CAAC,CAAC;SACnE,CAAC,CAAC;QACH,MAAM,CAAC,QAAQ,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC;IACnD,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,0BAA0B,EAAE,GAAG,EAAE;QAClC,MAAM,IAAI,GAAG,UAAU,CAAgB;YACrC,IAAI,EAAE,WAAW;YACjB,QAAQ,EAAE,CAAC,UAAU,CAAW,EAAE,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,aAAa,EAAE,CAAC,CAAC;SACzE,CAAC,CAAC;QACH,MAAM,CAAC,QAAQ,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC,CAAC,IAAI,CAAC,aAAa,CAAC,CAAC;IACvD,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,yBAAyB,EAAE,GAAG,EAAE;QACjC,MAAM,IAAI,GAAG,UAAU,CAAa;YAClC,IAAI,EAAE,QAAQ;YACd,QAAQ,EAAE,CAAC,UAAU,CAAW,EAAE,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,EAAE,CAAC,CAAC;SAClE,CAAC,CAAC;QACH,MAAM,CAAC,QAAQ,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC,CAAC,IAAI,CAAC,UAAU,CAAC,CAAC;IACpD,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,2BAA2B,EAAE,GAAG,EAAE;QACnC,MAAM,IAAI,GAAG,UAAU,CAAe;YACpC,IAAI,EAAE,UAAU;YAChB,QAAQ,EAAE,CAAC,UAAU,CAAW,EAAE,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,QAAQ,EAAE,CAAC,CAAC;SACpE,CAAC,CAAC;QACH,MAAM,CAAC,QAAQ,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC,CAAC,IAAI,CAAC,UAAU,CAAC,CAAC;IACpD,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,qBAAqB,EAAE,GAAG,EAAE;QAC7B,MAAM,IAAI,GAAG,UAAU,CAAW;YAChC,IAAI,EAAE,MAAM;YACZ,IAAI,EAAE,qBAAqB;YAC3B,QAAQ,EAAE,CAAC,UAAU,CAAW,EAAE,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,SAAS,EAAE,CAAC,CAAC;SACrE,CAAC,CAAC;QACH,MAAM,CAAC,QAAQ,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC,CAAC,IAAI,CAAC,gCAAgC,CAAC,CAAC;IAC1E,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,sBAAsB,EAAE,GAAG,EAAE;QAC9B,MAAM,IAAI,GAAG,UAAU,CAAY;YACjC,IAAI,EAAE,OAAO;YACb,GAAG,EAAE,WAAW;YAChB,GAAG,EAAE,UAAU;SAChB,CAAC,CAAC;QACH,MAAM,CAAC,QAAQ,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC,CAAC,IAAI,CAAC,wBAAwB,CAAC,CAAC;IAClE,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,2BAA2B,EAAE,GAAG,EAAE;QACnC,MAAM,IAAI,GAAG,UAAU,CAAW;YAChC,IAAI,EAAE,MAAM;YACZ,QAAQ,EAAE,YAAY;YACtB,KAAK,EAAE,cAAc;SACtB,CAAC,CAAC;QACH,MAAM,CAAC,QAAQ,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC,CAAC,SAAS,CAAC,YAAY,CAAC,CAAC;QACzD,MAAM,CAAC,QAAQ,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC,CAAC,SAAS,CAAC,cAAc,CAAC,CAAC;IAC7D,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,sBAAsB,EAAE,GAAG,EAAE;QAC9B,MAAM,IAAI,GAAG,UAAU,CAAY;YACjC,IAAI,EAAE,OAAO;YACb,QAAQ,EAAE;gBACR,UAAU,CAAe;oBACvB,IAAI,EAAE,WAAW;oBACjB,QAAQ,EAAE,IAAI;oBACd,QAAQ,EAAE;wBACR,UAAU,CAAgB;4BACxB,IAAI,EAAE,YAAY;4BAClB,QAAQ,EAAE,CAAC,UAAU,CAAW,EAAE,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,EAAE,CAAC,CAAC;yBAClE,CAAC;qBACH;iBACF,CAAC;gBACF,UAAU,CAAe;oBACvB,IAAI,EAAE,WAAW;oBACjB,QAAQ,EAAE;wBACR,UAAU,CAAgB;4BACxB,IAAI,EAAE,YAAY;4BAClB,QAAQ,EAAE,CAAC,UAAU,CAAW,EAAE,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,MAAM,EAAE,CAAC,CAAC;yBAClE,CAAC;qBACH;iBACF,CAAC;aACH;SACF,CAAC,CAAC;QACH,MAAM,EAAE,GAAG,QAAQ,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC;QACpC,MAAM,CAAC,EAAE,CAAC,CAAC,SAAS,CAAC,UAAU,CAAC,CAAC;QACjC,MAAM,CAAC,EAAE,CAAC,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC;QAC5B,MAAM,CAAC,EAAE,CAAC,CAAC,SAAS,CAAC,UAAU,CAAC,CAAC;IACnC,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,qBAAqB,EAAE,GAAG,EAAE;QAC7B,MAAM,IAAI,GAAG,UAAU,CAAW;YAChC,IAAI,EAAE,MAAM;YACZ,OAAO,EAAE,KAAK;YACd,QAAQ,EAAE;gBACR,UAAU,CAAe;oBACvB,IAAI,EAAE,WAAW;oBACjB,QAAQ,EAAE,CAAC,UAAU,CAAW,EAAE,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,QAAQ,EAAE,CAAC,CAAC;iBACpE,CAAC;gBACF,UAAU,CAAe;oBACvB,IAAI,EAAE,WAAW;oBACjB,QAAQ,EAAE,CAAC,UAAU,CAAW,EAAE,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,QAAQ,EAAE,CAAC,CAAC;iBACpE,CAAC;aACH;SACF,CAAC,CAAC;QACH,MAAM,EAAE,GAAG,QAAQ,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC;QACpC,MAAM,CAAC,EAAE,CAAC,CAAC,SAAS,CAAC,UAAU,CAAC,CAAC;QACjC,MAAM,CAAC,EAAE,CAAC,CAAC,SAAS,CAAC,UAAU,CAAC,CAAC;IACnC,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,8BAA8B,EAAE,GAAG,EAAE;QACtC,MAAM,GAAG,GAAG,UAAU,CAAe;YACnC,IAAI,EAAE,UAAU;YAChB,QAAQ,EAAE;gBACR,UAAU,CAAc;oBACtB,IAAI,EAAE,SAAS;oBACf,KAAK,EAAE,CAAC;oBACR,QAAQ,EAAE,CAAC,UAAU,CAAW,EAAE,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,OAAO,EAAE,CAAC,CAAC;iBACnE,CAAC;gBACF,UAAU,CAAgB;oBACxB,IAAI,EAAE,WAAW;oBACjB,QAAQ,EAAE,CAAC,UAAU,CAAW,EAAE,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,SAAS,EAAE,CAAC,CAAC;iBACrE,CAAC;aACH;SACF,CAAC,CAAC;QACH,MAAM,EAAE,GAAG,QAAQ,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC;QACnC,MAAM,CAAC,EAAE,CAAC,CAAC,SAAS,CAAC,SAAS,CAAC,CAAC;QAChC,MAAM,CAAC,EAAE,CAAC,CAAC,SAAS,CAAC,SAAS,CAAC,CAAC;IAClC,CAAC,CAAC,CAAC;AACL,CAAC,CAAC,CAAC"}
@@ -0,0 +1,15 @@
1
+ import type { AssetInfo, ImageInfo } from "@markitdownjs/shared";
2
+ export declare class AssetManager {
3
+ private assets;
4
+ private images;
5
+ addAsset(asset: Omit<AssetInfo, "id">): AssetInfo;
6
+ addImage(image: Omit<ImageInfo, "id">): ImageInfo;
7
+ getAsset(id: string): AssetInfo | undefined;
8
+ getImage(id: string): ImageInfo | undefined;
9
+ getAllAssets(): AssetInfo[];
10
+ getAllImages(): ImageInfo[];
11
+ clear(): void;
12
+ toDataUrl(data: Uint8Array, mimeType: string): string;
13
+ getImageAsDataUrl(id: string): string | undefined;
14
+ }
15
+ //# sourceMappingURL=asset-manager.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"asset-manager.d.ts","sourceRoot":"","sources":["../src/asset-manager.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,SAAS,EAAE,SAAS,EAAE,MAAM,sBAAsB,CAAC;AAGjE,qBAAa,YAAY;IACvB,OAAO,CAAC,MAAM,CAAgC;IAC9C,OAAO,CAAC,MAAM,CAAgC;IAE9C,QAAQ,CAAC,KAAK,EAAE,IAAI,CAAC,SAAS,EAAE,IAAI,CAAC,GAAG,SAAS;IAOjD,QAAQ,CAAC,KAAK,EAAE,IAAI,CAAC,SAAS,EAAE,IAAI,CAAC,GAAG,SAAS;IAOjD,QAAQ,CAAC,EAAE,EAAE,MAAM,GAAG,SAAS,GAAG,SAAS;IAI3C,QAAQ,CAAC,EAAE,EAAE,MAAM,GAAG,SAAS,GAAG,SAAS;IAI3C,YAAY,IAAI,SAAS,EAAE;IAI3B,YAAY,IAAI,SAAS,EAAE;IAI3B,KAAK,IAAI,IAAI;IAKb,SAAS,CAAC,IAAI,EAAE,UAAU,EAAE,QAAQ,EAAE,MAAM,GAAG,MAAM;IAIrD,iBAAiB,CAAC,EAAE,EAAE,MAAM,GAAG,MAAM,GAAG,SAAS;CAKlD"}
@@ -0,0 +1,43 @@
1
+ import { generateId, uint8ArrayToDataUrl } from "@markitdownjs/shared";
2
+ export class AssetManager {
3
+ assets = new Map();
4
+ images = new Map();
5
+ addAsset(asset) {
6
+ const id = generateId();
7
+ const fullAsset = { ...asset, id };
8
+ this.assets.set(id, fullAsset);
9
+ return fullAsset;
10
+ }
11
+ addImage(image) {
12
+ const id = generateId();
13
+ const fullImage = { ...image, id };
14
+ this.images.set(id, fullImage);
15
+ return fullImage;
16
+ }
17
+ getAsset(id) {
18
+ return this.assets.get(id);
19
+ }
20
+ getImage(id) {
21
+ return this.images.get(id);
22
+ }
23
+ getAllAssets() {
24
+ return Array.from(this.assets.values());
25
+ }
26
+ getAllImages() {
27
+ return Array.from(this.images.values());
28
+ }
29
+ clear() {
30
+ this.assets.clear();
31
+ this.images.clear();
32
+ }
33
+ toDataUrl(data, mimeType) {
34
+ return uint8ArrayToDataUrl(data, mimeType);
35
+ }
36
+ getImageAsDataUrl(id) {
37
+ const image = this.images.get(id);
38
+ if (!image?.data || !image.mimeType)
39
+ return undefined;
40
+ return this.toDataUrl(image.data, image.mimeType);
41
+ }
42
+ }
43
+ //# sourceMappingURL=asset-manager.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"asset-manager.js","sourceRoot":"","sources":["../src/asset-manager.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,UAAU,EAAE,mBAAmB,EAAE,MAAM,sBAAsB,CAAC;AAEvE,MAAM,OAAO,YAAY;IACf,MAAM,GAAG,IAAI,GAAG,EAAqB,CAAC;IACtC,MAAM,GAAG,IAAI,GAAG,EAAqB,CAAC;IAE9C,QAAQ,CAAC,KAA4B;QACnC,MAAM,EAAE,GAAG,UAAU,EAAE,CAAC;QACxB,MAAM,SAAS,GAAc,EAAE,GAAG,KAAK,EAAE,EAAE,EAAE,CAAC;QAC9C,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,EAAE,EAAE,SAAS,CAAC,CAAC;QAC/B,OAAO,SAAS,CAAC;IACnB,CAAC;IAED,QAAQ,CAAC,KAA4B;QACnC,MAAM,EAAE,GAAG,UAAU,EAAE,CAAC;QACxB,MAAM,SAAS,GAAc,EAAE,GAAG,KAAK,EAAE,EAAE,EAAE,CAAC;QAC9C,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,EAAE,EAAE,SAAS,CAAC,CAAC;QAC/B,OAAO,SAAS,CAAC;IACnB,CAAC;IAED,QAAQ,CAAC,EAAU;QACjB,OAAO,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC;IAC7B,CAAC;IAED,QAAQ,CAAC,EAAU;QACjB,OAAO,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC;IAC7B,CAAC;IAED,YAAY;QACV,OAAO,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,MAAM,CAAC,MAAM,EAAE,CAAC,CAAC;IAC1C,CAAC;IAED,YAAY;QACV,OAAO,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,MAAM,CAAC,MAAM,EAAE,CAAC,CAAC;IAC1C,CAAC;IAED,KAAK;QACH,IAAI,CAAC,MAAM,CAAC,KAAK,EAAE,CAAC;QACpB,IAAI,CAAC,MAAM,CAAC,KAAK,EAAE,CAAC;IACtB,CAAC;IAED,SAAS,CAAC,IAAgB,EAAE,QAAgB;QAC1C,OAAO,mBAAmB,CAAC,IAAI,EAAE,QAAQ,CAAC,CAAC;IAC7C,CAAC;IAED,iBAAiB,CAAC,EAAU;QAC1B,MAAM,KAAK,GAAG,IAAI,CAAC,MAAM,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC;QAClC,IAAI,CAAC,KAAK,EAAE,IAAI,IAAI,CAAC,KAAK,CAAC,QAAQ;YAAE,OAAO,SAAS,CAAC;QACtD,OAAO,IAAI,CAAC,SAAS,CAAC,KAAK,CAAC,IAAI,EAAE,KAAK,CAAC,QAAQ,CAAC,CAAC;IACpD,CAAC;CACF"}
@@ -0,0 +1,8 @@
1
+ export { MarkItDown } from "./parser.js";
2
+ export type { MarkItDownOptions } from "./parser.js";
3
+ export { DefaultConverterRegistry } from "./registry.js";
4
+ export { DocumentPipeline } from "./pipeline.js";
5
+ export { MarkdownRenderer } from "./renderer.js";
6
+ export { MetadataExtractor } from "./metadata-extractor.js";
7
+ export { AssetManager } from "./asset-manager.js";
8
+ //# sourceMappingURL=index.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,UAAU,EAAE,MAAM,aAAa,CAAC;AACzC,YAAY,EAAE,iBAAiB,EAAE,MAAM,aAAa,CAAC;AACrD,OAAO,EAAE,wBAAwB,EAAE,MAAM,eAAe,CAAC;AACzD,OAAO,EAAE,gBAAgB,EAAE,MAAM,eAAe,CAAC;AACjD,OAAO,EAAE,gBAAgB,EAAE,MAAM,eAAe,CAAC;AACjD,OAAO,EAAE,iBAAiB,EAAE,MAAM,yBAAyB,CAAC;AAC5D,OAAO,EAAE,YAAY,EAAE,MAAM,oBAAoB,CAAC"}
package/dist/index.js ADDED
@@ -0,0 +1,7 @@
1
+ export { MarkItDown } from "./parser.js";
2
+ export { DefaultConverterRegistry } from "./registry.js";
3
+ export { DocumentPipeline } from "./pipeline.js";
4
+ export { MarkdownRenderer } from "./renderer.js";
5
+ export { MetadataExtractor } from "./metadata-extractor.js";
6
+ export { AssetManager } from "./asset-manager.js";
7
+ //# sourceMappingURL=index.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"index.js","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,UAAU,EAAE,MAAM,aAAa,CAAC;AAEzC,OAAO,EAAE,wBAAwB,EAAE,MAAM,eAAe,CAAC;AACzD,OAAO,EAAE,gBAAgB,EAAE,MAAM,eAAe,CAAC;AACjD,OAAO,EAAE,gBAAgB,EAAE,MAAM,eAAe,CAAC;AACjD,OAAO,EAAE,iBAAiB,EAAE,MAAM,yBAAyB,CAAC;AAC5D,OAAO,EAAE,YAAY,EAAE,MAAM,oBAAoB,CAAC"}
@@ -0,0 +1,7 @@
1
+ import type { DocumentMetadata } from "@markitdownjs/shared";
2
+ export declare class MetadataExtractor {
3
+ extractFromMarkdown(markdown: string): DocumentMetadata;
4
+ extractFromAST(ast: unknown): DocumentMetadata;
5
+ merge(a: DocumentMetadata, b: DocumentMetadata): DocumentMetadata;
6
+ }
7
+ //# sourceMappingURL=metadata-extractor.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"metadata-extractor.d.ts","sourceRoot":"","sources":["../src/metadata-extractor.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,gBAAgB,EAAE,MAAM,sBAAsB,CAAC;AAE7D,qBAAa,iBAAiB;IAC5B,mBAAmB,CAAC,QAAQ,EAAE,MAAM,GAAG,gBAAgB;IAkBvD,cAAc,CAAC,GAAG,EAAE,OAAO,GAAG,gBAAgB;IAW9C,KAAK,CAAC,CAAC,EAAE,gBAAgB,EAAE,CAAC,EAAE,gBAAgB,GAAG,gBAAgB;CAUlE"}
@@ -0,0 +1,37 @@
1
+ export class MetadataExtractor {
2
+ extractFromMarkdown(markdown) {
3
+ const metadata = {};
4
+ const titleMatch = markdown.match(/^#\s+(.+)$/m);
5
+ if (titleMatch?.[1]) {
6
+ metadata.title = titleMatch[1].trim();
7
+ }
8
+ const words = markdown
9
+ .replace(/```[\s\S]*?```/g, "")
10
+ .replace(/[#*_`\[\]()!]/g, "")
11
+ .split(/\s+/)
12
+ .filter((w) => w.length > 0);
13
+ metadata.wordCount = words.length;
14
+ return metadata;
15
+ }
16
+ extractFromAST(ast) {
17
+ const metadata = {};
18
+ if (ast && typeof ast === "object" && "metadata" in ast) {
19
+ const nodeAst = ast;
20
+ if (nodeAst.metadata) {
21
+ Object.assign(metadata, nodeAst.metadata);
22
+ }
23
+ }
24
+ return metadata;
25
+ }
26
+ merge(a, b) {
27
+ return {
28
+ ...a,
29
+ ...b,
30
+ customProperties: {
31
+ ...a.customProperties,
32
+ ...b.customProperties,
33
+ },
34
+ };
35
+ }
36
+ }
37
+ //# sourceMappingURL=metadata-extractor.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"metadata-extractor.js","sourceRoot":"","sources":["../src/metadata-extractor.ts"],"names":[],"mappings":"AAEA,MAAM,OAAO,iBAAiB;IAC5B,mBAAmB,CAAC,QAAgB;QAClC,MAAM,QAAQ,GAAqB,EAAE,CAAC;QAEtC,MAAM,UAAU,GAAG,QAAQ,CAAC,KAAK,CAAC,aAAa,CAAC,CAAC;QACjD,IAAI,UAAU,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;YACpB,QAAQ,CAAC,KAAK,GAAG,UAAU,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;QACxC,CAAC;QAED,MAAM,KAAK,GAAG,QAAQ;aACnB,OAAO,CAAC,iBAAiB,EAAE,EAAE,CAAC;aAC9B,OAAO,CAAC,gBAAgB,EAAE,EAAE,CAAC;aAC7B,KAAK,CAAC,KAAK,CAAC;aACZ,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;QAC/B,QAAQ,CAAC,SAAS,GAAG,KAAK,CAAC,MAAM,CAAC;QAElC,OAAO,QAAQ,CAAC;IAClB,CAAC;IAED,cAAc,CAAC,GAAY;QACzB,MAAM,QAAQ,GAAqB,EAAE,CAAC;QACtC,IAAI,GAAG,IAAI,OAAO,GAAG,KAAK,QAAQ,IAAI,UAAU,IAAI,GAAG,EAAE,CAAC;YACxD,MAAM,OAAO,GAAG,GAA6C,CAAC;YAC9D,IAAI,OAAO,CAAC,QAAQ,EAAE,CAAC;gBACrB,MAAM,CAAC,MAAM,CAAC,QAAQ,EAAE,OAAO,CAAC,QAAQ,CAAC,CAAC;YAC5C,CAAC;QACH,CAAC;QACD,OAAO,QAAQ,CAAC;IAClB,CAAC;IAED,KAAK,CAAC,CAAmB,EAAE,CAAmB;QAC5C,OAAO;YACL,GAAG,CAAC;YACJ,GAAG,CAAC;YACJ,gBAAgB,EAAE;gBAChB,GAAG,CAAC,CAAC,gBAAgB;gBACrB,GAAG,CAAC,CAAC,gBAAgB;aACtB;SACF,CAAC;IACJ,CAAC;CACF"}
@@ -0,0 +1,15 @@
1
+ import type { ConversionInput, ConversionResult, ConverterRegistry } from "@markitdownjs/shared";
2
+ export interface MarkItDownOptions {
3
+ registry?: ConverterRegistry;
4
+ }
5
+ export declare class MarkItDown {
6
+ private pipeline;
7
+ private renderer;
8
+ constructor(options?: MarkItDownOptions);
9
+ getRegistry(): ConverterRegistry;
10
+ convert(input: ConversionInput | File | Blob | Uint8Array | string): Promise<ConversionResult>;
11
+ convertToMarkdown(input: ConversionInput | File | Blob | Uint8Array | string): Promise<string>;
12
+ convertToJson(input: ConversionInput | File | Blob | Uint8Array | string): Promise<string>;
13
+ private normalizeInput;
14
+ }
15
+ //# sourceMappingURL=parser.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"parser.d.ts","sourceRoot":"","sources":["../src/parser.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EACV,eAAe,EACf,gBAAgB,EAChB,iBAAiB,EAClB,MAAM,sBAAsB,CAAC;AAK9B,MAAM,WAAW,iBAAiB;IAChC,QAAQ,CAAC,EAAE,iBAAiB,CAAC;CAC9B;AAED,qBAAa,UAAU;IACrB,OAAO,CAAC,QAAQ,CAAmB;IACnC,OAAO,CAAC,QAAQ,CAAmB;gBAEvB,OAAO,CAAC,EAAE,iBAAiB;IAMvC,WAAW,IAAI,iBAAiB;IAI1B,OAAO,CACX,KAAK,EAAE,eAAe,GAAG,IAAI,GAAG,IAAI,GAAG,UAAU,GAAG,MAAM,GACzD,OAAO,CAAC,gBAAgB,CAAC;IAKtB,iBAAiB,CACrB,KAAK,EAAE,eAAe,GAAG,IAAI,GAAG,IAAI,GAAG,UAAU,GAAG,MAAM,GACzD,OAAO,CAAC,MAAM,CAAC;IAKZ,aAAa,CACjB,KAAK,EAAE,eAAe,GAAG,IAAI,GAAG,IAAI,GAAG,UAAU,GAAG,MAAM,GACzD,OAAO,CAAC,MAAM,CAAC;IAKlB,OAAO,CAAC,cAAc;CAqBvB"}
package/dist/parser.js ADDED
@@ -0,0 +1,47 @@
1
+ import { DefaultConverterRegistry } from "./registry.js";
2
+ import { DocumentPipeline } from "./pipeline.js";
3
+ import { MarkdownRenderer } from "./renderer.js";
4
+ export class MarkItDown {
5
+ pipeline;
6
+ renderer;
7
+ constructor(options) {
8
+ const registry = options?.registry ?? new DefaultConverterRegistry();
9
+ this.pipeline = new DocumentPipeline(registry);
10
+ this.renderer = new MarkdownRenderer();
11
+ }
12
+ getRegistry() {
13
+ return this.pipeline.getRegistry();
14
+ }
15
+ async convert(input) {
16
+ const normalizedInput = this.normalizeInput(input);
17
+ return this.pipeline.convert(normalizedInput);
18
+ }
19
+ async convertToMarkdown(input) {
20
+ const result = await this.convert(input);
21
+ return result.markdown;
22
+ }
23
+ async convertToJson(input) {
24
+ const result = await this.convert(input);
25
+ return this.renderer.render(result, "json");
26
+ }
27
+ normalizeInput(input) {
28
+ if (typeof input === "string") {
29
+ return { data: input };
30
+ }
31
+ if (input instanceof Uint8Array) {
32
+ return { data: input };
33
+ }
34
+ if (typeof File !== "undefined" && input instanceof File) {
35
+ return {
36
+ data: input,
37
+ fileName: input.name,
38
+ mimeType: input.type || undefined,
39
+ };
40
+ }
41
+ if (typeof Blob !== "undefined" && input instanceof Blob) {
42
+ return { data: input };
43
+ }
44
+ return input;
45
+ }
46
+ }
47
+ //# sourceMappingURL=parser.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"parser.js","sourceRoot":"","sources":["../src/parser.ts"],"names":[],"mappings":"AAKA,OAAO,EAAE,wBAAwB,EAAE,MAAM,eAAe,CAAC;AACzD,OAAO,EAAE,gBAAgB,EAAE,MAAM,eAAe,CAAC;AACjD,OAAO,EAAE,gBAAgB,EAAE,MAAM,eAAe,CAAC;AAMjD,MAAM,OAAO,UAAU;IACb,QAAQ,CAAmB;IAC3B,QAAQ,CAAmB;IAEnC,YAAY,OAA2B;QACrC,MAAM,QAAQ,GAAG,OAAO,EAAE,QAAQ,IAAI,IAAI,wBAAwB,EAAE,CAAC;QACrE,IAAI,CAAC,QAAQ,GAAG,IAAI,gBAAgB,CAAC,QAAQ,CAAC,CAAC;QAC/C,IAAI,CAAC,QAAQ,GAAG,IAAI,gBAAgB,EAAE,CAAC;IACzC,CAAC;IAED,WAAW;QACT,OAAO,IAAI,CAAC,QAAQ,CAAC,WAAW,EAAE,CAAC;IACrC,CAAC;IAED,KAAK,CAAC,OAAO,CACX,KAA0D;QAE1D,MAAM,eAAe,GAAG,IAAI,CAAC,cAAc,CAAC,KAAK,CAAC,CAAC;QACnD,OAAO,IAAI,CAAC,QAAQ,CAAC,OAAO,CAAC,eAAe,CAAC,CAAC;IAChD,CAAC;IAED,KAAK,CAAC,iBAAiB,CACrB,KAA0D;QAE1D,MAAM,MAAM,GAAG,MAAM,IAAI,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC;QACzC,OAAO,MAAM,CAAC,QAAQ,CAAC;IACzB,CAAC;IAED,KAAK,CAAC,aAAa,CACjB,KAA0D;QAE1D,MAAM,MAAM,GAAG,MAAM,IAAI,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC;QACzC,OAAO,IAAI,CAAC,QAAQ,CAAC,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;IAC9C,CAAC;IAEO,cAAc,CACpB,KAA0D;QAE1D,IAAI,OAAO,KAAK,KAAK,QAAQ,EAAE,CAAC;YAC9B,OAAO,EAAE,IAAI,EAAE,KAAK,EAAE,CAAC;QACzB,CAAC;QACD,IAAI,KAAK,YAAY,UAAU,EAAE,CAAC;YAChC,OAAO,EAAE,IAAI,EAAE,KAAK,EAAE,CAAC;QACzB,CAAC;QACD,IAAI,OAAO,IAAI,KAAK,WAAW,IAAI,KAAK,YAAY,IAAI,EAAE,CAAC;YACzD,OAAO;gBACL,IAAI,EAAE,KAAK;gBACX,QAAQ,EAAE,KAAK,CAAC,IAAI;gBACpB,QAAQ,EAAE,KAAK,CAAC,IAAI,IAAI,SAAS;aAClC,CAAC;QACJ,CAAC;QACD,IAAI,OAAO,IAAI,KAAK,WAAW,IAAI,KAAK,YAAY,IAAI,EAAE,CAAC;YACzD,OAAO,EAAE,IAAI,EAAE,KAAK,EAAE,CAAC;QACzB,CAAC;QACD,OAAO,KAAwB,CAAC;IAClC,CAAC;CACF"}
@@ -0,0 +1,9 @@
1
+ import type { ConversionInput, ConversionResult, ConverterRegistry } from "@markitdownjs/shared";
2
+ export declare class DocumentPipeline {
3
+ private registry;
4
+ constructor(registry?: ConverterRegistry);
5
+ getRegistry(): ConverterRegistry;
6
+ convert(input: ConversionInput): Promise<ConversionResult>;
7
+ convertWithFallback(input: ConversionInput): Promise<ConversionResult>;
8
+ }
9
+ //# sourceMappingURL=pipeline.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"pipeline.d.ts","sourceRoot":"","sources":["../src/pipeline.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EACV,eAAe,EACf,gBAAgB,EAChB,iBAAiB,EAClB,MAAM,sBAAsB,CAAC;AAK9B,qBAAa,gBAAgB;IAC3B,OAAO,CAAC,QAAQ,CAAoB;gBAExB,QAAQ,CAAC,EAAE,iBAAiB;IAIxC,WAAW,IAAI,iBAAiB;IAI1B,OAAO,CAAC,KAAK,EAAE,eAAe,GAAG,OAAO,CAAC,gBAAgB,CAAC;IAiE1D,mBAAmB,CACvB,KAAK,EAAE,eAAe,GACrB,OAAO,CAAC,gBAAgB,CAAC;CAW7B"}
@@ -0,0 +1,73 @@
1
+ import { ConversionError, CancellationError } from "@markitdownjs/shared";
2
+ import { checkSignal, readInputData } from "@markitdownjs/shared";
3
+ import { DefaultConverterRegistry } from "./registry.js";
4
+ export class DocumentPipeline {
5
+ registry;
6
+ constructor(registry) {
7
+ this.registry = registry ?? new DefaultConverterRegistry();
8
+ }
9
+ getRegistry() {
10
+ return this.registry;
11
+ }
12
+ async convert(input) {
13
+ const signal = input.options?.signal;
14
+ checkSignal(signal);
15
+ const startTime = performance.now();
16
+ const data = await readInputData(input.data);
17
+ checkSignal(signal);
18
+ const enrichedInput = {
19
+ ...input,
20
+ data,
21
+ };
22
+ const converter = await this.registry.canConvert(enrichedInput);
23
+ if (!converter) {
24
+ throw new ConversionError(`No converter found for input${input.fileName ? ` "${input.fileName}"` : ""}`);
25
+ }
26
+ checkSignal(signal);
27
+ const middlewares = this.registry.getMiddlewares();
28
+ let processedInput = enrichedInput;
29
+ for (const middleware of middlewares) {
30
+ if (middleware.beforeConvert) {
31
+ processedInput = await middleware.beforeConvert(processedInput);
32
+ }
33
+ }
34
+ checkSignal(signal);
35
+ let result;
36
+ try {
37
+ result = await converter.convert(processedInput);
38
+ }
39
+ catch (error) {
40
+ if (error instanceof CancellationError)
41
+ throw error;
42
+ throw new ConversionError(`Converter "${converter.id}" failed: ${error instanceof Error ? error.message : String(error)}`, converter.id, error instanceof Error ? error : undefined);
43
+ }
44
+ for (const middleware of middlewares) {
45
+ if (middleware.afterConvert) {
46
+ result = await middleware.afterConvert(result);
47
+ }
48
+ }
49
+ const endTime = performance.now();
50
+ result.stats = {
51
+ ...result.stats,
52
+ startTime,
53
+ endTime,
54
+ duration: endTime - startTime,
55
+ inputSize: data.byteLength,
56
+ outputSize: result.markdown.length,
57
+ };
58
+ return result;
59
+ }
60
+ async convertWithFallback(input) {
61
+ try {
62
+ return await this.convert(input);
63
+ }
64
+ catch (error) {
65
+ if (input.mimeType) {
66
+ const fallbackInput = { ...input, mimeType: undefined };
67
+ return await this.convert(fallbackInput);
68
+ }
69
+ throw error;
70
+ }
71
+ }
72
+ }
73
+ //# sourceMappingURL=pipeline.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"pipeline.js","sourceRoot":"","sources":["../src/pipeline.ts"],"names":[],"mappings":"AAKA,OAAO,EAAE,eAAe,EAAE,iBAAiB,EAAE,MAAM,sBAAsB,CAAC;AAC1E,OAAO,EAAE,WAAW,EAAE,aAAa,EAAE,MAAM,sBAAsB,CAAC;AAClE,OAAO,EAAE,wBAAwB,EAAE,MAAM,eAAe,CAAC;AAEzD,MAAM,OAAO,gBAAgB;IACnB,QAAQ,CAAoB;IAEpC,YAAY,QAA4B;QACtC,IAAI,CAAC,QAAQ,GAAG,QAAQ,IAAI,IAAI,wBAAwB,EAAE,CAAC;IAC7D,CAAC;IAED,WAAW;QACT,OAAO,IAAI,CAAC,QAAQ,CAAC;IACvB,CAAC;IAED,KAAK,CAAC,OAAO,CAAC,KAAsB;QAClC,MAAM,MAAM,GAAG,KAAK,CAAC,OAAO,EAAE,MAAM,CAAC;QACrC,WAAW,CAAC,MAAM,CAAC,CAAC;QAEpB,MAAM,SAAS,GAAG,WAAW,CAAC,GAAG,EAAE,CAAC;QACpC,MAAM,IAAI,GAAG,MAAM,aAAa,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;QAE7C,WAAW,CAAC,MAAM,CAAC,CAAC;QAEpB,MAAM,aAAa,GAAoB;YACrC,GAAG,KAAK;YACR,IAAI;SACL,CAAC;QAEF,MAAM,SAAS,GAAG,MAAM,IAAI,CAAC,QAAQ,CAAC,UAAU,CAAC,aAAa,CAAC,CAAC;QAChE,IAAI,CAAC,SAAS,EAAE,CAAC;YACf,MAAM,IAAI,eAAe,CACvB,+BAA+B,KAAK,CAAC,QAAQ,CAAC,CAAC,CAAC,KAAK,KAAK,CAAC,QAAQ,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAC9E,CAAC;QACJ,CAAC;QAED,WAAW,CAAC,MAAM,CAAC,CAAC;QAEpB,MAAM,WAAW,GAAG,IAAI,CAAC,QAAQ,CAAC,cAAc,EAAE,CAAC;QACnD,IAAI,cAAc,GAAG,aAAa,CAAC;QAEnC,KAAK,MAAM,UAAU,IAAI,WAAW,EAAE,CAAC;YACrC,IAAI,UAAU,CAAC,aAAa,EAAE,CAAC;gBAC7B,cAAc,GAAG,MAAM,UAAU,CAAC,aAAa,CAAC,cAAc,CAAC,CAAC;YAClE,CAAC;QACH,CAAC;QAED,WAAW,CAAC,MAAM,CAAC,CAAC;QAEpB,IAAI,MAAwB,CAAC;QAC7B,IAAI,CAAC;YACH,MAAM,GAAG,MAAM,SAAS,CAAC,OAAO,CAAC,cAAc,CAAC,CAAC;QACnD,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YACf,IAAI,KAAK,YAAY,iBAAiB;gBAAE,MAAM,KAAK,CAAC;YACpD,MAAM,IAAI,eAAe,CACvB,cAAc,SAAS,CAAC,EAAE,aAAa,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,EAAE,EAC/F,SAAS,CAAC,EAAE,EACZ,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,SAAS,CAC3C,CAAC;QACJ,CAAC;QAED,KAAK,MAAM,UAAU,IAAI,WAAW,EAAE,CAAC;YACrC,IAAI,UAAU,CAAC,YAAY,EAAE,CAAC;gBAC5B,MAAM,GAAG,MAAM,UAAU,CAAC,YAAY,CAAC,MAAM,CAAC,CAAC;YACjD,CAAC;QACH,CAAC;QAED,MAAM,OAAO,GAAG,WAAW,CAAC,GAAG,EAAE,CAAC;QAClC,MAAM,CAAC,KAAK,GAAG;YACb,GAAG,MAAM,CAAC,KAAK;YACf,SAAS;YACT,OAAO;YACP,QAAQ,EAAE,OAAO,GAAG,SAAS;YAC7B,SAAS,EAAE,IAAI,CAAC,UAAU;YAC1B,UAAU,EAAE,MAAM,CAAC,QAAQ,CAAC,MAAM;SACnC,CAAC;QAEF,OAAO,MAAM,CAAC;IAChB,CAAC;IAED,KAAK,CAAC,mBAAmB,CACvB,KAAsB;QAEtB,IAAI,CAAC;YACH,OAAO,MAAM,IAAI,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC;QACnC,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YACf,IAAI,KAAK,CAAC,QAAQ,EAAE,CAAC;gBACnB,MAAM,aAAa,GAAG,EAAE,GAAG,KAAK,EAAE,QAAQ,EAAE,SAAS,EAAE,CAAC;gBACxD,OAAO,MAAM,IAAI,CAAC,OAAO,CAAC,aAAa,CAAC,CAAC;YAC3C,CAAC;YACD,MAAM,KAAK,CAAC;QACd,CAAC;IACH,CAAC;CACF"}
@@ -0,0 +1,20 @@
1
+ import type { Converter, ConverterId, ConverterRegistry, ConversionInput, MimeType, FileExtension, Plugin, Logger, ConversionMiddleware } from "@markitdownjs/shared";
2
+ export declare class DefaultConverterRegistry implements ConverterRegistry {
3
+ private converters;
4
+ private plugins;
5
+ private middlewares;
6
+ private logger;
7
+ constructor(logger?: Logger);
8
+ register(converter: Converter): void;
9
+ unregister(id: ConverterId): void;
10
+ get(id: ConverterId): Converter | undefined;
11
+ getByMimeType(mimeType: MimeType): Converter | undefined;
12
+ getByExtension(extension: FileExtension): Converter | undefined;
13
+ list(): Converter[];
14
+ canConvert(input: ConversionInput): Promise<Converter | undefined>;
15
+ registerPlugin(plugin: Plugin): Promise<void>;
16
+ unregisterPlugin(id: string): Promise<void>;
17
+ addMiddleware(middleware: ConversionMiddleware): void;
18
+ getMiddlewares(): ConversionMiddleware[];
19
+ }
20
+ //# sourceMappingURL=registry.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"registry.d.ts","sourceRoot":"","sources":["../src/registry.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EACV,SAAS,EACT,WAAW,EACX,iBAAiB,EACjB,eAAe,EACf,QAAQ,EACR,aAAa,EACb,MAAM,EAEN,MAAM,EACN,oBAAoB,EACrB,MAAM,sBAAsB,CAAC;AAU9B,qBAAa,wBAAyB,YAAW,iBAAiB;IAChE,OAAO,CAAC,UAAU,CAAqC;IACvD,OAAO,CAAC,OAAO,CAA6B;IAC5C,OAAO,CAAC,WAAW,CAA8B;IACjD,OAAO,CAAC,MAAM,CAAS;gBAEX,MAAM,CAAC,EAAE,MAAM;IAI3B,QAAQ,CAAC,SAAS,EAAE,SAAS,GAAG,IAAI;IAUpC,UAAU,CAAC,EAAE,EAAE,WAAW,GAAG,IAAI;IASjC,GAAG,CAAC,EAAE,EAAE,WAAW,GAAG,SAAS,GAAG,SAAS;IAI3C,aAAa,CAAC,QAAQ,EAAE,QAAQ,GAAG,SAAS,GAAG,SAAS;IASxD,cAAc,CAAC,SAAS,EAAE,aAAa,GAAG,SAAS,GAAG,SAAS;IAU/D,IAAI,IAAI,SAAS,EAAE;IAIb,UAAU,CAAC,KAAK,EAAE,eAAe,GAAG,OAAO,CAAC,SAAS,GAAG,SAAS,CAAC;IAmClE,cAAc,CAAC,MAAM,EAAE,MAAM,GAAG,OAAO,CAAC,IAAI,CAAC;IAkC7C,gBAAgB,CAAC,EAAE,EAAE,MAAM,GAAG,OAAO,CAAC,IAAI,CAAC;IA6BjD,aAAa,CAAC,UAAU,EAAE,oBAAoB,GAAG,IAAI;IAKrD,cAAc,IAAI,oBAAoB,EAAE;CAGzC"}
@@ -0,0 +1,146 @@
1
+ import { detectMimeType } from "@markitdownjs/shared";
2
+ const consoleLogger = {
3
+ debug: console.debug,
4
+ info: console.info,
5
+ warn: console.warn,
6
+ error: console.error,
7
+ };
8
+ export class DefaultConverterRegistry {
9
+ converters = new Map();
10
+ plugins = new Map();
11
+ middlewares = [];
12
+ logger;
13
+ constructor(logger) {
14
+ this.logger = logger ?? consoleLogger;
15
+ }
16
+ register(converter) {
17
+ if (this.converters.has(converter.id)) {
18
+ this.logger.warn(`Converter "${converter.id}" is already registered, overwriting.`);
19
+ }
20
+ this.converters.set(converter.id, converter);
21
+ this.logger.debug(`Registered converter: ${converter.id}`);
22
+ }
23
+ unregister(id) {
24
+ if (!this.converters.has(id)) {
25
+ this.logger.warn(`Converter "${id}" not found, cannot unregister.`);
26
+ return;
27
+ }
28
+ this.converters.delete(id);
29
+ this.logger.debug(`Unregistered converter: ${id}`);
30
+ }
31
+ get(id) {
32
+ return this.converters.get(id);
33
+ }
34
+ getByMimeType(mimeType) {
35
+ for (const converter of this.converters.values()) {
36
+ if (converter.supportedMimeTypes.includes(mimeType)) {
37
+ return converter;
38
+ }
39
+ }
40
+ return undefined;
41
+ }
42
+ getByExtension(extension) {
43
+ const ext = extension.startsWith(".") ? extension : `.${extension}`;
44
+ for (const converter of this.converters.values()) {
45
+ if (converter.supportedExtensions.includes(ext)) {
46
+ return converter;
47
+ }
48
+ }
49
+ return undefined;
50
+ }
51
+ list() {
52
+ return Array.from(this.converters.values());
53
+ }
54
+ async canConvert(input) {
55
+ const converters = this.list();
56
+ for (const converter of converters) {
57
+ try {
58
+ if (await converter.canConvert(input)) {
59
+ return converter;
60
+ }
61
+ }
62
+ catch {
63
+ continue;
64
+ }
65
+ }
66
+ if (input.mimeType) {
67
+ const byMime = this.getByMimeType(input.mimeType);
68
+ if (byMime)
69
+ return byMime;
70
+ }
71
+ if (input.fileName) {
72
+ const mime = detectMimeType(input.fileName);
73
+ if (mime) {
74
+ const byMime = this.getByMimeType(mime);
75
+ if (byMime)
76
+ return byMime;
77
+ }
78
+ const dotIndex = input.fileName.lastIndexOf(".");
79
+ if (dotIndex !== -1) {
80
+ const ext = input.fileName.substring(dotIndex);
81
+ const byExt = this.getByExtension(ext);
82
+ if (byExt)
83
+ return byExt;
84
+ }
85
+ }
86
+ return undefined;
87
+ }
88
+ async registerPlugin(plugin) {
89
+ if (this.plugins.has(plugin.id)) {
90
+ throw new Error(`Plugin "${plugin.id}" is already registered.`);
91
+ }
92
+ const context = {
93
+ registry: this,
94
+ logger: this.logger,
95
+ config: {},
96
+ };
97
+ try {
98
+ await plugin.initialize?.(context);
99
+ }
100
+ catch (error) {
101
+ throw new Error(`Failed to initialize plugin "${plugin.id}": ${error instanceof Error ? error.message : String(error)}`);
102
+ }
103
+ if (plugin.converters) {
104
+ for (const converter of plugin.converters) {
105
+ this.register(converter);
106
+ }
107
+ }
108
+ if (plugin.middleware) {
109
+ this.middlewares.push(...plugin.middleware);
110
+ this.middlewares.sort((a, b) => a.priority - b.priority);
111
+ }
112
+ this.plugins.set(plugin.id, plugin);
113
+ this.logger.info(`Registered plugin: ${plugin.id}`);
114
+ }
115
+ async unregisterPlugin(id) {
116
+ const plugin = this.plugins.get(id);
117
+ if (!plugin) {
118
+ this.logger.warn(`Plugin "${id}" not found.`);
119
+ return;
120
+ }
121
+ try {
122
+ await plugin.destroy?.();
123
+ }
124
+ catch (error) {
125
+ this.logger.error(`Error destroying plugin "${id}"`, error);
126
+ }
127
+ if (plugin.converters) {
128
+ for (const converter of plugin.converters) {
129
+ this.unregister(converter.id);
130
+ }
131
+ }
132
+ if (plugin.middleware) {
133
+ this.middlewares = this.middlewares.filter((m) => !plugin.middleware.includes(m));
134
+ }
135
+ this.plugins.delete(id);
136
+ this.logger.info(`Unregistered plugin: ${id}`);
137
+ }
138
+ addMiddleware(middleware) {
139
+ this.middlewares.push(middleware);
140
+ this.middlewares.sort((a, b) => a.priority - b.priority);
141
+ }
142
+ getMiddlewares() {
143
+ return [...this.middlewares];
144
+ }
145
+ }
146
+ //# sourceMappingURL=registry.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"registry.js","sourceRoot":"","sources":["../src/registry.ts"],"names":[],"mappings":"AAYA,OAAO,EAAE,cAAc,EAAE,MAAM,sBAAsB,CAAC;AAEtD,MAAM,aAAa,GAAW;IAC5B,KAAK,EAAE,OAAO,CAAC,KAAK;IACpB,IAAI,EAAE,OAAO,CAAC,IAAI;IAClB,IAAI,EAAE,OAAO,CAAC,IAAI;IAClB,KAAK,EAAE,OAAO,CAAC,KAAK;CACrB,CAAC;AAEF,MAAM,OAAO,wBAAwB;IAC3B,UAAU,GAAG,IAAI,GAAG,EAA0B,CAAC;IAC/C,OAAO,GAAG,IAAI,GAAG,EAAkB,CAAC;IACpC,WAAW,GAA2B,EAAE,CAAC;IACzC,MAAM,CAAS;IAEvB,YAAY,MAAe;QACzB,IAAI,CAAC,MAAM,GAAG,MAAM,IAAI,aAAa,CAAC;IACxC,CAAC;IAED,QAAQ,CAAC,SAAoB;QAC3B,IAAI,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,SAAS,CAAC,EAAE,CAAC,EAAE,CAAC;YACtC,IAAI,CAAC,MAAM,CAAC,IAAI,CACd,cAAc,SAAS,CAAC,EAAE,uCAAuC,CAClE,CAAC;QACJ,CAAC;QACD,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,SAAS,CAAC,EAAE,EAAE,SAAS,CAAC,CAAC;QAC7C,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,yBAAyB,SAAS,CAAC,EAAE,EAAE,CAAC,CAAC;IAC7D,CAAC;IAED,UAAU,CAAC,EAAe;QACxB,IAAI,CAAC,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,EAAE,CAAC,EAAE,CAAC;YAC7B,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,cAAc,EAAE,iCAAiC,CAAC,CAAC;YACpE,OAAO;QACT,CAAC;QACD,IAAI,CAAC,UAAU,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC;QAC3B,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,2BAA2B,EAAE,EAAE,CAAC,CAAC;IACrD,CAAC;IAED,GAAG,CAAC,EAAe;QACjB,OAAO,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC;IACjC,CAAC;IAED,aAAa,CAAC,QAAkB;QAC9B,KAAK,MAAM,SAAS,IAAI,IAAI,CAAC,UAAU,CAAC,MAAM,EAAE,EAAE,CAAC;YACjD,IAAI,SAAS,CAAC,kBAAkB,CAAC,QAAQ,CAAC,QAAQ,CAAC,EAAE,CAAC;gBACpD,OAAO,SAAS,CAAC;YACnB,CAAC;QACH,CAAC;QACD,OAAO,SAAS,CAAC;IACnB,CAAC;IAED,cAAc,CAAC,SAAwB;QACrC,MAAM,GAAG,GAAG,SAAS,CAAC,UAAU,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,IAAI,SAAS,EAAE,CAAC;QACpE,KAAK,MAAM,SAAS,IAAI,IAAI,CAAC,UAAU,CAAC,MAAM,EAAE,EAAE,CAAC;YACjD,IAAI,SAAS,CAAC,mBAAmB,CAAC,QAAQ,CAAC,GAAG,CAAC,EAAE,CAAC;gBAChD,OAAO,SAAS,CAAC;YACnB,CAAC;QACH,CAAC;QACD,OAAO,SAAS,CAAC;IACnB,CAAC;IAED,IAAI;QACF,OAAO,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,UAAU,CAAC,MAAM,EAAE,CAAC,CAAC;IAC9C,CAAC;IAED,KAAK,CAAC,UAAU,CAAC,KAAsB;QACrC,MAAM,UAAU,GAAG,IAAI,CAAC,IAAI,EAAE,CAAC;QAE/B,KAAK,MAAM,SAAS,IAAI,UAAU,EAAE,CAAC;YACnC,IAAI,CAAC;gBACH,IAAI,MAAM,SAAS,CAAC,UAAU,CAAC,KAAK,CAAC,EAAE,CAAC;oBACtC,OAAO,SAAS,CAAC;gBACnB,CAAC;YACH,CAAC;YAAC,MAAM,CAAC;gBACP,SAAS;YACX,CAAC;QACH,CAAC;QAED,IAAI,KAAK,CAAC,QAAQ,EAAE,CAAC;YACnB,MAAM,MAAM,GAAG,IAAI,CAAC,aAAa,CAAC,KAAK,CAAC,QAAQ,CAAC,CAAC;YAClD,IAAI,MAAM;gBAAE,OAAO,MAAM,CAAC;QAC5B,CAAC;QAED,IAAI,KAAK,CAAC,QAAQ,EAAE,CAAC;YACnB,MAAM,IAAI,GAAG,cAAc,CAAC,KAAK,CAAC,QAAQ,CAAC,CAAC;YAC5C,IAAI,IAAI,EAAE,CAAC;gBACT,MAAM,MAAM,GAAG,IAAI,CAAC,aAAa,CAAC,IAAI,CAAC,CAAC;gBACxC,IAAI,MAAM;oBAAE,OAAO,MAAM,CAAC;YAC5B,CAAC;YACD,MAAM,QAAQ,GAAG,KAAK,CAAC,QAAQ,CAAC,WAAW,CAAC,GAAG,CAAC,CAAC;YACjD,IAAI,QAAQ,KAAK,CAAC,CAAC,EAAE,CAAC;gBACpB,MAAM,GAAG,GAAG,KAAK,CAAC,QAAQ,CAAC,SAAS,CAAC,QAAQ,CAAC,CAAC;gBAC/C,MAAM,KAAK,GAAG,IAAI,CAAC,cAAc,CAAC,GAAG,CAAC,CAAC;gBACvC,IAAI,KAAK;oBAAE,OAAO,KAAK,CAAC;YAC1B,CAAC;QACH,CAAC;QAED,OAAO,SAAS,CAAC;IACnB,CAAC;IAED,KAAK,CAAC,cAAc,CAAC,MAAc;QACjC,IAAI,IAAI,CAAC,OAAO,CAAC,GAAG,CAAC,MAAM,CAAC,EAAE,CAAC,EAAE,CAAC;YAChC,MAAM,IAAI,KAAK,CAAC,WAAW,MAAM,CAAC,EAAE,0BAA0B,CAAC,CAAC;QAClE,CAAC;QAED,MAAM,OAAO,GAAkB;YAC7B,QAAQ,EAAE,IAAI;YACd,MAAM,EAAE,IAAI,CAAC,MAAM;YACnB,MAAM,EAAE,EAAE;SACX,CAAC;QAEF,IAAI,CAAC;YACH,MAAM,MAAM,CAAC,UAAU,EAAE,CAAC,OAAO,CAAC,CAAC;QACrC,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YACf,MAAM,IAAI,KAAK,CACb,gCAAgC,MAAM,CAAC,EAAE,MAAM,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,EAAE,CACxG,CAAC;QACJ,CAAC;QAED,IAAI,MAAM,CAAC,UAAU,EAAE,CAAC;YACtB,KAAK,MAAM,SAAS,IAAI,MAAM,CAAC,UAAU,EAAE,CAAC;gBAC1C,IAAI,CAAC,QAAQ,CAAC,SAAS,CAAC,CAAC;YAC3B,CAAC;QACH,CAAC;QAED,IAAI,MAAM,CAAC,UAAU,EAAE,CAAC;YACtB,IAAI,CAAC,WAAW,CAAC,IAAI,CAAC,GAAG,MAAM,CAAC,UAAU,CAAC,CAAC;YAC5C,IAAI,CAAC,WAAW,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,GAAG,CAAC,CAAC,QAAQ,CAAC,CAAC;QAC3D,CAAC;QAED,IAAI,CAAC,OAAO,CAAC,GAAG,CAAC,MAAM,CAAC,EAAE,EAAE,MAAM,CAAC,CAAC;QACpC,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,sBAAsB,MAAM,CAAC,EAAE,EAAE,CAAC,CAAC;IACtD,CAAC;IAED,KAAK,CAAC,gBAAgB,CAAC,EAAU;QAC/B,MAAM,MAAM,GAAG,IAAI,CAAC,OAAO,CAAC,GAAG,CAAC,EAAE,CAAC,CAAC;QACpC,IAAI,CAAC,MAAM,EAAE,CAAC;YACZ,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,WAAW,EAAE,cAAc,CAAC,CAAC;YAC9C,OAAO;QACT,CAAC;QAED,IAAI,CAAC;YACH,MAAM,MAAM,CAAC,OAAO,EAAE,EAAE,CAAC;QAC3B,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YACf,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,4BAA4B,EAAE,GAAG,EAAE,KAAK,CAAC,CAAC;QAC9D,CAAC;QAED,IAAI,MAAM,CAAC,UAAU,EAAE,CAAC;YACtB,KAAK,MAAM,SAAS,IAAI,MAAM,CAAC,UAAU,EAAE,CAAC;gBAC1C,IAAI,CAAC,UAAU,CAAC,SAAS,CAAC,EAAE,CAAC,CAAC;YAChC,CAAC;QACH,CAAC;QAED,IAAI,MAAM,CAAC,UAAU,EAAE,CAAC;YACtB,IAAI,CAAC,WAAW,GAAG,IAAI,CAAC,WAAW,CAAC,MAAM,CACxC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,MAAM,CAAC,UAAW,CAAC,QAAQ,CAAC,CAAC,CAAC,CACvC,CAAC;QACJ,CAAC;QAED,IAAI,CAAC,OAAO,CAAC,MAAM,CAAC,EAAE,CAAC,CAAC;QACxB,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,wBAAwB,EAAE,EAAE,CAAC,CAAC;IACjD,CAAC;IAED,aAAa,CAAC,UAAgC;QAC5C,IAAI,CAAC,WAAW,CAAC,IAAI,CAAC,UAAU,CAAC,CAAC;QAClC,IAAI,CAAC,WAAW,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,GAAG,CAAC,CAAC,QAAQ,CAAC,CAAC;IAC3D,CAAC;IAED,cAAc;QACZ,OAAO,CAAC,GAAG,IAAI,CAAC,WAAW,CAAC,CAAC;IAC/B,CAAC;CACF"}
@@ -0,0 +1,12 @@
1
+ import type { AnyNode, ConversionResult, OutputFormat } from "@markitdownjs/shared";
2
+ export declare class MarkdownRenderer {
3
+ render(result: ConversionResult, format?: OutputFormat): string;
4
+ renderAst(ast: AnyNode): string;
5
+ private renderNode;
6
+ private renderChildren;
7
+ private renderTable;
8
+ private toAst;
9
+ private toPlainText;
10
+ private markdownToHtml;
11
+ }
12
+ //# sourceMappingURL=renderer.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"renderer.d.ts","sourceRoot":"","sources":["../src/renderer.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EACV,OAAO,EACP,gBAAgB,EAChB,YAAY,EAYb,MAAM,sBAAsB,CAAC;AAE9B,qBAAa,gBAAgB;IAC3B,MAAM,CAAC,MAAM,EAAE,gBAAgB,EAAE,MAAM,GAAE,YAAyB,GAAG,MAAM;IAe3E,SAAS,CAAC,GAAG,EAAE,OAAO,GAAG,MAAM;IAI/B,OAAO,CAAC,UAAU;IAsElB,OAAO,CAAC,cAAc;IAItB,OAAO,CAAC,WAAW;IAiCnB,OAAO,CAAC,KAAK;IAQb,OAAO,CAAC,WAAW;IAmBnB,OAAO,CAAC,cAAc;CA0DvB"}
@@ -0,0 +1,179 @@
1
+ export class MarkdownRenderer {
2
+ render(result, format = "markdown") {
3
+ switch (format) {
4
+ case "markdown":
5
+ return result.markdown;
6
+ case "json":
7
+ return JSON.stringify(result.ast ?? this.toAst(result), null, 2);
8
+ case "plaintext":
9
+ return this.toPlainText(result.markdown);
10
+ case "html":
11
+ return this.markdownToHtml(result.markdown);
12
+ default:
13
+ return result.markdown;
14
+ }
15
+ }
16
+ renderAst(ast) {
17
+ return this.renderNode(ast);
18
+ }
19
+ renderNode(node) {
20
+ switch (node.type) {
21
+ case "document":
22
+ return (node.children ?? []).map((c) => this.renderNode(c)).join("\n\n");
23
+ case "heading": {
24
+ const n = node;
25
+ return `${"#".repeat(n.level)} ${this.renderChildren(n)}`;
26
+ }
27
+ case "paragraph":
28
+ return this.renderChildren(node);
29
+ case "text": {
30
+ const n = node;
31
+ return n.value;
32
+ }
33
+ case "emphasis":
34
+ return `*${this.renderChildren(node)}*`;
35
+ case "strong":
36
+ return `**${this.renderChildren(node)}**`;
37
+ case "inline-code": {
38
+ const n = node;
39
+ return `\`${n.value}\``;
40
+ }
41
+ case "code": {
42
+ const n = node;
43
+ return n.language
44
+ ? `\`\`\`${n.language}\n${n.value}\n\`\`\``
45
+ : `\`\`\`\n${n.value}\n\`\`\``;
46
+ }
47
+ case "link": {
48
+ const n = node;
49
+ return `[${this.renderChildren(n)}](${n.href}${n.title ? ` "${n.title}"` : ""})`;
50
+ }
51
+ case "image": {
52
+ const n = node;
53
+ return `![${n.alt ?? ""}](${n.src}${n.title ? ` "${n.title}"` : ""})`;
54
+ }
55
+ case "list": {
56
+ const n = node;
57
+ return (n.children
58
+ ?.map((item, i) => n.ordered
59
+ ? `${i + 1}. ${this.renderNode(item)}`
60
+ : `- ${this.renderNode(item)}`)
61
+ .join("\n") ?? "");
62
+ }
63
+ case "list-item":
64
+ return this.renderChildren(node);
65
+ case "table":
66
+ return this.renderTable(node);
67
+ case "blockquote":
68
+ return (this.renderChildren(node)
69
+ .split("\n")
70
+ .map((line) => `> ${line}`)
71
+ .join("\n"));
72
+ case "thematic-break":
73
+ return "---";
74
+ case "html": {
75
+ const n = node;
76
+ return n.value;
77
+ }
78
+ default:
79
+ return "";
80
+ }
81
+ }
82
+ renderChildren(node) {
83
+ return (node.children ?? []).map((c) => this.renderNode(c)).join("");
84
+ }
85
+ renderTable(table) {
86
+ const rows = table.children.filter((r) => r.type === "table-row");
87
+ if (rows.length === 0)
88
+ return "";
89
+ const headerRow = rows[0];
90
+ const bodyRows = rows.slice(1);
91
+ const headerCells = headerRow.children.map((c) => (c.type === "table-cell"
92
+ ? this.renderChildren(c)
93
+ : "").replace(/\|/g, "\\|"));
94
+ const separator = headerCells.map(() => "---").join(" | ");
95
+ const headerLine = `| ${headerCells.join(" | ")} |`;
96
+ const bodyLines = bodyRows.map((row) => {
97
+ const cells = row.children.map((c) => (c.type === "table-cell"
98
+ ? this.renderChildren(c)
99
+ : "").replace(/\|/g, "\\|"));
100
+ return `| ${cells.join(" | ")} |`;
101
+ });
102
+ return [headerLine, separator, ...bodyLines].join("\n");
103
+ }
104
+ toAst(result) {
105
+ return {
106
+ type: "document",
107
+ children: [],
108
+ metadata: result.metadata,
109
+ };
110
+ }
111
+ toPlainText(markdown) {
112
+ return markdown
113
+ .replace(/^#{1,6}\s+/gm, "")
114
+ .replace(/\*\*(.*?)\*\*/g, "$1")
115
+ .replace(/\*(.*?)\*/g, "$1")
116
+ .replace(/`(.*?)`/g, "$1")
117
+ .replace(/`{3}[\s\S]*?`{3}/g, (match) => {
118
+ const lines = match.split("\n").slice(1, -1);
119
+ return lines.join("\n");
120
+ })
121
+ .replace(/\[([^\]]+)\]\([^)]+\)/g, "$1")
122
+ .replace(/!\[([^\]]*)\]\([^)]+\)/g, "[$1]")
123
+ .replace(/^[-*+]\s+/gm, "• ")
124
+ .replace(/^>\s+/gm, "")
125
+ .replace(/^---$/gm, "")
126
+ .replace(/\n{3,}/g, "\n\n")
127
+ .trim();
128
+ }
129
+ markdownToHtml(markdown) {
130
+ let html = markdown;
131
+ html = html.replace(/^### (.+)$/gm, "<h3>$1</h3>");
132
+ html = html.replace(/^## (.+)$/gm, "<h2>$1</h2>");
133
+ html = html.replace(/^# (.+)$/gm, "<h1>$1</h1>");
134
+ html = html.replace(/\*\*(.*?)\*\*/g, "<strong>$1</strong>");
135
+ html = html.replace(/\*(.*?)\*/g, "<em>$1</em>");
136
+ html = html.replace(/`(.*?)`/g, "<code>$1</code>");
137
+ html = html.replace(/`{3}(\w+)?\n([\s\S]*?)`{3}/g, '<pre><code class="language-$1">$2</code></pre>');
138
+ html = html.replace(/\[([^\]]+)\]\(([^)]+)\)/g, '<a href="$2">$1</a>');
139
+ html = html.replace(/!\[([^\]]*)\]\(([^)]+)\)/g, '<img src="$2" alt="$1" />');
140
+ html = html.replace(/^> (.+)$/gm, "<blockquote><p>$1</p></blockquote>");
141
+ html = html.replace(/^[-*+] (.+)$/gm, "<li>$1</li>");
142
+ const lines = html.split("\n");
143
+ const result = [];
144
+ let inParagraph = false;
145
+ for (const line of lines) {
146
+ const trimmed = line.trim();
147
+ if (trimmed === "") {
148
+ if (inParagraph) {
149
+ result.push("</p>");
150
+ inParagraph = false;
151
+ }
152
+ continue;
153
+ }
154
+ if (trimmed.startsWith("<h") ||
155
+ trimmed.startsWith("<pre") ||
156
+ trimmed.startsWith("<ul") ||
157
+ trimmed.startsWith("<blockquote") ||
158
+ trimmed.startsWith("<img") ||
159
+ trimmed.startsWith("<a ")) {
160
+ if (inParagraph) {
161
+ result.push("</p>");
162
+ inParagraph = false;
163
+ }
164
+ result.push(trimmed);
165
+ }
166
+ else {
167
+ if (!inParagraph) {
168
+ result.push("<p>");
169
+ inParagraph = true;
170
+ }
171
+ result.push(trimmed);
172
+ }
173
+ }
174
+ if (inParagraph)
175
+ result.push("</p>");
176
+ return result.join("\n");
177
+ }
178
+ }
179
+ //# sourceMappingURL=renderer.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"renderer.js","sourceRoot":"","sources":["../src/renderer.ts"],"names":[],"mappings":"AAiBA,MAAM,OAAO,gBAAgB;IAC3B,MAAM,CAAC,MAAwB,EAAE,SAAuB,UAAU;QAChE,QAAQ,MAAM,EAAE,CAAC;YACf,KAAK,UAAU;gBACb,OAAO,MAAM,CAAC,QAAQ,CAAC;YACzB,KAAK,MAAM;gBACT,OAAO,IAAI,CAAC,SAAS,CAAC,MAAM,CAAC,GAAG,IAAI,IAAI,CAAC,KAAK,CAAC,MAAM,CAAC,EAAE,IAAI,EAAE,CAAC,CAAC,CAAC;YACnE,KAAK,WAAW;gBACd,OAAO,IAAI,CAAC,WAAW,CAAC,MAAM,CAAC,QAAQ,CAAC,CAAC;YAC3C,KAAK,MAAM;gBACT,OAAO,IAAI,CAAC,cAAc,CAAC,MAAM,CAAC,QAAQ,CAAC,CAAC;YAC9C;gBACE,OAAO,MAAM,CAAC,QAAQ,CAAC;QAC3B,CAAC;IACH,CAAC;IAED,SAAS,CAAC,GAAY;QACpB,OAAO,IAAI,CAAC,UAAU,CAAC,GAAG,CAAC,CAAC;IAC9B,CAAC;IAEO,UAAU,CAAC,IAAa;QAC9B,QAAQ,IAAI,CAAC,IAAI,EAAE,CAAC;YAClB,KAAK,UAAU;gBACb,OAAO,CAAC,IAAI,CAAC,QAAQ,IAAI,EAAE,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,IAAI,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;YAC3E,KAAK,SAAS,CAAC,CAAC,CAAC;gBACf,MAAM,CAAC,GAAG,IAAmB,CAAC;gBAC9B,OAAO,GAAG,GAAG,CAAC,MAAM,CAAC,CAAC,CAAC,KAAK,CAAC,IAAI,IAAI,CAAC,cAAc,CAAC,CAAC,CAAC,EAAE,CAAC;YAC5D,CAAC;YACD,KAAK,WAAW;gBACd,OAAO,IAAI,CAAC,cAAc,CAAC,IAAI,CAAC,CAAC;YACnC,KAAK,MAAM,CAAC,CAAC,CAAC;gBACZ,MAAM,CAAC,GAAG,IAAgB,CAAC;gBAC3B,OAAO,CAAC,CAAC,KAAK,CAAC;YACjB,CAAC;YACD,KAAK,UAAU;gBACb,OAAO,IAAI,IAAI,CAAC,cAAc,CAAC,IAAI,CAAC,GAAG,CAAC;YAC1C,KAAK,QAAQ;gBACX,OAAO,KAAK,IAAI,CAAC,cAAc,CAAC,IAAI,CAAC,IAAI,CAAC;YAC5C,KAAK,aAAa,CAAC,CAAC,CAAC;gBACnB,MAAM,CAAC,GAAG,IAAsB,CAAC;gBACjC,OAAO,KAAK,CAAC,CAAC,KAAK,IAAI,CAAC;YAC1B,CAAC;YACD,KAAK,MAAM,CAAC,CAAC,CAAC;gBACZ,MAAM,CAAC,GAAG,IAAgB,CAAC;gBAC3B,OAAO,CAAC,CAAC,QAAQ;oBACf,CAAC,CAAC,SAAS,CAAC,CAAC,QAAQ,KAAK,CAAC,CAAC,KAAK,UAAU;oBAC3C,CAAC,CAAC,WAAW,CAAC,CAAC,KAAK,UAAU,CAAC;YACnC,CAAC;YACD,KAAK,MAAM,CAAC,CAAC,CAAC;gBACZ,MAAM,CAAC,GAAG,IAAgB,CAAC;gBAC3B,OAAO,IAAI,IAAI,CAAC,cAAc,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,IAAI,GAAG,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,KAAK,GAAG,CAAC,CAAC,CAAC,EAAE,GAAG,CAAC;YACnF,CAAC;YACD,KAAK,OAAO,CAAC,CAAC,CAAC;gBACb,MAAM,CAAC,GAAG,IAAiB,CAAC;gBAC5B,OAAO,KAAK,CAAC,CAAC,GAAG,IAAI,EAAE,KAAK,CAAC,CAAC,GAAG,GAAG,CAAC,CAAC,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,CAAC,KAAK,GAAG,CAAC,CAAC,CAAC,EAAE,GAAG,CAAC;YACxE,CAAC;YACD,KAAK,MAAM,CAAC,CAAC,CAAC;gBACZ,MAAM,CAAC,GAAG,IAAgB,CAAC;gBAC3B,OAAO,CACL,CAAC,CAAC,QAAQ;oBACR,EAAE,GAAG,CAAC,CAAC,IAAI,EAAE,CAAC,EAAE,EAAE,CAChB,CAAC,CAAC,OAAO;oBACP,CAAC,CAAC,GAAG,CAAC,GAAG,CAAC,KAAK,IAAI,CAAC,UAAU,CAAC,IAAI,CAAC,EAAE;oBACtC,CAAC,CAAC,KAAK,IAAI,CAAC,UAAU,CAAC,IAAI,CAAC,EAAE,CACjC;qBACA,IAAI,CAAC,IAAI,CAAC,IAAI,EAAE,CACpB,CAAC;YACJ,CAAC;YACD,KAAK,WAAW;gBACd,OAAO,IAAI,CAAC,cAAc,CAAC,IAAI,CAAC,CAAC;YACnC,KAAK,OAAO;gBACV,OAAO,IAAI,CAAC,WAAW,CAAC,IAAiB,CAAC,CAAC;YAC7C,KAAK,YAAY;gBACf,OAAO,CACL,IAAI,CAAC,cAAc,CAAC,IAAI,CAAC;qBACtB,KAAK,CAAC,IAAI,CAAC;qBACX,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,KAAK,IAAI,EAAE,CAAC;qBAC1B,IAAI,CAAC,IAAI,CAAC,CACd,CAAC;YACJ,KAAK,gBAAgB;gBACnB,OAAO,KAAK,CAAC;YACf,KAAK,MAAM,CAAC,CAAC,CAAC;gBACZ,MAAM,CAAC,GAAG,IAAgB,CAAC;gBAC3B,OAAO,CAAC,CAAC,KAAK,CAAC;YACjB,CAAC;YACD;gBACE,OAAO,EAAE,CAAC;QACd,CAAC;IACH,CAAC;IAEO,cAAc,CAAC,IAA8B;QACnD,OAAO,CAAC,IAAI,CAAC,QAAQ,IAAI,EAAE,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,IAAI,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;IACvE,CAAC;IAEO,WAAW,CAAC,KAAgB;QAClC,MAAM,IAAI,GAAG,KAAK,CAAC,QAAQ,CAAC,MAAM,CAChC,CAAC,CAAC,EAAqB,EAAE,CAAC,CAAC,CAAC,IAAI,KAAK,WAAW,CACjD,CAAC;QACF,IAAI,IAAI,CAAC,MAAM,KAAK,CAAC;YAAE,OAAO,EAAE,CAAC;QAEjC,MAAM,SAAS,GAAG,IAAI,CAAC,CAAC,CAAE,CAAC;QAC3B,MAAM,QAAQ,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC;QAE/B,MAAM,WAAW,GAAG,SAAS,CAAC,QAAQ,CAAC,GAAG,CACxC,CAAC,CAAC,EAAE,EAAE,CACJ,CAAC,CAAC,CAAC,IAAI,KAAK,YAAY;YACtB,CAAC,CAAC,IAAI,CAAC,cAAc,CAAC,CAAkB,CAAC;YACzC,CAAC,CAAC,EAAE,CACL,CAAC,OAAO,CAAC,KAAK,EAAE,KAAK,CAAC,CAC1B,CAAC;QACF,MAAM,SAAS,GAAG,WAAW,CAAC,GAAG,CAAC,GAAG,EAAE,CAAC,KAAK,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;QAC3D,MAAM,UAAU,GAAG,KAAK,WAAW,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC;QAEpD,MAAM,SAAS,GAAG,QAAQ,CAAC,GAAG,CAAC,CAAC,GAAG,EAAE,EAAE;YACrC,MAAM,KAAK,GAAG,GAAG,CAAC,QAAQ,CAAC,GAAG,CAC5B,CAAC,CAAC,EAAE,EAAE,CACJ,CAAC,CAAC,CAAC,IAAI,KAAK,YAAY;gBACtB,CAAC,CAAC,IAAI,CAAC,cAAc,CAAC,CAAkB,CAAC;gBACzC,CAAC,CAAC,EAAE,CACL,CAAC,OAAO,CAAC,KAAK,EAAE,KAAK,CAAC,CAC1B,CAAC;YACF,OAAO,KAAK,KAAK,CAAC,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC;QACpC,CAAC,CAAC,CAAC;QAEH,OAAO,CAAC,UAAU,EAAE,SAAS,EAAE,GAAG,SAAS,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IAC1D,CAAC;IAEO,KAAK,CAAC,MAAwB;QACpC,OAAO;YACL,IAAI,EAAE,UAAU;YAChB,QAAQ,EAAE,EAAE;YACZ,QAAQ,EAAE,MAAM,CAAC,QAAQ;SAC1B,CAAC;IACJ,CAAC;IAEO,WAAW,CAAC,QAAgB;QAClC,OAAO,QAAQ;aACZ,OAAO,CAAC,cAAc,EAAE,EAAE,CAAC;aAC3B,OAAO,CAAC,gBAAgB,EAAE,IAAI,CAAC;aAC/B,OAAO,CAAC,YAAY,EAAE,IAAI,CAAC;aAC3B,OAAO,CAAC,UAAU,EAAE,IAAI,CAAC;aACzB,OAAO,CAAC,mBAAmB,EAAE,CAAC,KAAK,EAAE,EAAE;YACtC,MAAM,KAAK,GAAG,KAAK,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC;YAC7C,OAAO,KAAK,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;QAC1B,CAAC,CAAC;aACD,OAAO,CAAC,wBAAwB,EAAE,IAAI,CAAC;aACvC,OAAO,CAAC,yBAAyB,EAAE,MAAM,CAAC;aAC1C,OAAO,CAAC,aAAa,EAAE,IAAI,CAAC;aAC5B,OAAO,CAAC,SAAS,EAAE,EAAE,CAAC;aACtB,OAAO,CAAC,SAAS,EAAE,EAAE,CAAC;aACtB,OAAO,CAAC,SAAS,EAAE,MAAM,CAAC;aAC1B,IAAI,EAAE,CAAC;IACZ,CAAC;IAEO,cAAc,CAAC,QAAgB;QACrC,IAAI,IAAI,GAAG,QAAQ,CAAC;QACpB,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,cAAc,EAAE,aAAa,CAAC,CAAC;QACnD,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,aAAa,EAAE,aAAa,CAAC,CAAC;QAClD,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,YAAY,EAAE,aAAa,CAAC,CAAC;QACjD,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,gBAAgB,EAAE,qBAAqB,CAAC,CAAC;QAC7D,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,YAAY,EAAE,aAAa,CAAC,CAAC;QACjD,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,UAAU,EAAE,iBAAiB,CAAC,CAAC;QACnD,IAAI,GAAG,IAAI,CAAC,OAAO,CACjB,6BAA6B,EAC7B,gDAAgD,CACjD,CAAC;QACF,IAAI,GAAG,IAAI,CAAC,OAAO,CACjB,0BAA0B,EAC1B,qBAAqB,CACtB,CAAC;QACF,IAAI,GAAG,IAAI,CAAC,OAAO,CACjB,2BAA2B,EAC3B,2BAA2B,CAC5B,CAAC;QACF,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,YAAY,EAAE,oCAAoC,CAAC,CAAC;QACxE,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,gBAAgB,EAAE,aAAa,CAAC,CAAC;QACrD,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC;QAC/B,MAAM,MAAM,GAAa,EAAE,CAAC;QAC5B,IAAI,WAAW,GAAG,KAAK,CAAC;QACxB,KAAK,MAAM,IAAI,IAAI,KAAK,EAAE,CAAC;YACzB,MAAM,OAAO,GAAG,IAAI,CAAC,IAAI,EAAE,CAAC;YAC5B,IAAI,OAAO,KAAK,EAAE,EAAE,CAAC;gBACnB,IAAI,WAAW,EAAE,CAAC;oBAChB,MAAM,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;oBACpB,WAAW,GAAG,KAAK,CAAC;gBACtB,CAAC;gBACD,SAAS;YACX,CAAC;YACD,IACE,OAAO,CAAC,UAAU,CAAC,IAAI,CAAC;gBACxB,OAAO,CAAC,UAAU,CAAC,MAAM,CAAC;gBAC1B,OAAO,CAAC,UAAU,CAAC,KAAK,CAAC;gBACzB,OAAO,CAAC,UAAU,CAAC,aAAa,CAAC;gBACjC,OAAO,CAAC,UAAU,CAAC,MAAM,CAAC;gBAC1B,OAAO,CAAC,UAAU,CAAC,KAAK,CAAC,EACzB,CAAC;gBACD,IAAI,WAAW,EAAE,CAAC;oBAChB,MAAM,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;oBACpB,WAAW,GAAG,KAAK,CAAC;gBACtB,CAAC;gBACD,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;YACvB,CAAC;iBAAM,CAAC;gBACN,IAAI,CAAC,WAAW,EAAE,CAAC;oBACjB,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;oBACnB,WAAW,GAAG,IAAI,CAAC;gBACrB,CAAC;gBACD,MAAM,CAAC,IAAI,CAAC,OAAO,CAAC,CAAC;YACvB,CAAC;QACH,CAAC;QACD,IAAI,WAAW;YAAE,MAAM,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;QACrC,OAAO,MAAM,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;IAC3B,CAAC;CACF"}
package/package.json ADDED
@@ -0,0 +1,34 @@
1
+ {
2
+ "name": "@markitdownjs/core",
3
+ "version": "0.1.0",
4
+ "description": "Core document conversion pipeline for MarkItDownJS",
5
+ "license": "MIT",
6
+ "type": "module",
7
+ "main": "./dist/index.js",
8
+ "module": "./dist/index.js",
9
+ "types": "./dist/index.d.ts",
10
+ "exports": {
11
+ ".": {
12
+ "import": "./dist/index.js",
13
+ "types": "./dist/index.d.ts"
14
+ }
15
+ },
16
+ "files": [
17
+ "dist"
18
+ ],
19
+ "dependencies": {
20
+ "@markitdownjs/shared": "0.1.0"
21
+ },
22
+ "devDependencies": {
23
+ "typescript": "^5.5.0",
24
+ "vitest": "^4.1.8"
25
+ },
26
+ "scripts": {
27
+ "build": "tsc --project tsconfig.json",
28
+ "dev": "tsc --watch --project tsconfig.json",
29
+ "typecheck": "tsc --noEmit",
30
+ "test": "vitest run",
31
+ "test:watch": "vitest",
32
+ "clean": "rm -rf dist tsconfig.tsbuildinfo"
33
+ }
34
+ }